Merge tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Davbe Airlie: "This is the main pull request for graphics for 5.6. Usual selection of changes all over. I've got one outstanding vmwgfx pull that touches mm so kept it separate until after all of this lands. I'll try and get it to you soon after this, but it might be early next week (nothing wrong with code, just my schedule is messy) This also hits a lot of fbdev drivers with some cleanups. Other notables: - vulkan timeline semaphore support added to syncobjs - nouveau turing secureboot/graphics support - Displayport MST display stream compression support Detailed summary: uapi: - dma-buf heaps added (and fixed) - command line add support for panel oreientation - command line allow overriding penguin count drm: - mipi dsi definition updates - lockdep annotations for dma_resv - remove dma-buf kmap/kunmap support - constify fb_ops in all fbdev drivers - MST fix for daisy chained hotplug- - CTA-861-G modes with VIC >= 193 added - fix drm_panel_of_backlight export - LVDS decoder support - more device based logging support - scanline alighment for dumb buffers - MST DSC helpers scheduler: - documentation fixes - job distribution improvements panel: - Logic PD type 28 panel support - Jimax8729d MIPI-DSI - igenic JZ4770 - generic DSI devicetree bindings - sony acx424AKP panel - Leadtek LTK500HD1829 - xinpeng XPP055C272 - AUO B116XAK01 - GiantPlus GPM940B0 - BOE NV140FHM-N49 - Satoz SAT050AT40H12R2 - Sharp LS020B1DD01D panels. ttm: - use blocking WW lock i915: - hw/uapi state separation - Lock annotation improvements - selftest improvements - ICL/TGL DSI VDSC support - VBT parsing improvments - Display refactoring - DSI updates + fixes - HDCP 2.2 for CFL - CML PCI ID fixes - GLK+ fbc fix - PSR fixes - GEN/GT refactor improvments - DP MST fixes - switch context id alloc to xarray - workaround updates - LMEM debugfs support - tiled monitor fixes - ICL+ clock gating programming removed - DP MST disable sequence fixed - LMEM discontiguous object maps - prefaulting for discontiguous objects - use LMEM for dumb buffers if possible - add LMEM mmap support amdgpu: - enable sync object timelines for vulkan - MST atomic routines - enable MST DSC support - add DMCUB display microengine support - DC OEM i2c support - Renoir DC fixes - Initial HDCP 2.x support - BACO support for Arcturus - Use BACO for runtime PM power save - gfxoff on navi10 - gfx10 golden updates and fixes - DCN support on POWER - GFXOFF for raven1 refresh - MM engine idle handlers cleanup - 10bpc EDP panel fixes - renoir watermark fixes - SR-IOV fixes - Arcturus VCN fixes - GDDR6 training fixes - freesync fixes - Pollock support amdkfd: - unify more codepath with amdgpu - use KIQ to setup HIQ rather than MMIO radeon: - fix vma fault handler race - PPC DMA fix - register check fixes for r100/r200 nouveau: - mmap_sem vs dma_resv fix - rewrite the ACR secure boot code for Turing - TU10x graphics engine support (TU11x pending) - Page kind mapping for turing - 10-bit LUT support - GP10B Tegra fixes - HD audio regression fix hisilicon/hibmc: - use generic fbdev code and helpers rockchip: - dsi/px30 support virtio: - fb damage support - static some functions vc4: - use dma_resv lock wrappers msm: - use dma_resv lock wrappers - sc7180 display + DSI support - a618 support - UBWC support improvements vmwgfx: - updates + new logging uapi exynos: - enable/disable callback cleanups etnaviv: - use dma_resv lock wrappers atmel-hlcdc: - clock fixes mediatek: - cmdq support - non-smooth cursor fixes - ctm property support sun4i: - suspend support - A64 mipi dsi support rcar-du: - Color management module support - LVDS encoder dual-link support - R8A77980 support analogic: - add support for an6345 ast: - atomic modeset support - primary plane garbage fix arcgpu: - fixes for fourcc handling tegra: - minor fixes and improvments mcde: - vblank support meson: - OSD1 plane AFBC commit gma500: - add pageflip support - reomve global drm_dev komeda: - tweak debugfs output - d32 support - runtime PM suppotr udl: - use generic shmem helpers - cleanup and fixes" * tag 'drm-next-2020-01-30' of git://anongit.freedesktop.org/drm/drm: (1998 commits) drm/nouveau/fb/gp102-: allow module to load even when scrubber binary is missing drm/nouveau/acr: return error when registering LSF if ACR not supported drm/nouveau/disp/gv100-: not all channel types support reporting error codes drm/nouveau/disp/nv50-: prevent oops when no channel method map provided drm/nouveau: support synchronous pushbuf submission drm/nouveau: signal pending fences when channel has been killed drm/nouveau: reject attempts to submit to dead channels drm/nouveau: zero vma pointer even if we only unreference it rather than free drm/nouveau: Add HD-audio component notifier support drm/nouveau: fix build error without CONFIG_IOMMU_API drm/nouveau/kms/nv04: remove set but not used variable 'width' drm/nouveau/kms/nv50: remove set but not unused variable 'nv_connector' drm/nouveau/mmu: fix comptag memory leak drm/nouveau/gr/gp10b: Use gp100_grctx and gp100_gr_zbc drm/nouveau/pmu/gm20b,gp10b: Fix Falcon bootstrapping drm/exynos: Rename Exynos to lowercase drm/exynos: change callback names drm/mst: Don't do atomic checks over disabled managers drm/amdgpu: add the lost mutex_init back drm/amd/display: skip opp blank or unblank if test pattern enabled ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2020-01-30 08:04:01 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2020-01-30 08:04:01 -0800
commit: 9f68e3655aae6d49d6ba05dd263f99f33c2567af (patch)
tree: 42c2c4579c4acbbb456695326af4f4ad8f402813
parent: 4cadc60d6bcfee9c626d4b55e9dc1475d21ad3bb (diff)
parent: d47c7f06268082bc0082a15297a07c0da59b0fc4 (diff)
1683 files changed, 78143 insertions, 41274 deletions
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-backend.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-backend.yaml
new file mode 100644
index 000000000000..86057d541065
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-backend.yaml
@@ -0,0 +1,291 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-display-backend.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Display Engine Backend Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The display engine backend exposes layers and sprites to the system.
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-display-backend
+      - allwinner,sun5i-a13-display-backend
+      - allwinner,sun6i-a31-display-backend
+      - allwinner,sun7i-a20-display-backend
+      - allwinner,sun8i-a23-display-backend
+      - allwinner,sun8i-a33-display-backend
+      - allwinner,sun9i-a80-display-backend
+
+  reg:
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: Display Backend registers
+      - description: SAT registers
+
+  reg-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      - const: be
+      - const: sat
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 3
+    maxItems: 4
+    items:
+      - description: The backend interface clock
+      - description: The backend module clock
+      - description: The backend DRAM clock
+      - description: The SAT clock
+
+  clock-names:
+    minItems: 3
+    maxItems: 4
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+      - const: sat
+
+  resets:
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: The Backend reset line
+      - description: The SAT reset line
+
+  reset-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      - const: be
+      - const: sat
+
+  # FIXME: This should be made required eventually once every SoC will
+  # have the MBUS declared.
+  interconnects:
+    maxItems: 1
+
+  # FIXME: This should be made required eventually once every SoC will
+  # have the MBUS declared.
+  interconnect-names:
+    const: dma-mem
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: allwinner,sun8i-a33-display-backend
+
+then:
+  properties:
+    reg:
+      minItems: 2
+
+    reg-names:
+      minItems: 2
+
+    clocks:
+      minItems: 4
+
+    clock-names:
+      minItems: 4
+
+    resets:
+      minItems: 2
+
+    reset-names:
+      minItems: 2
+
+  required:
+    - reg-names
+    - reset-names
+
+else:
+  properties:
+    reg:
+      maxItems: 1
+
+    reg-names:
+      maxItems: 1
+
+    clocks:
+      maxItems: 3
+
+    clock-names:
+      maxItems: 3
+
+    resets:
+      maxItems: 1
+
+    reset-names:
+      maxItems: 1
+
+examples:
+  - |
+    /*
+     * This comes from the clock/sun4i-a10-ccu.h and
+     * reset/sun4i-a10-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_AHB_DE_BE0	42
+    #define CLK_DRAM_DE_BE0	140
+    #define CLK_DE_BE0		144
+    #define RST_DE_BE0		5
+
+    display-backend@1e60000 {
+        compatible = "allwinner,sun4i-a10-display-backend";
+        reg = <0x01e60000 0x10000>;
+        interrupts = <47>;
+        clocks = <&ccu CLK_AHB_DE_BE0>, <&ccu CLK_DE_BE0>,
+                 <&ccu CLK_DRAM_DE_BE0>;
+        clock-names = "ahb", "mod",
+                      "ram";
+        resets = <&ccu RST_DE_BE0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&fe0_out_be0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&fe1_out_be0>;
+                };
+            };
+
+            port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon0_in_be0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon1_in_be0>;
+                };
+            };
+        };
+    };
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun8i-a23-a33-ccu.h and
+     * reset/sun8i-a23-a33-ccu.h headers, but we can't include them
+     * since it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_BUS_DE_BE	40
+    #define CLK_BUS_SAT		46
+    #define CLK_DRAM_DE_BE	84
+    #define CLK_DE_BE		85
+    #define RST_BUS_DE_BE	21
+    #define RST_BUS_SAT		27
+
+    display-backend@1e60000 {
+        compatible = "allwinner,sun8i-a33-display-backend";
+        reg = <0x01e60000 0x10000>, <0x01e80000 0x1000>;
+        reg-names = "be", "sat";
+        interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_DE_BE>, <&ccu CLK_DE_BE>,
+                 <&ccu CLK_DRAM_DE_BE>, <&ccu CLK_BUS_SAT>;
+        clock-names = "ahb", "mod",
+                      "ram", "sat";
+        resets = <&ccu RST_BUS_DE_BE>, <&ccu RST_BUS_SAT>;
+        reset-names = "be", "sat";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+
+                endpoint {
+                    remote-endpoint = <&fe0_out_be0>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+
+                endpoint {
+                    remote-endpoint = <&drc0_in_be0>;
+                };
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml
new file mode 100644
index 000000000000..944ff2f1cf93
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml
@@ -0,0 +1,114 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-display-engine.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Display Engine Pipeline Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The display engine pipeline (and its entry point, since it can be
+  either directly the backend or the frontend) is represented as an
+  extra node.
+
+  The Allwinner A10 Display pipeline is composed of several components
+  that are going to be documented below:
+
+  For all connections between components up to the TCONs in the
+  display pipeline, when there are multiple components of the same
+  type at the same depth, the local endpoint ID must be the same as
+  the remote component's index. For example, if the remote endpoint is
+  Frontend 1, then the local endpoint ID must be 1.
+
+  Frontend 0  [0] ------- [0]  Backend 0  [0] ------- [0]  TCON 0
+              [1] --   -- [1]             [1] --   -- [1]
+                    \ /                         \ /
+                     X                           X
+                    / \                         / \
+              [0] --   -- [0]             [0] --   -- [0]
+  Frontend 1  [1] ------- [1]  Backend 1  [1] ------- [1]  TCON 1
+
+  For a two pipeline system such as the one depicted above, the lines
+  represent the connections between the components, while the numbers
+  within the square brackets corresponds to the ID of the local endpoint.
+
+  The same rule also applies to DE 2.0 mixer-TCON connections:
+
+  Mixer 0  [0] ----------- [0]  TCON 0
+           [1] ----   ---- [1]
+                   \ /
+                    X
+                   / \
+           [0] ----   ---- [0]
+  Mixer 1  [1] ----------- [1]  TCON 1
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-display-engine
+      - allwinner,sun5i-a10s-display-engine
+      - allwinner,sun5i-a13-display-engine
+      - allwinner,sun6i-a31-display-engine
+      - allwinner,sun6i-a31s-display-engine
+      - allwinner,sun7i-a20-display-engine
+      - allwinner,sun8i-a23-display-engine
+      - allwinner,sun8i-a33-display-engine
+      - allwinner,sun8i-a83t-display-engine
+      - allwinner,sun8i-h3-display-engine
+      - allwinner,sun8i-r40-display-engine
+      - allwinner,sun8i-v3s-display-engine
+      - allwinner,sun9i-a80-display-engine
+      - allwinner,sun50i-a64-display-engine
+      - allwinner,sun50i-h6-display-engine
+
+  allwinner,pipelines:
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/phandle-array
+      - minItems: 1
+        maxItems: 2
+    description: |
+      Available display engine frontends (DE 1.0) or mixers (DE
+      2.0/3.0) available.
+
+required:
+  - compatible
+  - allwinner,pipelines
+
+additionalProperties: false
+
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - allwinner,sun4i-a10-display-engine
+          - allwinner,sun6i-a31-display-engine
+          - allwinner,sun6i-a31s-display-engine
+          - allwinner,sun7i-a20-display-engine
+          - allwinner,sun8i-a83t-display-engine
+          - allwinner,sun8i-r40-display-engine
+          - allwinner,sun9i-a80-display-engine
+          - allwinner,sun50i-a64-display-engine
+
+then:
+  properties:
+    allwinner,pipelines:
+      minItems: 2
+
+else:
+  properties:
+    allwinner,pipelines:
+      maxItems: 1
+
+examples:
+  - |
+      de: display-engine {
+          compatible = "allwinner,sun4i-a10-display-engine";
+          allwinner,pipelines = <&fe0>, <&fe1>;
+      };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-frontend.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-frontend.yaml
new file mode 100644
index 000000000000..3eb1c2bbf4e7
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-frontend.yaml
@@ -0,0 +1,138 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-display-frontend.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Display Engine Frontend Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The display engine frontend does formats conversion, scaling,
+  deinterlacing and color space conversion.
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-display-frontend
+      - allwinner,sun5i-a13-display-frontend
+      - allwinner,sun6i-a31-display-frontend
+      - allwinner,sun7i-a20-display-frontend
+      - allwinner,sun8i-a23-display-frontend
+      - allwinner,sun8i-a33-display-frontend
+      - allwinner,sun9i-a80-display-frontend
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The frontend interface clock
+      - description: The frontend module clock
+      - description: The frontend DRAM clock
+
+  clock-names:
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+
+  # FIXME: This should be made required eventually once every SoC will
+  # have the MBUS declared.
+  interconnects:
+    maxItems: 1
+
+  # FIXME: This should be made required eventually once every SoC will
+  # have the MBUS declared.
+  interconnect-names:
+    const: dma-mem
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun4i-a10-ccu.h>
+    #include <dt-bindings/reset/sun4i-a10-ccu.h>
+
+    fe0: display-frontend@1e00000 {
+        compatible = "allwinner,sun4i-a10-display-frontend";
+        reg = <0x01e00000 0x20000>;
+        interrupts = <47>;
+        clocks = <&ccu CLK_AHB_DE_FE0>, <&ccu CLK_DE_FE0>,
+                 <&ccu CLK_DRAM_DE_FE0>;
+        clock-names = "ahb", "mod",
+                      "ram";
+        resets = <&ccu RST_DE_FE0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            fe0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                fe0_out_be0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&be0_in_fe0>;
+                };
+
+                fe0_out_be1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&be1_in_fe0>;
+                };
+            };
+        };
+    };
+
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-hdmi.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-hdmi.yaml
new file mode 100644
index 000000000000..5d4915aed1e2
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-hdmi.yaml
@@ -0,0 +1,183 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-hdmi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 HDMI Controller Device Tree Bindings
+
+description: |
+  The HDMI Encoder supports the HDMI video and audio outputs, and does
+  CEC. It is one end of the pipeline.
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    oneOf:
+      - const: allwinner,sun4i-a10-hdmi
+      - const: allwinner,sun5i-a10s-hdmi
+      - const: allwinner,sun6i-a31-hdmi
+      - items:
+        - const: allwinner,sun7i-a20-hdmi
+        - const: allwinner,sun5i-a10s-hdmi
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    oneOf:
+      - items:
+        - description: The HDMI interface clock
+        - description: The HDMI module clock
+        - description: The first video PLL
+        - description: The second video PLL
+
+      - items:
+        - description: The HDMI interface clock
+        - description: The HDMI module clock
+        - description: The HDMI DDC clock
+        - description: The first video PLL
+        - description: The second video PLL
+
+  clock-names:
+    oneOf:
+      - items:
+        - const: ahb
+        - const: mod
+        - const: pll-0
+        - const: pll-1
+
+      - items:
+        - const: ahb
+        - const: mod
+        - const: ddc
+        - const: pll-0
+        - const: pll-1
+
+  resets:
+    maxItems: 1
+
+  dmas:
+    items:
+      - description: DDC Transmission DMA Channel
+      - description: DDC Reception DMA Channel
+      - description: Audio Transmission DMA Channel
+
+  dma-names:
+    items:
+      - const: ddc-tx
+      - const: ddc-rx
+      - const: audio-tx
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller. Usually an HDMI
+          connector.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - dmas
+  - dma-names
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: allwinner,sun6i-a31-hdmi
+
+then:
+  properties:
+    clocks:
+      minItems: 5
+
+    clock-names:
+      minItems: 5
+
+  required:
+    - resets
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun4i-a10-ccu.h>
+    #include <dt-bindings/dma/sun4i-a10.h>
+    #include <dt-bindings/reset/sun4i-a10-ccu.h>
+
+    hdmi: hdmi@1c16000 {
+        compatible = "allwinner,sun4i-a10-hdmi";
+        reg = <0x01c16000 0x1000>;
+        interrupts = <58>;
+        clocks = <&ccu CLK_AHB_HDMI0>, <&ccu CLK_HDMI>,
+                 <&ccu CLK_PLL_VIDEO0_2X>,
+                 <&ccu CLK_PLL_VIDEO1_2X>;
+        clock-names = "ahb", "mod", "pll-0", "pll-1";
+        dmas = <&dma SUN4I_DMA_NORMAL 16>,
+               <&dma SUN4I_DMA_NORMAL 16>,
+               <&dma SUN4I_DMA_DEDICATED 24>;
+        dma-names = "ddc-tx", "ddc-rx", "audio-tx";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            hdmi_in: port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                hdmi_in_tcon0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon0_out_hdmi>;
+                };
+
+                hdmi_in_tcon1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon1_out_hdmi>;
+                };
+            };
+
+            hdmi_out: port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
new file mode 100644
index 000000000000..86ad617d2327
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
@@ -0,0 +1,676 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-tcon.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Timings Controller (TCON) Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The TCON acts as a timing controller for RGB, LVDS and TV
+  interfaces.
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    oneOf:
+      - const: allwinner,sun4i-a10-tcon
+      - const: allwinner,sun5i-a13-tcon
+      - const: allwinner,sun6i-a31-tcon
+      - const: allwinner,sun6i-a31s-tcon
+      - const: allwinner,sun7i-a20-tcon
+      - const: allwinner,sun8i-a23-tcon
+      - const: allwinner,sun8i-a33-tcon
+      - const: allwinner,sun8i-a83t-tcon-lcd
+      - const: allwinner,sun8i-a83t-tcon-tv
+      - const: allwinner,sun8i-r40-tcon-tv
+      - const: allwinner,sun8i-v3s-tcon
+      - const: allwinner,sun9i-a80-tcon-lcd
+      - const: allwinner,sun9i-a80-tcon-tv
+
+      - items:
+        - enum:
+            - allwinner,sun50i-a64-tcon-lcd
+        - const: allwinner,sun8i-a83t-tcon-lcd
+
+      - items:
+        - enum:
+          - allwinner,sun8i-h3-tcon-tv
+          - allwinner,sun50i-a64-tcon-tv
+          - allwinner,sun50i-h6-tcon-tv
+        - const: allwinner,sun8i-a83t-tcon-tv
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 4
+
+  clock-names:
+    minItems: 1
+    maxItems: 4
+
+  clock-output-names:
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/string-array
+      - maxItems: 1
+    description:
+      Name of the LCD pixel clock created.
+
+  dmas:
+    maxItems: 1
+
+  resets:
+    anyOf:
+      - items:
+        - description: TCON Reset Line
+
+      - items:
+        - description: TCON Reset Line
+        - description: TCON LVDS Reset Line
+
+      - items:
+        - description: TCON Reset Line
+        - description: TCON eDP Reset Line
+
+      - items:
+        - description: TCON Reset Line
+        - description: TCON eDP Reset Line
+        - description: TCON LVDS Reset Line
+
+  reset-names:
+    oneOf:
+      - const: lcd
+
+      - items:
+        - const: lcd
+        - const: lvds
+
+      - items:
+        - const: lcd
+        - const: edp
+
+      - items:
+        - const: lcd
+        - const: edp
+        - const: lvds
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+        patternProperties:
+          "^endpoint(@[0-9])$":
+            type: object
+
+            properties:
+              allwinner,tcon-channel:
+                $ref: /schemas/types.yaml#/definitions/uint32
+                description: |
+                  TCON can have 1 or 2 channels, usually with the
+                  first channel being used for the panels interfaces
+                  (RGB, LVDS, etc.), and the second being used for the
+                  outputs that require another controller (TV Encoder,
+                  HDMI, etc.).
+
+                  If that property is present, specifies the TCON
+                  channel the endpoint is associated to. If that
+                  property is not present, the endpoint number will be
+                  used as the channel number.
+
+            unevaluatedProperties: true
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun4i-a10-tcon
+              - allwinner,sun5i-a13-tcon
+              - allwinner,sun7i-a20-tcon
+
+    then:
+      properties:
+        clocks:
+          minItems: 3
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch0
+            - const: tcon-ch1
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun6i-a31-tcon
+              - allwinner,sun6i-a31s-tcon
+
+    then:
+      properties:
+        clocks:
+          minItems: 4
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch0
+            - const: tcon-ch1
+            - const: lvds-alt
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun8i-a23-tcon
+              - allwinner,sun8i-a33-tcon
+
+    then:
+      properties:
+        clocks:
+          minItems: 3
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch0
+            - const: lvds-alt
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun8i-a83t-tcon-lcd
+              - allwinner,sun8i-v3s-tcon
+              - allwinner,sun9i-a80-tcon-lcd
+
+    then:
+      properties:
+        clocks:
+          minItems: 2
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch0
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun8i-a83t-tcon-tv
+              - allwinner,sun8i-r40-tcon-tv
+              - allwinner,sun9i-a80-tcon-tv
+
+    then:
+      properties:
+        clocks:
+          minItems: 2
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch1
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun5i-a13-tcon
+              - allwinner,sun6i-a31-tcon
+              - allwinner,sun6i-a31s-tcon
+              - allwinner,sun7i-a20-tcon
+              - allwinner,sun8i-a23-tcon
+              - allwinner,sun8i-a33-tcon
+              - allwinner,sun8i-v3s-tcon
+              - allwinner,sun9i-a80-tcon-lcd
+              - allwinner,sun4i-a10-tcon
+              - allwinner,sun8i-a83t-tcon-lcd
+
+    then:
+      required:
+        - "#clock-cells"
+        - clock-output-names
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun6i-a31-tcon
+              - allwinner,sun6i-a31s-tcon
+              - allwinner,sun8i-a23-tcon
+              - allwinner,sun8i-a33-tcon
+              - allwinner,sun8i-a83t-tcon-lcd
+
+    then:
+      properties:
+        resets:
+          minItems: 2
+
+        reset-names:
+          items:
+            - const: lcd
+            - const: lvds
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun9i-a80-tcon-lcd
+
+    then:
+      properties:
+        resets:
+          minItems: 3
+
+        reset-names:
+          items:
+            - const: lcd
+            - const: edp
+            - const: lvds
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun9i-a80-tcon-tv
+
+    then:
+      properties:
+        resets:
+          minItems: 2
+
+        reset-names:
+          items:
+            - const: lcd
+            - const: edp
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun4i-a10-tcon
+              - allwinner,sun5i-a13-tcon
+              - allwinner,sun6i-a31-tcon
+              - allwinner,sun6i-a31s-tcon
+              - allwinner,sun7i-a20-tcon
+              - allwinner,sun8i-a23-tcon
+              - allwinner,sun8i-a33-tcon
+
+    then:
+      required:
+        - dmas
+
+examples:
+  - |
+    #include <dt-bindings/dma/sun4i-a10.h>
+
+    /*
+     * This comes from the clock/sun4i-a10-ccu.h and
+     * reset/sun4i-a10-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_AHB_LCD0	56
+    #define CLK_TCON0_CH0	149
+    #define CLK_TCON0_CH1	155
+    #define RST_TCON0		11
+
+    lcd-controller@1c0c000 {
+        compatible = "allwinner,sun4i-a10-tcon";
+        reg = <0x01c0c000 0x1000>;
+        interrupts = <44>;
+        resets = <&ccu RST_TCON0>;
+        reset-names = "lcd";
+        clocks = <&ccu CLK_AHB_LCD0>,
+                 <&ccu CLK_TCON0_CH0>,
+                 <&ccu CLK_TCON0_CH1>;
+        clock-names = "ahb",
+                      "tcon-ch0",
+                      "tcon-ch1";
+        clock-output-names = "tcon0-pixel-clock";
+        #clock-cells = <0>;
+        dmas = <&dma SUN4I_DMA_DEDICATED 14>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&be0_out_tcon0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&be1_out_tcon0>;
+                };
+            };
+
+            port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&hdmi_in_tcon0>;
+                    allwinner,tcon-channel = <1>;
+                };
+            };
+        };
+    };
+
+    #undef CLK_AHB_LCD0
+    #undef CLK_TCON0_CH0
+    #undef CLK_TCON0_CH1
+    #undef RST_TCON0
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun6i-a31-ccu.h and
+     * reset/sun6i-a31-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_PLL_MIPI	15
+    #define CLK_AHB1_LCD0	47
+    #define CLK_LCD0_CH0	127
+    #define CLK_LCD0_CH1	129
+    #define RST_AHB1_LCD0	27
+    #define RST_AHB1_LVDS	41
+
+    lcd-controller@1c0c000 {
+        compatible = "allwinner,sun6i-a31-tcon";
+        reg = <0x01c0c000 0x1000>;
+        interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+        dmas = <&dma 11>;
+        resets = <&ccu RST_AHB1_LCD0>, <&ccu RST_AHB1_LVDS>;
+        reset-names = "lcd", "lvds";
+        clocks = <&ccu CLK_AHB1_LCD0>,
+                 <&ccu CLK_LCD0_CH0>,
+                 <&ccu CLK_LCD0_CH1>,
+                 <&ccu CLK_PLL_MIPI>;
+        clock-names = "ahb",
+                      "tcon-ch0",
+                      "tcon-ch1",
+                      "lvds-alt";
+        clock-output-names = "tcon0-pixel-clock";
+        #clock-cells = <0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&drc0_out_tcon0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&drc1_out_tcon0>;
+                };
+            };
+
+            port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&hdmi_in_tcon0>;
+                    allwinner,tcon-channel = <1>;
+                };
+            };
+        };
+    };
+
+    #undef CLK_PLL_MIPI
+    #undef CLK_AHB1_LCD0
+    #undef CLK_LCD0_CH0
+    #undef CLK_LCD0_CH1
+    #undef RST_AHB1_LCD0
+    #undef RST_AHB1_LVDS
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun9i-a80-ccu.h and
+     * reset/sun9i-a80-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_BUS_LCD0	102
+    #define CLK_LCD0		58
+    #define RST_BUS_LCD0	22
+    #define RST_BUS_EDP		24
+    #define RST_BUS_LVDS	25
+
+    lcd-controller@3c00000 {
+        compatible = "allwinner,sun9i-a80-tcon-lcd";
+        reg = <0x03c00000 0x10000>;
+        interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_LCD0>, <&ccu CLK_LCD0>;
+        clock-names = "ahb", "tcon-ch0";
+        resets = <&ccu RST_BUS_LCD0>, <&ccu RST_BUS_EDP>, <&ccu RST_BUS_LVDS>;
+        reset-names = "lcd", "edp", "lvds";
+        clock-output-names = "tcon0-pixel-clock";
+        #clock-cells = <0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+
+                endpoint {
+                    remote-endpoint = <&drc0_out_tcon0>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+    #undef CLK_BUS_TCON0
+    #undef CLK_TCON0
+    #undef RST_BUS_TCON0
+    #undef RST_BUS_EDP
+    #undef RST_BUS_LVDS
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun8i-a83t-ccu.h and
+     * reset/sun8i-a83t-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_BUS_TCON0	36
+    #define CLK_TCON0		85
+    #define RST_BUS_TCON0	22
+    #define RST_BUS_LVDS	31
+
+    lcd-controller@1c0c000 {
+        compatible = "allwinner,sun8i-a83t-tcon-lcd";
+        reg = <0x01c0c000 0x1000>;
+        interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_TCON0>, <&ccu CLK_TCON0>;
+        clock-names = "ahb", "tcon-ch0";
+        clock-output-names = "tcon-pixel-clock";
+        #clock-cells = <0>;
+        resets = <&ccu RST_BUS_TCON0>, <&ccu RST_BUS_LVDS>;
+        reset-names = "lcd", "lvds";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&mixer0_out_tcon0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&mixer1_out_tcon0>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+    #undef CLK_BUS_TCON0
+    #undef CLK_TCON0
+    #undef RST_BUS_TCON0
+    #undef RST_BUS_LVDS
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun8i-r40-ccu.h and
+     * reset/sun8i-r40-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_BUS_TCON_TV0	73
+    #define RST_BUS_TCON_TV0	49
+
+    tcon_tv0: lcd-controller@1c73000 {
+        compatible = "allwinner,sun8i-r40-tcon-tv";
+        reg = <0x01c73000 0x1000>;
+        interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_TCON_TV0>, <&tcon_top 0>;
+        clock-names = "ahb", "tcon-ch1";
+        resets = <&ccu RST_BUS_TCON_TV0>;
+        reset-names = "lcd";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon_top_mixer0_out_tcon_tv0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon_top_mixer1_out_tcon_tv0>;
+                };
+            };
+
+            tcon_tv0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon_top_hdmi_in_tcon_tv0>;
+                };
+            };
+        };
+    };
+
+    #undef CLK_BUS_TCON_TV0
+    #undef RST_BUS_TCON_TV0
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml
new file mode 100644
index 000000000000..5d5d39665119
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-tv-encoder.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 TV Encoder Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    const: allwinner,sun4i-a10-tv-encoder
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  port:
+    type: object
+    description:
+      A port node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt. The
+      first port should be the input endpoint, usually coming from the
+      associated TCON.
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - resets
+  - port
+
+additionalProperties: false
+
+examples:
+  - |
+    tve0: tv-encoder@1c0a000 {
+        compatible = "allwinner,sun4i-a10-tv-encoder";
+        reg = <0x01c0a000 0x1000>;
+        clocks = <&ahb_gates 34>;
+        resets = <&tcon_ch0_clk 0>;
+
+        port {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            tve0_in_tcon0: endpoint@0 {
+                reg = <0>;
+                remote-endpoint = <&tcon0_out_tve0>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-drc.yaml b/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-drc.yaml
new file mode 100644
index 000000000000..0c1ce55940e1
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-drc.yaml
@@ -0,0 +1,138 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun6i-a31-drc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A31 Dynamic Range Controller Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The DRC (Dynamic Range Controller) allows to dynamically adjust
+  pixel brightness/contrast based on histogram measurements for LCD
+  content adaptive backlight control.
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun6i-a31-drc
+      - allwinner,sun6i-a31s-drc
+      - allwinner,sun8i-a23-drc
+      - allwinner,sun8i-a33-drc
+      - allwinner,sun9i-a80-drc
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The DRC interface clock
+      - description: The DRC module clock
+      - description: The DRC DRAM clock
+
+  clock-names:
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    #include <dt-bindings/clock/sun6i-a31-ccu.h>
+    #include <dt-bindings/reset/sun6i-a31-ccu.h>
+
+    drc0: drc@1e70000 {
+        compatible = "allwinner,sun6i-a31-drc";
+        reg = <0x01e70000 0x10000>;
+        interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_AHB1_DRC0>, <&ccu CLK_IEP_DRC0>,
+                 <&ccu CLK_DRAM_DRC0>;
+        clock-names = "ahb", "mod",
+                      "ram";
+        resets = <&ccu RST_AHB1_DRC0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            drc0_in: port@0 {
+                reg = <0>;
+
+                drc0_in_be0: endpoint {
+                    remote-endpoint = <&be0_out_drc0>;
+                };
+            };
+
+            drc0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                drc0_out_tcon0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon0_in_drc0>;
+                };
+
+                drc0_out_tcon1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon1_in_drc0>;
+                };
+            };
+        };
+    };
+
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-mipi-dsi.yaml b/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-mipi-dsi.yaml
index 0f7074977c04..9e90c2b00960 100644
--- a/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-mipi-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-mipi-dsi.yaml
@@ -15,7 +15,9 @@ properties:
   "#size-cells": true
 
   compatible:
-    const: allwinner,sun6i-a31-mipi-dsi
+    enum:
+      - allwinner,sun6i-a31-mipi-dsi
+      - allwinner,sun50i-a64-mipi-dsi
 
   reg:
     maxItems: 1
@@ -24,6 +26,8 @@ properties:
     maxItems: 1
 
   clocks:
+    minItems: 1
+    maxItems: 2
     items:
       - description: Bus Clock
       - description: Module Clock
@@ -63,13 +67,38 @@ required:
   - reg
   - interrupts
   - clocks
-  - clock-names
   - phys
   - phy-names
   - resets
   - vcc-dsi-supply
   - port
 
+allOf:
+  - if:
+      properties:
+         compatible:
+           contains:
+             const: allwinner,sun6i-a31-mipi-dsi
+
+    then:
+        properties:
+          clocks:
+            minItems: 2
+
+        required:
+          - clock-names
+
+  - if:
+      properties:
+         compatible:
+           contains:
+             const: allwinner,sun50i-a64-mipi-dsi
+
+    then:
+        properties:
+          clocks:
+            minItems: 1
+
 additionalProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-de2-mixer.yaml b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-de2-mixer.yaml
new file mode 100644
index 000000000000..1dee641e3ea1
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-de2-mixer.yaml
@@ -0,0 +1,118 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun8i-a83t-de2-mixer.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner Display Engine 2.0 Mixer Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun8i-a83t-de2-mixer-0
+      - allwinner,sun8i-a83t-de2-mixer-1
+      - allwinner,sun8i-h3-de2-mixer-0
+      - allwinner,sun8i-r40-de2-mixer-0
+      - allwinner,sun8i-r40-de2-mixer-1
+      - allwinner,sun8i-v3s-de2-mixer
+      - allwinner,sun50i-a64-de2-mixer-0
+      - allwinner,sun50i-a64-de2-mixer-1
+      - allwinner,sun50i-h6-de3-mixer-0
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The mixer interface clock
+      - description: The mixer module clock
+
+  clock-names:
+    items:
+      - const: bus
+      - const: mod
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun8i-de2.h>
+    #include <dt-bindings/reset/sun8i-de2.h>
+
+    mixer0: mixer@1100000 {
+        compatible = "allwinner,sun8i-a83t-de2-mixer-0";
+        reg = <0x01100000 0x100000>;
+        clocks = <&display_clocks CLK_BUS_MIXER0>,
+                 <&display_clocks CLK_MIXER0>;
+        clock-names = "bus",
+                      "mod";
+        resets = <&display_clocks RST_MIXER0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            mixer0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                mixer0_out_tcon0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon0_in_mixer0>;
+                };
+
+                mixer0_out_tcon1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon1_in_mixer0>;
+                };
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-dw-hdmi.yaml b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-dw-hdmi.yaml
new file mode 100644
index 000000000000..4d6795690ac3
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-dw-hdmi.yaml
@@ -0,0 +1,273 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun8i-a83t-dw-hdmi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A83t DWC HDMI TX Encoder Device Tree Bindings
+
+description: |
+  The HDMI transmitter is a Synopsys DesignWare HDMI 1.4 TX controller
+  IP with Allwinner\'s own PHY IP. It supports audio and video outputs
+  and CEC.
+
+  These DT bindings follow the Synopsys DWC HDMI TX bindings defined
+  in Documentation/devicetree/bindings/display/bridge/dw_hdmi.txt with
+  the following device-specific properties.
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 0
+
+  compatible:
+    oneOf:
+      - const: allwinner,sun8i-a83t-dw-hdmi
+      - const: allwinner,sun50i-h6-dw-hdmi
+
+      - items:
+        - enum:
+          - allwinner,sun8i-h3-dw-hdmi
+          - allwinner,sun8i-r40-dw-hdmi
+          - allwinner,sun50i-a64-dw-hdmi
+        - const: allwinner,sun8i-a83t-dw-hdmi
+
+  reg:
+    maxItems: 1
+
+  reg-io-width:
+    const: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 3
+    maxItems: 6
+    items:
+      - description: Bus Clock
+      - description: Register Clock
+      - description: TMDS Clock
+      - description: HDMI CEC Clock
+      - description: HDCP Clock
+      - description: HDCP Bus Clock
+
+  clock-names:
+    minItems: 3
+    maxItems: 6
+    items:
+      - const: iahb
+      - const: isfr
+      - const: tmds
+      - const: cec
+      - const: hdcp
+      - const: hdcp-bus
+
+  resets:
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: HDMI Controller Reset
+      - description: HDCP Reset
+
+  reset-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      - const: ctrl
+      - const: hdcp
+
+  phys:
+    maxItems: 1
+    description:
+      Phandle to the DWC HDMI PHY.
+
+  phy-names:
+    const: phy
+
+  hvcc-supply:
+    description:
+      The VCC power supply of the controller
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller. Usually the associated
+          TCON.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller. Usually an HDMI
+          connector.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - reg-io-width
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+  - phys
+  - phy-names
+  - ports
+
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - allwinner,sun50i-h6-dw-hdmi
+
+then:
+  properties:
+    clocks:
+      minItems: 6
+
+    clock-names:
+      minItems: 6
+
+    resets:
+      minItems: 2
+
+    reset-names:
+      minItems: 2
+
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun8i-a83t-ccu.h and
+     * reset/sun8i-a83t-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+    #define CLK_BUS_HDMI	39
+    #define CLK_HDMI		93
+    #define CLK_HDMI_SLOW	94
+    #define RST_BUS_HDMI1	26
+
+    hdmi@1ee0000 {
+        compatible = "allwinner,sun8i-a83t-dw-hdmi";
+        reg = <0x01ee0000 0x10000>;
+        reg-io-width = <1>;
+        interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_HDMI>, <&ccu CLK_HDMI_SLOW>,
+                 <&ccu CLK_HDMI>;
+        clock-names = "iahb", "isfr", "tmds";
+        resets = <&ccu RST_BUS_HDMI1>;
+        reset-names = "ctrl";
+        phys = <&hdmi_phy>;
+        phy-names = "phy";
+        pinctrl-names = "default";
+        pinctrl-0 = <&hdmi_pins>;
+        status = "disabled";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+
+                endpoint {
+                    remote-endpoint = <&tcon1_out_hdmi>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+    /* Cleanup after ourselves */
+    #undef CLK_BUS_HDMI
+    #undef CLK_HDMI
+    #undef CLK_HDMI_SLOW
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun50i-h6-ccu.h and
+     * reset/sun50i-h6-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+    #define CLK_BUS_HDMI	126
+    #define CLK_BUS_HDCP	137
+    #define CLK_HDMI		123
+    #define CLK_HDMI_SLOW	124
+    #define CLK_HDMI_CEC	125
+    #define CLK_HDCP		136
+    #define RST_BUS_HDMI_SUB	57
+    #define RST_BUS_HDCP	62
+
+    hdmi@6000000 {
+        compatible = "allwinner,sun50i-h6-dw-hdmi";
+        reg = <0x06000000 0x10000>;
+        reg-io-width = <1>;
+        interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_HDMI>, <&ccu CLK_HDMI_SLOW>,
+                 <&ccu CLK_HDMI>, <&ccu CLK_HDMI_CEC>,
+                 <&ccu CLK_HDCP>, <&ccu CLK_BUS_HDCP>;
+        clock-names = "iahb", "isfr", "tmds", "cec", "hdcp",
+                      "hdcp-bus";
+        resets = <&ccu RST_BUS_HDMI_SUB>, <&ccu RST_BUS_HDCP>;
+        reset-names = "ctrl", "hdcp";
+        phys = <&hdmi_phy>;
+        phy-names = "phy";
+        pinctrl-names = "default";
+        pinctrl-0 = <&hdmi_pins>;
+        status = "disabled";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+
+                endpoint {
+                    remote-endpoint = <&tcon_top_hdmi_out_hdmi>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-hdmi-phy.yaml b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-hdmi-phy.yaml
new file mode 100644
index 000000000000..501cec16168c
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-hdmi-phy.yaml
@@ -0,0 +1,117 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun8i-a83t-hdmi-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A83t HDMI PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun8i-a83t-hdmi-phy
+      - allwinner,sun8i-h3-hdmi-phy
+      - allwinner,sun8i-r40-hdmi-phy
+      - allwinner,sun50i-a64-hdmi-phy
+      - allwinner,sun50i-h6-hdmi-phy
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 2
+    maxItems: 4
+    items:
+      - description: Bus Clock
+      - description: Module Clock
+      - description: Parent of the PHY clock
+      - description: Second possible parent of the PHY clock
+
+  clock-names:
+    minItems: 2
+    maxItems: 4
+    items:
+      - const: bus
+      - const: mod
+      - const: pll-0
+      - const: pll-1
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    const: phy
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - allwinner,sun8i-r40-hdmi-phy
+
+then:
+  properties:
+    clocks:
+      minItems: 4
+
+    clock-names:
+      minItems: 4
+
+else:
+  if:
+    properties:
+      compatible:
+        contains:
+          enum:
+            - allwinner,sun8i-h3-hdmi-phy
+            - allwinner,sun50i-a64-hdmi-phy
+
+  then:
+    properties:
+      clocks:
+        minItems: 3
+
+      clock-names:
+        minItems: 3
+
+  else:
+    properties:
+      clocks:
+        maxItems: 2
+
+      clock-names:
+        maxItems: 2
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun8i-a83t-ccu.h>
+    #include <dt-bindings/reset/sun8i-a83t-ccu.h>
+
+    hdmi_phy: hdmi-phy@1ef0000 {
+        compatible = "allwinner,sun8i-a83t-hdmi-phy";
+        reg = <0x01ef0000 0x10000>;
+        clocks = <&ccu CLK_BUS_HDMI>, <&ccu CLK_HDMI_SLOW>;
+        clock-names = "bus", "mod";
+        resets = <&ccu RST_BUS_HDMI0>;
+        reset-names = "phy";
+        #phy-cells = <0>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun8i-r40-tcon-top.yaml b/Documentation/devicetree/bindings/display/allwinner,sun8i-r40-tcon-top.yaml
new file mode 100644
index 000000000000..b98ca609824b
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun8i-r40-tcon-top.yaml
@@ -0,0 +1,382 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun8i-r40-tcon-top.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner R40 TCON TOP Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  TCON TOPs main purpose is to configure whole display pipeline. It
+  determines relationships between mixers and TCONs, selects source
+  TCON for HDMI, muxes LCD and TV encoder GPIO output, selects TV
+  encoder clock source and contains additional TV TCON and DSI gates.
+
+  It allows display pipeline to be configured in very different ways:
+
+                                  / LCD0/LVDS0
+                   / [0] TCON-LCD0
+                   |              \ MIPI DSI
+   mixer0          |
+          \        / [1] TCON-LCD1 - LCD1/LVDS1
+           TCON-TOP
+          /        \ [2] TCON-TV0 [0] - TVE0/RGB
+   mixer1          |                  \
+                   |                   TCON-TOP - HDMI
+                   |                  /
+                   \ [3] TCON-TV1 [1] - TVE1/RGB
+
+  Note that both TCON TOP references same physical unit. Both mixers
+  can be connected to any TCON. Not all TCON TOP variants support all
+  features.
+
+properties:
+  "#clock-cells":
+    const: 1
+
+  compatible:
+    enum:
+      - allwinner,sun8i-r40-tcon-top
+      - allwinner,sun50i-h6-tcon-top
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 2
+    maxItems: 6
+    items:
+      - description: The TCON TOP interface clock
+      - description: The TCON TOP TV0 clock
+      - description: The TCON TOP TVE0 clock
+      - description: The TCON TOP TV1 clock
+      - description: The TCON TOP TVE1 clock
+      - description: The TCON TOP MIPI DSI clock
+
+  clock-names:
+    minItems: 2
+    maxItems: 6
+    items:
+      - const: bus
+      - const: tcon-tv0
+      - const: tve0
+      - const: tcon-tv1
+      - const: tve1
+      - const: dsi
+
+  clock-output-names:
+    minItems: 1
+    maxItems: 3
+    description: >
+      The first item is the name of the clock created for the TV0
+      channel, the second item is the name of the TCON TV1 channel
+      clock and the third one is the name of the DSI channel clock.
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+      All ports should have only one endpoint connected to
+      remote endpoint.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoint for Mixer 0 mux.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoint for Mixer 0 mux
+
+        properties:
+          "#address-cells":
+            const: 1
+
+          "#size-cells":
+            const: 0
+
+          reg: true
+
+        patternProperties:
+          "^endpoint@[0-9]$":
+            type: object
+
+            properties:
+              reg:
+                description: |
+                  ID of the target TCON
+
+            required:
+              - reg
+
+        required:
+          - "#address-cells"
+          - "#size-cells"
+
+        additionalProperties: false
+
+      port@2:
+        type: object
+        description: |
+          Input endpoint for Mixer 1 mux.
+
+      port@3:
+        type: object
+        description: |
+          Output endpoint for Mixer 1 mux
+
+        properties:
+          "#address-cells":
+            const: 1
+
+          "#size-cells":
+            const: 0
+
+          reg: true
+
+        patternProperties:
+          "^endpoint@[0-9]$":
+            type: object
+
+            properties:
+              reg:
+                description: |
+                  ID of the target TCON
+
+            required:
+              - reg
+
+        required:
+          - "#address-cells"
+          - "#size-cells"
+
+        additionalProperties: false
+
+      port@4:
+        type: object
+        description: |
+          Input endpoint for HDMI mux.
+
+        properties:
+          "#address-cells":
+            const: 1
+
+          "#size-cells":
+            const: 0
+
+          reg: true
+
+        patternProperties:
+          "^endpoint@[0-9]$":
+            type: object
+
+            properties:
+              reg:
+                description: |
+                  ID of the target TCON
+
+            required:
+              - reg
+
+        required:
+          - "#address-cells"
+          - "#size-cells"
+
+        additionalProperties: false
+
+      port@5:
+        type: object
+        description: |
+          Output endpoint for HDMI mux
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+      - port@4
+      - port@5
+
+    additionalProperties: false
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - clock-output-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: allwinner,sun50i-h6-tcon-top
+
+then:
+  properties:
+    clocks:
+      maxItems: 2
+
+    clock-output-names:
+      maxItems: 1
+
+else:
+  properties:
+    clocks:
+      minItems: 6
+
+    clock-output-names:
+      minItems: 3
+
+    ports:
+      required:
+        - port@2
+        - port@3
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    #include <dt-bindings/clock/sun8i-r40-ccu.h>
+    #include <dt-bindings/reset/sun8i-r40-ccu.h>
+
+      tcon_top: tcon-top@1c70000 {
+          compatible = "allwinner,sun8i-r40-tcon-top";
+          reg = <0x01c70000 0x1000>;
+          clocks = <&ccu CLK_BUS_TCON_TOP>,
+                   <&ccu CLK_TCON_TV0>,
+                   <&ccu CLK_TVE0>,
+                   <&ccu CLK_TCON_TV1>,
+                   <&ccu CLK_TVE1>,
+                   <&ccu CLK_DSI_DPHY>;
+          clock-names = "bus",
+                        "tcon-tv0",
+                        "tve0",
+                        "tcon-tv1",
+                        "tve1",
+                        "dsi";
+          clock-output-names = "tcon-top-tv0",
+                               "tcon-top-tv1",
+                               "tcon-top-dsi";
+          resets = <&ccu RST_BUS_TCON_TOP>;
+          #clock-cells = <1>;
+
+          ports {
+              #address-cells = <1>;
+              #size-cells = <0>;
+
+              tcon_top_mixer0_in: port@0 {
+                  reg = <0>;
+
+                  tcon_top_mixer0_in_mixer0: endpoint {
+                      remote-endpoint = <&mixer0_out_tcon_top>;
+                  };
+              };
+
+              tcon_top_mixer0_out: port@1 {
+                  #address-cells = <1>;
+                  #size-cells = <0>;
+                  reg = <1>;
+
+                  tcon_top_mixer0_out_tcon_lcd0: endpoint@0 {
+                      reg = <0>;
+                  };
+
+                  tcon_top_mixer0_out_tcon_lcd1: endpoint@1 {
+                      reg = <1>;
+                  };
+
+                  tcon_top_mixer0_out_tcon_tv0: endpoint@2 {
+                      reg = <2>;
+                      remote-endpoint = <&tcon_tv0_in_tcon_top_mixer0>;
+                  };
+
+                  tcon_top_mixer0_out_tcon_tv1: endpoint@3 {
+                      reg = <3>;
+                      remote-endpoint = <&tcon_tv1_in_tcon_top_mixer0>;
+                  };
+              };
+
+              tcon_top_mixer1_in: port@2 {
+                  #address-cells = <1>;
+                  #size-cells = <0>;
+                  reg = <2>;
+
+                  tcon_top_mixer1_in_mixer1: endpoint@1 {
+                      reg = <1>;
+                      remote-endpoint = <&mixer1_out_tcon_top>;
+                  };
+              };
+
+              tcon_top_mixer1_out: port@3 {
+                  #address-cells = <1>;
+                  #size-cells = <0>;
+                  reg = <3>;
+
+                  tcon_top_mixer1_out_tcon_lcd0: endpoint@0 {
+                      reg = <0>;
+                  };
+
+                  tcon_top_mixer1_out_tcon_lcd1: endpoint@1 {
+                      reg = <1>;
+                  };
+
+                  tcon_top_mixer1_out_tcon_tv0: endpoint@2 {
+                      reg = <2>;
+                      remote-endpoint = <&tcon_tv0_in_tcon_top_mixer1>;
+                  };
+
+                  tcon_top_mixer1_out_tcon_tv1: endpoint@3 {
+                      reg = <3>;
+                      remote-endpoint = <&tcon_tv1_in_tcon_top_mixer1>;
+                  };
+              };
+
+              tcon_top_hdmi_in: port@4 {
+                  #address-cells = <1>;
+                  #size-cells = <0>;
+                  reg = <4>;
+
+                  tcon_top_hdmi_in_tcon_tv0: endpoint@0 {
+                      reg = <0>;
+                      remote-endpoint = <&tcon_tv0_out_tcon_top>;
+                  };
+
+                  tcon_top_hdmi_in_tcon_tv1: endpoint@1 {
+                      reg = <1>;
+                      remote-endpoint = <&tcon_tv1_out_tcon_top>;
+                  };
+              };
+
+              tcon_top_hdmi_out: port@5 {
+                  reg = <5>;
+
+                  tcon_top_hdmi_out_hdmi: endpoint {
+                      remote-endpoint = <&hdmi_in_tcon_top>;
+                  };
+              };
+          };
+      };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun9i-a80-deu.yaml b/Documentation/devicetree/bindings/display/allwinner,sun9i-a80-deu.yaml
new file mode 100644
index 000000000000..96de41d32b3e
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun9i-a80-deu.yaml
@@ -0,0 +1,133 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun9i-a80-deu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 Detail Enhancement Unit Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The DEU (Detail Enhancement Unit), found in the Allwinner A80 SoC,
+  can sharpen the display content in both luma and chroma channels.
+
+properties:
+  compatible:
+    const: allwinner,sun9i-a80-deu
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The DEU interface clock
+      - description: The DEU module clock
+      - description: The DEU DRAM clock
+
+  clock-names:
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    #include <dt-bindings/clock/sun9i-a80-de.h>
+    #include <dt-bindings/reset/sun9i-a80-de.h>
+
+    deu0: deu@3300000 {
+        compatible = "allwinner,sun9i-a80-deu";
+        reg = <0x03300000 0x40000>;
+        interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&de_clocks CLK_BUS_DEU0>,
+                 <&de_clocks CLK_IEP_DEU0>,
+                 <&de_clocks CLK_DRAM_DEU0>;
+        clock-names = "ahb",
+                      "mod",
+                      "ram";
+        resets = <&de_clocks RST_DEU0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            deu0_in: port@0 {
+                reg = <0>;
+
+                deu0_in_fe0: endpoint {
+                    remote-endpoint = <&fe0_out_deu0>;
+                };
+            };
+
+            deu0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                deu0_out_be0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&be0_in_deu0>;
+                };
+
+                deu0_out_be1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&be1_in_deu0>;
+                };
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
new file mode 100644
index 000000000000..8f373029f5d2
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
@@ -0,0 +1,131 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/bridge/lvds-codec.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Transparent LVDS encoders and decoders
+
+maintainers:
+  - Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
+
+description: |
+  This binding supports transparent LVDS encoders and decoders that don't
+  require any configuration.
+
+  LVDS is a physical layer specification defined in ANSI/TIA/EIA-644-A. Multiple
+  incompatible data link layers have been used over time to transmit image data
+  to LVDS panels. This binding targets devices compatible with the following
+  specifications only.
+
+  [JEIDA] "Digital Interface Standards for Monitor", JEIDA-59-1999, February
+  1999 (Version 1.0), Japan Electronic Industry Development Association (JEIDA)
+  [LDI] "Open LVDS Display Interface", May 1999 (Version 0.95), National
+  Semiconductor
+  [VESA] "VESA Notebook Panel Standard", October 2007 (Version 1.0), Video
+  Electronics Standards Association (VESA)
+
+  Those devices have been marketed under the FPD-Link and FlatLink brand names
+  among others.
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+        - enum:
+          - ti,ds90c185       # For the TI DS90C185 FPD-Link Serializer
+          - ti,ds90c187       # For the TI DS90C187 FPD-Link Serializer
+          - ti,sn75lvds83     # For the TI SN75LVDS83 FlatLink transmitter
+        - const: lvds-encoder # Generic LVDS encoder compatible fallback
+      - items:
+        - enum:
+          - ti,ds90cf384a     # For the DS90CF384A FPD-Link LVDS Receiver
+        - const: lvds-decoder # Generic LVDS decoders compatible fallback
+      - enum:
+        - thine,thc63lvdm83d  # For the THC63LVDM83D LVDS serializer
+
+  ports:
+    type: object
+    description: |
+      This device has two video ports. Their connections are modeled using the
+      OF graph bindings specified in Documentation/devicetree/bindings/graph.txt
+    properties:
+      port@0:
+        type: object
+        description: |
+          For LVDS encoders, port 0 is the parallel input
+          For LVDS decoders, port 0 is the LVDS input
+
+      port@1:
+        type: object
+        description: |
+          For LVDS encoders, port 1 is the LVDS output
+          For LVDS decoders, port 1 is the parallel output
+
+    required:
+      - port@0
+      - port@1
+
+  powerdown-gpios:
+    description:
+      The GPIO used to control the power down line of this device.
+    maxItems: 1
+
+required:
+  - compatible
+  - ports
+
+examples:
+  - |
+    lvds-encoder {
+      compatible = "ti,ds90c185", "lvds-encoder";
+
+      ports {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        port@0 {
+          reg = <0>;
+
+          lvds_enc_in: endpoint {
+            remote-endpoint = <&display_out_rgb>;
+          };
+        };
+
+        port@1 {
+          reg = <1>;
+
+          lvds_enc_out: endpoint {
+            remote-endpoint = <&lvds_panel_in>;
+          };
+        };
+      };
+    };
+
+  - |
+    lvds-decoder {
+      compatible = "ti,ds90cf384a", "lvds-decoder";
+
+      ports {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        port@0 {
+          reg = <0>;
+
+          lvds_dec_in: endpoint {
+            remote-endpoint = <&display_out_lvds>;
+          };
+        };
+
+        port@1 {
+          reg = <1>;
+
+          lvds_dec_out: endpoint {
+            remote-endpoint = <&rgb_panel_in>;
+          };
+        };
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/bridge/lvds-transmitter.txt b/Documentation/devicetree/bindings/display/bridge/lvds-transmitter.txt
deleted file mode 100644
index 60091db5dfa5..000000000000
--- a/Documentation/devicetree/bindings/display/bridge/lvds-transmitter.txt
+++ /dev/null
@@ -1,66 +0,0 @@
-Parallel to LVDS Encoder
-------------------------
-
-This binding supports the parallel to LVDS encoders that don't require any
-configuration.
-
-LVDS is a physical layer specification defined in ANSI/TIA/EIA-644-A. Multiple
-incompatible data link layers have been used over time to transmit image data
-to LVDS panels. This binding targets devices compatible with the following
-specifications only.
-
-[JEIDA] "Digital Interface Standards for Monitor", JEIDA-59-1999, February
-1999 (Version 1.0), Japan Electronic Industry Development Association (JEIDA)
-[LDI] "Open LVDS Display Interface", May 1999 (Version 0.95), National
-Semiconductor
-[VESA] "VESA Notebook Panel Standard", October 2007 (Version 1.0), Video
-Electronics Standards Association (VESA)
-
-Those devices have been marketed under the FPD-Link and FlatLink brand names
-among others.
-
-
-Required properties:
-
-- compatible: Must be "lvds-encoder"
-
-  Any encoder compatible with this generic binding, but with additional
-  properties not listed here, must list a device specific compatible first
-  followed by this generic compatible.
-
-Required nodes:
-
-This device has two video ports. Their connections are modeled using the OF
-graph bindings specified in Documentation/devicetree/bindings/graph.txt.
-
-- Video port 0 for parallel input
-- Video port 1 for LVDS output
-
-
-Example
--------
-
-lvds-encoder {
-	compatible = "lvds-encoder";
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			reg = <0>;
-
-			lvds_enc_in: endpoint {
-				remote-endpoint = <&display_out_rgb>;
-			};
-		};
-
-		port@1 {
-			reg = <1>;
-
-			lvds_enc_out: endpoint {
-				remote-endpoint = <&lvds_panel_in>;
-			};
-		};
-	};
-};
diff --git a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvdm83d.txt b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvdm83d.txt
deleted file mode 100644
index fee3c88e1a17..000000000000
--- a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvdm83d.txt
+++ /dev/null
@@ -1,50 +0,0 @@
-THine Electronics THC63LVDM83D LVDS serializer
-----------------------------------------------
-
-The THC63LVDM83D is an LVDS serializer designed to support pixel data
-transmission between a host and a flat panel.
-
-Required properties:
-
-- compatible: Should be "thine,thc63lvdm83d"
-
-Optional properties:
-
-- powerdown-gpios: Power down control GPIO (the /PWDN pin, active low).
-
-Required nodes:
-
-The THC63LVDM83D has two video ports. Their connections are modeled using the
-OFgraph bindings specified in Documentation/devicetree/bindings/graph.txt.
-
-- Video port 0 for CMOS/TTL input
-- Video port 1 for LVDS output
-
-
-Example
--------
-
-	lvds_enc: encoder@0 {
-		compatible = "thine,thc63lvdm83d";
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			port@0 {
-				reg = <0>;
-
-				lvds_enc_in: endpoint@0 {
-					remote-endpoint = <&rgb_out>;
-				};
-			};
-
-			port@1 {
-				reg = <1>;
-
-				lvds_enc_out: endpoint@0 {
-					remote-endpoint = <&panel_in>;
-				};
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/display/bridge/ti,ds90c185.txt b/Documentation/devicetree/bindings/display/bridge/ti,ds90c185.txt
deleted file mode 100644
index e575f996959a..000000000000
--- a/Documentation/devicetree/bindings/display/bridge/ti,ds90c185.txt
+++ /dev/null
@@ -1,55 +0,0 @@
-Texas Instruments FPD-Link (LVDS) Serializer
---------------------------------------------
-
-The DS90C185 and DS90C187 are low-power serializers for portable
-battery-powered applications that reduces the size of the RGB
-interface between the host GPU and the display.
-
-Required properties:
-
-- compatible: Should be
-  "ti,ds90c185", "lvds-encoder"  for the TI DS90C185 FPD-Link Serializer
-  "ti,ds90c187", "lvds-encoder"  for the TI DS90C187 FPD-Link Serializer
-
-Optional properties:
-
-- powerdown-gpios: Power down control GPIO (the PDB pin, active-low)
-
-Required nodes:
-
-The devices have two video ports. Their connections are modeled using the OF
-graph bindings specified in Documentation/devicetree/bindings/graph.txt.
-
-- Video port 0 for parallel input
-- Video port 1 for LVDS output
-
-
-Example
--------
-
-lvds-encoder {
-	compatible = "ti,ds90c185", "lvds-encoder";
-
-	powerdown-gpios = <&gpio 17 GPIO_ACTIVE_LOW>;
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			reg = <0>;
-
-			lvds_enc_in: endpoint {
-				remote-endpoint = <&lcdc_out_rgb>;
-			};
-		};
-
-		port@1 {
-			reg = <1>;
-
-			lvds_enc_out: endpoint {
-				remote-endpoint = <&lvds_panel_in>;
-			};
-		};
-	};
-};
diff --git a/Documentation/devicetree/bindings/display/dsi-controller.yaml b/Documentation/devicetree/bindings/display/dsi-controller.yaml
new file mode 100644
index 000000000000..fd986c36c737
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/dsi-controller.yaml
@@ -0,0 +1,91 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/dsi-controller.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Common Properties for DSI Display Panels
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+description: |
+  This document defines device tree properties common to DSI, Display
+  Serial Interface controllers and attached panels. It doesn't constitute
+  a device tree binding specification by itself but is meant to be referenced
+  by device tree bindings.
+
+  When referenced from panel device tree bindings the properties defined in
+  this document are defined as follows. The panel device tree bindings are
+  responsible for defining whether each property is required or optional.
+
+  Notice: this binding concerns DSI panels connected directly to a master
+  without any intermediate port graph to the panel. Each DSI master
+  can control one to four virtual channels to one panel. Each virtual
+  channel should have a node "panel" for their virtual channel with their
+  reg-property set to the virtual channel number, usually there is just
+  one virtual channel, number 0.
+
+properties:
+  $nodename:
+    pattern: "^dsi-controller(@.*)?$"
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+patternProperties:
+  "^panel@[0-3]$":
+    description: Panels connected to the DSI link
+    type: object
+
+    properties:
+      reg:
+        minimum: 0
+        maximum: 3
+        description:
+          The virtual channel number of a DSI peripheral. Must be in the range
+          from 0 to 3, as DSI uses a 2-bit addressing scheme. Some DSI
+          peripherals respond to more than a single virtual channel. In that
+          case the reg property can take multiple entries, one for each virtual
+          channel that the peripheral responds to.
+
+      clock-master:
+        type: boolean
+        description:
+           Should be enabled if the host is being used in conjunction with
+           another DSI host to drive the same peripheral. Hardware supporting
+           such a configuration generally requires the data on both the busses
+           to be driven by the same clock. Only the DSI host instance
+           controlling this clock should contain this property.
+
+      enforce-video-mode:
+        type: boolean
+        description:
+          The best option is usually to run a panel in command mode, as this
+          gives better control over the panel hardware. However for different
+          reasons like broken hardware, missing features or testing, it may be
+          useful to be able to force a command mode-capable panel into video
+          mode.
+
+    required:
+      - reg
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    dsi-controller@a0351000 {
+        reg = <0xa0351000 0x1000>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+        panel@0 {
+            compatible = "sony,acx424akp";
+            reg = <0>;
+            vddi-supply = <&ab8500_ldo_aux1_reg>;
+            reset-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/ingenic,lcd.txt b/Documentation/devicetree/bindings/display/ingenic,lcd.txt
index 7b536c8c6dde..01e3261defb6 100644
--- a/Documentation/devicetree/bindings/display/ingenic,lcd.txt
+++ b/Documentation/devicetree/bindings/display/ingenic,lcd.txt
@@ -4,6 +4,7 @@ Required properties:
 - compatible: one of:
   * ingenic,jz4740-lcd
   * ingenic,jz4725b-lcd
+  * ingenic,jz4770-lcd
 - reg: LCD registers location and length
 - clocks: LCD pixclock and device clock specifiers.
 	   The device clock is only required on the JZ4740.
diff --git a/Documentation/devicetree/bindings/display/msm/dpu.txt b/Documentation/devicetree/bindings/display/msm/dpu.txt
index a61dd40f3792..551ae26f60da 100644
--- a/Documentation/devicetree/bindings/display/msm/dpu.txt
+++ b/Documentation/devicetree/bindings/display/msm/dpu.txt
@@ -8,7 +8,7 @@ The DPU display controller is found in SDM845 SoC.
 
 MDSS:
 Required properties:
-- compatible: "qcom,sdm845-mdss"
+- compatible:  "qcom,sdm845-mdss", "qcom,sc7180-mdss"
 - reg: physical base address and length of contoller's registers.
 - reg-names: register region names. The following region is required:
   * "mdss"
@@ -41,7 +41,7 @@ Optional properties:
 
 MDP:
 Required properties:
-- compatible: "qcom,sdm845-dpu"
+- compatible: "qcom,sdm845-dpu", "qcom,sc7180-dpu"
 - reg: physical base address and length of controller's registers.
 - reg-names : register region names. The following region is required:
   * "mdp"
diff --git a/Documentation/devicetree/bindings/display/msm/gpu.txt b/Documentation/devicetree/bindings/display/msm/gpu.txt
index 2b8fd26c43b0..7edc298a15f2 100644
--- a/Documentation/devicetree/bindings/display/msm/gpu.txt
+++ b/Documentation/devicetree/bindings/display/msm/gpu.txt
@@ -23,13 +23,18 @@ Required properties:
 - iommus: optional phandle to an adreno iommu instance
 - operating-points-v2: optional phandle to the OPP operating points
 - interconnects: optional phandle to an interconnect provider.  See
-  ../interconnect/interconnect.txt for details.
+  ../interconnect/interconnect.txt for details. Some A3xx and all A4xx platforms
+  will have two paths; all others will have one path.
+- interconnect-names: The names of the interconnect paths that correspond to the
+  interconnects property. Values must be gfx-mem and ocmem.
 - qcom,gmu: For GMU attached devices a phandle to the GMU device that will
   control the power for the GPU. Applicable targets:
     - qcom,adreno-630.2
 - zap-shader: For a5xx and a6xx devices this node contains a memory-region that
   points to reserved memory to store the zap shader that can be used to help
   bring the GPU out of secure mode.
+- firmware-name: optional property of the 'zap-shader' node, listing the
+  relative path of the device specific zap firmware.
 
 Example 3xx/4xx/a5xx:
 
@@ -76,11 +81,13 @@ Example a6xx (with GMU):
 		operating-points-v2 = <&gpu_opp_table>;
 
 		interconnects = <&rsc_hlos MASTER_GFX3D &rsc_hlos SLAVE_EBI1>;
+		interconnect-names = "gfx-mem";
 
 		qcom,gmu = <&gmu>;
 
 		zap-shader {
 			memory-region = <&zap_shader_region>;
+			firmware-name = "qcom/LENOVO/81JL/qcdxkmsuc850.mbn"
 		};
 	};
 };
diff --git a/Documentation/devicetree/bindings/display/panel/ampire,am-480272h3tmqw-t01h.yaml b/Documentation/devicetree/bindings/display/panel/ampire,am-480272h3tmqw-t01h.yaml
deleted file mode 100644
index c6e33e7f36d0..000000000000
--- a/Documentation/devicetree/bindings/display/panel/ampire,am-480272h3tmqw-t01h.yaml
+++ /dev/null
@@ -1,42 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/display/panel/ampire,am-480272h3tmqw-t01h.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: Ampire AM-480272H3TMQW-T01H 4.3" WQVGA TFT LCD panel
-
-maintainers:
-  - Yannick Fertre <yannick.fertre@st.com>
-  - Thierry Reding <treding@nvidia.com>
-
-allOf:
-  - $ref: panel-common.yaml#
-
-properties:
-  compatible:
-    const: ampire,am-480272h3tmqw-t01h
-
-  power-supply: true
-  enable-gpios: true
-  backlight: true
-  port: true
-
-required:
-  - compatible
-
-additionalProperties: false
-
-examples:
-  - |
-    panel_rgb: panel {
-      compatible = "ampire,am-480272h3tmqw-t01h";
-      enable-gpios = <&gpioa 8 1>;
-      port {
-        panel_in_rgb: endpoint {
-          remote-endpoint = <&controller_out_rgb>;
-        };
-      };
-    };
-
-...
diff --git a/Documentation/devicetree/bindings/display/panel/ampire,am800480r3tmqwa1h.txt b/Documentation/devicetree/bindings/display/panel/ampire,am800480r3tmqwa1h.txt
deleted file mode 100644
index 83e2cae1cc1b..000000000000
--- a/Documentation/devicetree/bindings/display/panel/ampire,am800480r3tmqwa1h.txt
+++ /dev/null
@@ -1,7 +0,0 @@
-Ampire AM-800480R3TMQW-A1H 7.0" WVGA TFT LCD panel
-
-Required properties:
-- compatible: should be "ampire,am800480r3tmqwa1h"
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/giantplus,gpm940b0.txt b/Documentation/devicetree/bindings/display/panel/giantplus,gpm940b0.txt
deleted file mode 100644
index 3dab52f92c26..000000000000
--- a/Documentation/devicetree/bindings/display/panel/giantplus,gpm940b0.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-GiantPlus 3.0" (320x240 pixels) 24-bit TFT LCD panel
-
-Required properties:
-- compatible: should be "giantplus,gpm940b0"
-- power-supply: as specified in the base binding
-
-Optional properties:
-- backlight: as specified in the base binding
-- enable-gpios: as specified in the base binding
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml
new file mode 100644
index 000000000000..4ebcea7d0c63
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/leadtek,ltk500hd1829.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Leadtek LTK500HD1829 5.0in 720x1280 DSI panel
+
+maintainers:
+  - Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: leadtek,ltk500hd1829
+  reg: true
+  backlight: true
+  reset-gpios: true
+  iovcc-supply:
+     description: regulator that supplies the iovcc voltage
+  vcc-supply:
+     description: regulator that supplies the vcc voltage
+
+required:
+  - compatible
+  - reg
+  - backlight
+  - iovcc-supply
+  - vcc-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    dsi@ff450000 {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        panel@0 {
+            compatible = "leadtek,ltk500hd1829";
+            reg = <0>;
+            backlight = <&backlight>;
+            iovcc-supply = <&vcc_1v8>;
+            vcc-supply = <&vcc_2v8>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/panel/logicpd,type28.yaml b/Documentation/devicetree/bindings/display/panel/logicpd,type28.yaml
new file mode 100644
index 000000000000..2834287b8d88
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/logicpd,type28.yaml
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/logicpd,type28.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Logic PD Type 28 4.3" WQVGA TFT LCD panel
+
+maintainers:
+  - Adam Ford <aford173@gmail.com>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: logicpd,type28
+
+  power-supply: true
+  enable-gpios: true
+  backlight: true
+  port: true
+
+required:
+  - compatible
+
+additionalProperties: false
+
+examples:
+  - |
+    lcd0: display {
+      compatible = "logicpd,type28";
+      enable-gpios = <&gpio5 27 0>;
+      backlight = <&backlight>;
+      port {
+        lcd_in: endpoint {
+          remote-endpoint = <&dpi_out>;
+        };
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
new file mode 100644
index 000000000000..8fe60ee2531c
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/panel-simple.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Simple panels with one power supply
+
+maintainers:
+  - Thierry Reding <thierry.reding@gmail.com>
+  - Sam Ravnborg <sam@ravnborg.org>
+
+description: |
+  This binding file is a collection of the simple (dumb) panels that
+  requires only a single power-supply.
+  There are optionally a backlight and an enable GPIO.
+  The panel may use an OF graph binding for the association to the display,
+  or it may be a direct child node of the display.
+
+  If the panel is more advanced a dedicated binding file is required.
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+
+  compatible:
+    enum:
+    # compatible must be listed in alphabetical order, ordered by compatible.
+    # The description in the comment is mandatory for each compatible.
+
+        # Ampire AM-480272H3TMQW-T01H 4.3" WQVGA TFT LCD panel
+      - ampire,am-480272h3tmqw-t01h
+        # Ampire AM-800480R3TMQW-A1H 7.0" WVGA TFT LCD panel
+      - ampire,am800480r3tmqwa1h
+        # AUO B116XAK01 eDP TFT LCD panel
+      - auo,b116xa01
+        # BOE NV140FHM-N49 14.0" FHD a-Si FT panel
+      - boe,nv140fhmn49
+        # GiantPlus GPM940B0 3.0" QVGA TFT LCD panel
+      - giantplus,gpm940b0
+        # Satoz SAT050AT40H12R2 5.0" WVGA TFT LCD panel
+      - satoz,sat050at40h12r2
+        # Sharp LS020B1DD01D 2.0" HQVGA TFT LCD panel
+      - sharp,ls020b1dd01d
+
+  backlight: true
+  enable-gpios: true
+  port: true
+  power-supply: true
+
+additionalProperties: false
+
+required:
+  - compatible
+  - power-supply
+
+examples:
+  - |
+    panel_rgb: panel-rgb {
+      compatible = "ampire,am-480272h3tmqw-t01h";
+      power-supply = <&vcc_lcd_reg>;
+
+      port {
+        panel_in_rgb: endpoint {
+          remote-endpoint = <&ltdc_out_rgb>;
+        };
+      };
+    };
diff --git a/Documentation/devicetree/bindings/display/panel/sharp,ls020b1dd01d.txt b/Documentation/devicetree/bindings/display/panel/sharp,ls020b1dd01d.txt
deleted file mode 100644
index e45edbc565a3..000000000000
--- a/Documentation/devicetree/bindings/display/panel/sharp,ls020b1dd01d.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-Sharp 2.0" (240x160 pixels) 16-bit TFT LCD panel
-
-Required properties:
-- compatible: should be "sharp,ls020b1dd01d"
-- power-supply: as specified in the base binding
-
-Optional properties:
-- backlight: as specified in the base binding
-- enable-gpios: as specified in the base binding
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/sony,acx424akp.yaml b/Documentation/devicetree/bindings/display/panel/sony,acx424akp.yaml
new file mode 100644
index 000000000000..185dcc8fd1f9
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/sony,acx424akp.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/sony,acx424akp.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sony ACX424AKP 4" 480x864 AMOLED panel
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: sony,acx424akp
+  reg: true
+  reset-gpios: true
+  vddi-supply:
+     description: regulator that supplies the vddi voltage
+  enforce-video-mode: true
+
+required:
+  - compatible
+  - reg
+  - reset-gpios
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    dsi-controller@a0351000 {
+        compatible = "ste,mcde-dsi";
+        reg = <0xa0351000 0x1000>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        panel@0 {
+            compatible = "sony,acx424akp";
+            reg = <0>;
+            vddi-supply = <&foo>;
+            reset-gpios = <&foo_gpio 0 GPIO_ACTIVE_LOW>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml
new file mode 100644
index 000000000000..186e5e1c8fa3
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/xinpeng,xpp055c272.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Xinpeng XPP055C272 5.5in 720x1280 DSI panel
+
+maintainers:
+  - Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: xinpeng,xpp055c272
+  reg: true
+  backlight: true
+  reset-gpios: true
+  iovcc-supply:
+     description: regulator that supplies the iovcc voltage
+  vci-supply:
+     description: regulator that supplies the vci voltage
+
+required:
+  - compatible
+  - reg
+  - backlight
+  - iovcc-supply
+  - vci-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    dsi@ff450000 {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        panel@0 {
+            compatible = "xinpeng,xpp055c272";
+            reg = <0>;
+            backlight = <&backlight>;
+            iovcc-supply = <&vcc_1v8>;
+            vci-supply = <&vcc3v3_lcd>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/renesas,cmm.yaml b/Documentation/devicetree/bindings/display/renesas,cmm.yaml
new file mode 100644
index 000000000000..a57037b9e9ba
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/renesas,cmm.yaml
@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/renesas,cmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas R-Car Color Management Module (CMM)
+
+maintainers:
+  - Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+  - Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
+  - Jacopo Mondi <jacopo+renesas@jmondi.org>
+
+description: |+
+  Renesas R-Car color management module connected to R-Car DU video channels.
+  It provides image enhancement functions such as 1-D look-up tables (LUT),
+  3-D look-up tables (CLU), 1D-histogram generation (HGO), and color
+  space conversion (CSC).
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+        - enum:
+          - renesas,r8a7795-cmm
+          - renesas,r8a7796-cmm
+          - renesas,r8a77965-cmm
+          - renesas,r8a77990-cmm
+          - renesas,r8a77995-cmm
+        - const: renesas,rcar-gen3-cmm
+      - items:
+        - const: renesas,rcar-gen2-cmm
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - resets
+  - power-domains
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a7796-cpg-mssr.h>
+    #include <dt-bindings/power/r8a7796-sysc.h>
+
+    cmm0: cmm@fea40000 {
+         compatible = "renesas,r8a7796-cmm",
+                      "renesas,rcar-gen3-cmm";
+         reg = <0 0xfea40000 0 0x1000>;
+         power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+         clocks = <&cpg CPG_MOD 711>;
+         resets = <&cpg 711>;
+    };
diff --git a/Documentation/devicetree/bindings/display/renesas,du.txt b/Documentation/devicetree/bindings/display/renesas,du.txt
index 17cb2771364b..eb4ae41fe41f 100644
--- a/Documentation/devicetree/bindings/display/renesas,du.txt
+++ b/Documentation/devicetree/bindings/display/renesas,du.txt
@@ -41,10 +41,14 @@ Required Properties:
       supplied they must be named "dclkin.x" with "x" being the input clock
       numerical index.
 
-  - vsps: A list of phandle and channel index tuples to the VSPs that handle
-    the memory interfaces for the DU channels. The phandle identifies the VSP
-    instance that serves the DU channel, and the channel index identifies the
-    LIF instance in that VSP.
+  - renesas,cmms: A list of phandles to the CMM instances present in the SoC,
+    one for each available DU channel. The property shall not be specified for
+    SoCs that do not provide any CMM (such as V3M and V3H).
+
+  - renesas,vsps: A list of phandle and channel index tuples to the VSPs that
+    handle the memory interfaces for the DU channels. The phandle identifies the
+    VSP instance that serves the DU channel, and the channel index identifies
+    the LIF instance in that VSP.
 
 Required nodes:
 
@@ -92,7 +96,8 @@ Example: R8A7795 (R-Car H3) ES2.0 DU
 			 <&cpg CPG_MOD 722>,
 			 <&cpg CPG_MOD 721>;
 		clock-names = "du.0", "du.1", "du.2", "du.3";
-		vsps = <&vspd0 0>, <&vspd1 0>, <&vspd2 0>, <&vspd0 1>;
+		renesas,cmms = <&cmm0>, <&cmm1>, <&cmm2>, <&cmm3>;
+		renesas,vsps = <&vspd0 0>, <&vspd1 0>, <&vspd2 0>, <&vspd0 1>;
 
 		ports {
 			#address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt b/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt
index ce4c1fc9116c..151be3bba06f 100644
--- a/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt
+++ b/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt
@@ -4,13 +4,16 @@ Rockchip specific extensions to the Synopsys Designware MIPI DSI
 Required properties:
 - #address-cells: Should be <1>.
 - #size-cells: Should be <0>.
-- compatible: "rockchip,rk3288-mipi-dsi", "snps,dw-mipi-dsi".
-	      "rockchip,rk3399-mipi-dsi", "snps,dw-mipi-dsi".
+- compatible: one of
+	"rockchip,px30-mipi-dsi", "snps,dw-mipi-dsi"
+	"rockchip,rk3288-mipi-dsi", "snps,dw-mipi-dsi"
+	"rockchip,rk3399-mipi-dsi", "snps,dw-mipi-dsi"
 - reg: Represent the physical address range of the controller.
 - interrupts: Represent the controller's interrupt to the CPU(s).
 - clocks, clock-names: Phandles to the controller's pll reference
-  clock(ref) and APB clock(pclk). For RK3399, a phy config clock
-  (phy_cfg) and a grf clock(grf) are required. As described in [1].
+  clock(ref) when using an internal dphy and APB clock(pclk).
+  For RK3399, a phy config clock (phy_cfg) and a grf clock(grf)
+  are required. As described in [1].
 - rockchip,grf: this soc should set GRF regs to mux vopl/vopb.
 - ports: contain a port node with endpoint definitions as defined in [2].
   For vopb,set the reg = <0> and set the reg = <1> for vopl.
@@ -18,6 +21,8 @@ Required properties:
 - video port 1 for either a panel or subsequent encoder
 
 Optional properties:
+- phys: from general PHY binding: the phandle for the PHY device.
+- phy-names: Should be "dphy" if phys references an external phy.
 - 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".
diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip-lvds.txt b/Documentation/devicetree/bindings/display/rockchip/rockchip-lvds.txt
index 7849ff039229..aaf8c44cf90f 100644
--- a/Documentation/devicetree/bindings/display/rockchip/rockchip-lvds.txt
+++ b/Documentation/devicetree/bindings/display/rockchip/rockchip-lvds.txt
@@ -4,6 +4,7 @@ Rockchip RK3288 LVDS interface
 Required properties:
 - compatible: matching the soc type, one of
 	- "rockchip,rk3288-lvds";
+	- "rockchip,px30-lvds";
 
 - reg: physical base address of the controller and length
 	of memory mapped region.
@@ -18,6 +19,9 @@ Required properties:
 - rockchip,grf: phandle to the general register files syscon
 - rockchip,output: "rgb", "lvds" or "duallvds", This describes the output interface
 
+- phys: LVDS/DSI DPHY (px30 only)
+- phy-names: name of the PHY, must be "dphy" (px30 only)
+
 Optional properties:
 - pinctrl-names: must contain a "lcdc" entry.
 - pinctrl-0: pin control group to be used for this controller.
diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
deleted file mode 100644
index 31ab72cba3d4..000000000000
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ /dev/null
@@ -1,637 +0,0 @@
-Allwinner A10 Display Pipeline
-==============================
-
-The Allwinner A10 Display pipeline is composed of several components
-that are going to be documented below:
-
-For all connections between components up to the TCONs in the display
-pipeline, when there are multiple components of the same type at the
-same depth, the local endpoint ID must be the same as the remote
-component's index. For example, if the remote endpoint is Frontend 1,
-then the local endpoint ID must be 1.
-
-    Frontend 0  [0] ------- [0]  Backend 0  [0] ------- [0]  TCON 0
-		[1] --   -- [1]             [1] --   -- [1]
-		      \ /                         \ /
-		       X                           X
-		      / \                         / \
-		[0] --   -- [0]             [0] --   -- [0]
-    Frontend 1  [1] ------- [1]  Backend 1  [1] ------- [1]  TCON 1
-
-For a two pipeline system such as the one depicted above, the lines
-represent the connections between the components, while the numbers
-within the square brackets corresponds to the ID of the local endpoint.
-
-The same rule also applies to DE 2.0 mixer-TCON connections:
-
-    Mixer 0  [0] ----------- [0]  TCON 0
-	     [1] ----   ---- [1]
-		     \ /
-		      X
-		     / \
-	     [0] ----   ---- [0]
-    Mixer 1  [1] ----------- [1]  TCON 1
-
-HDMI Encoder
-------------
-
-The HDMI Encoder supports the HDMI video and audio outputs, and does
-CEC. It is one end of the pipeline.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun4i-a10-hdmi
-    * allwinner,sun5i-a10s-hdmi
-    * allwinner,sun6i-a31-hdmi
-  - reg: base address and size of memory-mapped region
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the HDMI encoder
-    * ahb: the HDMI interface clock
-    * mod: the HDMI module clock
-    * ddc: the HDMI ddc clock (A31 only)
-    * pll-0: the first video PLL
-    * pll-1: the second video PLL
-  - clock-names: the clock names mentioned above
-  - resets: phandle to the reset control for the HDMI encoder (A31 only)
-  - dmas: phandles to the DMA channels used by the HDMI encoder
-    * ddc-tx: The channel for DDC transmission
-    * ddc-rx: The channel for DDC reception
-    * audio-tx: The channel used for audio transmission
-  - dma-names: the channel names mentioned above
-
-  - ports: A ports node with endpoint definitions as defined in
-    Documentation/devicetree/bindings/media/video-interfaces.txt. The
-    first port should be the input endpoint. The second should be the
-    output, usually to an HDMI connector.
-
-DWC HDMI TX Encoder
--------------------
-
-The HDMI transmitter is a Synopsys DesignWare HDMI 1.4 TX controller IP
-with Allwinner's own PHY IP. It supports audio and video outputs and CEC.
-
-These DT bindings follow the Synopsys DWC HDMI TX bindings defined in
-Documentation/devicetree/bindings/display/bridge/dw_hdmi.txt with the
-following device-specific properties.
-
-Required properties:
-
-  - compatible: value must be one of:
-    * "allwinner,sun8i-a83t-dw-hdmi"
-    * "allwinner,sun50i-a64-dw-hdmi", "allwinner,sun8i-a83t-dw-hdmi"
-    * "allwinner,sun50i-h6-dw-hdmi"
-  - reg: base address and size of memory-mapped region
-  - reg-io-width: See dw_hdmi.txt. Shall be 1.
-  - interrupts: HDMI interrupt number
-  - clocks: phandles to the clocks feeding the HDMI encoder
-    * iahb: the HDMI bus clock
-    * isfr: the HDMI register clock
-    * tmds: TMDS clock
-    * cec: HDMI CEC clock (H6 only)
-    * hdcp: HDCP clock (H6 only)
-    * hdcp-bus: HDCP bus clock (H6 only)
-  - clock-names: the clock names mentioned above
-  - resets:
-    * ctrl: HDMI controller reset
-    * hdcp: HDCP reset (H6 only)
-  - reset-names: reset names mentioned above
-  - phys: phandle to the DWC HDMI PHY
-  - phy-names: must be "phy"
-
-  - ports: A ports node with endpoint definitions as defined in
-    Documentation/devicetree/bindings/media/video-interfaces.txt. The
-    first port should be the input endpoint. The second should be the
-    output, usually to an HDMI connector.
-
-Optional properties:
-  - hvcc-supply: the VCC power supply of the controller
-
-DWC HDMI PHY
-------------
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun8i-a83t-hdmi-phy
-    * allwinner,sun8i-h3-hdmi-phy
-    * allwinner,sun8i-r40-hdmi-phy
-    * allwinner,sun50i-a64-hdmi-phy
-    * allwinner,sun50i-h6-hdmi-phy
-  - reg: base address and size of memory-mapped region
-  - clocks: phandles to the clocks feeding the HDMI PHY
-    * bus: the HDMI PHY interface clock
-    * mod: the HDMI PHY module clock
-  - clock-names: the clock names mentioned above
-  - resets: phandle to the reset controller driving the PHY
-  - reset-names: must be "phy"
-
-H3, A64 and R40 HDMI PHY require additional clocks:
-  - pll-0: parent of phy clock
-  - pll-1: second possible phy clock parent (A64/R40 only)
-
-TV Encoder
-----------
-
-The TV Encoder supports the composite and VGA output. It is one end of
-the pipeline.
-
-Required properties:
- - compatible: value should be "allwinner,sun4i-a10-tv-encoder".
- - reg: base address and size of memory-mapped region
- - clocks: the clocks driving the TV encoder
- - resets: phandle to the reset controller driving the encoder
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoint.
-
-TCON
-----
-
-The TCON acts as a timing controller for RGB, LVDS and TV interfaces.
-
-Required properties:
- - compatible: value must be either:
-   * allwinner,sun4i-a10-tcon
-   * allwinner,sun5i-a13-tcon
-   * allwinner,sun6i-a31-tcon
-   * allwinner,sun6i-a31s-tcon
-   * allwinner,sun7i-a20-tcon
-   * allwinner,sun8i-a23-tcon
-   * allwinner,sun8i-a33-tcon
-   * allwinner,sun8i-a83t-tcon-lcd
-   * allwinner,sun8i-a83t-tcon-tv
-   * allwinner,sun8i-r40-tcon-tv
-   * allwinner,sun8i-v3s-tcon
-   * allwinner,sun9i-a80-tcon-lcd
-   * allwinner,sun9i-a80-tcon-tv
-   * "allwinner,sun50i-a64-tcon-lcd", "allwinner,sun8i-a83t-tcon-lcd"
-   * "allwinner,sun50i-a64-tcon-tv", "allwinner,sun8i-a83t-tcon-tv"
-   * allwinner,sun50i-h6-tcon-tv, allwinner,sun8i-r40-tcon-tv
- - reg: base address and size of memory-mapped region
- - interrupts: interrupt associated to this IP
- - clocks: phandles to the clocks feeding the TCON.
-   - 'ahb': the interface clocks
-   - 'tcon-ch0': The clock driving the TCON channel 0, if supported
- - resets: phandles to the reset controllers driving the encoder
-   - "lcd": the reset line for the TCON
-   - "edp": the reset line for the eDP block (A80 only)
-
- - clock-names: the clock names mentioned above
- - reset-names: the reset names mentioned above
- - clock-output-names: Name of the pixel clock created, if TCON supports
-   channel 0.
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoint, the second one the output
-
-  The output may have multiple endpoints. TCON can have 1 or 2 channels,
-  usually with the first channel being used for the panels interfaces
-  (RGB, LVDS, etc.), and the second being used for the outputs that
-  require another controller (TV Encoder, HDMI, etc.). The endpoints
-  will take an extra property, allwinner,tcon-channel, to specify the
-  channel the endpoint is associated to. If that property is not
-  present, the endpoint number will be used as the channel number.
-
-For TCONs with channel 0, there is one more clock required:
-   - 'tcon-ch0': The clock driving the TCON channel 0
-For TCONs with channel 1, there is one more clock required:
-   - 'tcon-ch1': The clock driving the TCON channel 1
-
-When TCON support LVDS (all TCONs except TV TCONs on A83T, R40 and those found
-in A13, H3, H5 and V3s SoCs), you need one more reset line:
-   - 'lvds': The reset line driving the LVDS logic
-
-And on the A23, A31, A31s and A33, you need one more clock line:
-   - 'lvds-alt': An alternative clock source, separate from the TCON channel 0
-                 clock, that can be used to drive the LVDS clock
-
-TCON TOP
---------
-
-TCON TOPs main purpose is to configure whole display pipeline. It determines
-relationships between mixers and TCONs, selects source TCON for HDMI, muxes
-LCD and TV encoder GPIO output, selects TV encoder clock source and contains
-additional TV TCON and DSI gates.
-
-It allows display pipeline to be configured in very different ways:
-
-                                / LCD0/LVDS0
-                 / [0] TCON-LCD0
-                 |              \ MIPI DSI
- mixer0          |
-        \        / [1] TCON-LCD1 - LCD1/LVDS1
-         TCON-TOP
-        /        \ [2] TCON-TV0 [0] - TVE0/RGB
- mixer1          |                  \
-                 |                   TCON-TOP - HDMI
-                 |                  /
-                 \ [3] TCON-TV1 [1] - TVE1/RGB
-
-Note that both TCON TOP references same physical unit. Both mixers can be
-connected to any TCON. Not all TCON TOP variants support all features.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun8i-r40-tcon-top
-    * allwinner,sun50i-h6-tcon-top
-  - reg: base address and size of the memory-mapped region.
-  - clocks: phandle to the clocks feeding the TCON TOP
-    * bus: TCON TOP interface clock
-    * tcon-tv0: TCON TV0 clock
-    * tve0: TVE0 clock (R40 only)
-    * tcon-tv1: TCON TV1 clock (R40 only)
-    * tve1: TVE0 clock (R40 only)
-    * dsi: MIPI DSI clock (R40 only)
-  - clock-names: clock name mentioned above
-  - resets: phandle to the reset line driving the TCON TOP
-  - #clock-cells : must contain 1
-  - clock-output-names: Names of clocks created for TCON TV0 channel clock,
-    TCON TV1 channel clock (R40 only) and DSI channel clock (R40 only), in
-    that order.
-
-- ports: A ports node with endpoint definitions as defined in
-    Documentation/devicetree/bindings/media/video-interfaces.txt. 6 ports should
-    be defined:
-    * port 0 is input for mixer0 mux
-    * port 1 is output for mixer0 mux
-    * port 2 is input for mixer1 mux
-    * port 3 is output for mixer1 mux
-    * port 4 is input for HDMI mux
-    * port 5 is output for HDMI mux
-    All output endpoints for mixer muxes and input endpoints for HDMI mux should
-    have reg property with the id of the target TCON, as shown in above graph
-    (0-3 for mixer muxes and 0-1 for HDMI mux). All ports should have only one
-    endpoint connected to remote endpoint.
-
-DRC
----
-
-The DRC (Dynamic Range Controller), found in the latest Allwinner SoCs
-(A31, A23, A33, A80), allows to dynamically adjust pixel
-brightness/contrast based on histogram measurements for LCD content
-adaptive backlight control.
-
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun6i-a31-drc
-    * allwinner,sun6i-a31s-drc
-    * allwinner,sun8i-a23-drc
-    * allwinner,sun8i-a33-drc
-    * allwinner,sun9i-a80-drc
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the DRC
-    * ahb: the DRC interface clock
-    * mod: the DRC module clock
-    * ram: the DRC DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset line driving the DRC
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the outputs
-
-Display Engine Backend
-----------------------
-
-The display engine backend exposes layers and sprites to the
-system.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun4i-a10-display-backend
-    * allwinner,sun5i-a13-display-backend
-    * allwinner,sun6i-a31-display-backend
-    * allwinner,sun7i-a20-display-backend
-    * allwinner,sun8i-a23-display-backend
-    * allwinner,sun8i-a33-display-backend
-    * allwinner,sun9i-a80-display-backend
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the frontend and backend
-    * ahb: the backend interface clock
-    * mod: the backend module clock
-    * ram: the backend DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset controllers driving the backend
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the output
-
-On the A33, some additional properties are required:
-  - reg needs to have an additional region corresponding to the SAT
-  - reg-names need to be set, with "be" and "sat"
-  - clocks and clock-names need to have a phandle to the SAT bus
-    clocks, whose name will be "sat"
-  - resets and reset-names need to have a phandle to the SAT bus
-    resets, whose name will be "sat"
-
-DEU
----
-
-The DEU (Detail Enhancement Unit), found in the Allwinner A80 SoC,
-can sharpen the display content in both luma and chroma channels.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun9i-a80-deu
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the DEU
-    * ahb: the DEU interface clock
-    * mod: the DEU module clock
-    * ram: the DEU DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset line driving the DEU
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the outputs
-
-Display Engine Frontend
------------------------
-
-The display engine frontend does formats conversion, scaling,
-deinterlacing and color space conversion.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun4i-a10-display-frontend
-    * allwinner,sun5i-a13-display-frontend
-    * allwinner,sun6i-a31-display-frontend
-    * allwinner,sun7i-a20-display-frontend
-    * allwinner,sun8i-a23-display-frontend
-    * allwinner,sun8i-a33-display-frontend
-    * allwinner,sun9i-a80-display-frontend
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the frontend and backend
-    * ahb: the backend interface clock
-    * mod: the backend module clock
-    * ram: the backend DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset controllers driving the backend
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the outputs
-
-Display Engine 2.0 Mixer
-------------------------
-
-The DE2 mixer have many functionalities, currently only layer blending is
-supported.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun8i-a83t-de2-mixer-0
-    * allwinner,sun8i-a83t-de2-mixer-1
-    * allwinner,sun8i-h3-de2-mixer-0
-    * allwinner,sun8i-r40-de2-mixer-0
-    * allwinner,sun8i-r40-de2-mixer-1
-    * allwinner,sun8i-v3s-de2-mixer
-    * allwinner,sun50i-a64-de2-mixer-0
-    * allwinner,sun50i-a64-de2-mixer-1
-    * allwinner,sun50i-h6-de3-mixer-0
-  - reg: base address and size of the memory-mapped region.
-  - clocks: phandles to the clocks feeding the mixer
-    * bus: the mixer interface clock
-    * mod: the mixer module clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset controllers driving the mixer
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the output
-
-
-Display Engine Pipeline
------------------------
-
-The display engine pipeline (and its entry point, since it can be
-either directly the backend or the frontend) is represented as an
-extra node.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun4i-a10-display-engine
-    * allwinner,sun5i-a10s-display-engine
-    * allwinner,sun5i-a13-display-engine
-    * allwinner,sun6i-a31-display-engine
-    * allwinner,sun6i-a31s-display-engine
-    * allwinner,sun7i-a20-display-engine
-    * allwinner,sun8i-a23-display-engine
-    * allwinner,sun8i-a33-display-engine
-    * allwinner,sun8i-a83t-display-engine
-    * allwinner,sun8i-h3-display-engine
-    * allwinner,sun8i-r40-display-engine
-    * allwinner,sun8i-v3s-display-engine
-    * allwinner,sun9i-a80-display-engine
-    * allwinner,sun50i-a64-display-engine
-    * allwinner,sun50i-h6-display-engine
-
-  - allwinner,pipelines: list of phandle to the display engine
-    frontends (DE 1.0) or mixers (DE 2.0/3.0) available.
-
-Example:
-
-panel: panel {
-	compatible = "olimex,lcd-olinuxino-43-ts";
-	#address-cells = <1>;
-	#size-cells = <0>;
-
-	port {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		panel_input: endpoint {
-			remote-endpoint = <&tcon0_out_panel>;
-		};
-	};
-};
-
-connector {
-	compatible = "hdmi-connector";
-	type = "a";
-
-	port {
-		hdmi_con_in: endpoint {
-			remote-endpoint = <&hdmi_out_con>;
-		};
-	};
-};
-
-hdmi: hdmi@1c16000 {
-	compatible = "allwinner,sun5i-a10s-hdmi";
-	reg = <0x01c16000 0x1000>;
-	interrupts = <58>;
-	clocks = <&ccu CLK_AHB_HDMI>, <&ccu CLK_HDMI>,
-		 <&ccu CLK_PLL_VIDEO0_2X>,
-		 <&ccu CLK_PLL_VIDEO1_2X>;
-	clock-names = "ahb", "mod", "pll-0", "pll-1";
-	dmas = <&dma SUN4I_DMA_NORMAL 16>,
-	       <&dma SUN4I_DMA_NORMAL 16>,
-	       <&dma SUN4I_DMA_DEDICATED 24>;
-	dma-names = "ddc-tx", "ddc-rx", "audio-tx";
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0>;
-
-			hdmi_in_tcon0: endpoint {
-				remote-endpoint = <&tcon0_out_hdmi>;
-			};
-		};
-
-		port@1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <1>;
-
-			hdmi_out_con: endpoint {
-				remote-endpoint = <&hdmi_con_in>;
-			};
-		};
-	};
-};
-
-tve0: tv-encoder@1c0a000 {
-	compatible = "allwinner,sun4i-a10-tv-encoder";
-	reg = <0x01c0a000 0x1000>;
-	clocks = <&ahb_gates 34>;
-	resets = <&tcon_ch0_clk 0>;
-
-	port {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		tve0_in_tcon0: endpoint@0 {
-			reg = <0>;
-			remote-endpoint = <&tcon0_out_tve0>;
-		};
-	};
-};
-
-tcon0: lcd-controller@1c0c000 {
-	compatible = "allwinner,sun5i-a13-tcon";
-	reg = <0x01c0c000 0x1000>;
-	interrupts = <44>;
-	resets = <&tcon_ch0_clk 1>;
-	reset-names = "lcd";
-	clocks = <&ahb_gates 36>,
-		 <&tcon_ch0_clk>,
-		 <&tcon_ch1_clk>;
-	clock-names = "ahb",
-		      "tcon-ch0",
-		      "tcon-ch1";
-	clock-output-names = "tcon-pixel-clock";
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		tcon0_in: port@0 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0>;
-
-			tcon0_in_be0: endpoint@0 {
-				reg = <0>;
-				remote-endpoint = <&be0_out_tcon0>;
-			};
-		};
-
-		tcon0_out: port@1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <1>;
-
-			tcon0_out_panel: endpoint@0 {
-				reg = <0>;
-				remote-endpoint = <&panel_input>;
-			};
-
-			tcon0_out_tve0: endpoint@1 {
-				reg = <1>;
-				remote-endpoint = <&tve0_in_tcon0>;
-			};
-		};
-	};
-};
-
-fe0: display-frontend@1e00000 {
-	compatible = "allwinner,sun5i-a13-display-frontend";
-	reg = <0x01e00000 0x20000>;
-	interrupts = <47>;
-	clocks = <&ahb_gates 46>, <&de_fe_clk>,
-		 <&dram_gates 25>;
-	clock-names = "ahb", "mod",
-		      "ram";
-	resets = <&de_fe_clk>;
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		fe0_out: port@1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <1>;
-
-			fe0_out_be0: endpoint {
-				remote-endpoint = <&be0_in_fe0>;
-			};
-		};
-	};
-};
-
-be0: display-backend@1e60000 {
-	compatible = "allwinner,sun5i-a13-display-backend";
-	reg = <0x01e60000 0x10000>;
-	interrupts = <47>;
-	clocks = <&ahb_gates 44>, <&de_be_clk>,
-		 <&dram_gates 26>;
-	clock-names = "ahb", "mod",
-		      "ram";
-	resets = <&de_be_clk>;
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		be0_in: port@0 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0>;
-
-			be0_in_fe0: endpoint@0 {
-				reg = <0>;
-				remote-endpoint = <&fe0_out_be0>;
-			};
-		};
-
-		be0_out: port@1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <1>;
-
-			be0_out_tcon0: endpoint@0 {
-				reg = <0>;
-				remote-endpoint = <&tcon0_in_be0>;
-			};
-		};
-	};
-};
-
-display-engine {
-	compatible = "allwinner,sun5i-a13-display-engine";
-	allwinner,pipelines = <&fe0>;
-};
diff --git a/Documentation/devicetree/bindings/display/tilcdc/tfp410.txt b/Documentation/devicetree/bindings/display/tilcdc/tfp410.txt
deleted file mode 100644
index a58ae7756fc6..000000000000
--- a/Documentation/devicetree/bindings/display/tilcdc/tfp410.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-Device-Tree bindings for tilcdc DRM TFP410 output driver
-
-Required properties:
- - compatible: value should be "ti,tilcdc,tfp410".
- - i2c: the phandle for the i2c device to use for DDC
-
-Recommended properties:
- - pinctrl-names, pinctrl-0: the pincontrol settings to configure
-   muxing properly for pins that connect to TFP410 device
- - powerdn-gpio: the powerdown GPIO, pulled low to power down the
-   TFP410 device (for DPMS_OFF)
-
-Example:
-
-	dvicape {
-		compatible = "ti,tilcdc,tfp410";
-		i2c = <&i2c2>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&bone_dvi_cape_dvi_00A1_pins>;
-		powerdn-gpio = <&gpio2 31 0>;
-	};
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml
index 230d74f22136..d0b541a461f3 100644
--- a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml
@@ -15,7 +15,11 @@ properties:
     const: 0
 
   compatible:
-    const: allwinner,sun6i-a31-mipi-dphy
+    oneOf:
+      - const: allwinner,sun6i-a31-mipi-dphy
+      - items:
+          - const: allwinner,sun50i-a64-mipi-dphy
+          - const: allwinner,sun6i-a31-mipi-dphy
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 146fbb688cda..1bc7b3c4b591 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -521,6 +521,8 @@ patternProperties:
     description: Lantiq Semiconductor
   "^lattice,.*":
     description: Lattice Semiconductor
+  "^leadtek,.*":
+    description: Shenzhen Leadtek Technology Co., Ltd.
   "^leez,.*":
     description: Leez
   "^lego,.*":
@@ -835,6 +837,8 @@ patternProperties:
     description: Sancloud Ltd
   "^sandisk,.*":
     description: Sandisk Corporation
+  "^satoz,.*":
+    description: Satoz International Co., Ltd
   "^sbs,.*":
     description: Smart Battery System
   "^schindler,.*":
@@ -1072,6 +1076,8 @@ patternProperties:
     description: Extreme Engineering Solutions (X-ES)
   "^xillybus,.*":
     description: Xillybus Ltd.
+  "^xinpeng,.*":
+    description: Shenzhen Xinpeng Technology Co., Ltd
   "^xlnx,.*":
     description: Xilinx
   "^xunlong,.*":
diff --git a/Documentation/fb/fbcon.rst b/Documentation/fb/fbcon.rst
index ebca41785abe..e57a3d1d085a 100644
--- a/Documentation/fb/fbcon.rst
+++ b/Documentation/fb/fbcon.rst
@@ -127,7 +127,7 @@ C. Boot options
 	is typically located on the same video card.  Thus, the consoles that
 	are controlled by the VGA console will be garbled.
 
-4. fbcon=rotate:<n>
+5. fbcon=rotate:<n>
 
 	This option changes the orientation angle of the console display. The
 	value 'n' accepts the following:
@@ -152,21 +152,21 @@ C. Boot options
 	Actually, the underlying fb driver is totally ignorant of console
 	rotation.
 
-5. fbcon=margin:<color>
+6. fbcon=margin:<color>
 
 	This option specifies the color of the margins. The margins are the
 	leftover area at the right and the bottom of the screen that are not
 	used by text. By default, this area will be black. The 'color' value
 	is an integer number that depends on the framebuffer driver being used.
 
-6. fbcon=nodefer
+7. fbcon=nodefer
 
 	If the kernel is compiled with deferred fbcon takeover support, normally
 	the framebuffer contents, left in place by the firmware/bootloader, will
 	be preserved until there actually is some text is output to the console.
 	This option causes fbcon to bind immediately to the fbdev device.
 
-7. fbcon=logo-pos:<location>
+8. fbcon=logo-pos:<location>
 
 	The only possible 'location' is 'center' (without quotes), and when
 	given, the bootup logo is moved from the default top-left corner
@@ -174,6 +174,11 @@ C. Boot options
 	displayed due to multiple CPUs, the collected line of logos is moved
 	as a whole.
 
+9. fbcon=logo-count:<n>
+
+	The value 'n' overrides the number of bootup logos. 0 disables the
+	logo, and -1 gives the default which is the number of online CPUs.
+
 C. Attaching, Detaching and Unloading
 
 Before going on to how to attach, detach and unload the framebuffer console, an
diff --git a/Documentation/fb/modedb.rst b/Documentation/fb/modedb.rst
index 9c4e3fd39e6d..624d08fd2856 100644
--- a/Documentation/fb/modedb.rst
+++ b/Documentation/fb/modedb.rst
@@ -65,6 +65,9 @@ Valid options are::
   - reflect_y (boolean): Perform an axial symmetry on the Y axis
   - rotate (integer): Rotate the initial framebuffer by x
     degrees. Valid values are 0, 90, 180 and 270.
+  - panel_orientation, one of "normal", "upside_down", "left_side_up", or
+    "right_side_up". For KMS drivers only, this sets the "panel orientation"
+    property on the kms connector as hint for kms users.
 
 
 -----------------------------------------------------------------------------
diff --git a/Documentation/gpu/drm-internals.rst b/Documentation/gpu/drm-internals.rst
index 966bd2d9f0cc..a73320576ca9 100644
--- a/Documentation/gpu/drm-internals.rst
+++ b/Documentation/gpu/drm-internals.rst
@@ -24,9 +24,9 @@ Driver Initialization
 At the core of every DRM driver is a :c:type:`struct drm_driver
 <drm_driver>` structure. Drivers typically statically initialize
 a drm_driver structure, and then pass it to
-:c:func:`drm_dev_alloc()` to allocate a device instance. After the
+drm_dev_alloc() to allocate a device instance. After the
 device instance is fully initialized it can be registered (which makes
-it accessible from userspace) using :c:func:`drm_dev_register()`.
+it accessible from userspace) using drm_dev_register().
 
 The :c:type:`struct drm_driver <drm_driver>` structure
 contains static information that describes the driver and features it
diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 23a3c986ef6d..906771e03103 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -3,7 +3,7 @@ Kernel Mode Setting (KMS)
 =========================
 
 Drivers must initialize the mode setting core by calling
-:c:func:`drm_mode_config_init()` on the DRM device. The function
+drm_mode_config_init() on the DRM device. The function
 initializes the :c:type:`struct drm_device <drm_device>`
 mode_config field and never fails. Once done, mode configuration must
 be setup by initializing the following fields.
@@ -181,8 +181,7 @@ Setting`_). The somewhat surprising part here is that properties are not
 directly instantiated on each object, but free-standing mode objects themselves,
 represented by :c:type:`struct drm_property <drm_property>`, which only specify
 the type and value range of a property. Any given property can be attached
-multiple times to different objects using :c:func:`drm_object_attach_property()
-<drm_object_attach_property>`.
+multiple times to different objects using drm_object_attach_property().
 
 .. kernel-doc:: include/drm/drm_mode_object.h
    :internal:
@@ -260,7 +259,8 @@ Taken all together there's two consequences for the atomic design:
   drm_connector_state <drm_connector_state>` for connectors. These are the only
   objects with userspace-visible and settable state. For internal state drivers
   can subclass these structures through embeddeding, or add entirely new state
-  structures for their globally shared hardware functions.
+  structures for their globally shared hardware functions, see :c:type:`struct
+  drm_private_state<drm_private_state>`.
 
 - An atomic update is assembled and validated as an entirely free-standing pile
   of structures within the :c:type:`drm_atomic_state <drm_atomic_state>`
@@ -269,6 +269,14 @@ Taken all together there's two consequences for the atomic design:
   to the driver and modeset objects. This way rolling back an update boils down
   to releasing memory and unreferencing objects like framebuffers.
 
+Locking of atomic state structures is internally using :c:type:`struct
+drm_modeset_lock <drm_modeset_lock>`. As a general rule the locking shouldn't be
+exposed to drivers, instead the right locks should be automatically acquired by
+any function that duplicates or peeks into a state, like e.g.
+drm_atomic_get_crtc_state().  Locking only protects the software data
+structure, ordering of committing state changes to hardware is sequenced using
+:c:type:`struct drm_crtc_commit <drm_crtc_commit>`.
+
 Read on in this chapter, and also in :ref:`drm_atomic_helper` for more detailed
 coverage of specific topics.
 
@@ -479,6 +487,9 @@ Color Management Properties
 .. kernel-doc:: drivers/gpu/drm/drm_color_mgmt.c
    :export:
 
+.. kernel-doc:: include/drm/drm_color_mgmt.h
+   :internal:
+
 Tile Group Property
 -------------------
 
diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst
index 59619296c84b..c77b32601260 100644
--- a/Documentation/gpu/drm-mm.rst
+++ b/Documentation/gpu/drm-mm.rst
@@ -149,19 +149,19 @@ struct :c:type:`struct drm_gem_object <drm_gem_object>`.
 To create a GEM object, a driver allocates memory for an instance of its
 specific GEM object type and initializes the embedded struct
 :c:type:`struct drm_gem_object <drm_gem_object>` with a call
-to :c:func:`drm_gem_object_init()`. The function takes a pointer
+to drm_gem_object_init(). The function takes a pointer
 to the DRM device, a pointer to the GEM object and the buffer object
 size in bytes.
 
 GEM uses shmem to allocate anonymous pageable memory.
-:c:func:`drm_gem_object_init()` will create an shmfs file of the
+drm_gem_object_init() will create an shmfs file of the
 requested size and store it into the struct :c:type:`struct
 drm_gem_object <drm_gem_object>` filp field. The memory is
 used as either main storage for the object when the graphics hardware
 uses system memory directly or as a backing store otherwise.
 
 Drivers are responsible for the actual physical pages allocation by
-calling :c:func:`shmem_read_mapping_page_gfp()` for each page.
+calling shmem_read_mapping_page_gfp() for each page.
 Note that they can decide to allocate pages when initializing the GEM
 object, or to delay allocation until the memory is needed (for instance
 when a page fault occurs as a result of a userspace memory access or
@@ -170,20 +170,18 @@ when the driver needs to start a DMA transfer involving the memory).
 Anonymous pageable memory allocation is not always desired, for instance
 when the hardware requires physically contiguous system memory as is
 often the case in embedded devices. Drivers can create GEM objects with
-no shmfs backing (called private GEM objects) by initializing them with
-a call to :c:func:`drm_gem_private_object_init()` instead of
-:c:func:`drm_gem_object_init()`. Storage for private GEM objects
-must be managed by drivers.
+no shmfs backing (called private GEM objects) by initializing them with a call
+to drm_gem_private_object_init() instead of drm_gem_object_init(). Storage for
+private GEM objects must be managed by drivers.
 
 GEM Objects Lifetime
 --------------------
 
 All GEM objects are reference-counted by the GEM core. References can be
-acquired and release by :c:func:`calling drm_gem_object_get()` and
-:c:func:`drm_gem_object_put()` respectively. The caller must hold the
-:c:type:`struct drm_device <drm_device>` struct_mutex lock when calling
-:c:func:`drm_gem_object_get()`. As a convenience, GEM provides
-:c:func:`drm_gem_object_put_unlocked()` functions that can be called without
+acquired and release by calling drm_gem_object_get() and drm_gem_object_put()
+respectively. The caller must hold the :c:type:`struct drm_device <drm_device>`
+struct_mutex lock when calling drm_gem_object_get(). As a convenience, GEM
+provides drm_gem_object_put_unlocked() functions that can be called without
 holding the lock.
 
 When the last reference to a GEM object is released the GEM core calls
@@ -194,7 +192,7 @@ free the GEM object and all associated resources.
 void (\*gem_free_object) (struct drm_gem_object \*obj); Drivers are
 responsible for freeing all GEM object resources. This includes the
 resources created by the GEM core, which need to be released with
-:c:func:`drm_gem_object_release()`.
+drm_gem_object_release().
 
 GEM Objects Naming
 ------------------
@@ -210,13 +208,11 @@ to the GEM object in other standard or driver-specific ioctls. Closing a
 DRM file handle frees all its GEM handles and dereferences the
 associated GEM objects.
 
-To create a handle for a GEM object drivers call
-:c:func:`drm_gem_handle_create()`. The function takes a pointer
-to the DRM file and the GEM object and returns a locally unique handle.
-When the handle is no longer needed drivers delete it with a call to
-:c:func:`drm_gem_handle_delete()`. Finally the GEM object
-associated with a handle can be retrieved by a call to
-:c:func:`drm_gem_object_lookup()`.
+To create a handle for a GEM object drivers call drm_gem_handle_create(). The
+function takes a pointer to the DRM file and the GEM object and returns a
+locally unique handle.  When the handle is no longer needed drivers delete it
+with a call to drm_gem_handle_delete(). Finally the GEM object associated with a
+handle can be retrieved by a call to drm_gem_object_lookup().
 
 Handles don't take ownership of GEM objects, they only take a reference
 to the object that will be dropped when the handle is destroyed. To
@@ -258,7 +254,7 @@ The mmap system call can't be used directly to map GEM objects, as they
 don't have their own file handle. Two alternative methods currently
 co-exist to map GEM objects to userspace. The first method uses a
 driver-specific ioctl to perform the mapping operation, calling
-:c:func:`do_mmap()` under the hood. This is often considered
+do_mmap() under the hood. This is often considered
 dubious, seems to be discouraged for new GEM-enabled drivers, and will
 thus not be described here.
 
@@ -267,23 +263,22 @@ The second method uses the mmap system call on the DRM file handle. void
 offset); DRM identifies the GEM object to be mapped by a fake offset
 passed through the mmap offset argument. Prior to being mapped, a GEM
 object must thus be associated with a fake offset. To do so, drivers
-must call :c:func:`drm_gem_create_mmap_offset()` on the object.
+must call drm_gem_create_mmap_offset() on the object.
 
 Once allocated, the fake offset value must be passed to the application
 in a driver-specific way and can then be used as the mmap offset
 argument.
 
-The GEM core provides a helper method :c:func:`drm_gem_mmap()` to
+The GEM core provides a helper method drm_gem_mmap() to
 handle object mapping. The method can be set directly as the mmap file
 operation handler. It will look up the GEM object based on the offset
 value and set the VMA operations to the :c:type:`struct drm_driver
-<drm_driver>` gem_vm_ops field. Note that
-:c:func:`drm_gem_mmap()` doesn't map memory to userspace, but
-relies on the driver-provided fault handler to map pages individually.
+<drm_driver>` gem_vm_ops field. Note that drm_gem_mmap() doesn't map memory to
+userspace, but relies on the driver-provided fault handler to map pages
+individually.
 
-To use :c:func:`drm_gem_mmap()`, drivers must fill the struct
-:c:type:`struct drm_driver <drm_driver>` gem_vm_ops field
-with a pointer to VM operations.
+To use drm_gem_mmap(), drivers must fill the struct :c:type:`struct drm_driver
+<drm_driver>` gem_vm_ops field with a pointer to VM operations.
 
 The VM operations is a :c:type:`struct vm_operations_struct <vm_operations_struct>`
 made up of several fields, the more interesting ones being:
@@ -298,9 +293,8 @@ made up of several fields, the more interesting ones being:
 
 
 The open and close operations must update the GEM object reference
-count. Drivers can use the :c:func:`drm_gem_vm_open()` and
-:c:func:`drm_gem_vm_close()` helper functions directly as open
-and close handlers.
+count. Drivers can use the drm_gem_vm_open() and drm_gem_vm_close() helper
+functions directly as open and close handlers.
 
 The fault operation handler is responsible for mapping individual pages
 to userspace when a page fault occurs. Depending on the memory
@@ -312,12 +306,12 @@ Drivers that want to map the GEM object upfront instead of handling page
 faults can implement their own mmap file operation handler.
 
 For platforms without MMU the GEM core provides a helper method
-:c:func:`drm_gem_cma_get_unmapped_area`. The mmap() routines will call
-this to get a proposed address for the mapping.
+drm_gem_cma_get_unmapped_area(). The mmap() routines will call this to get a
+proposed address for the mapping.
 
-To use :c:func:`drm_gem_cma_get_unmapped_area`, drivers must fill the
-struct :c:type:`struct file_operations <file_operations>` get_unmapped_area
-field with a pointer on :c:func:`drm_gem_cma_get_unmapped_area`.
+To use drm_gem_cma_get_unmapped_area(), drivers must fill the struct
+:c:type:`struct file_operations <file_operations>` get_unmapped_area field with
+a pointer on drm_gem_cma_get_unmapped_area().
 
 More detailed information about get_unmapped_area can be found in
 Documentation/nommu-mmap.txt
diff --git a/Documentation/gpu/drm-uapi.rst b/Documentation/gpu/drm-uapi.rst
index 94f90521f58c..56fec6ed1ad8 100644
--- a/Documentation/gpu/drm-uapi.rst
+++ b/Documentation/gpu/drm-uapi.rst
@@ -254,36 +254,45 @@ Validating changes with IGT
 There's a collection of tests that aims to cover the whole functionality of
 DRM drivers and that can be used to check that changes to DRM drivers or the
 core don't regress existing functionality. This test suite is called IGT and
-its code can be found in https://cgit.freedesktop.org/drm/igt-gpu-tools/.
+its code and instructions to build and run can be found in
+https://gitlab.freedesktop.org/drm/igt-gpu-tools/.
 
-To build IGT, start by installing its build dependencies. In Debian-based
-systems::
+Using VKMS to test DRM API
+--------------------------
 
-	# apt-get build-dep intel-gpu-tools
+VKMS is a software-only model of a KMS driver that is useful for testing
+and for running compositors. VKMS aims to enable a virtual display without
+the need for a hardware display capability. These characteristics made VKMS
+a perfect tool for validating the DRM core behavior and also support the
+compositor developer. VKMS makes it possible to test DRM functions in a
+virtual machine without display, simplifying the validation of some of the
+core changes.
 
-And in Fedora-based systems::
+To Validate changes in DRM API with VKMS, start setting the kernel: make
+sure to enable VKMS module; compile the kernel with the VKMS enabled and
+install it in the target machine. VKMS can be run in a Virtual Machine
+(QEMU, virtme or similar). It's recommended the use of KVM with the minimum
+of 1GB of RAM and four cores.
 
-	# dnf builddep intel-gpu-tools
+It's possible to run the IGT-tests in a VM in two ways:
 
-Then clone the repository::
+	1. Use IGT inside a VM
+	2. Use IGT from the host machine and write the results in a shared directory.
 
-	$ git clone git://anongit.freedesktop.org/drm/igt-gpu-tools
+As follow, there is an example of using a VM with a shared directory with
+the host machine to run igt-tests. As an example it's used virtme::
 
-Configure the build system and start the build::
+	$ virtme-run --rwdir /path/for/shared_dir --kdir=path/for/kernel/directory --mods=auto
 
-	$ cd igt-gpu-tools && ./autogen.sh && make -j6
+Run the igt-tests in the guest machine, as example it's ran the 'kms_flip'
+tests::
 
-Download the piglit dependency::
+	$ /path/for/igt-gpu-tools/scripts/run-tests.sh -p -s -t "kms_flip.*" -v
 
-	$ ./scripts/run-tests.sh -d
-
-And run the tests::
-
-	$ ./scripts/run-tests.sh -t kms -t core -s
-
-run-tests.sh is a wrapper around piglit that will execute the tests matching
-the -t options. A report in HTML format will be available in
-./results/html/index.html. Results can be compared with piglit.
+In this example, instead of build the igt_runner, Piglit is used
+(-p option); it's created html summary of the tests results and it's saved
+in the folder "igt-gpu-tools/results"; it's executed only the igt-tests
+matching the -t option.
 
 Display CRC Support
 -------------------
diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index d0947c5c4ab8..e539c42a3e78 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -466,9 +466,6 @@ GuC-based command submission
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
    :doc: GuC-based command submission
 
-.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
-   :internal:
-
 HuC
 ---
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c
diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index 6792fa9b6b6b..bc869b23fc39 100644
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@@ -142,14 +142,14 @@ Contact: Daniel Vetter, respective driver maintainers
 
 Level: Advanced
 
-Convert instances of dev_info/dev_err/dev_warn to their DRM_DEV_* equivalent
-----------------------------------------------------------------------------
+Convert logging to drm_* functions with drm_device paramater
+------------------------------------------------------------
 
 For drivers which could have multiple instances, it is necessary to
 differentiate between which is which in the logs. Since DRM_INFO/WARN/ERROR
 don't do this, drivers used dev_info/warn/err to make this differentiation. We
-now have DRM_DEV_* variants of the drm print macros, so we can start to convert
-those drivers back to using drm-formwatted specific log messages.
+now have drm_* variants of the drm print functions, so we can start to convert
+those drivers back to using drm-formatted specific log messages.
 
 Before you start this conversion please contact the relevant maintainers to make
 sure your work will be merged - not everyone agrees that the DRM dmesg macros
@@ -171,23 +171,40 @@ Contact: Maintainer of the driver you plan to convert
 
 Level: Intermediate
 
-Convert drivers to use drm_fb_helper_fbdev_setup/teardown()
------------------------------------------------------------
+Convert drivers to use drm_fbdev_generic_setup()
+------------------------------------------------
 
-Most drivers can use drm_fb_helper_fbdev_setup() except maybe:
+Most drivers can use drm_fbdev_generic_setup(). Driver have to implement
+atomic modesetting and GEM vmap support. Current generic fbdev emulation
+expects the framebuffer in system memory (or system-like memory).
 
-- amdgpu which has special logic to decide whether to call
-  drm_helper_disable_unused_functions()
+Contact: Maintainer of the driver you plan to convert
+
+Level: Intermediate
 
-- armada which isn't atomic and doesn't call
-  drm_helper_disable_unused_functions()
+drm_framebuffer_funcs and drm_mode_config_funcs.fb_create cleanup
+-----------------------------------------------------------------
 
-- i915 which calls drm_fb_helper_initial_config() in a worker
+A lot more drivers could be switched over to the drm_gem_framebuffer helpers.
+Various hold-ups:
 
-Drivers that use drm_framebuffer_remove() to clean up the fbdev framebuffer can
-probably use drm_fb_helper_fbdev_teardown().
+- Need to switch over to the generic dirty tracking code using
+  drm_atomic_helper_dirtyfb first (e.g. qxl).
 
-Contact: Maintainer of the driver you plan to convert
+- Need to switch to drm_fbdev_generic_setup(), otherwise a lot of the custom fb
+  setup code can't be deleted.
+
+- Many drivers wrap drm_gem_fb_create() only to check for valid formats. For
+  atomic drivers we could check for valid formats by calling
+  drm_plane_check_pixel_format() against all planes, and pass if any plane
+  supports the format. For non-atomic that's not possible since like the format
+  list for the primary plane is fake and we'd therefor reject valid formats.
+
+- Many drivers subclass drm_framebuffer, we'd need a embedding compatible
+  version of the varios drm_gem_fb_create functions. Maybe called
+  drm_gem_fb_create/_with_dirty/_with_funcs as needed.
+
+Contact: Daniel Vetter
 
 Level: Intermediate
 
@@ -328,8 +345,8 @@ drm_fb_helper tasks
   these igt tests need to be fixed: kms_fbcon_fbt@psr and
   kms_fbcon_fbt@psr-suspend.
 
-- The max connector argument for drm_fb_helper_init() and
-  drm_fb_helper_fbdev_setup() isn't used anymore and can be removed.
+- The max connector argument for drm_fb_helper_init() isn't used anymore and
+  can be removed.
 
 - The helper doesn't keep an array of connectors anymore so these can be
   removed: drm_fb_helper_single_add_all_connectors(),
@@ -351,6 +368,23 @@ connector register/unregister fixes
 
 Level: Intermediate
 
+Remove load/unload callbacks from all non-DRIVER_LEGACY drivers
+---------------------------------------------------------------
+
+The load/unload callbacks in struct &drm_driver are very much midlayers, plus
+for historical reasons they get the ordering wrong (and we can't fix that)
+between setting up the &drm_driver structure and calling drm_dev_register().
+
+- Rework drivers to no longer use the load/unload callbacks, directly coding the
+  load/unload sequence into the driver's probe function.
+
+- Once all non-DRIVER_LEGACY drivers are converted, disallow the load/unload
+  callbacks for all modern drivers.
+
+Contact: Daniel Vetter
+
+Level: Intermediate
+
 Core refactorings
 =================
 
diff --git a/MAINTAINERS b/MAINTAINERS
index ccbf31b92100..dc833b88c8bc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5025,6 +5025,24 @@ F:	Documentation/driver-api/dma-buf.rst
 K:	dma_(buf|fence|resv)
 T:	git git://anongit.freedesktop.org/drm/drm-misc
 
+DMA-BUF HEAPS FRAMEWORK
+M:	Sumit Semwal <sumit.semwal@linaro.org>
+R:	Andrew F. Davis <afd@ti.com>
+R:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
+R:	Liam Mark <lmark@codeaurora.org>
+R:	Laura Abbott <labbott@redhat.com>
+R:	Brian Starkey <Brian.Starkey@arm.com>
+R:	John Stultz <john.stultz@linaro.org>
+S:	Maintained
+L:	linux-media@vger.kernel.org
+L:	dri-devel@lists.freedesktop.org
+L:	linaro-mm-sig@lists.linaro.org (moderated for non-subscribers)
+F:	include/uapi/linux/dma-heap.h
+F:	include/linux/dma-heap.h
+F:	drivers/dma-buf/dma-heap.c
+F:	drivers/dma-buf/heaps/*
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+
 DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
 M:	Vinod Koul <vkoul@kernel.org>
 L:	dmaengine@vger.kernel.org
@@ -5230,6 +5248,12 @@ T:	git git://anongit.freedesktop.org/drm/drm-misc
 S:	Maintained
 F:	drivers/gpu/drm/bochs/
 
+DRM DRIVER FOR BOE HIMAX8279D PANELS
+M:	Jerry Han <hanxu5@huaqin.corp-partner.google.com>
+S:	Maintained
+F:	drivers/gpu/drm/panel/panel-boe-himax8279d.c
+F:	Documentation/devicetree/bindings/display/panel/boe,himax8279d.txt
+
 DRM DRIVER FOR FARADAY TVE200 TV ENCODER
 M:	Linus Walleij <linus.walleij@linaro.org>
 T:	git git://anongit.freedesktop.org/drm/drm-misc
@@ -5385,6 +5409,12 @@ S:	Maintained
 F:	drivers/gpu/drm/tiny/st7735r.c
 F:	Documentation/devicetree/bindings/display/sitronix,st7735r.txt
 
+DRM DRIVER FOR SONY ACX424AKP PANELS
+M:	Linus Walleij <linus.walleij@linaro.org>
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+S:	Maintained
+F:	drivers/gpu/drm/panel/panel-sony-acx424akp.c
+
 DRM DRIVER FOR ST-ERICSSON MCDE
 M:	Linus Walleij <linus.walleij@linaro.org>
 T:	git git://anongit.freedesktop.org/drm/drm-misc
@@ -5457,7 +5487,6 @@ F:	include/linux/vga*
 DRM DRIVERS AND MISC GPU PATCHES
 M:	Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
 M:	Maxime Ripard <mripard@kernel.org>
-M:	Sean Paul <sean@poorly.run>
 W:	https://01.org/linuxgraphics/gfx-docs/maintainer-tools/drm-misc.html
 S:	Maintained
 T:	git git://anongit.freedesktop.org/drm/drm-misc
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
index 44d1f884c3d3..139738bbdd36 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
@@ -6,21 +6,31 @@
  * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
  */
 
-#include <linux/gpio.h>
-#include <linux/platform_data/tc35876x.h>
+#include <linux/gpio/machine.h>
 #include <asm/intel-mid.h>
 
+static struct gpiod_lookup_table tc35876x_gpio_table = {
+	.dev_id	= "i2c_disp_brig",
+	.table	= {
+		GPIO_LOOKUP("0000:00:0c.0", -1, "bridge-reset", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("0000:00:0c.0", -1, "bl-en", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("0000:00:0c.0", -1, "vadd", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 /*tc35876x DSI_LVDS bridge chip and panel platform data*/
 static void *tc35876x_platform_data(void *data)
 {
-	static struct tc35876x_platform_data pdata;
+	struct gpiod_lookup_table *table = &tc35876x_gpio_table;
+	struct gpiod_lookup *lookup = table->table;
 
-	/* gpio pins set to -1 will not be used by the driver */
-	pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN");
-	pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN");
-	pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3");
+	lookup[0].chip_hwnum = get_gpio_by_name("LCMB_RXEN");
+	lookup[1].chip_hwnum = get_gpio_by_name("6S6P_BL_EN");
+	lookup[2].chip_hwnum = get_gpio_by_name("EN_VREG_LCD_V3P3");
+	gpiod_add_lookup_table(table);
 
-	return &pdata;
+	return NULL;
 }
 
 static const struct devs_id tc35876x_dev_id __initconst = {
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 70f740b09684..db18df6cb330 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -69,10 +69,6 @@ ACPI_MODULE_NAME("acpi_lpss");
 #define LPSS_SAVE_CTX			BIT(4)
 #define LPSS_NO_D3_DELAY		BIT(5)
 
-/* Crystal Cove PMIC shares same ACPI ID between different platforms */
-#define BYT_CRC_HRV			2
-#define CHT_CRC_HRV			3
-
 struct lpss_private_data;
 
 struct lpss_device_desc {
@@ -158,7 +154,7 @@ static void lpss_deassert_reset(struct lpss_private_data *pdata)
  */
 static struct pwm_lookup byt_pwm_lookup[] = {
 	PWM_LOOKUP_WITH_MODULE("80860F09:00", 0, "0000:00:02.0",
-			       "pwm_backlight", 0, PWM_POLARITY_NORMAL,
+			       "pwm_soc_backlight", 0, PWM_POLARITY_NORMAL,
 			       "pwm-lpss-platform"),
 };
 
@@ -170,8 +166,7 @@ static void byt_pwm_setup(struct lpss_private_data *pdata)
 	if (!adev->pnp.unique_id || strcmp(adev->pnp.unique_id, "1"))
 		return;
 
-	if (!acpi_dev_present("INT33FD", NULL, BYT_CRC_HRV))
-		pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
+	pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
 }
 
 #define LPSS_I2C_ENABLE			0x6c
@@ -204,7 +199,7 @@ static void byt_i2c_setup(struct lpss_private_data *pdata)
 /* BSW PWM used for backlight control by the i915 driver */
 static struct pwm_lookup bsw_pwm_lookup[] = {
 	PWM_LOOKUP_WITH_MODULE("80862288:00", 0, "0000:00:02.0",
-			       "pwm_backlight", 0, PWM_POLARITY_NORMAL,
+			       "pwm_soc_backlight", 0, PWM_POLARITY_NORMAL,
 			       "pwm-lpss-platform"),
 };
 
diff --git a/drivers/auxdisplay/cfag12864bfb.c b/drivers/auxdisplay/cfag12864bfb.c
index 4074886b7bc8..2002291ab338 100644
--- a/drivers/auxdisplay/cfag12864bfb.c
+++ b/drivers/auxdisplay/cfag12864bfb.c
@@ -57,7 +57,7 @@ static int cfag12864bfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	return vm_map_pages_zero(vma, &pages, 1);
 }
 
-static struct fb_ops cfag12864bfb_ops = {
+static const struct fb_ops cfag12864bfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_read = fb_sys_read,
 	.fb_write = fb_sys_write,
diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c
index a2fcde582e2a..d951d54b26f5 100644
--- a/drivers/auxdisplay/ht16k33.c
+++ b/drivers/auxdisplay/ht16k33.c
@@ -228,7 +228,7 @@ static int ht16k33_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	return vm_map_pages_zero(vma, &pages, 1);
 }
 
-static struct fb_ops ht16k33_fb_ops = {
+static const struct fb_ops ht16k33_fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_read = fb_sys_read,
 	.fb_write = fb_sys_write,
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index a23b6752d11a..0613bb7770f5 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -44,4 +44,15 @@ config DMABUF_SELFTESTS
 	default n
 	depends on DMA_SHARED_BUFFER
 
+menuconfig DMABUF_HEAPS
+	bool "DMA-BUF Userland Memory Heaps"
+	select DMA_SHARED_BUFFER
+	help
+	  Choose this option to enable the DMA-BUF userland memory heaps.
+	  This options creates per heap chardevs in /dev/dma_heap/ which
+	  allows userspace to allocate dma-bufs that can be shared
+	  between drivers.
+
+source "drivers/dma-buf/heaps/Kconfig"
+
 endmenu
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 03479da06422..9c190026bfab 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
 	 dma-resv.o seqno-fence.o
+obj-$(CONFIG_DMABUF_HEAPS)	+= dma-heap.o
+obj-$(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
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index ce41cd9b758a..d4097856c86b 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -878,29 +878,9 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
  *   with calls to dma_buf_begin_cpu_access() and dma_buf_end_cpu_access()
  *   access.
  *
- *   To support dma_buf objects residing in highmem cpu access is page-based
- *   using an api similar to kmap. Accessing a dma_buf is done in aligned chunks
- *   of PAGE_SIZE size. Before accessing a chunk it needs to be mapped, which
- *   returns a pointer in kernel virtual address space. Afterwards the chunk
- *   needs to be unmapped again. There is no limit on how often a given chunk
- *   can be mapped and unmapped, i.e. the importer does not need to call
- *   begin_cpu_access again before mapping the same chunk again.
- *
- *   Interfaces::
- *      void \*dma_buf_kmap(struct dma_buf \*, unsigned long);
- *      void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*);
- *
- *   Implementing the functions is optional for exporters and for importers all
- *   the restrictions of using kmap apply.
- *
- *   dma_buf kmap calls outside of the range specified in begin_cpu_access are
- *   undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on
- *   the partial chunks at the beginning and end but may return stale or bogus
- *   data outside of the range (in these partial chunks).
- *
- *   For some cases the overhead of kmap can be too high, a vmap interface
- *   is introduced. This interface should be used very carefully, as vmalloc
- *   space is a limited resources on many architectures.
+ *   Since for most kernel internal dma-buf accesses need the entire buffer, a
+ *   vmap interface is introduced. Note that on very old 32-bit architectures
+ *   vmalloc space might be limited and result in vmap calls failing.
  *
  *   Interfaces::
  *      void \*dma_buf_vmap(struct dma_buf \*dmabuf)
@@ -1050,43 +1030,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dmabuf,
 }
 EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access);
 
-/**
- * dma_buf_kmap - Map a page of the buffer object into kernel address space. The
- * same restrictions as for kmap and friends apply.
- * @dmabuf:	[in]	buffer to map page from.
- * @page_num:	[in]	page in PAGE_SIZE units to map.
- *
- * This call must always succeed, any necessary preparations that might fail
- * need to be done in begin_cpu_access.
- */
-void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num)
-{
-	WARN_ON(!dmabuf);
-
-	if (!dmabuf->ops->map)
-		return NULL;
-	return dmabuf->ops->map(dmabuf, page_num);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kmap);
-
-/**
- * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap.
- * @dmabuf:	[in]	buffer to unmap page from.
- * @page_num:	[in]	page in PAGE_SIZE units to unmap.
- * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap.
- *
- * This call must always succeed.
- */
-void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long page_num,
-		    void *vaddr)
-{
-	WARN_ON(!dmabuf);
-
-	if (dmabuf->ops->unmap)
-		dmabuf->ops->unmap(dmabuf, page_num, vaddr);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kunmap);
-
 
 /**
  * dma_buf_mmap - Setup up a userspace mmap with the given vma
diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c
new file mode 100644
index 000000000000..afd22c9dbdcf
--- /dev/null
+++ b/drivers/dma-buf/dma-heap.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Framework for userspace DMA-BUF allocations
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#include <linux/cdev.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/err.h>
+#include <linux/xarray.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/dma-heap.h>
+#include <uapi/linux/dma-heap.h>
+
+#define DEVNAME "dma_heap"
+
+#define NUM_HEAP_MINORS 128
+
+/**
+ * struct dma_heap - represents a dmabuf heap in the system
+ * @name:		used for debugging/device-node name
+ * @ops:		ops struct for this heap
+ * @heap_devt		heap device node
+ * @list		list head connecting to list of heaps
+ * @heap_cdev		heap char device
+ *
+ * Represents a heap of memory from which buffers can be made.
+ */
+struct dma_heap {
+	const char *name;
+	const struct dma_heap_ops *ops;
+	void *priv;
+	dev_t heap_devt;
+	struct list_head list;
+	struct cdev heap_cdev;
+};
+
+static LIST_HEAD(heap_list);
+static DEFINE_MUTEX(heap_list_lock);
+static dev_t dma_heap_devt;
+static struct class *dma_heap_class;
+static DEFINE_XARRAY_ALLOC(dma_heap_minors);
+
+static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len,
+				 unsigned int fd_flags,
+				 unsigned int heap_flags)
+{
+	/*
+	 * Allocations from all heaps have to begin
+	 * and end on page boundaries.
+	 */
+	len = PAGE_ALIGN(len);
+	if (!len)
+		return -EINVAL;
+
+	return heap->ops->allocate(heap, len, fd_flags, heap_flags);
+}
+
+static int dma_heap_open(struct inode *inode, struct file *file)
+{
+	struct dma_heap *heap;
+
+	heap = xa_load(&dma_heap_minors, iminor(inode));
+	if (!heap) {
+		pr_err("dma_heap: minor %d unknown.\n", iminor(inode));
+		return -ENODEV;
+	}
+
+	/* instance data as context */
+	file->private_data = heap;
+	nonseekable_open(inode, file);
+
+	return 0;
+}
+
+static long dma_heap_ioctl_allocate(struct file *file, void *data)
+{
+	struct dma_heap_allocation_data *heap_allocation = data;
+	struct dma_heap *heap = file->private_data;
+	int fd;
+
+	if (heap_allocation->fd)
+		return -EINVAL;
+
+	if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS)
+		return -EINVAL;
+
+	if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS)
+		return -EINVAL;
+
+	fd = dma_heap_buffer_alloc(heap, heap_allocation->len,
+				   heap_allocation->fd_flags,
+				   heap_allocation->heap_flags);
+	if (fd < 0)
+		return fd;
+
+	heap_allocation->fd = fd;
+
+	return 0;
+}
+
+static unsigned int dma_heap_ioctl_cmds[] = {
+	DMA_HEAP_IOCTL_ALLOC,
+};
+
+static long dma_heap_ioctl(struct file *file, unsigned int ucmd,
+			   unsigned long arg)
+{
+	char stack_kdata[128];
+	char *kdata = stack_kdata;
+	unsigned int kcmd;
+	unsigned int in_size, out_size, drv_size, ksize;
+	int nr = _IOC_NR(ucmd);
+	int ret = 0;
+
+	if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds))
+		return -EINVAL;
+
+	/* Get the kernel ioctl cmd that matches */
+	kcmd = dma_heap_ioctl_cmds[nr];
+
+	/* Figure out the delta between user cmd size and kernel cmd size */
+	drv_size = _IOC_SIZE(kcmd);
+	out_size = _IOC_SIZE(ucmd);
+	in_size = out_size;
+	if ((ucmd & kcmd & IOC_IN) == 0)
+		in_size = 0;
+	if ((ucmd & kcmd & IOC_OUT) == 0)
+		out_size = 0;
+	ksize = max(max(in_size, out_size), drv_size);
+
+	/* If necessary, allocate buffer for ioctl argument */
+	if (ksize > sizeof(stack_kdata)) {
+		kdata = kmalloc(ksize, GFP_KERNEL);
+		if (!kdata)
+			return -ENOMEM;
+	}
+
+	if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) {
+		ret = -EFAULT;
+		goto err;
+	}
+
+	/* zero out any difference between the kernel/user structure size */
+	if (ksize > in_size)
+		memset(kdata + in_size, 0, ksize - in_size);
+
+	switch (kcmd) {
+	case DMA_HEAP_IOCTL_ALLOC:
+		ret = dma_heap_ioctl_allocate(file, kdata);
+		break;
+	default:
+		ret = -ENOTTY;
+		goto err;
+	}
+
+	if (copy_to_user((void __user *)arg, kdata, out_size) != 0)
+		ret = -EFAULT;
+err:
+	if (kdata != stack_kdata)
+		kfree(kdata);
+	return ret;
+}
+
+static const struct file_operations dma_heap_fops = {
+	.owner          = THIS_MODULE,
+	.open		= dma_heap_open,
+	.unlocked_ioctl = dma_heap_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= dma_heap_ioctl,
+#endif
+};
+
+/**
+ * dma_heap_get_drvdata() - get per-subdriver data for the heap
+ * @heap: DMA-Heap to retrieve private data for
+ *
+ * Returns:
+ * The per-subdriver data for the heap.
+ */
+void *dma_heap_get_drvdata(struct dma_heap *heap)
+{
+	return heap->priv;
+}
+
+struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info)
+{
+	struct dma_heap *heap, *h, *err_ret;
+	struct device *dev_ret;
+	unsigned int minor;
+	int ret;
+
+	if (!exp_info->name || !strcmp(exp_info->name, "")) {
+		pr_err("dma_heap: Cannot add heap without a name\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!exp_info->ops || !exp_info->ops->allocate) {
+		pr_err("dma_heap: Cannot add heap with invalid ops struct\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* check the name is unique */
+	mutex_lock(&heap_list_lock);
+	list_for_each_entry(h, &heap_list, list) {
+		if (!strcmp(h->name, exp_info->name)) {
+			mutex_unlock(&heap_list_lock);
+			pr_err("dma_heap: Already registered heap named %s\n",
+			       exp_info->name);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+	mutex_unlock(&heap_list_lock);
+
+	heap = kzalloc(sizeof(*heap), GFP_KERNEL);
+	if (!heap)
+		return ERR_PTR(-ENOMEM);
+
+	heap->name = exp_info->name;
+	heap->ops = exp_info->ops;
+	heap->priv = exp_info->priv;
+
+	/* Find unused minor number */
+	ret = xa_alloc(&dma_heap_minors, &minor, heap,
+		       XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("dma_heap: Unable to get minor number for heap\n");
+		err_ret = ERR_PTR(ret);
+		goto err0;
+	}
+
+	/* Create device */
+	heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor);
+
+	cdev_init(&heap->heap_cdev, &dma_heap_fops);
+	ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1);
+	if (ret < 0) {
+		pr_err("dma_heap: Unable to add char device\n");
+		err_ret = ERR_PTR(ret);
+		goto err1;
+	}
+
+	dev_ret = device_create(dma_heap_class,
+				NULL,
+				heap->heap_devt,
+				NULL,
+				heap->name);
+	if (IS_ERR(dev_ret)) {
+		pr_err("dma_heap: Unable to create device\n");
+		err_ret = ERR_CAST(dev_ret);
+		goto err2;
+	}
+	/* Add heap to the list */
+	mutex_lock(&heap_list_lock);
+	list_add(&heap->list, &heap_list);
+	mutex_unlock(&heap_list_lock);
+
+	return heap;
+
+err2:
+	cdev_del(&heap->heap_cdev);
+err1:
+	xa_erase(&dma_heap_minors, minor);
+err0:
+	kfree(heap);
+	return err_ret;
+}
+
+static char *dma_heap_devnode(struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev));
+}
+
+static int dma_heap_init(void)
+{
+	int ret;
+
+	ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME);
+	if (ret)
+		return ret;
+
+	dma_heap_class = class_create(THIS_MODULE, DEVNAME);
+	if (IS_ERR(dma_heap_class)) {
+		unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS);
+		return PTR_ERR(dma_heap_class);
+	}
+	dma_heap_class->devnode = dma_heap_devnode;
+
+	return 0;
+}
+subsys_initcall(dma_heap_init);
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 709002515550..4264e64788c4 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -34,6 +34,7 @@
 
 #include <linux/dma-resv.h>
 #include <linux/export.h>
+#include <linux/sched/mm.h>
 
 /**
  * DOC: Reservation Object Overview
@@ -95,6 +96,37 @@ static void dma_resv_list_free(struct dma_resv_list *list)
 	kfree_rcu(list, rcu);
 }
 
+#if IS_ENABLED(CONFIG_LOCKDEP)
+static int __init dma_resv_lockdep(void)
+{
+	struct mm_struct *mm = mm_alloc();
+	struct ww_acquire_ctx ctx;
+	struct dma_resv obj;
+	int ret;
+
+	if (!mm)
+		return -ENOMEM;
+
+	dma_resv_init(&obj);
+
+	down_read(&mm->mmap_sem);
+	ww_acquire_init(&ctx, &reservation_ww_class);
+	ret = dma_resv_lock(&obj, &ctx);
+	if (ret == -EDEADLK)
+		dma_resv_lock_slow(&obj, &ctx);
+	fs_reclaim_acquire(GFP_KERNEL);
+	fs_reclaim_release(GFP_KERNEL);
+	ww_mutex_unlock(&obj.lock);
+	ww_acquire_fini(&ctx);
+	up_read(&mm->mmap_sem);
+	
+	mmput(mm);
+
+	return 0;
+}
+subsys_initcall(dma_resv_lockdep);
+#endif
+
 /**
  * dma_resv_init - initialize a reservation object
  * @obj: the reservation object
diff --git a/drivers/dma-buf/heaps/Kconfig b/drivers/dma-buf/heaps/Kconfig
new file mode 100644
index 000000000000..a5eef06c4226
--- /dev/null
+++ b/drivers/dma-buf/heaps/Kconfig
@@ -0,0 +1,14 @@
+config DMABUF_HEAPS_SYSTEM
+	bool "DMA-BUF System Heap"
+	depends on DMABUF_HEAPS
+	help
+	  Choose this option to enable the system dmabuf heap. The system heap
+	  is backed by pages from the buddy allocator. If in doubt, say Y.
+
+config DMABUF_HEAPS_CMA
+	bool "DMA-BUF CMA Heap"
+	depends on DMABUF_HEAPS && DMA_CMA
+	help
+	  Choose this option to enable dma-buf CMA heap. This heap is backed
+	  by the Contiguous Memory Allocator (CMA). If your system has these
+	  regions, you should say Y here.
diff --git a/drivers/dma-buf/heaps/Makefile b/drivers/dma-buf/heaps/Makefile
new file mode 100644
index 000000000000..6e54cdec3da0
--- /dev/null
+++ b/drivers/dma-buf/heaps/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y					+= heap-helpers.o
+obj-$(CONFIG_DMABUF_HEAPS_SYSTEM)	+= system_heap.o
+obj-$(CONFIG_DMABUF_HEAPS_CMA)		+= cma_heap.o
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
new file mode 100644
index 000000000000..626cf7fd033a
--- /dev/null
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMABUF CMA heap exporter
+ *
+ * Copyright (C) 2012, 2019 Linaro Ltd.
+ * Author: <benjamin.gaignard@linaro.org> for ST-Ericsson.
+ */
+
+#include <linux/cma.h>
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-heap.h>
+#include <linux/dma-contiguous.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/scatterlist.h>
+#include <linux/sched/signal.h>
+
+#include "heap-helpers.h"
+
+struct cma_heap {
+	struct dma_heap *heap;
+	struct cma *cma;
+};
+
+static void cma_heap_free(struct heap_helper_buffer *buffer)
+{
+	struct cma_heap *cma_heap = dma_heap_get_drvdata(buffer->heap);
+	unsigned long nr_pages = buffer->pagecount;
+	struct page *cma_pages = buffer->priv_virt;
+
+	/* free page list */
+	kfree(buffer->pages);
+	/* release memory */
+	cma_release(cma_heap->cma, cma_pages, nr_pages);
+	kfree(buffer);
+}
+
+/* dmabuf heap CMA operations functions */
+static int cma_heap_allocate(struct dma_heap *heap,
+			     unsigned long len,
+			     unsigned long fd_flags,
+			     unsigned long heap_flags)
+{
+	struct cma_heap *cma_heap = dma_heap_get_drvdata(heap);
+	struct heap_helper_buffer *helper_buffer;
+	struct page *cma_pages;
+	size_t size = PAGE_ALIGN(len);
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	unsigned long align = get_order(size);
+	struct dma_buf *dmabuf;
+	int ret = -ENOMEM;
+	pgoff_t pg;
+
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL);
+	if (!helper_buffer)
+		return -ENOMEM;
+
+	init_heap_helper_buffer(helper_buffer, cma_heap_free);
+	helper_buffer->heap = heap;
+	helper_buffer->size = len;
+
+	cma_pages = cma_alloc(cma_heap->cma, nr_pages, align, false);
+	if (!cma_pages)
+		goto free_buf;
+
+	if (PageHighMem(cma_pages)) {
+		unsigned long nr_clear_pages = nr_pages;
+		struct page *page = cma_pages;
+
+		while (nr_clear_pages > 0) {
+			void *vaddr = kmap_atomic(page);
+
+			memset(vaddr, 0, PAGE_SIZE);
+			kunmap_atomic(vaddr);
+			/*
+			 * Avoid wasting time zeroing memory if the process
+			 * has been killed by by SIGKILL
+			 */
+			if (fatal_signal_pending(current))
+				goto free_cma;
+
+			page++;
+			nr_clear_pages--;
+		}
+	} else {
+		memset(page_address(cma_pages), 0, size);
+	}
+
+	helper_buffer->pagecount = nr_pages;
+	helper_buffer->pages = kmalloc_array(helper_buffer->pagecount,
+					     sizeof(*helper_buffer->pages),
+					     GFP_KERNEL);
+	if (!helper_buffer->pages) {
+		ret = -ENOMEM;
+		goto free_cma;
+	}
+
+	for (pg = 0; pg < helper_buffer->pagecount; pg++)
+		helper_buffer->pages[pg] = &cma_pages[pg];
+
+	/* create the dmabuf */
+	dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		goto free_pages;
+	}
+
+	helper_buffer->dmabuf = dmabuf;
+	helper_buffer->priv_virt = cma_pages;
+
+	ret = dma_buf_fd(dmabuf, fd_flags);
+	if (ret < 0) {
+		dma_buf_put(dmabuf);
+		/* just return, as put will call release and that will free */
+		return ret;
+	}
+
+	return ret;
+
+free_pages:
+	kfree(helper_buffer->pages);
+free_cma:
+	cma_release(cma_heap->cma, cma_pages, nr_pages);
+free_buf:
+	kfree(helper_buffer);
+	return ret;
+}
+
+static const struct dma_heap_ops cma_heap_ops = {
+	.allocate = cma_heap_allocate,
+};
+
+static int __add_cma_heap(struct cma *cma, void *data)
+{
+	struct cma_heap *cma_heap;
+	struct dma_heap_export_info exp_info;
+
+	cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL);
+	if (!cma_heap)
+		return -ENOMEM;
+	cma_heap->cma = cma;
+
+	exp_info.name = cma_get_name(cma);
+	exp_info.ops = &cma_heap_ops;
+	exp_info.priv = cma_heap;
+
+	cma_heap->heap = dma_heap_add(&exp_info);
+	if (IS_ERR(cma_heap->heap)) {
+		int ret = PTR_ERR(cma_heap->heap);
+
+		kfree(cma_heap);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int add_default_cma_heap(void)
+{
+	struct cma *default_cma = dev_get_cma_area(NULL);
+	int ret = 0;
+
+	if (default_cma)
+		ret = __add_cma_heap(default_cma, NULL);
+
+	return ret;
+}
+module_init(add_default_cma_heap);
+MODULE_DESCRIPTION("DMA-BUF CMA Heap");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma-buf/heaps/heap-helpers.c b/drivers/dma-buf/heaps/heap-helpers.c
new file mode 100644
index 000000000000..9f964ca3f59c
--- /dev/null
+++ b/drivers/dma-buf/heaps/heap-helpers.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <uapi/linux/dma-heap.h>
+
+#include "heap-helpers.h"
+
+void init_heap_helper_buffer(struct heap_helper_buffer *buffer,
+			     void (*free)(struct heap_helper_buffer *))
+{
+	buffer->priv_virt = NULL;
+	mutex_init(&buffer->lock);
+	buffer->vmap_cnt = 0;
+	buffer->vaddr = NULL;
+	buffer->pagecount = 0;
+	buffer->pages = NULL;
+	INIT_LIST_HEAD(&buffer->attachments);
+	buffer->free = free;
+}
+
+struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer,
+					  int fd_flags)
+{
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+
+	exp_info.ops = &heap_helper_ops;
+	exp_info.size = buffer->size;
+	exp_info.flags = fd_flags;
+	exp_info.priv = buffer;
+
+	return dma_buf_export(&exp_info);
+}
+
+static void *dma_heap_map_kernel(struct heap_helper_buffer *buffer)
+{
+	void *vaddr;
+
+	vaddr = vmap(buffer->pages, buffer->pagecount, VM_MAP, PAGE_KERNEL);
+	if (!vaddr)
+		return ERR_PTR(-ENOMEM);
+
+	return vaddr;
+}
+
+static void dma_heap_buffer_destroy(struct heap_helper_buffer *buffer)
+{
+	if (buffer->vmap_cnt > 0) {
+		WARN(1, "%s: buffer still mapped in the kernel\n", __func__);
+		vunmap(buffer->vaddr);
+	}
+
+	buffer->free(buffer);
+}
+
+static void *dma_heap_buffer_vmap_get(struct heap_helper_buffer *buffer)
+{
+	void *vaddr;
+
+	if (buffer->vmap_cnt) {
+		buffer->vmap_cnt++;
+		return buffer->vaddr;
+	}
+	vaddr = dma_heap_map_kernel(buffer);
+	if (IS_ERR(vaddr))
+		return vaddr;
+	buffer->vaddr = vaddr;
+	buffer->vmap_cnt++;
+	return vaddr;
+}
+
+static void dma_heap_buffer_vmap_put(struct heap_helper_buffer *buffer)
+{
+	if (!--buffer->vmap_cnt) {
+		vunmap(buffer->vaddr);
+		buffer->vaddr = NULL;
+	}
+}
+
+struct dma_heaps_attachment {
+	struct device *dev;
+	struct sg_table table;
+	struct list_head list;
+};
+
+static int dma_heap_attach(struct dma_buf *dmabuf,
+			   struct dma_buf_attachment *attachment)
+{
+	struct dma_heaps_attachment *a;
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	int ret;
+
+	a = kzalloc(sizeof(*a), GFP_KERNEL);
+	if (!a)
+		return -ENOMEM;
+
+	ret = sg_alloc_table_from_pages(&a->table, buffer->pages,
+					buffer->pagecount, 0,
+					buffer->pagecount << PAGE_SHIFT,
+					GFP_KERNEL);
+	if (ret) {
+		kfree(a);
+		return ret;
+	}
+
+	a->dev = attachment->dev;
+	INIT_LIST_HEAD(&a->list);
+
+	attachment->priv = a;
+
+	mutex_lock(&buffer->lock);
+	list_add(&a->list, &buffer->attachments);
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static void dma_heap_detach(struct dma_buf *dmabuf,
+			    struct dma_buf_attachment *attachment)
+{
+	struct dma_heaps_attachment *a = attachment->priv;
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	mutex_lock(&buffer->lock);
+	list_del(&a->list);
+	mutex_unlock(&buffer->lock);
+
+	sg_free_table(&a->table);
+	kfree(a);
+}
+
+static
+struct sg_table *dma_heap_map_dma_buf(struct dma_buf_attachment *attachment,
+				      enum dma_data_direction direction)
+{
+	struct dma_heaps_attachment *a = attachment->priv;
+	struct sg_table *table;
+
+	table = &a->table;
+
+	if (!dma_map_sg(attachment->dev, table->sgl, table->nents,
+			direction))
+		table = ERR_PTR(-ENOMEM);
+	return table;
+}
+
+static void dma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment,
+				   struct sg_table *table,
+				   enum dma_data_direction direction)
+{
+	dma_unmap_sg(attachment->dev, table->sgl, table->nents, direction);
+}
+
+static vm_fault_t dma_heap_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct heap_helper_buffer *buffer = vma->vm_private_data;
+
+	if (vmf->pgoff > buffer->pagecount)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = buffer->pages[vmf->pgoff];
+	get_page(vmf->page);
+
+	return 0;
+}
+
+static const struct vm_operations_struct dma_heap_vm_ops = {
+	.fault = dma_heap_vm_fault,
+};
+
+static int dma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
+		return -EINVAL;
+
+	vma->vm_ops = &dma_heap_vm_ops;
+	vma->vm_private_data = buffer;
+
+	return 0;
+}
+
+static void dma_heap_dma_buf_release(struct dma_buf *dmabuf)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	dma_heap_buffer_destroy(buffer);
+}
+
+static int dma_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
+					     enum dma_data_direction direction)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	struct dma_heaps_attachment *a;
+	int ret = 0;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		invalidate_kernel_vmap_range(buffer->vaddr, buffer->size);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		dma_sync_sg_for_cpu(a->dev, a->table.sgl, a->table.nents,
+				    direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return ret;
+}
+
+static int dma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf,
+					   enum dma_data_direction direction)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	struct dma_heaps_attachment *a;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		flush_kernel_vmap_range(buffer->vaddr, buffer->size);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		dma_sync_sg_for_device(a->dev, a->table.sgl, a->table.nents,
+				       direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static void *dma_heap_dma_buf_vmap(struct dma_buf *dmabuf)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	void *vaddr;
+
+	mutex_lock(&buffer->lock);
+	vaddr = dma_heap_buffer_vmap_get(buffer);
+	mutex_unlock(&buffer->lock);
+
+	return vaddr;
+}
+
+static void dma_heap_dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	mutex_lock(&buffer->lock);
+	dma_heap_buffer_vmap_put(buffer);
+	mutex_unlock(&buffer->lock);
+}
+
+const struct dma_buf_ops heap_helper_ops = {
+	.map_dma_buf = dma_heap_map_dma_buf,
+	.unmap_dma_buf = dma_heap_unmap_dma_buf,
+	.mmap = dma_heap_mmap,
+	.release = dma_heap_dma_buf_release,
+	.attach = dma_heap_attach,
+	.detach = dma_heap_detach,
+	.begin_cpu_access = dma_heap_dma_buf_begin_cpu_access,
+	.end_cpu_access = dma_heap_dma_buf_end_cpu_access,
+	.vmap = dma_heap_dma_buf_vmap,
+	.vunmap = dma_heap_dma_buf_vunmap,
+};
diff --git a/drivers/dma-buf/heaps/heap-helpers.h b/drivers/dma-buf/heaps/heap-helpers.h
new file mode 100644
index 000000000000..805d2df88024
--- /dev/null
+++ b/drivers/dma-buf/heaps/heap-helpers.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DMABUF Heaps helper code
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#ifndef _HEAP_HELPERS_H
+#define _HEAP_HELPERS_H
+
+#include <linux/dma-heap.h>
+#include <linux/list.h>
+
+/**
+ * struct heap_helper_buffer - helper buffer metadata
+ * @heap:		back pointer to the heap the buffer came from
+ * @dmabuf:		backing dma-buf for this buffer
+ * @size:		size of the buffer
+ * @priv_virt		pointer to heap specific private value
+ * @lock		mutext to protect the data in this structure
+ * @vmap_cnt		count of vmap references on the buffer
+ * @vaddr		vmap'ed virtual address
+ * @pagecount		number of pages in the buffer
+ * @pages		list of page pointers
+ * @attachments		list of device attachments
+ *
+ * @free		heap callback to free the buffer
+ */
+struct heap_helper_buffer {
+	struct dma_heap *heap;
+	struct dma_buf *dmabuf;
+	size_t size;
+
+	void *priv_virt;
+	struct mutex lock;
+	int vmap_cnt;
+	void *vaddr;
+	pgoff_t pagecount;
+	struct page **pages;
+	struct list_head attachments;
+
+	void (*free)(struct heap_helper_buffer *buffer);
+};
+
+void init_heap_helper_buffer(struct heap_helper_buffer *buffer,
+			     void (*free)(struct heap_helper_buffer *));
+
+struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer,
+					  int fd_flags);
+
+extern const struct dma_buf_ops heap_helper_ops;
+#endif /* _HEAP_HELPERS_H */
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
new file mode 100644
index 000000000000..0bf688e3c023
--- /dev/null
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMABUF System heap exporter
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma-heap.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+#include <asm/page.h>
+
+#include "heap-helpers.h"
+
+struct dma_heap *sys_heap;
+
+static void system_heap_free(struct heap_helper_buffer *buffer)
+{
+	pgoff_t pg;
+
+	for (pg = 0; pg < buffer->pagecount; pg++)
+		__free_page(buffer->pages[pg]);
+	kfree(buffer->pages);
+	kfree(buffer);
+}
+
+static int system_heap_allocate(struct dma_heap *heap,
+				unsigned long len,
+				unsigned long fd_flags,
+				unsigned long heap_flags)
+{
+	struct heap_helper_buffer *helper_buffer;
+	struct dma_buf *dmabuf;
+	int ret = -ENOMEM;
+	pgoff_t pg;
+
+	helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL);
+	if (!helper_buffer)
+		return -ENOMEM;
+
+	init_heap_helper_buffer(helper_buffer, system_heap_free);
+	helper_buffer->heap = heap;
+	helper_buffer->size = len;
+
+	helper_buffer->pagecount = len / PAGE_SIZE;
+	helper_buffer->pages = kmalloc_array(helper_buffer->pagecount,
+					     sizeof(*helper_buffer->pages),
+					     GFP_KERNEL);
+	if (!helper_buffer->pages) {
+		ret = -ENOMEM;
+		goto err0;
+	}
+
+	for (pg = 0; pg < helper_buffer->pagecount; pg++) {
+		/*
+		 * Avoid trying to allocate memory if the process
+		 * has been killed by by SIGKILL
+		 */
+		if (fatal_signal_pending(current))
+			goto err1;
+
+		helper_buffer->pages[pg] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!helper_buffer->pages[pg])
+			goto err1;
+	}
+
+	/* create the dmabuf */
+	dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		goto err1;
+	}
+
+	helper_buffer->dmabuf = dmabuf;
+
+	ret = dma_buf_fd(dmabuf, fd_flags);
+	if (ret < 0) {
+		dma_buf_put(dmabuf);
+		/* just return, as put will call release and that will free */
+		return ret;
+	}
+
+	return ret;
+
+err1:
+	while (pg > 0)
+		__free_page(helper_buffer->pages[--pg]);
+	kfree(helper_buffer->pages);
+err0:
+	kfree(helper_buffer);
+
+	return ret;
+}
+
+static const struct dma_heap_ops system_heap_ops = {
+	.allocate = system_heap_allocate,
+};
+
+static int system_heap_create(void)
+{
+	struct dma_heap_export_info exp_info;
+	int ret = 0;
+
+	exp_info.name = "system";
+	exp_info.ops = &system_heap_ops;
+	exp_info.priv = NULL;
+
+	sys_heap = dma_heap_add(&exp_info);
+	if (IS_ERR(sys_heap))
+		ret = PTR_ERR(sys_heap);
+
+	return ret;
+}
+module_init(system_heap_create);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 9635897458a0..acb26c627d27 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -18,6 +18,8 @@ static const size_t size_limit_mb = 64; /* total dmabuf size, in megabytes  */
 struct udmabuf {
 	pgoff_t pagecount;
 	struct page **pages;
+	struct sg_table *sg;
+	struct miscdevice *device;
 };
 
 static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
@@ -46,10 +48,10 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
 	return 0;
 }
 
-static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
-				    enum dma_data_direction direction)
+static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
+				     enum dma_data_direction direction)
 {
-	struct udmabuf *ubuf = at->dmabuf->priv;
+	struct udmabuf *ubuf = buf->priv;
 	struct sg_table *sg;
 	int ret;
 
@@ -61,7 +63,7 @@ static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
 					GFP_KERNEL);
 	if (ret < 0)
 		goto err;
-	if (!dma_map_sg(at->dev, sg->sgl, sg->nents, direction)) {
+	if (!dma_map_sg(dev, sg->sgl, sg->nents, direction)) {
 		ret = -EINVAL;
 		goto err;
 	}
@@ -73,54 +75,89 @@ err:
 	return ERR_PTR(ret);
 }
 
+static void put_sg_table(struct device *dev, struct sg_table *sg,
+			 enum dma_data_direction direction)
+{
+	dma_unmap_sg(dev, sg->sgl, sg->nents, direction);
+	sg_free_table(sg);
+	kfree(sg);
+}
+
+static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
+				    enum dma_data_direction direction)
+{
+	return get_sg_table(at->dev, at->dmabuf, direction);
+}
+
 static void unmap_udmabuf(struct dma_buf_attachment *at,
 			  struct sg_table *sg,
 			  enum dma_data_direction direction)
 {
-	dma_unmap_sg(at->dev, sg->sgl, sg->nents, direction);
-	sg_free_table(sg);
-	kfree(sg);
+	return put_sg_table(at->dev, sg, direction);
 }
 
 static void release_udmabuf(struct dma_buf *buf)
 {
 	struct udmabuf *ubuf = buf->priv;
+	struct device *dev = ubuf->device->this_device;
 	pgoff_t pg;
 
+	if (ubuf->sg)
+		put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
+
 	for (pg = 0; pg < ubuf->pagecount; pg++)
 		put_page(ubuf->pages[pg]);
 	kfree(ubuf->pages);
 	kfree(ubuf);
 }
 
-static void *kmap_udmabuf(struct dma_buf *buf, unsigned long page_num)
+static int begin_cpu_udmabuf(struct dma_buf *buf,
+			     enum dma_data_direction direction)
 {
 	struct udmabuf *ubuf = buf->priv;
-	struct page *page = ubuf->pages[page_num];
+	struct device *dev = ubuf->device->this_device;
+
+	if (!ubuf->sg) {
+		ubuf->sg = get_sg_table(dev, buf, direction);
+		if (IS_ERR(ubuf->sg))
+			return PTR_ERR(ubuf->sg);
+	} else {
+		dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
+				    direction);
+	}
 
-	return kmap(page);
+	return 0;
 }
 
-static void kunmap_udmabuf(struct dma_buf *buf, unsigned long page_num,
-			   void *vaddr)
+static int end_cpu_udmabuf(struct dma_buf *buf,
+			   enum dma_data_direction direction)
 {
-	kunmap(vaddr);
+	struct udmabuf *ubuf = buf->priv;
+	struct device *dev = ubuf->device->this_device;
+
+	if (!ubuf->sg)
+		return -EINVAL;
+
+	dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
+	return 0;
 }
 
 static const struct dma_buf_ops udmabuf_ops = {
-	.map_dma_buf	  = map_udmabuf,
-	.unmap_dma_buf	  = unmap_udmabuf,
-	.release	  = release_udmabuf,
-	.map		  = kmap_udmabuf,
-	.unmap		  = kunmap_udmabuf,
-	.mmap		  = mmap_udmabuf,
+	.cache_sgt_mapping = true,
+	.map_dma_buf	   = map_udmabuf,
+	.unmap_dma_buf	   = unmap_udmabuf,
+	.release	   = release_udmabuf,
+	.mmap		   = mmap_udmabuf,
+	.begin_cpu_access  = begin_cpu_udmabuf,
+	.end_cpu_access    = end_cpu_udmabuf,
 };
 
 #define SEALS_WANTED (F_SEAL_SHRINK)
 #define SEALS_DENIED (F_SEAL_WRITE)
 
-static long udmabuf_create(const struct udmabuf_create_list *head,
-			   const struct udmabuf_create_item *list)
+static long udmabuf_create(struct miscdevice *device,
+			   struct udmabuf_create_list *head,
+			   struct udmabuf_create_item *list)
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 	struct file *memfd = NULL;
@@ -187,6 +224,7 @@ static long udmabuf_create(const struct udmabuf_create_list *head,
 	exp_info.priv = ubuf;
 	exp_info.flags = O_RDWR;
 
+	ubuf->device = device;
 	buf = dma_buf_export(&exp_info);
 	if (IS_ERR(buf)) {
 		ret = PTR_ERR(buf);
@@ -224,7 +262,7 @@ static long udmabuf_ioctl_create(struct file *filp, unsigned long arg)
 	list.offset = create.offset;
 	list.size   = create.size;
 
-	return udmabuf_create(&head, &list);
+	return udmabuf_create(filp->private_data, &head, &list);
 }
 
 static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg)
@@ -243,7 +281,7 @@ static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg)
 	if (IS_ERR(list))
 		return PTR_ERR(list);
 
-	ret = udmabuf_create(&head, list);
+	ret = udmabuf_create(filp->private_data, &head, list);
 	kfree(list);
 	return ret;
 }
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index bfdadc3667e0..d0aa6cff2e02 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -54,6 +54,9 @@ config DRM_DEBUG_MM
 
 	  If in doubt, say "N".
 
+config DRM_EXPORT_FOR_TESTS
+	bool
+
 config DRM_DEBUG_SELFTEST
 	tristate "kselftests for DRM"
 	depends on DRM
@@ -61,6 +64,7 @@ config DRM_DEBUG_SELFTEST
 	select PRIME_NUMBERS
 	select DRM_LIB_RANDOM
 	select DRM_KMS_HELPER
+	select DRM_EXPORT_FOR_TESTS if m
 	default n
 	help
 	  This option provides kernel modules that can be used to run
@@ -164,6 +168,7 @@ config DRM_LOAD_EDID_FIRMWARE
 
 config DRM_DP_CEC
 	bool "Enable DisplayPort CEC-Tunneling-over-AUX HDMI support"
+	depends on DRM
 	select CEC_CORE
 	help
 	  Choose this option if you want to enable HDMI CEC support for
@@ -294,9 +299,6 @@ config DRM_VKMS
 
 	  If M is selected the module will be called vkms.
 
-config DRM_ATI_PCIGART
-        bool
-
 source "drivers/gpu/drm/exynos/Kconfig"
 
 source "drivers/gpu/drm/rockchip/Kconfig"
@@ -393,7 +395,6 @@ menuconfig DRM_LEGACY
 	bool "Enable legacy drivers (DANGEROUS)"
 	depends on DRM && MMU
 	select DRM_VM
-	select DRM_ATI_PCIGART if PCI
 	help
 	  Enable legacy DRI1 drivers. Those drivers expose unsafe and dangerous
 	  APIs to user-space, which can be used to circumvent access
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 9f1c7c486f88..6493088a0fdd 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -5,7 +5,7 @@
 
 drm-y       :=	drm_auth.o drm_cache.o \
 		drm_file.o drm_gem.o drm_ioctl.o drm_irq.o \
-		drm_memory.o drm_drv.o drm_pci.o \
+		drm_memory.o drm_drv.o \
 		drm_sysfs.o drm_hashtab.o drm_mm.o \
 		drm_crtc.o drm_fourcc.o drm_modes.o drm_edid.o \
 		drm_encoder_slave.o \
@@ -25,10 +25,10 @@ drm-$(CONFIG_DRM_VM) += drm_vm.o
 drm-$(CONFIG_COMPAT) += drm_ioc32.o
 drm-$(CONFIG_DRM_GEM_CMA_HELPER) += drm_gem_cma_helper.o
 drm-$(CONFIG_DRM_GEM_SHMEM_HELPER) += drm_gem_shmem_helper.o
-drm-$(CONFIG_DRM_ATI_PCIGART) += ati_pcigart.o
 drm-$(CONFIG_DRM_PANEL) += drm_panel.o
 drm-$(CONFIG_OF) += drm_of.o
 drm-$(CONFIG_AGP) += drm_agpsupport.o
+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
 
diff --git a/drivers/gpu/drm/amd/acp/Kconfig b/drivers/gpu/drm/amd/acp/Kconfig
index 0d12ebf66174..13340f353ea8 100644
--- a/drivers/gpu/drm/amd/acp/Kconfig
+++ b/drivers/gpu/drm/amd/acp/Kconfig
@@ -2,11 +2,11 @@
 menu "ACP (Audio CoProcessor) Configuration"
 
 config DRM_AMD_ACP
-       bool "Enable AMD Audio CoProcessor IP support"
-       depends on DRM_AMDGPU
-       select MFD_CORE
-       select PM_GENERIC_DOMAINS if PM
-       help
+	bool "Enable AMD Audio CoProcessor IP support"
+	depends on DRM_AMDGPU
+	select MFD_CORE
+	select PM_GENERIC_DOMAINS if PM
+	help
 	Choose this option to enable ACP IP support for AMD SOCs.
 	This adds the ACP (Audio CoProcessor) IP driver and wires
 	it up into the amdgpu driver.  The ACP block provides the DMA
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index ca0e435559d5..7ae3b22c5628 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -147,12 +147,16 @@ amdgpu-y += \
 	vce_v3_0.o \
 	vce_v4_0.o
 
-# add VCN block
+# add VCN and JPEG block
 amdgpu-y += \
 	amdgpu_vcn.o \
 	vcn_v1_0.o \
 	vcn_v2_0.o \
-	vcn_v2_5.o
+	vcn_v2_5.o \
+	amdgpu_jpeg.o \
+	jpeg_v1_0.o \
+	jpeg_v2_0.o \
+	jpeg_v2_5.o
 
 # add ATHUB block
 amdgpu-y += \
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 0c229a92a24b..b1bb10625cd9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -69,6 +69,7 @@
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
 #include "amdgpu_vcn.h"
+#include "amdgpu_jpeg.h"
 #include "amdgpu_mn.h"
 #include "amdgpu_gmc.h"
 #include "amdgpu_gfx.h"
@@ -89,6 +90,7 @@
 #include "amdgpu_mes.h"
 #include "amdgpu_umc.h"
 #include "amdgpu_mmhub.h"
+#include "amdgpu_df.h"
 
 #define MAX_GPU_INSTANCE		16
 
@@ -588,6 +590,8 @@ struct amdgpu_asic_funcs {
 	bool (*need_reset_on_init)(struct amdgpu_device *adev);
 	/* PCIe replay counter */
 	uint64_t (*get_pcie_replay_count)(struct amdgpu_device *adev);
+	/* device supports BACO */
+	bool (*supports_baco)(struct amdgpu_device *adev);
 };
 
 /*
@@ -633,9 +637,8 @@ struct amdgpu_fw_vram_usage {
 	struct amdgpu_bo *reserved_bo;
 	void *va;
 
-	/* Offset on the top of VRAM, used as c2p write buffer.
+	/* GDDR6 training support flag.
 	*/
-	u64 mem_train_fb_loc;
 	bool mem_train_support;
 };
 
@@ -662,29 +665,6 @@ struct amdgpu_mmio_remap {
 	resource_size_t bus_addr;
 };
 
-struct amdgpu_df_funcs {
-	void (*sw_init)(struct amdgpu_device *adev);
-	void (*sw_fini)(struct amdgpu_device *adev);
-	void (*enable_broadcast_mode)(struct amdgpu_device *adev,
-				      bool enable);
-	u32 (*get_fb_channel_number)(struct amdgpu_device *adev);
-	u32 (*get_hbm_channel_number)(struct amdgpu_device *adev);
-	void (*update_medium_grain_clock_gating)(struct amdgpu_device *adev,
-						 bool enable);
-	void (*get_clockgating_state)(struct amdgpu_device *adev,
-				      u32 *flags);
-	void (*enable_ecc_force_par_wr_rmw)(struct amdgpu_device *adev,
-					    bool enable);
-	int (*pmc_start)(struct amdgpu_device *adev, uint64_t config,
-					 int is_enable);
-	int (*pmc_stop)(struct amdgpu_device *adev, uint64_t config,
-					 int is_disable);
-	void (*pmc_get_count)(struct amdgpu_device *adev, uint64_t config,
-					 uint64_t *count);
-	uint64_t (*get_fica)(struct amdgpu_device *adev, uint32_t ficaa_val);
-	void (*set_fica)(struct amdgpu_device *adev, uint32_t ficaa_val,
-			 uint32_t ficadl_val, uint32_t ficadh_val);
-};
 /* Define the HW IP blocks will be used in driver , add more if necessary */
 enum amd_hw_ip_block_type {
 	GC_HWIP = 1,
@@ -704,6 +684,7 @@ enum amd_hw_ip_block_type {
 	MP1_HWIP,
 	UVD_HWIP,
 	VCN_HWIP = UVD_HWIP,
+	JPEG_HWIP = VCN_HWIP,
 	VCE_HWIP,
 	DF_HWIP,
 	DCE_HWIP,
@@ -899,6 +880,9 @@ struct amdgpu_device {
 	/* vcn */
 	struct amdgpu_vcn		vcn;
 
+	/* jpeg */
+	struct amdgpu_jpeg		jpeg;
+
 	/* firmwares */
 	struct amdgpu_firmware		firmware;
 
@@ -924,6 +908,9 @@ struct amdgpu_device {
 	bool                            enable_mes;
 	struct amdgpu_mes               mes;
 
+	/* df */
+	struct amdgpu_df                df;
+
 	struct amdgpu_ip_block          ip_blocks[AMDGPU_MAX_IP_NUM];
 	int				num_ip_blocks;
 	struct mutex	mn_lock;
@@ -937,8 +924,6 @@ struct amdgpu_device {
 	/* soc15 register offset based on ip, instance and  segment */
 	uint32_t 		*reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
 
-	const struct amdgpu_df_funcs	*df_funcs;
-
 	/* delayed work_func for deferring clockgating during resume */
 	struct delayed_work     delayed_init_work;
 
@@ -982,6 +967,11 @@ struct amdgpu_device {
 
 	/* device pstate */
 	int				pstate;
+	/* enable runtime pm on the device */
+	bool                            runpm;
+
+	bool                            pm_sysfs_en;
+	bool                            ucode_sysfs_en;
 };
 
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
@@ -1117,6 +1107,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define amdgpu_asic_get_pcie_usage(adev, cnt0, cnt1) ((adev)->asic_funcs->get_pcie_usage((adev), (cnt0), (cnt1)))
 #define amdgpu_asic_need_reset_on_init(adev) (adev)->asic_funcs->need_reset_on_init((adev))
 #define amdgpu_asic_get_pcie_replay_count(adev) ((adev)->asic_funcs->get_pcie_replay_count((adev)))
+#define amdgpu_asic_supports_baco(adev) (adev)->asic_funcs->supports_baco((adev))
+
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
 /* Common functions */
@@ -1133,9 +1125,12 @@ void amdgpu_device_program_register_sequence(struct amdgpu_device *adev,
 					     const u32 *registers,
 					     const u32 array_size);
 
-bool amdgpu_device_is_px(struct drm_device *dev);
+bool amdgpu_device_supports_boco(struct drm_device *dev);
+bool amdgpu_device_supports_baco(struct drm_device *dev);
 bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 				      struct amdgpu_device *peer_adev);
+int amdgpu_device_baco_enter(struct drm_device *dev);
+int amdgpu_device_baco_exit(struct drm_device *dev);
 
 /* atpx handler */
 #if defined(CONFIG_VGA_SWITCHEROO)
@@ -1173,8 +1168,8 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
 void amdgpu_driver_postclose_kms(struct drm_device *dev,
 				 struct drm_file *file_priv);
 int amdgpu_device_ip_suspend(struct amdgpu_device *adev);
-int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon);
-int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon);
+int amdgpu_device_suspend(struct drm_device *dev, bool fbcon);
+int amdgpu_device_resume(struct drm_device *dev, bool fbcon);
 u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe);
 int amdgpu_enable_vblank_kms(struct drm_device *dev, unsigned int pipe);
 void amdgpu_disable_vblank_kms(struct drm_device *dev, unsigned int pipe);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index d3da9dde4ee1..8609287620ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -613,15 +613,9 @@ void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
-	if (is_support_sw_smu(adev))
-		smu_switch_power_profile(&adev->smu,
-					 PP_SMC_POWER_PROFILE_COMPUTE,
-					 !idle);
-	else if (adev->powerplay.pp_funcs &&
-		 adev->powerplay.pp_funcs->switch_power_profile)
-		amdgpu_dpm_switch_power_profile(adev,
-						PP_SMC_POWER_PROFILE_COMPUTE,
-						!idle);
+	amdgpu_dpm_switch_power_profile(adev,
+					PP_SMC_POWER_PROFILE_COMPUTE,
+					!idle);
 }
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
@@ -634,6 +628,38 @@ bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 	return false;
 }
 
+int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct kgd_dev *kgd, uint16_t vmid)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	if (adev->family == AMDGPU_FAMILY_AI) {
+		int i;
+
+		for (i = 0; i < adev->num_vmhubs; i++)
+			amdgpu_gmc_flush_gpu_tlb(adev, vmid, i, 0);
+	} else {
+		amdgpu_gmc_flush_gpu_tlb(adev, vmid, AMDGPU_GFXHUB_0, 0);
+	}
+
+	return 0;
+}
+
+int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+	uint32_t flush_type = 0;
+	bool all_hub = false;
+
+	if (adev->gmc.xgmi.num_physical_nodes &&
+		adev->asic_type == CHIP_VEGA20)
+		flush_type = 2;
+
+	if (adev->family == AMDGPU_FAMILY_AI)
+		all_hub = true;
+
+	return amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub);
+}
+
 bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 069d5d230810..47b0f2957d1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -136,6 +136,8 @@ int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t *ib_cmd, uint32_t ib_len);
 void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
 bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd);
+int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct kgd_dev *kgd, uint16_t vmid);
+int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index b6713e0ed1b2..4bcc175a149d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -46,6 +46,8 @@
 #include "soc15.h"
 #include "soc15d.h"
 #include "amdgpu_amdkfd_gfx_v9.h"
+#include "gfxhub_v1_0.h"
+#include "mmhub_v9_4.h"
 
 #define HQD_N_REGS 56
 #define DUMP_REG(addr) do {				\
@@ -69,32 +71,56 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev,
 				unsigned int engine_id,
 				unsigned int queue_id)
 {
-	uint32_t sdma_engine_reg_base[8] = {
-		SOC15_REG_OFFSET(SDMA0, 0,
-				 mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA1, 0,
-				 mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA2, 0,
-				 mmSDMA2_RLC0_RB_CNTL) - mmSDMA2_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA3, 0,
-				 mmSDMA3_RLC0_RB_CNTL) - mmSDMA3_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA4, 0,
-				 mmSDMA4_RLC0_RB_CNTL) - mmSDMA4_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA5, 0,
-				 mmSDMA5_RLC0_RB_CNTL) - mmSDMA5_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA6, 0,
-				 mmSDMA6_RLC0_RB_CNTL) - mmSDMA6_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA7, 0,
-				 mmSDMA7_RLC0_RB_CNTL) - mmSDMA7_RLC0_RB_CNTL
-	};
-
-	uint32_t retval = sdma_engine_reg_base[engine_id]
+	uint32_t sdma_engine_reg_base = 0;
+	uint32_t sdma_rlc_reg_offset;
+
+	switch (engine_id) {
+	default:
+		dev_warn(adev->dev,
+			 "Invalid sdma engine id (%d), using engine id 0\n",
+			 engine_id);
+		/* fall through */
+	case 0:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0,
+				mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL;
+		break;
+	case 1:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA1, 0,
+				mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL;
+		break;
+	case 2:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA2, 0,
+				mmSDMA2_RLC0_RB_CNTL) - mmSDMA2_RLC0_RB_CNTL;
+		break;
+	case 3:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA3, 0,
+				mmSDMA3_RLC0_RB_CNTL) - mmSDMA3_RLC0_RB_CNTL;
+		break;
+	case 4:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA4, 0,
+				mmSDMA4_RLC0_RB_CNTL) - mmSDMA4_RLC0_RB_CNTL;
+		break;
+	case 5:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA5, 0,
+				mmSDMA5_RLC0_RB_CNTL) - mmSDMA5_RLC0_RB_CNTL;
+		break;
+	case 6:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA6, 0,
+				mmSDMA6_RLC0_RB_CNTL) - mmSDMA6_RLC0_RB_CNTL;
+		break;
+	case 7:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA7, 0,
+				mmSDMA7_RLC0_RB_CNTL) - mmSDMA7_RLC0_RB_CNTL;
+		break;
+	}
+
+	sdma_rlc_reg_offset = sdma_engine_reg_base
 		+ queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL);
 
 	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id,
-			queue_id, retval);
+			queue_id, sdma_rlc_reg_offset);
 
-	return retval;
+	return sdma_rlc_reg_offset;
 }
 
 static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
@@ -258,11 +284,28 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 	return 0;
 }
 
+static void kgd_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
+		uint64_t page_table_base)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
+		pr_err("trying to set page table base for wrong VMID %u\n",
+		       vmid);
+		return;
+	}
+
+	mmhub_v9_4_setup_vm_pt_regs(adev, vmid, page_table_base);
+
+	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+}
+
 const struct kfd2kgd_calls arcturus_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_gfx_v9_init_interrupts,
 	.hqd_load = kgd_gfx_v9_hqd_load,
+	.hiq_mqd_load = kgd_gfx_v9_hiq_mqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
 	.hqd_dump = kgd_gfx_v9_hqd_dump,
 	.hqd_sdma_dump = kgd_hqd_sdma_dump,
@@ -277,8 +320,6 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = kgd_gfx_v9_get_tile_config,
-	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
-	.invalidate_tlbs = kgd_gfx_v9_invalidate_tlbs,
-	.invalidate_tlbs_vmid = kgd_gfx_v9_invalidate_tlbs_vmid,
+	.set_vm_context_page_table_base = kgd_set_vm_context_page_table_base,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 61cd707158e4..a7b17c8deb00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -107,13 +107,13 @@ static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 	lock_srbm(kgd, mec, pipe, queue_id, 0);
 }
 
-static uint32_t get_queue_mask(struct amdgpu_device *adev,
+static uint64_t get_queue_mask(struct amdgpu_device *adev,
 			       uint32_t pipe_id, uint32_t queue_id)
 {
-	unsigned int bit = (pipe_id * adev->gfx.mec.num_queue_per_pipe +
-			    queue_id) & 31;
+	unsigned int bit = pipe_id * adev->gfx.mec.num_queue_per_pipe +
+			queue_id;
 
-	return ((uint32_t)1) << bit;
+	return 1ull << bit;
 }
 
 static void release_queue(struct kgd_dev *kgd)
@@ -268,21 +268,6 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	pr_debug("Load hqd of pipe %d queue %d\n", pipe_id, queue_id);
 	acquire_queue(kgd, pipe_id, queue_id);
 
-	/* HIQ is set during driver init period with vmid set to 0*/
-	if (m->cp_hqd_vmid == 0) {
-		uint32_t value, mec, pipe;
-
-		mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
-		pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
-
-		pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
-			mec, pipe, queue_id);
-		value = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS));
-		value = REG_SET_FIELD(value, RLC_CP_SCHEDULERS, scheduler1,
-			((mec << 5) | (pipe << 3) | queue_id | 0x80));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), value);
-	}
-
 	/* HQD registers extend from CP_MQD_BASE_ADDR to CP_HQD_EOP_WPTR_MEM. */
 	mqd_hqd = &m->cp_mqd_base_addr_lo;
 	hqd_base = SOC15_REG_OFFSET(GC, 0, mmCP_MQD_BASE_ADDR);
@@ -332,9 +317,10 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 		       lower_32_bits((uint64_t)wptr));
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
 		       upper_32_bits((uint64_t)wptr));
-		pr_debug("%s setting CP_PQ_WPTR_POLL_CNTL1 to %x\n", __func__, get_queue_mask(adev, pipe_id, queue_id));
+		pr_debug("%s setting CP_PQ_WPTR_POLL_CNTL1 to %x\n", __func__,
+			 (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
-		       get_queue_mask(adev, pipe_id, queue_id));
+		       (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 	}
 
 	/* Start the EOP fetcher */
@@ -350,6 +336,59 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
+static int kgd_hiq_mqd_load(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
+	struct v10_compute_mqd *m;
+	uint32_t mec, pipe;
+	int r;
+
+	m = get_mqd(mqd);
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
+
+	pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
+		 mec, pipe, queue_id);
+
+	spin_lock(&adev->gfx.kiq.ring_lock);
+	r = amdgpu_ring_alloc(kiq_ring, 7);
+	if (r) {
+		pr_err("Failed to alloc KIQ (%d).\n", r);
+		goto out_unlock;
+	}
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
+			  PACKET3_MAP_QUEUES_VMID(m->cp_hqd_vmid) | /* VMID */
+			  PACKET3_MAP_QUEUES_QUEUE(queue_id) |
+			  PACKET3_MAP_QUEUES_PIPE(pipe) |
+			  PACKET3_MAP_QUEUES_ME((mec - 1)) |
+			  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
+			  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
+			  PACKET3_MAP_QUEUES_ENGINE_SEL(1) | /* engine_sel: hiq */
+			  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_DOORBELL_OFFSET(doorbell_off));
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_hi);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_hi);
+	amdgpu_ring_commit(kiq_ring);
+
+out_unlock:
+	spin_unlock(&adev->gfx.kiq.ring_lock);
+	release_queue(kgd);
+
+	return r;
+}
+
 static int kgd_hqd_dump(struct kgd_dev *kgd,
 			uint32_t pipe_id, uint32_t queue_id,
 			uint32_t (**dump)[2], uint32_t *n_regs)
@@ -686,71 +725,6 @@ static bool get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
 	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
-static int invalidate_tlbs_with_kiq(struct amdgpu_device *adev, uint16_t pasid)
-{
-	signed long r;
-	uint32_t seq;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-
-	spin_lock(&adev->gfx.kiq.ring_lock);
-	amdgpu_ring_alloc(ring, 12); /* fence + invalidate_tlbs package*/
-	amdgpu_ring_write(ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
-	amdgpu_ring_write(ring,
-			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
-			PACKET3_INVALIDATE_TLBS_PASID(pasid));
-	amdgpu_fence_emit_polling(ring, &seq);
-	amdgpu_ring_commit(ring);
-	spin_unlock(&adev->gfx.kiq.ring_lock);
-
-	r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
-	if (r < 1) {
-		DRM_ERROR("wait for kiq fence error: %ld.\n", r);
-		return -ETIME;
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid;
-	uint16_t queried_pasid;
-	bool ret;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-
-	if (amdgpu_emu_mode == 0 && ring->sched.ready)
-		return invalidate_tlbs_with_kiq(adev, pasid);
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		ret = get_atc_vmid_pasid_mapping_info(kgd, vmid,
-				&queried_pasid);
-		if (ret	&& queried_pasid == pasid) {
-			amdgpu_gmc_flush_gpu_tlb(adev, vmid,
-					AMDGPU_GFXHUB_0, 0);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid %d\n", vmid);
-		return 0;
-	}
-
-	amdgpu_gmc_flush_gpu_tlb(adev, vmid, AMDGPU_GFXHUB_0, 0);
-	return 0;
-}
-
 static int kgd_address_watch_disable(struct kgd_dev *kgd)
 {
 	return 0;
@@ -817,6 +791,7 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_init_interrupts,
 	.hqd_load = kgd_hqd_load,
+	.hiq_mqd_load = kgd_hiq_mqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
 	.hqd_dump = kgd_hqd_dump,
 	.hqd_sdma_dump = kgd_hqd_sdma_dump,
@@ -832,7 +807,5 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 			get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = amdgpu_amdkfd_get_tile_config,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 6e6f0a99ec06..8f052e98a3c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -696,45 +696,6 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		lower_32_bits(page_table_base));
 }
 
-static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid;
-	unsigned int tmp;
-
-	if (adev->in_gpu_reset)
-		return -EIO;
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
-		if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
-			(tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
-			WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
-			RREG32(mmVM_INVALIDATE_RESPONSE);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid\n");
-		return 0;
-	}
-
-	WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
-	RREG32(mmVM_INVALIDATE_RESPONSE);
-	return 0;
-}
-
  /**
   * read_vmid_from_vmfault_reg - read vmid from register
   *
@@ -771,7 +732,5 @@ const struct kfd2kgd_calls gfx_v7_kfd2kgd = {
 	.set_scratch_backing_va = set_scratch_backing_va,
 	.get_tile_config = get_tile_config,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index bfbddedb2380..19a10db93d68 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -657,45 +657,6 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 			lower_32_bits(page_table_base));
 }
 
-static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid;
-	unsigned int tmp;
-
-	if (adev->in_gpu_reset)
-		return -EIO;
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
-		if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
-			(tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
-			WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
-			RREG32(mmVM_INVALIDATE_RESPONSE);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid %d\n", vmid);
-		return -EINVAL;
-	}
-
-	WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
-	RREG32(mmVM_INVALIDATE_RESPONSE);
-	return 0;
-}
-
 const struct kfd2kgd_calls gfx_v8_kfd2kgd = {
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
@@ -717,6 +678,4 @@ const struct kfd2kgd_calls gfx_v8_kfd2kgd = {
 	.set_scratch_backing_va = set_scratch_backing_va,
 	.get_tile_config = get_tile_config,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 47c853ef1051..8562afe5b761 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -40,7 +40,6 @@
 #include "soc15d.h"
 #include "mmhub_v1_0.h"
 #include "gfxhub_v1_0.h"
-#include "gmc_v9_0.h"
 
 
 enum hqd_dequeue_request_type {
@@ -104,13 +103,13 @@ static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 	lock_srbm(kgd, mec, pipe, queue_id, 0);
 }
 
-static uint32_t get_queue_mask(struct amdgpu_device *adev,
+static uint64_t get_queue_mask(struct amdgpu_device *adev,
 			       uint32_t pipe_id, uint32_t queue_id)
 {
-	unsigned int bit = (pipe_id * adev->gfx.mec.num_queue_per_pipe +
-			    queue_id) & 31;
+	unsigned int bit = pipe_id * adev->gfx.mec.num_queue_per_pipe +
+			queue_id;
 
-	return ((uint32_t)1) << bit;
+	return 1ull << bit;
 }
 
 static void release_queue(struct kgd_dev *kgd)
@@ -259,21 +258,6 @@ int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 
 	acquire_queue(kgd, pipe_id, queue_id);
 
-	/* HIQ is set during driver init period with vmid set to 0*/
-	if (m->cp_hqd_vmid == 0) {
-		uint32_t value, mec, pipe;
-
-		mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
-		pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
-
-		pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
-			mec, pipe, queue_id);
-		value = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS));
-		value = REG_SET_FIELD(value, RLC_CP_SCHEDULERS, scheduler1,
-			((mec << 5) | (pipe << 3) | queue_id | 0x80));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), value);
-	}
-
 	/* HQD registers extend from CP_MQD_BASE_ADDR to CP_HQD_EOP_WPTR_MEM. */
 	mqd_hqd = &m->cp_mqd_base_addr_lo;
 	hqd_base = SOC15_REG_OFFSET(GC, 0, mmCP_MQD_BASE_ADDR);
@@ -324,7 +308,7 @@ int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 		WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
 		       upper_32_bits((uintptr_t)wptr));
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
-		       get_queue_mask(adev, pipe_id, queue_id));
+		       (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 	}
 
 	/* Start the EOP fetcher */
@@ -340,6 +324,59 @@ int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
+int kgd_gfx_v9_hiq_mqd_load(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
+	struct v9_mqd *m;
+	uint32_t mec, pipe;
+	int r;
+
+	m = get_mqd(mqd);
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
+
+	pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
+		 mec, pipe, queue_id);
+
+	spin_lock(&adev->gfx.kiq.ring_lock);
+	r = amdgpu_ring_alloc(kiq_ring, 7);
+	if (r) {
+		pr_err("Failed to alloc KIQ (%d).\n", r);
+		goto out_unlock;
+	}
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
+			  PACKET3_MAP_QUEUES_VMID(m->cp_hqd_vmid) | /* VMID */
+			  PACKET3_MAP_QUEUES_QUEUE(queue_id) |
+			  PACKET3_MAP_QUEUES_PIPE(pipe) |
+			  PACKET3_MAP_QUEUES_ME((mec - 1)) |
+			  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
+			  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
+			  PACKET3_MAP_QUEUES_ENGINE_SEL(1) | /* engine_sel: hiq */
+			  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_DOORBELL_OFFSET(doorbell_off));
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_hi);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_hi);
+	amdgpu_ring_commit(kiq_ring);
+
+out_unlock:
+	spin_unlock(&adev->gfx.kiq.ring_lock);
+	release_queue(kgd);
+
+	return r;
+}
+
 int kgd_gfx_v9_hqd_dump(struct kgd_dev *kgd,
 			uint32_t pipe_id, uint32_t queue_id,
 			uint32_t (**dump)[2], uint32_t *n_regs)
@@ -618,100 +655,6 @@ bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
 	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
-static int invalidate_tlbs_with_kiq(struct amdgpu_device *adev, uint16_t pasid,
-			uint32_t flush_type)
-{
-	signed long r;
-	uint32_t seq;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-
-	spin_lock(&adev->gfx.kiq.ring_lock);
-	amdgpu_ring_alloc(ring, 12); /* fence + invalidate_tlbs package*/
-	amdgpu_ring_write(ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
-	amdgpu_ring_write(ring,
-			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
-			PACKET3_INVALIDATE_TLBS_ALL_HUB(1) |
-			PACKET3_INVALIDATE_TLBS_PASID(pasid) |
-			PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(flush_type));
-	amdgpu_fence_emit_polling(ring, &seq);
-	amdgpu_ring_commit(ring);
-	spin_unlock(&adev->gfx.kiq.ring_lock);
-
-	r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
-	if (r < 1) {
-		DRM_ERROR("wait for kiq fence error: %ld.\n", r);
-		return -ETIME;
-	}
-
-	return 0;
-}
-
-int kgd_gfx_v9_invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid, i;
-	uint16_t queried_pasid;
-	bool ret;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-	uint32_t flush_type = 0;
-
-	if (adev->in_gpu_reset)
-		return -EIO;
-	if (adev->gmc.xgmi.num_physical_nodes &&
-		adev->asic_type == CHIP_VEGA20)
-		flush_type = 2;
-
-	if (ring->sched.ready)
-		return invalidate_tlbs_with_kiq(adev, pasid, flush_type);
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		ret = kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(kgd, vmid,
-				&queried_pasid);
-		if (ret && queried_pasid == pasid) {
-			for (i = 0; i < adev->num_vmhubs; i++)
-				amdgpu_gmc_flush_gpu_tlb(adev, vmid,
-							i, flush_type);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-int kgd_gfx_v9_invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int i;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid %d\n", vmid);
-		return 0;
-	}
-
-	/* Use legacy mode tlb invalidation.
-	 *
-	 * Currently on Raven the code below is broken for anything but
-	 * legacy mode due to a MMHUB power gating problem. A workaround
-	 * is for MMHUB to wait until the condition PER_VMID_INVALIDATE_REQ
-	 * == PER_VMID_INVALIDATE_ACK instead of simply waiting for the ack
-	 * bit.
-	 *
-	 * TODO 1: agree on the right set of invalidation registers for
-	 * KFD use. Use the last one for now. Invalidate both GC and
-	 * MMHUB.
-	 *
-	 * TODO 2: support range-based invalidation, requires kfg2kgd
-	 * interface change
-	 */
-	for (i = 0; i < adev->num_vmhubs; i++)
-		amdgpu_gmc_flush_gpu_tlb(adev, vmid, i, 0);
-
-	return 0;
-}
-
 int kgd_gfx_v9_address_watch_disable(struct kgd_dev *kgd)
 {
 	return 0;
@@ -758,8 +701,8 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 	return 0;
 }
 
-void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
-		uint64_t page_table_base)
+static void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
+			uint32_t vmid, uint64_t page_table_base)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 
@@ -769,16 +712,7 @@ void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmi
 		return;
 	}
 
-	/* TODO: take advantage of per-process address space size. For
-	 * now, all processes share the same address space size, like
-	 * on GFX8 and older.
-	 */
-	if (adev->asic_type == CHIP_ARCTURUS) {
-		/* Two MMHUBs */
-		mmhub_v9_4_setup_vm_pt_regs(adev, 0, vmid, page_table_base);
-		mmhub_v9_4_setup_vm_pt_regs(adev, 1, vmid, page_table_base);
-	} else
-		mmhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+	mmhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
 
 	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
 }
@@ -788,6 +722,7 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_gfx_v9_init_interrupts,
 	.hqd_load = kgd_gfx_v9_hqd_load,
+	.hiq_mqd_load = kgd_gfx_v9_hiq_mqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
 	.hqd_dump = kgd_gfx_v9_hqd_dump,
 	.hqd_sdma_dump = kgd_hqd_sdma_dump,
@@ -803,7 +738,5 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = kgd_gfx_v9_get_tile_config,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
-	.invalidate_tlbs = kgd_gfx_v9_invalidate_tlbs,
-	.invalidate_tlbs_vmid = kgd_gfx_v9_invalidate_tlbs_vmid,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index d9e9ad22b2bd..63d3e6683dfe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -33,6 +33,9 @@ int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr,
 			uint32_t wptr_shift, uint32_t wptr_mask,
 			struct mm_struct *mm);
+int kgd_gfx_v9_hiq_mqd_load(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off);
 int kgd_gfx_v9_hqd_dump(struct kgd_dev *kgd,
 			uint32_t pipe_id, uint32_t queue_id,
 			uint32_t (**dump)[2], uint32_t *n_regs);
@@ -57,9 +60,5 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 
 bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
 					uint8_t vmid, uint16_t *p_pasid);
-void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
-		uint64_t page_table_base);
-int kgd_gfx_v9_invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid);
-int kgd_gfx_v9_invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid);
 int kgd_gfx_v9_get_tile_config(struct kgd_dev *kgd,
 		struct tile_config *config);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 888209eb8cec..b2487f4f271b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -85,7 +85,7 @@ static bool check_if_add_bo_to_vm(struct amdgpu_vm *avm,
 }
 
 /* Set memory usage limits. Current, limits are
- *  System (TTM + userptr) memory - 3/4th System RAM
+ *  System (TTM + userptr) memory - 15/16th System RAM
  *  TTM memory - 3/8th System RAM
  */
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
@@ -98,7 +98,7 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
 	mem *= si.mem_unit;
 
 	spin_lock_init(&kfd_mem_limit.mem_limit_lock);
-	kfd_mem_limit.max_system_mem_limit = (mem >> 1) + (mem >> 2);
+	kfd_mem_limit.max_system_mem_limit = mem - (mem >> 4);
 	kfd_mem_limit.max_ttm_mem_limit = (mem >> 1) - (mem >> 3);
 	pr_debug("Kernel memory limit %lluM, TTM limit %lluM\n",
 		(kfd_mem_limit.max_system_mem_limit >> 20),
@@ -358,7 +358,7 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 	if (ret)
 		return ret;
 
-	return amdgpu_sync_fence(NULL, sync, vm->last_update, false);
+	return amdgpu_sync_fence(sync, vm->last_update, false);
 }
 
 static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
@@ -750,7 +750,7 @@ static int unmap_bo_from_gpuvm(struct amdgpu_device *adev,
 
 	amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
-	amdgpu_sync_fence(NULL, sync, bo_va->last_pt_update, false);
+	amdgpu_sync_fence(sync, bo_va->last_pt_update, false);
 
 	return 0;
 }
@@ -769,7 +769,7 @@ static int update_gpuvm_pte(struct amdgpu_device *adev,
 		return ret;
 	}
 
-	return amdgpu_sync_fence(NULL, sync, bo_va->last_pt_update, false);
+	return amdgpu_sync_fence(sync, bo_va->last_pt_update, false);
 }
 
 static int map_bo_to_gpuvm(struct amdgpu_device *adev,
@@ -1674,10 +1674,10 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem,
 				struct mm_struct *mm)
 {
 	struct amdkfd_process_info *process_info = mem->process_info;
-	int invalid, evicted_bos;
+	int evicted_bos;
 	int r = 0;
 
-	invalid = atomic_inc_return(&mem->invalid);
+	atomic_inc(&mem->invalid);
 	evicted_bos = atomic_inc_return(&process_info->evicted_bos);
 	if (evicted_bos == 1) {
 		/* First eviction, stop the queues */
@@ -2048,7 +2048,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 			pr_debug("Memory eviction: Validate BOs failed. Try again\n");
 			goto validate_map_fail;
 		}
-		ret = amdgpu_sync_fence(NULL, &sync_obj, bo->tbo.moving, false);
+		ret = amdgpu_sync_fence(&sync_obj, bo->tbo.moving, false);
 		if (ret) {
 			pr_debug("Memory eviction: Sync BO fence failed. Try again\n");
 			goto validate_map_fail;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 72232fccf61a..fdd52d86a4d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -338,17 +338,9 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 		path_size += le16_to_cpu(path->usSize);
 
 		if (device_support & le16_to_cpu(path->usDeviceTag)) {
-			uint8_t con_obj_id, con_obj_num, con_obj_type;
-
-			con_obj_id =
+			uint8_t con_obj_id =
 			    (le16_to_cpu(path->usConnObjectId) & OBJECT_ID_MASK)
 			    >> OBJECT_ID_SHIFT;
-			con_obj_num =
-			    (le16_to_cpu(path->usConnObjectId) & ENUM_ID_MASK)
-			    >> ENUM_ID_SHIFT;
-			con_obj_type =
-			    (le16_to_cpu(path->usConnObjectId) &
-			     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
 			/* Skip TV/CV support */
 			if ((le16_to_cpu(path->usDeviceTag) ==
@@ -373,15 +365,7 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 			router.ddc_valid = false;
 			router.cd_valid = false;
 			for (j = 0; j < ((le16_to_cpu(path->usSize) - 8) / 2); j++) {
-				uint8_t grph_obj_id, grph_obj_num, grph_obj_type;
-
-				grph_obj_id =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
-				grph_obj_num =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     ENUM_ID_MASK) >> ENUM_ID_SHIFT;
-				grph_obj_type =
+				uint8_t grph_obj_type =
 				    (le16_to_cpu(path->usGraphicObjIds[j]) &
 				     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
@@ -2038,7 +2022,7 @@ int amdgpu_atombios_init(struct amdgpu_device *adev)
 	if (adev->is_atom_fw) {
 		amdgpu_atomfirmware_scratch_regs_init(adev);
 		amdgpu_atomfirmware_allocate_fb_scratch(adev);
-		ret = amdgpu_atomfirmware_get_mem_train_fb_loc(adev);
+		ret = amdgpu_atomfirmware_get_mem_train_info(adev);
 		if (ret) {
 			DRM_ERROR("Failed to get mem train fb location.\n");
 			return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index ff4eb96bdfb5..58f9d8c3a17a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -525,16 +525,12 @@ static int gddr6_mem_train_support(struct amdgpu_device *adev)
 	return ret;
 }
 
-int amdgpu_atomfirmware_get_mem_train_fb_loc(struct amdgpu_device *adev)
+int amdgpu_atomfirmware_get_mem_train_info(struct amdgpu_device *adev)
 {
 	struct atom_context *ctx = adev->mode_info.atom_context;
-	unsigned char *bios = ctx->bios;
-	struct vram_reserve_block *reserved_block;
-	int index, block_number;
+	int index;
 	uint8_t frev, crev;
 	uint16_t data_offset, size;
-	uint32_t start_address_in_kb;
-	uint64_t offset;
 	int ret;
 
 	adev->fw_vram_usage.mem_train_support = false;
@@ -569,32 +565,6 @@ int amdgpu_atomfirmware_get_mem_train_fb_loc(struct amdgpu_device *adev)
 		return -EINVAL;
 	}
 
-	reserved_block = (struct vram_reserve_block *)
-		(bios + data_offset + sizeof(struct atom_common_table_header));
-	block_number = ((unsigned int)size - sizeof(struct atom_common_table_header))
-		/ sizeof(struct vram_reserve_block);
-	reserved_block += (block_number > 0) ? block_number-1 : 0;
-	DRM_DEBUG("block_number:0x%04x, last block: 0x%08xkb sz, %dkb fw, %dkb drv.\n",
-		  block_number,
-		  le32_to_cpu(reserved_block->start_address_in_kb),
-		  le16_to_cpu(reserved_block->used_by_firmware_in_kb),
-		  le16_to_cpu(reserved_block->used_by_driver_in_kb));
-	if (reserved_block->used_by_firmware_in_kb > 0) {
-		start_address_in_kb = le32_to_cpu(reserved_block->start_address_in_kb);
-		offset = (uint64_t)start_address_in_kb * ONE_KiB;
-		if ((offset & (ONE_MiB - 1)) < (4 * ONE_KiB + 1) ) {
-			offset -= ONE_MiB;
-		}
-
-		offset &= ~(ONE_MiB - 1);
-		adev->fw_vram_usage.mem_train_fb_loc = offset;
-		adev->fw_vram_usage.mem_train_support = true;
-		DRM_DEBUG("mem_train_fb_loc:0x%09llx.\n", offset);
-		ret = 0;
-	} else {
-		DRM_ERROR("used_by_firmware_in_kb is 0!\n");
-		ret = -EINVAL;
-	}
-
-	return ret;
+	adev->fw_vram_usage.mem_train_support = true;
+	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
index f871af5ea6f3..434fe2fa0089 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
@@ -31,7 +31,7 @@ void amdgpu_atomfirmware_scratch_regs_init(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 	int *vram_width, int *vram_type, int *vram_vendor);
-int amdgpu_atomfirmware_get_mem_train_fb_loc(struct amdgpu_device *adev);
+int amdgpu_atomfirmware_get_mem_train_info(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 5ca905b4a0fb..a52a084158b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -795,29 +795,23 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(adev, &p->job->sync,
-			      fpriv->prt_va->last_pt_update, false);
+	r = amdgpu_sync_vm_fence(&p->job->sync, fpriv->prt_va->last_pt_update);
 	if (r)
 		return r;
 
 	if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
-		struct dma_fence *f;
-
 		bo_va = fpriv->csa_va;
 		BUG_ON(!bo_va);
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			return r;
 
-		f = bo_va->last_pt_update;
-		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
+		r = amdgpu_sync_vm_fence(&p->job->sync, bo_va->last_pt_update);
 		if (r)
 			return r;
 	}
 
 	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
-		struct dma_fence *f;
-
 		/* ignore duplicates */
 		bo = ttm_to_amdgpu_bo(e->tv.bo);
 		if (!bo)
@@ -831,8 +825,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (r)
 			return r;
 
-		f = bo_va->last_pt_update;
-		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
+		r = amdgpu_sync_vm_fence(&p->job->sync, bo_va->last_pt_update);
 		if (r)
 			return r;
 	}
@@ -845,7 +838,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(adev, &p->job->sync, vm->last_update, false);
+	r = amdgpu_sync_vm_fence(&p->job->sync, vm->last_update);
 	if (r)
 		return r;
 
@@ -916,6 +909,11 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 		if (parser->entity && parser->entity != entity)
 			return -EINVAL;
 
+		/* Return if there is no run queue associated with this entity.
+		 * Possibly because of disabled HW IP*/
+		if (entity->rq == NULL)
+			return -EINVAL;
+
 		parser->entity = entity;
 
 		ring = to_amdgpu_ring(entity->rq->sched);
@@ -987,7 +985,7 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
 			dma_fence_put(old);
 		}
 
-		r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
+		r = amdgpu_sync_fence(&p->job->sync, fence, true);
 		dma_fence_put(fence);
 		if (r)
 			return r;
@@ -1009,7 +1007,7 @@ static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
 		return r;
 	}
 
-	r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
+	r = amdgpu_sync_fence(&p->job->sync, fence, true);
 	dma_fence_put(fence);
 
 	return r;
@@ -1236,7 +1234,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 		goto error_abort;
 	}
 
-	job->owner = p->filp;
 	p->fence = dma_fence_get(&job->base.s_fence->finished);
 
 	amdgpu_ctx_add_fence(p->ctx, entity, p->fence, &seq);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 6614d8a6f4c8..64e2babbc36e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -74,7 +74,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 			   struct amdgpu_ctx *ctx)
 {
 	unsigned num_entities = amdgpu_ctx_total_num_entities();
-	unsigned i, j, k;
+	unsigned i, j;
 	int r;
 
 	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_MAX)
@@ -121,72 +121,57 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 	ctx->override_priority = DRM_SCHED_PRIORITY_UNSET;
 
 	for (i = 0; i < AMDGPU_HW_IP_NUM; ++i) {
-		struct amdgpu_ring *rings[AMDGPU_MAX_RINGS];
-		struct drm_sched_rq *rqs[AMDGPU_MAX_RINGS];
-		unsigned num_rings = 0;
-		unsigned num_rqs = 0;
+		struct drm_gpu_scheduler **scheds;
+		struct drm_gpu_scheduler *sched;
+		unsigned num_scheds = 0;
 
 		switch (i) {
 		case AMDGPU_HW_IP_GFX:
-			rings[0] = &adev->gfx.gfx_ring[0];
-			num_rings = 1;
+			sched = &adev->gfx.gfx_ring[0].sched;
+			scheds = &sched;
+			num_scheds = 1;
 			break;
 		case AMDGPU_HW_IP_COMPUTE:
-			for (j = 0; j < adev->gfx.num_compute_rings; ++j)
-				rings[j] = &adev->gfx.compute_ring[j];
-			num_rings = adev->gfx.num_compute_rings;
+			scheds = adev->gfx.compute_sched;
+			num_scheds = adev->gfx.num_compute_sched;
 			break;
 		case AMDGPU_HW_IP_DMA:
-			for (j = 0; j < adev->sdma.num_instances; ++j)
-				rings[j] = &adev->sdma.instance[j].ring;
-			num_rings = adev->sdma.num_instances;
+			scheds = adev->sdma.sdma_sched;
+			num_scheds = adev->sdma.num_sdma_sched;
 			break;
 		case AMDGPU_HW_IP_UVD:
-			rings[0] = &adev->uvd.inst[0].ring;
-			num_rings = 1;
+			sched = &adev->uvd.inst[0].ring.sched;
+			scheds = &sched;
+			num_scheds = 1;
 			break;
 		case AMDGPU_HW_IP_VCE:
-			rings[0] = &adev->vce.ring[0];
-			num_rings = 1;
+			sched = &adev->vce.ring[0].sched;
+			scheds = &sched;
+			num_scheds = 1;
 			break;
 		case AMDGPU_HW_IP_UVD_ENC:
-			rings[0] = &adev->uvd.inst[0].ring_enc[0];
-			num_rings = 1;
+			sched = &adev->uvd.inst[0].ring_enc[0].sched;
+			scheds = &sched;
+			num_scheds = 1;
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
-			for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
-				if (adev->vcn.harvest_config & (1 << j))
-					continue;
-				rings[num_rings++] = &adev->vcn.inst[j].ring_dec;
-			}
+			scheds = adev->vcn.vcn_dec_sched;
+			num_scheds =  adev->vcn.num_vcn_dec_sched;
 			break;
 		case AMDGPU_HW_IP_VCN_ENC:
-			for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
-				if (adev->vcn.harvest_config & (1 << j))
-					continue;
-				for (k = 0; k < adev->vcn.num_enc_rings; ++k)
-					rings[num_rings++] = &adev->vcn.inst[j].ring_enc[k];
-			}
+			scheds = adev->vcn.vcn_enc_sched;
+			num_scheds =  adev->vcn.num_vcn_enc_sched;
 			break;
 		case AMDGPU_HW_IP_VCN_JPEG:
-			for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
-				if (adev->vcn.harvest_config & (1 << j))
-					continue;
-				rings[num_rings++] = &adev->vcn.inst[j].ring_jpeg;
-			}
+			scheds = adev->jpeg.jpeg_sched;
+			num_scheds =  adev->jpeg.num_jpeg_sched;
 			break;
 		}
 
-		for (j = 0; j < num_rings; ++j) {
-			if (!rings[j]->adev)
-				continue;
-
-			rqs[num_rqs++] = &rings[j]->sched.sched_rq[priority];
-		}
-
 		for (j = 0; j < amdgpu_ctx_num_entities[i]; ++j)
 			r = drm_sched_entity_init(&ctx->entities[i][j].entity,
-						  rqs, num_rqs, &ctx->guilty);
+						  priority, scheds,
+						  num_scheds, &ctx->guilty);
 		if (r)
 			goto error_cleanup_entities;
 	}
@@ -627,3 +612,45 @@ void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
 	idr_destroy(&mgr->ctx_handles);
 	mutex_destroy(&mgr->lock);
 }
+
+void amdgpu_ctx_init_sched(struct amdgpu_device *adev)
+{
+	int i, j;
+
+	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
+		adev->gfx.gfx_sched[i] = &adev->gfx.gfx_ring[i].sched;
+		adev->gfx.num_gfx_sched++;
+	}
+
+	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+		adev->gfx.compute_sched[i] = &adev->gfx.compute_ring[i].sched;
+		adev->gfx.num_compute_sched++;
+	}
+
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		adev->sdma.sdma_sched[i] = &adev->sdma.instance[i].ring.sched;
+		adev->sdma.num_sdma_sched++;
+	}
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+		adev->vcn.vcn_dec_sched[adev->vcn.num_vcn_dec_sched++] =
+			&adev->vcn.inst[i].ring_dec.sched;
+	}
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+		for (j = 0; j < adev->vcn.num_enc_rings; ++j)
+			adev->vcn.vcn_enc_sched[adev->vcn.num_vcn_enc_sched++] =
+				&adev->vcn.inst[i].ring_enc[j].sched;
+	}
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+		adev->jpeg.jpeg_sched[adev->jpeg.num_jpeg_sched++] =
+			&adev->jpeg.inst[i].ring_dec.sched;
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
index da808633732b..4ad90a44dc3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
@@ -87,4 +87,7 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr);
 long amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr, long timeout);
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
 
+void amdgpu_ctx_init_sched(struct amdgpu_device *adev);
+
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 8e6726e0d035..f24ed9a1a3e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -26,6 +26,7 @@
 #include <linux/kthread.h>
 #include <linux/pci.h>
 #include <linux/uaccess.h>
+#include <linux/pm_runtime.h>
 
 #include <drm/drm_debugfs.h>
 
@@ -129,7 +130,7 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 			sh_bank = 0xFFFFFFFF;
 		if (instance_bank == 0x3FF)
 			instance_bank = 0xFFFFFFFF;
-		use_bank = 1;
+		use_bank = true;
 	} else if (*pos & (1ULL << 61)) {
 
 		me = (*pos & GENMASK_ULL(33, 24)) >> 24;
@@ -137,17 +138,24 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 		queue = (*pos & GENMASK_ULL(53, 44)) >> 44;
 		vmid = (*pos & GENMASK_ULL(58, 54)) >> 54;
 
-		use_ring = 1;
+		use_ring = true;
 	} else {
-		use_bank = use_ring = 0;
+		use_bank = use_ring = false;
 	}
 
 	*pos &= (1UL << 22) - 1;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	if (use_bank) {
 		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
-		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines))
+		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines)) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 		mutex_lock(&adev->grbm_idx_mutex);
 		amdgpu_gfx_select_se_sh(adev, se_bank,
 					sh_bank, instance_bank);
@@ -193,6 +201,9 @@ end:
 	if (pm_pg_lock)
 		mutex_unlock(&adev->pm.mutex);
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -237,13 +248,20 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		value = RREG32_PCIE(*pos >> 2);
 		r = put_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		result += 4;
 		buf += 4;
@@ -251,6 +269,9 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -276,12 +297,19 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		r = get_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		WREG32_PCIE(*pos >> 2, value);
 
@@ -291,6 +319,9 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -316,13 +347,20 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		value = RREG32_DIDT(*pos >> 2);
 		r = put_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		result += 4;
 		buf += 4;
@@ -330,6 +368,9 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -355,12 +396,19 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		r = get_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		WREG32_DIDT(*pos >> 2, value);
 
@@ -370,6 +418,9 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -395,13 +446,20 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		value = RREG32_SMC(*pos);
 		r = put_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		result += 4;
 		buf += 4;
@@ -409,6 +467,9 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -434,12 +495,19 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		r = get_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		WREG32_SMC(*pos, value);
 
@@ -449,6 +517,9 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -572,7 +643,16 @@ static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
 	idx = *pos >> 2;
 
 	valuesize = sizeof(values);
+
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	r = amdgpu_dpm_read_sensor(adev, idx, &values[0], &valuesize);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -633,6 +713,10 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 	wave = (*pos & GENMASK_ULL(36, 31)) >> 31;
 	simd = (*pos & GENMASK_ULL(44, 37)) >> 37;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	/* switch to the specific se/sh/cu */
 	mutex_lock(&adev->grbm_idx_mutex);
 	amdgpu_gfx_select_se_sh(adev, se, sh, cu);
@@ -644,6 +728,9 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (!x)
 		return -EINVAL;
 
@@ -711,6 +798,10 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	if (!data)
 		return -ENOMEM;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	/* switch to the specific se/sh/cu */
 	mutex_lock(&adev->grbm_idx_mutex);
 	amdgpu_gfx_select_se_sh(adev, se, sh, cu);
@@ -726,6 +817,9 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	while (size) {
 		uint32_t value;
 
@@ -859,6 +953,10 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
 	struct amdgpu_device *adev = dev->dev_private;
 	int r = 0, i;
 
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
+
 	/* Avoid accidently unparking the sched thread during GPU reset */
 	mutex_lock(&adev->lock_reset);
 
@@ -889,6 +987,9 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
 
 	mutex_unlock(&adev->lock_reset);
 
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
 	return 0;
 }
 
@@ -907,8 +1008,17 @@ static int amdgpu_debugfs_evict_vram(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	int r;
+
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
 
 	seq_printf(m, "(%d)\n", amdgpu_bo_evict_vram(adev));
+
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
 	return 0;
 }
 
@@ -917,8 +1027,17 @@ static int amdgpu_debugfs_evict_gtt(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	int r;
+
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
 
 	seq_printf(m, "(%d)\n", ttm_bo_evict_mm(&adev->mman.bdev, TTM_PL_TT));
+
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c17505fba988..53d882000101 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -66,6 +66,7 @@
 #include "amdgpu_pmu.h"
 
 #include <linux/suspend.h>
+#include <drm/task_barrier.h>
 
 MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin");
@@ -137,14 +138,14 @@ static DEVICE_ATTR(pcie_replay_count, S_IRUGO,
 static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev);
 
 /**
- * amdgpu_device_is_px - Is the device is a dGPU with HG/PX power control
+ * amdgpu_device_supports_boco - Is the device a dGPU with HG/PX power control
  *
  * @dev: drm_device pointer
  *
  * Returns true if the device is a dGPU with HG/PX power control,
  * otherwise return false.
  */
-bool amdgpu_device_is_px(struct drm_device *dev)
+bool amdgpu_device_supports_boco(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = dev->dev_private;
 
@@ -154,6 +155,21 @@ bool amdgpu_device_is_px(struct drm_device *dev)
 }
 
 /**
+ * amdgpu_device_supports_baco - Does the device support BACO
+ *
+ * @dev: drm_device pointer
+ *
+ * Returns true if the device supporte BACO,
+ * otherwise return false.
+ */
+bool amdgpu_device_supports_baco(struct drm_device *dev)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+
+	return amdgpu_asic_supports_baco(adev);
+}
+
+/**
  * VRAM access helper functions.
  *
  * amdgpu_device_vram_access - read/write a buffer in vram
@@ -1016,8 +1032,6 @@ def_value:
  */
 static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 {
-	int ret = 0;
-
 	if (amdgpu_sched_jobs < 4) {
 		dev_warn(adev->dev, "sched jobs (%d) must be at least 4\n",
 			 amdgpu_sched_jobs);
@@ -1057,7 +1071,7 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -1072,8 +1086,9 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
+	int r;
 
-	if (amdgpu_device_is_px(dev) && state == VGA_SWITCHEROO_OFF)
+	if (amdgpu_device_supports_boco(dev) && state == VGA_SWITCHEROO_OFF)
 		return;
 
 	if (state == VGA_SWITCHEROO_ON) {
@@ -1081,7 +1096,12 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 		/* don't suspend or resume card normally */
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 
-		amdgpu_device_resume(dev, true, true);
+		pci_set_power_state(dev->pdev, PCI_D0);
+		pci_restore_state(dev->pdev);
+		r = pci_enable_device(dev->pdev);
+		if (r)
+			DRM_WARN("pci_enable_device failed (%d)\n", r);
+		amdgpu_device_resume(dev, true);
 
 		dev->switch_power_state = DRM_SWITCH_POWER_ON;
 		drm_kms_helper_poll_enable(dev);
@@ -1089,7 +1109,11 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 		pr_info("amdgpu: switched off\n");
 		drm_kms_helper_poll_disable(dev);
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-		amdgpu_device_suspend(dev, true, true);
+		amdgpu_device_suspend(dev, true);
+		pci_save_state(dev->pdev);
+		/* Shut down the device */
+		pci_disable_device(dev->pdev);
+		pci_set_power_state(dev->pdev, PCI_D3cold);
 		dev->switch_power_state = DRM_SWITCH_POWER_OFF;
 	}
 }
@@ -1527,7 +1551,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 		}
 
 parse_soc_bounding_box:
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		/*
 		 * soc bounding box info is not integrated in disocovery table,
 		 * we always need to parse it from gpu info firmware.
@@ -1538,7 +1561,6 @@ parse_soc_bounding_box:
 									le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 			adev->dm.soc_bounding_box = &gpu_info_fw->soc_bounding_box;
 		}
-#endif
 		break;
 	}
 	default:
@@ -1787,7 +1809,8 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
 		}
 	}
 
-	r = amdgpu_pm_load_smu_firmware(adev, &smu_version);
+	if (!amdgpu_sriov_vf(adev) || adev->asic_type == CHIP_TONGA)
+		r = amdgpu_pm_load_smu_firmware(adev, &smu_version);
 
 	return r;
 }
@@ -1854,6 +1877,9 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 		}
 	}
 
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_init_data_exchange(adev);
+
 	r = amdgpu_ib_pool_init(adev);
 	if (r) {
 		dev_err(adev->dev, "IB initialization failed (%d).\n", r);
@@ -1895,11 +1921,8 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	amdgpu_amdkfd_device_init(adev);
 
 init_failed:
-	if (amdgpu_sriov_vf(adev)) {
-		if (!r)
-			amdgpu_virt_init_data_exchange(adev);
+	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, true);
-	}
 
 	return r;
 }
@@ -1938,6 +1961,7 @@ static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev)
  * amdgpu_device_set_cg_state - set clockgating for amdgpu device
  *
  * @adev: amdgpu_device pointer
+ * @state: clockgating state (gate or ungate)
  *
  * The list of all the hardware IPs that make up the asic is walked and the
  * set_clockgating_state callbacks are run.
@@ -1962,6 +1986,7 @@ static int amdgpu_device_set_cg_state(struct amdgpu_device *adev,
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG &&
 		    adev->ip_blocks[i].version->funcs->set_clockgating_state) {
 			/* enable clockgating to save power */
 			r = adev->ip_blocks[i].version->funcs->set_clockgating_state((void *)adev,
@@ -1992,6 +2017,7 @@ static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_power
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG &&
 		    adev->ip_blocks[i].version->funcs->set_powergating_state) {
 			/* enable powergating to save power */
 			r = adev->ip_blocks[i].version->funcs->set_powergating_state((void *)adev,
@@ -2319,14 +2345,7 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = false;
 		/* handle putting the SMC in the appropriate state */
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
-			if (is_support_sw_smu(adev)) {
-				r = smu_set_mp1_state(&adev->smu, adev->mp1_state);
-			} else if (adev->powerplay.pp_funcs &&
-					   adev->powerplay.pp_funcs->set_mp1_state) {
-				r = adev->powerplay.pp_funcs->set_mp1_state(
-					adev->powerplay.pp_handle,
-					adev->mp1_state);
-			}
+			r = amdgpu_dpm_set_mp1_state(adev, adev->mp1_state);
 			if (r) {
 				DRM_ERROR("SMC failed to set mp1 state %d, %d\n",
 					  adev->mp1_state, r);
@@ -2413,7 +2432,8 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 		AMD_IP_BLOCK_TYPE_GFX,
 		AMD_IP_BLOCK_TYPE_SDMA,
 		AMD_IP_BLOCK_TYPE_UVD,
-		AMD_IP_BLOCK_TYPE_VCE
+		AMD_IP_BLOCK_TYPE_VCE,
+		AMD_IP_BLOCK_TYPE_VCN
 	};
 
 	for (i = 0; i < ARRAY_SIZE(ip_order); i++) {
@@ -2428,7 +2448,11 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 				block->status.hw)
 				continue;
 
-			r = block->version->funcs->hw_init(adev);
+			if (block->version->type == AMD_IP_BLOCK_TYPE_SMC)
+				r = block->version->funcs->resume(adev);
+			else
+				r = block->version->funcs->hw_init(adev);
+
 			DRM_INFO("RE-INIT-late: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
@@ -2600,20 +2624,19 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case CHIP_RAVEN:
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case CHIP_RENOIR:
 #endif
 		return amdgpu_dc != 0;
 #endif
 	default:
+		if (amdgpu_dc > 0)
+			DRM_INFO("Display Core has been requested via kernel parameter "
+					 "but isn't supported by ASIC, ignoring\n");
 		return false;
 	}
 }
@@ -2638,8 +2661,38 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work)
 {
 	struct amdgpu_device *adev =
 		container_of(__work, struct amdgpu_device, xgmi_reset_work);
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
+
+	/* It's a bug to not have a hive within this function */
+	if (WARN_ON(!hive))
+		return;
+
+	/*
+	 * Use task barrier to synchronize all xgmi reset works across the
+	 * hive. task_barrier_enter and task_barrier_exit will block
+	 * until all the threads running the xgmi reset works reach
+	 * those points. task_barrier_full will do both blocks.
+	 */
+	if (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+
+		task_barrier_enter(&hive->tb);
+		adev->asic_reset_res = amdgpu_device_baco_enter(adev->ddev);
+
+		if (adev->asic_reset_res)
+			goto fail;
+
+		task_barrier_exit(&hive->tb);
+		adev->asic_reset_res = amdgpu_device_baco_exit(adev->ddev);
+
+		if (adev->asic_reset_res)
+			goto fail;
+	} else {
+
+		task_barrier_full(&hive->tb);
+		adev->asic_reset_res =  amdgpu_asic_reset(adev);
+	}
 
-	adev->asic_reset_res =  amdgpu_asic_reset(adev);
+fail:
 	if (adev->asic_reset_res)
 		DRM_WARN("ASIC reset failed with error, %d for drm dev, %s",
 			 adev->asic_reset_res, adev->ddev->unique);
@@ -2731,7 +2784,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		       uint32_t flags)
 {
 	int r, i;
-	bool runtime = false;
+	bool boco = false;
 	u32 max_MBps;
 
 	adev->shutdown = false;
@@ -2754,7 +2807,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	adev->mman.buffer_funcs = NULL;
 	adev->mman.buffer_funcs_ring = NULL;
 	adev->vm_manager.vm_pte_funcs = NULL;
-	adev->vm_manager.vm_pte_num_rqs = 0;
+	adev->vm_manager.vm_pte_num_scheds = 0;
 	adev->gmc.gmc_funcs = NULL;
 	adev->fence_context = dma_fence_context_alloc(AMDGPU_MAX_RINGS);
 	bitmap_zero(adev->gfx.pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
@@ -2794,9 +2847,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->virt.vf_errors.lock);
 	hash_init(adev->mn_hash);
 	mutex_init(&adev->lock_reset);
-	mutex_init(&adev->notifier_lock);
-	mutex_init(&adev->virt.dpm_mutex);
 	mutex_init(&adev->psp.mutex);
+	mutex_init(&adev->notifier_lock);
 
 	r = amdgpu_device_check_arguments(adev);
 	if (r)
@@ -2902,12 +2954,15 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * ignore it */
 	vga_client_register(adev->pdev, adev, NULL, amdgpu_device_vga_set_decode);
 
-	if (amdgpu_device_is_px(ddev))
-		runtime = true;
-	if (!pci_is_thunderbolt_attached(adev->pdev))
+	if (amdgpu_device_supports_boco(ddev))
+		boco = true;
+	if (amdgpu_has_atpx() &&
+	    (amdgpu_is_atpx_hybrid() ||
+	     amdgpu_has_atpx_dgpu_power_cntl()) &&
+	    !pci_is_thunderbolt_attached(adev->pdev))
 		vga_switcheroo_register_client(adev->pdev,
-					       &amdgpu_switcheroo_ops, runtime);
-	if (runtime)
+					       &amdgpu_switcheroo_ops, boco);
+	if (boco)
 		vga_switcheroo_init_domain_pm_ops(adev->dev, &adev->vga_pm_domain);
 
 	if (amdgpu_emu_mode == 1) {
@@ -2994,11 +3049,17 @@ fence_driver_init:
 		}
 		dev_err(adev->dev, "amdgpu_device_ip_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
-		if (amdgpu_virt_request_full_gpu(adev, false))
-			amdgpu_virt_release_full_gpu(adev, false);
 		goto failed;
 	}
 
+	DRM_DEBUG("SE %d, SH per SE %d, CU per SH %d, active_cu_number %d\n",
+			adev->gfx.config.max_shader_engines,
+			adev->gfx.config.max_sh_per_se,
+			adev->gfx.config.max_cu_per_sh,
+			adev->gfx.cu_info.number);
+
+	amdgpu_ctx_init_sched(adev);
+
 	adev->accel_working = true;
 
 	amdgpu_vm_check_compute_bug(adev);
@@ -3013,16 +3074,19 @@ fence_driver_init:
 
 	amdgpu_fbdev_init(adev);
 
-	if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev))
-		amdgpu_pm_virt_sysfs_init(adev);
-
 	r = amdgpu_pm_sysfs_init(adev);
-	if (r)
+	if (r) {
+		adev->pm_sysfs_en = false;
 		DRM_ERROR("registering pm debugfs failed (%d).\n", r);
+	} else
+		adev->pm_sysfs_en = true;
 
 	r = amdgpu_ucode_sysfs_init(adev);
-	if (r)
+	if (r) {
+		adev->ucode_sysfs_en = false;
 		DRM_ERROR("Creating firmware sysfs failed (%d).\n", r);
+	} else
+		adev->ucode_sysfs_en = true;
 
 	r = amdgpu_debugfs_gem_init(adev);
 	if (r)
@@ -3091,7 +3155,7 @@ fence_driver_init:
 
 failed:
 	amdgpu_vf_error_trans_all(adev);
-	if (runtime)
+	if (boco)
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 
 	return r;
@@ -3122,7 +3186,8 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 			drm_atomic_helper_shutdown(adev->ddev);
 	}
 	amdgpu_fence_driver_fini(adev);
-	amdgpu_pm_sysfs_fini(adev);
+	if (adev->pm_sysfs_en)
+		amdgpu_pm_sysfs_fini(adev);
 	amdgpu_fbdev_fini(adev);
 	r = amdgpu_device_ip_fini(adev);
 	if (adev->firmware.gpu_info_fw) {
@@ -3139,9 +3204,12 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 
 	kfree(adev->bios);
 	adev->bios = NULL;
-	if (!pci_is_thunderbolt_attached(adev->pdev))
+	if (amdgpu_has_atpx() &&
+	    (amdgpu_is_atpx_hybrid() ||
+	     amdgpu_has_atpx_dgpu_power_cntl()) &&
+	    !pci_is_thunderbolt_attached(adev->pdev))
 		vga_switcheroo_unregister_client(adev->pdev);
-	if (adev->flags & AMD_IS_PX)
+	if (amdgpu_device_supports_boco(adev->ddev))
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 	vga_client_register(adev->pdev, NULL, NULL, NULL);
 	if (adev->rio_mem)
@@ -3150,12 +3218,11 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	iounmap(adev->rmmio);
 	adev->rmmio = NULL;
 	amdgpu_device_doorbell_fini(adev);
-	if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev))
-		amdgpu_pm_virt_sysfs_fini(adev);
 
 	amdgpu_debugfs_regs_cleanup(adev);
 	device_remove_file(adev->dev, &dev_attr_pcie_replay_count);
-	amdgpu_ucode_sysfs_fini(adev);
+	if (adev->ucode_sysfs_en)
+		amdgpu_ucode_sysfs_fini(adev);
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		amdgpu_pmu_fini(adev);
 	amdgpu_debugfs_preempt_cleanup(adev);
@@ -3178,7 +3245,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
  * Returns 0 for success or an error on failure.
  * Called at driver suspend.
  */
-int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
+int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 {
 	struct amdgpu_device *adev;
 	struct drm_crtc *crtc;
@@ -3261,13 +3328,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	 */
 	amdgpu_bo_evict_vram(adev);
 
-	if (suspend) {
-		pci_save_state(dev->pdev);
-		/* Shut down the device */
-		pci_disable_device(dev->pdev);
-		pci_set_power_state(dev->pdev, PCI_D3hot);
-	}
-
 	return 0;
 }
 
@@ -3282,7 +3342,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
  * Returns 0 for success or an error on failure.
  * Called at driver resume.
  */
-int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
+int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 {
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
@@ -3293,14 +3353,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	if (resume) {
-		pci_set_power_state(dev->pdev, PCI_D0);
-		pci_restore_state(dev->pdev);
-		r = pci_enable_device(dev->pdev);
-		if (r)
-			return r;
-	}
-
 	/* post card */
 	if (amdgpu_device_need_post(adev)) {
 		r = amdgpu_atom_asic_init(adev->mode_info.atom_context);
@@ -3639,13 +3691,12 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
 		goto error;
 
+	amdgpu_virt_init_data_exchange(adev);
 	/* we need recover gart prior to run SMC/CP/SDMA resume */
 	amdgpu_gtt_mgr_recover(&adev->mman.bdev.man[TTM_PL_TT]);
 
@@ -3663,7 +3714,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	amdgpu_amdkfd_post_reset(adev);
 
 error:
-	amdgpu_virt_init_data_exchange(adev);
 	amdgpu_virt_release_full_gpu(adev, true);
 	if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
 		amdgpu_inc_vram_lost(adev);
@@ -3709,6 +3759,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 		case CHIP_VEGA10:
 		case CHIP_VEGA12:
 		case CHIP_RAVEN:
+		case CHIP_ARCTURUS:
 			break;
 		default:
 			goto disabled;
@@ -3785,7 +3836,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 		list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 			/* For XGMI run all resets in parallel to speed up the process */
 			if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
-				if (!queue_work(system_highpri_wq, &tmp_adev->xgmi_reset_work))
+				if (!queue_work(system_unbound_wq, &tmp_adev->xgmi_reset_work))
 					r = -EALREADY;
 			} else
 				r = amdgpu_asic_reset(tmp_adev);
@@ -3797,7 +3848,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 			}
 		}
 
-		/* For XGMI wait for all PSP resets to complete before proceed */
+		/* For XGMI wait for all resets to complete before proceed */
 		if (!r) {
 			list_for_each_entry(tmp_adev, device_list_handle,
 					    gmc.xgmi.head) {
@@ -3811,6 +3862,8 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 		}
 	}
 
+	if (!r && amdgpu_ras_intr_triggered())
+		amdgpu_ras_intr_cleared();
 
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 		if (need_full_reset) {
@@ -3899,7 +3952,7 @@ static bool amdgpu_device_lock_adev(struct amdgpu_device *adev, bool trylock)
 		mutex_lock(&adev->lock_reset);
 
 	atomic_inc(&adev->gpu_reset_counter);
-	adev->in_gpu_reset = 1;
+	adev->in_gpu_reset = true;
 	switch (amdgpu_asic_reset_method(adev)) {
 	case AMD_RESET_METHOD_MODE1:
 		adev->mp1_state = PP_MP1_STATE_SHUTDOWN;
@@ -3919,7 +3972,7 @@ static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
 {
 	amdgpu_vf_error_trans_all(adev);
 	adev->mp1_state = PP_MP1_STATE_NONE;
-	adev->in_gpu_reset = 0;
+	adev->in_gpu_reset = false;
 	mutex_unlock(&adev->lock_reset);
 }
 
@@ -3943,12 +3996,15 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	struct amdgpu_device *tmp_adev = NULL;
 	int i, r = 0;
 	bool in_ras_intr = amdgpu_ras_intr_triggered();
+	bool use_baco =
+		(amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) ?
+		true : false;
 
 	/*
 	 * Flush RAM to disk so that after reboot
 	 * the user can read log and see why the system rebooted.
 	 */
-	if (in_ras_intr && amdgpu_ras_get_context(adev)->reboot) {
+	if (in_ras_intr && !use_baco && amdgpu_ras_get_context(adev)->reboot) {
 
 		DRM_WARN("Emergency reboot.");
 
@@ -3959,7 +4015,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	need_full_reset = job_signaled = false;
 	INIT_LIST_HEAD(&device_list);
 
-	dev_info(adev->dev, "GPU %s begin!\n", in_ras_intr ? "jobs stop":"reset");
+	dev_info(adev->dev, "GPU %s begin!\n",
+		(in_ras_intr && !use_baco) ? "jobs stop":"reset");
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
 
@@ -4026,7 +4083,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		amdgpu_unregister_gpu_instance(tmp_adev);
 
 		/* disable ras on ALL IPs */
-		if (!in_ras_intr && amdgpu_device_ip_need_full_reset(tmp_adev))
+		if (!(in_ras_intr && !use_baco) &&
+		      amdgpu_device_ip_need_full_reset(tmp_adev))
 			amdgpu_ras_suspend(tmp_adev);
 
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
@@ -4037,13 +4095,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 			drm_sched_stop(&ring->sched, job ? &job->base : NULL);
 
-			if (in_ras_intr)
+			if (in_ras_intr && !use_baco)
 				amdgpu_job_stop_all_jobs_on_sched(&ring->sched);
 		}
 	}
 
 
-	if (in_ras_intr)
+	if (in_ras_intr && !use_baco)
 		goto skip_sched_resume;
 
 	/*
@@ -4136,7 +4194,7 @@ skip_hw_reset:
 skip_sched_resume:
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 		/*unlock kfd: SRIOV would do it separately */
-		if (!in_ras_intr && !amdgpu_sriov_vf(tmp_adev))
+		if (!(in_ras_intr && !use_baco) && !amdgpu_sriov_vf(tmp_adev))
 	                amdgpu_amdkfd_post_reset(tmp_adev);
 		amdgpu_device_unlock_adev(tmp_adev);
 	}
@@ -4285,3 +4343,35 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 	}
 }
 
+int amdgpu_device_baco_enter(struct drm_device *dev)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+
+	if (!amdgpu_device_supports_baco(adev->ddev))
+		return -ENOTSUPP;
+
+	if (ras && ras->supported)
+		adev->nbio.funcs->enable_doorbell_interrupt(adev, false);
+
+	return amdgpu_dpm_baco_enter(adev);
+}
+
+int amdgpu_device_baco_exit(struct drm_device *dev)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	int ret = 0;
+
+	if (!amdgpu_device_supports_baco(adev->ddev))
+		return -ENOTSUPP;
+
+	ret = amdgpu_dpm_baco_exit(adev);
+	if (ret)
+		return ret;
+
+	if (ras && ras->supported)
+		adev->nbio.funcs->enable_doorbell_interrupt(adev, true);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
new file mode 100644
index 000000000000..61a26c15c8dd
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __AMDGPU_DF_H__
+#define __AMDGPU_DF_H__
+
+struct amdgpu_df_hash_status {
+	bool hash_64k;
+	bool hash_2m;
+	bool hash_1g;
+};
+
+struct amdgpu_df_funcs {
+	void (*sw_init)(struct amdgpu_device *adev);
+	void (*sw_fini)(struct amdgpu_device *adev);
+	void (*enable_broadcast_mode)(struct amdgpu_device *adev,
+				      bool enable);
+	u32 (*get_fb_channel_number)(struct amdgpu_device *adev);
+	u32 (*get_hbm_channel_number)(struct amdgpu_device *adev);
+	void (*update_medium_grain_clock_gating)(struct amdgpu_device *adev,
+						 bool enable);
+	void (*get_clockgating_state)(struct amdgpu_device *adev,
+				      u32 *flags);
+	void (*enable_ecc_force_par_wr_rmw)(struct amdgpu_device *adev,
+					    bool enable);
+	int (*pmc_start)(struct amdgpu_device *adev, uint64_t config,
+					 int is_enable);
+	int (*pmc_stop)(struct amdgpu_device *adev, uint64_t config,
+					 int is_disable);
+	void (*pmc_get_count)(struct amdgpu_device *adev, uint64_t config,
+					 uint64_t *count);
+	uint64_t (*get_fica)(struct amdgpu_device *adev, uint32_t ficaa_val);
+	void (*set_fica)(struct amdgpu_device *adev, uint32_t ficaa_val,
+			 uint32_t ficadl_val, uint32_t ficadh_val);
+};
+
+struct amdgpu_df {
+	struct amdgpu_df_hash_status	hash_status;
+	const struct amdgpu_df_funcs	*funcs;
+};
+
+#endif /* __AMDGPU_DF_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 3cadb0b76f22..6d520a3eec40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -513,13 +513,23 @@ uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
 	 * will not allow USWC mappings.
 	 * Also, don't allow GTT domain if the BO doens't have USWC falg set.
 	 */
-	if (adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type < CHIP_RAVEN &&
-	    (adev->flags & AMD_IS_APU) &&
-	    (bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) &&
+	if ((bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) &&
 	    amdgpu_bo_support_uswc(bo_flags) &&
-	    amdgpu_device_asic_has_dc_support(adev->asic_type))
-		domain |= AMDGPU_GEM_DOMAIN_GTT;
+	    amdgpu_device_asic_has_dc_support(adev->asic_type)) {
+		switch (adev->asic_type) {
+		case CHIP_CARRIZO:
+		case CHIP_STONEY:
+			domain |= AMDGPU_GEM_DOMAIN_GTT;
+			break;
+		case CHIP_RAVEN:
+			/* enable S/G on PCO and RV2 */
+			if (adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
+				domain |= AMDGPU_GEM_DOMAIN_GTT;
+			break;
+		default:
+			break;
+		}
+	}
 #endif
 
 	return domain;
@@ -690,7 +700,6 @@ bool amdgpu_display_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct amdgpu_encoder *amdgpu_encoder;
 	struct drm_connector *connector;
-	struct amdgpu_connector *amdgpu_connector;
 	u32 src_v = 1, dst_v = 1;
 	u32 src_h = 1, dst_h = 1;
 
@@ -702,7 +711,6 @@ bool amdgpu_display_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
 			continue;
 		amdgpu_encoder = to_amdgpu_encoder(encoder);
 		connector = amdgpu_get_connector_for_encoder(encoder);
-		amdgpu_connector = to_amdgpu_connector(connector);
 
 		/* set scaling */
 		if (amdgpu_encoder->rmx_type == RMX_OFF)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index e2eec7b66334..a59cd47aa6c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -360,10 +360,8 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
 		return ERR_PTR(-EPERM);
 
 	buf = drm_gem_prime_export(gobj, flags);
-	if (!IS_ERR(buf)) {
-		buf->file->f_mapping = gobj->dev->anon_inode->i_mapping;
+	if (!IS_ERR(buf))
 		buf->ops = &amdgpu_dmabuf_ops;
-	}
 
 	return buf;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 9cc270efee7c..a2e8c3dfb4f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -946,20 +946,63 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 	bool swsmu = is_support_sw_smu(adev);
 
 	switch (block_type) {
-	case AMD_IP_BLOCK_TYPE_GFX:
 	case AMD_IP_BLOCK_TYPE_UVD:
-	case AMD_IP_BLOCK_TYPE_VCN:
 	case AMD_IP_BLOCK_TYPE_VCE:
+		if (swsmu) {
+			ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate);
+		} else if (adev->powerplay.pp_funcs &&
+			   adev->powerplay.pp_funcs->set_powergating_by_smu) {
+			/*
+			 * TODO: need a better lock mechanism
+			 *
+			 * Here adev->pm.mutex lock protection is enforced on
+			 * UVD and VCE cases only. Since for other cases, there
+			 * may be already lock protection in amdgpu_pm.c.
+			 * This is a quick fix for the deadlock issue below.
+			 *     NFO: task ocltst:2028 blocked for more than 120 seconds.
+			 *     Tainted: G           OE     5.0.0-37-generic #40~18.04.1-Ubuntu
+			 *     echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
+			 *     cltst          D    0  2028   2026 0x00000000
+			 *     all Trace:
+			 *     __schedule+0x2c0/0x870
+			 *     schedule+0x2c/0x70
+			 *     schedule_preempt_disabled+0xe/0x10
+			 *     __mutex_lock.isra.9+0x26d/0x4e0
+			 *     __mutex_lock_slowpath+0x13/0x20
+			 *     ? __mutex_lock_slowpath+0x13/0x20
+			 *     mutex_lock+0x2f/0x40
+			 *     amdgpu_dpm_set_powergating_by_smu+0x64/0xe0 [amdgpu]
+			 *     gfx_v8_0_enable_gfx_static_mg_power_gating+0x3c/0x70 [amdgpu]
+			 *     gfx_v8_0_set_powergating_state+0x66/0x260 [amdgpu]
+			 *     amdgpu_device_ip_set_powergating_state+0x62/0xb0 [amdgpu]
+			 *     pp_dpm_force_performance_level+0xe7/0x100 [amdgpu]
+			 *     amdgpu_set_dpm_forced_performance_level+0x129/0x330 [amdgpu]
+			 */
+			mutex_lock(&adev->pm.mutex);
+			ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
+				(adev)->powerplay.pp_handle, block_type, gate));
+			mutex_unlock(&adev->pm.mutex);
+		}
+		break;
+	case AMD_IP_BLOCK_TYPE_GFX:
+	case AMD_IP_BLOCK_TYPE_VCN:
 	case AMD_IP_BLOCK_TYPE_SDMA:
 		if (swsmu)
 			ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate);
-		else
+		else if (adev->powerplay.pp_funcs &&
+			 adev->powerplay.pp_funcs->set_powergating_by_smu)
 			ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
 				(adev)->powerplay.pp_handle, block_type, gate));
 		break;
+	case AMD_IP_BLOCK_TYPE_JPEG:
+		if (swsmu)
+			ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate);
+		break;
 	case AMD_IP_BLOCK_TYPE_GMC:
 	case AMD_IP_BLOCK_TYPE_ACP:
-		ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
+		if (adev->powerplay.pp_funcs &&
+		    adev->powerplay.pp_funcs->set_powergating_by_smu)
+			ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
 				(adev)->powerplay.pp_handle, block_type, gate));
 		break;
 	default:
@@ -968,3 +1011,163 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 
 	return ret;
 }
+
+int amdgpu_dpm_baco_enter(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+	int ret = 0;
+
+	if (is_support_sw_smu(adev)) {
+		ret = smu_baco_enter(smu);
+	} else {
+		if (!pp_funcs || !pp_funcs->set_asic_baco_state)
+			return -ENOENT;
+
+		/* enter BACO state */
+		ret = pp_funcs->set_asic_baco_state(pp_handle, 1);
+	}
+
+	return ret;
+}
+
+int amdgpu_dpm_baco_exit(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+	int ret = 0;
+
+	if (is_support_sw_smu(adev)) {
+		ret = smu_baco_exit(smu);
+	} else {
+		if (!pp_funcs || !pp_funcs->set_asic_baco_state)
+			return -ENOENT;
+
+		/* exit BACO state */
+		ret = pp_funcs->set_asic_baco_state(pp_handle, 0);
+	}
+
+	return ret;
+}
+
+int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
+			     enum pp_mp1_state mp1_state)
+{
+	int ret = 0;
+
+	if (is_support_sw_smu(adev)) {
+		ret = smu_set_mp1_state(&adev->smu, mp1_state);
+	} else if (adev->powerplay.pp_funcs &&
+		   adev->powerplay.pp_funcs->set_mp1_state) {
+		ret = adev->powerplay.pp_funcs->set_mp1_state(
+				adev->powerplay.pp_handle,
+				mp1_state);
+	}
+
+	return ret;
+}
+
+bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+	bool baco_cap;
+
+	if (is_support_sw_smu(adev)) {
+		return smu_baco_is_support(smu);
+	} else {
+		if (!pp_funcs || !pp_funcs->get_asic_baco_capability)
+			return false;
+
+		if (pp_funcs->get_asic_baco_capability(pp_handle, &baco_cap))
+			return false;
+
+		return baco_cap ? true : false;
+	}
+}
+
+int amdgpu_dpm_mode2_reset(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+
+	if (is_support_sw_smu(adev)) {
+		return smu_mode2_reset(smu);
+	} else {
+		if (!pp_funcs || !pp_funcs->asic_reset_mode_2)
+			return -ENOENT;
+
+		return pp_funcs->asic_reset_mode_2(pp_handle);
+	}
+}
+
+int amdgpu_dpm_baco_reset(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+	int ret = 0;
+
+	dev_info(adev->dev, "GPU BACO reset\n");
+
+	if (is_support_sw_smu(adev)) {
+		ret = smu_baco_enter(smu);
+		if (ret)
+			return ret;
+
+		ret = smu_baco_exit(smu);
+		if (ret)
+			return ret;
+	} else {
+		if (!pp_funcs
+		    || !pp_funcs->set_asic_baco_state)
+			return -ENOENT;
+
+		/* enter BACO state */
+		ret = pp_funcs->set_asic_baco_state(pp_handle, 1);
+		if (ret)
+			return ret;
+
+		/* exit BACO state */
+		ret = pp_funcs->set_asic_baco_state(pp_handle, 0);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
+				    enum PP_SMC_POWER_PROFILE type,
+				    bool en)
+{
+	int ret = 0;
+
+	if (is_support_sw_smu(adev))
+		ret = smu_switch_power_profile(&adev->smu, type, en);
+	else if (adev->powerplay.pp_funcs &&
+		 adev->powerplay.pp_funcs->switch_power_profile)
+		ret = adev->powerplay.pp_funcs->switch_power_profile(
+			adev->powerplay.pp_handle, type, en);
+
+	return ret;
+}
+
+int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
+			       uint32_t pstate)
+{
+	int ret = 0;
+
+	if (is_support_sw_smu_xgmi(adev))
+		ret = smu_set_xgmi_pstate(&adev->smu, pstate);
+	else if (adev->powerplay.pp_funcs &&
+		 adev->powerplay.pp_funcs->set_xgmi_pstate)
+		ret = adev->powerplay.pp_funcs->set_xgmi_pstate(adev->powerplay.pp_handle,
+								pstate);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index 2cfb677272af..902ca6c00cca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -341,10 +341,6 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->reset_power_profile_state(\
 			(adev)->powerplay.pp_handle, request))
 
-#define amdgpu_dpm_switch_power_profile(adev, type, en) \
-		((adev)->powerplay.pp_funcs->switch_power_profile(\
-			(adev)->powerplay.pp_handle, type, en))
-
 #define amdgpu_dpm_set_clockgating_by_smu(adev, msg_id) \
 		((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
 			(adev)->powerplay.pp_handle, msg_id))
@@ -517,4 +513,24 @@ extern int amdgpu_dpm_get_sclk(struct amdgpu_device *adev, bool low);
 
 extern int amdgpu_dpm_get_mclk(struct amdgpu_device *adev, bool low);
 
+int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
+			       uint32_t pstate);
+
+int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
+				    enum PP_SMC_POWER_PROFILE type,
+				    bool en);
+
+int amdgpu_dpm_baco_reset(struct amdgpu_device *adev);
+
+int amdgpu_dpm_mode2_reset(struct amdgpu_device *adev);
+
+bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev);
+
+int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
+			     enum pp_mp1_state mp1_state);
+
+int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
+
+int amdgpu_dpm_baco_enter(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 30a1e3ac21d6..94e2fd758e01 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1147,7 +1147,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	return amdgpu_device_suspend(drm_dev, true, true);
+	return amdgpu_device_suspend(drm_dev, true);
 }
 
 static int amdgpu_pmops_resume(struct device *dev)
@@ -1155,13 +1155,14 @@ static int amdgpu_pmops_resume(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
 	/* GPU comes up enabled by the bios on resume */
-	if (amdgpu_device_is_px(drm_dev)) {
+	if (amdgpu_device_supports_boco(drm_dev) ||
+	    amdgpu_device_supports_baco(drm_dev)) {
 		pm_runtime_disable(dev);
 		pm_runtime_set_active(dev);
 		pm_runtime_enable(dev);
 	}
 
-	return amdgpu_device_resume(drm_dev, true, true);
+	return amdgpu_device_resume(drm_dev, true);
 }
 
 static int amdgpu_pmops_freeze(struct device *dev)
@@ -1170,7 +1171,7 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	struct amdgpu_device *adev = drm_dev->dev_private;
 	int r;
 
-	r = amdgpu_device_suspend(drm_dev, false, true);
+	r = amdgpu_device_suspend(drm_dev, true);
 	if (r)
 		return r;
 	return amdgpu_asic_reset(adev);
@@ -1180,46 +1181,66 @@ static int amdgpu_pmops_thaw(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	return amdgpu_device_resume(drm_dev, false, true);
+	return amdgpu_device_resume(drm_dev, true);
 }
 
 static int amdgpu_pmops_poweroff(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	return amdgpu_device_suspend(drm_dev, true, true);
+	return amdgpu_device_suspend(drm_dev, true);
 }
 
 static int amdgpu_pmops_restore(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	return amdgpu_device_resume(drm_dev, false, true);
+	return amdgpu_device_resume(drm_dev, true);
 }
 
 static int amdgpu_pmops_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
-	int ret;
+	struct amdgpu_device *adev = drm_dev->dev_private;
+	int ret, i;
 
-	if (!amdgpu_device_is_px(drm_dev)) {
+	if (!adev->runpm) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 
-	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+	/* wait for all rings to drain before suspending */
+	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+		struct amdgpu_ring *ring = adev->rings[i];
+		if (ring && ring->sched.ready) {
+			ret = amdgpu_fence_wait_empty(ring);
+			if (ret)
+				return -EBUSY;
+		}
+	}
+
+	if (amdgpu_device_supports_boco(drm_dev))
+		drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 	drm_kms_helper_poll_disable(drm_dev);
 
-	ret = amdgpu_device_suspend(drm_dev, false, false);
-	pci_save_state(pdev);
-	pci_disable_device(pdev);
-	pci_ignore_hotplug(pdev);
-	if (amdgpu_is_atpx_hybrid())
-		pci_set_power_state(pdev, PCI_D3cold);
-	else if (!amdgpu_has_atpx_dgpu_power_cntl())
-		pci_set_power_state(pdev, PCI_D3hot);
-	drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+	ret = amdgpu_device_suspend(drm_dev, false);
+	if (amdgpu_device_supports_boco(drm_dev)) {
+		/* Only need to handle PCI state in the driver for ATPX
+		 * PCI core handles it for _PR3.
+		 */
+		if (amdgpu_is_atpx_hybrid()) {
+			pci_ignore_hotplug(pdev);
+		} else {
+			pci_save_state(pdev);
+			pci_disable_device(pdev);
+			pci_ignore_hotplug(pdev);
+			pci_set_power_state(pdev, PCI_D3cold);
+		}
+		drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+	} else if (amdgpu_device_supports_baco(drm_dev)) {
+		amdgpu_device_baco_enter(drm_dev);
+	}
 
 	return 0;
 }
@@ -1228,34 +1249,45 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct amdgpu_device *adev = drm_dev->dev_private;
 	int ret;
 
-	if (!amdgpu_device_is_px(drm_dev))
+	if (!adev->runpm)
 		return -EINVAL;
 
-	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-
-	if (amdgpu_is_atpx_hybrid() ||
-	    !amdgpu_has_atpx_dgpu_power_cntl())
-		pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
-	ret = pci_enable_device(pdev);
-	if (ret)
-		return ret;
-	pci_set_master(pdev);
-
-	ret = amdgpu_device_resume(drm_dev, false, false);
+	if (amdgpu_device_supports_boco(drm_dev)) {
+		drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+
+		/* Only need to handle PCI state in the driver for ATPX
+		 * PCI core handles it for _PR3.
+		 */
+		if (amdgpu_is_atpx_hybrid()) {
+			pci_set_master(pdev);
+		} else {
+			pci_set_power_state(pdev, PCI_D0);
+			pci_restore_state(pdev);
+			ret = pci_enable_device(pdev);
+			if (ret)
+				return ret;
+			pci_set_master(pdev);
+		}
+	} else if (amdgpu_device_supports_baco(drm_dev)) {
+		amdgpu_device_baco_exit(drm_dev);
+	}
+	ret = amdgpu_device_resume(drm_dev, false);
 	drm_kms_helper_poll_enable(drm_dev);
-	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
+	if (amdgpu_device_supports_boco(drm_dev))
+		drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
 	return 0;
 }
 
 static int amdgpu_pmops_runtime_idle(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_dev->dev_private;
 	struct drm_crtc *crtc;
 
-	if (!amdgpu_device_is_px(drm_dev)) {
+	if (!adev->runpm) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 143753d237e7..2672dc64a310 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -69,7 +69,7 @@ amdgpufb_release(struct fb_info *info, int user)
 	return 0;
 }
 
-static struct fb_ops amdgpufb_ops = {
+static const struct fb_ops amdgpufb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open = amdgpufb_open,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 377fe20bce23..3c01252b1e0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -34,6 +34,7 @@
 #include <linux/kref.h>
 #include <linux/slab.h>
 #include <linux/firmware.h>
+#include <linux/pm_runtime.h>
 
 #include <drm/drm_debugfs.h>
 
@@ -154,7 +155,7 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
 		       seq);
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, flags | AMDGPU_FENCE_FLAG_INT);
-
+	pm_runtime_get_noresume(adev->ddev->dev);
 	ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask];
 	if (unlikely(rcu_dereference_protected(*ptr, 1))) {
 		struct dma_fence *old;
@@ -234,6 +235,7 @@ static void amdgpu_fence_schedule_fallback(struct amdgpu_ring *ring)
 bool amdgpu_fence_process(struct amdgpu_ring *ring)
 {
 	struct amdgpu_fence_driver *drv = &ring->fence_drv;
+	struct amdgpu_device *adev = ring->adev;
 	uint32_t seq, last_seq;
 	int r;
 
@@ -274,6 +276,8 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring)
 			BUG();
 
 		dma_fence_put(fence);
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 	} while (last_seq != seq);
 
 	return true;
@@ -737,10 +741,18 @@ static int amdgpu_debugfs_gpu_recover(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	int r;
+
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return 0;
 
 	seq_printf(m, "gpu recover\n");
 	amdgpu_device_gpu_recover(adev, NULL);
 
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 19705e399905..e01e681d2a60 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -302,6 +302,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
  * @pages: number of pages to bind
  * @pagelist: pages to bind
  * @dma_addr: DMA addresses of pages
+ * @flags: page table entry flags
  *
  * Binds the requested pages to the gart page table
  * (all asics).
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index e00b46180d2e..b88b8b82bb64 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -543,12 +543,6 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 	if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 		return;
 
-	if (!is_support_sw_smu(adev) &&
-	    (!adev->powerplay.pp_funcs ||
-	     !adev->powerplay.pp_funcs->set_powergating_by_smu))
-		return;
-
-
 	mutex_lock(&adev->gfx.gfx_off_mutex);
 
 	if (!enable)
@@ -641,7 +635,7 @@ int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
 		kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
 		if (adev->gfx.funcs->query_ras_error_count)
 			adev->gfx.funcs->query_ras_error_count(adev, err_data);
-		amdgpu_ras_reset_gpu(adev, 0);
+		amdgpu_ras_reset_gpu(adev);
 	}
 	return AMDGPU_RAS_SUCCESS;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 0ae0a2715b0d..af4bd279f42f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -76,11 +76,15 @@ struct kiq_pm4_funcs {
 					struct amdgpu_ring *ring,
 					u64 addr,
 					u64 seq);
+	void (*kiq_invalidate_tlbs)(struct amdgpu_ring *kiq_ring,
+				uint16_t pasid, uint32_t flush_type,
+				bool all_hub);
 	/* Packet sizes */
 	int set_resources_size;
 	int map_queues_size;
 	int unmap_queues_size;
 	int query_status_size;
+	int invalidate_tlbs_size;
 };
 
 struct amdgpu_kiq {
@@ -269,8 +273,12 @@ struct amdgpu_gfx {
 	bool				me_fw_write_wait;
 	bool				cp_fw_write_wait;
 	struct amdgpu_ring		gfx_ring[AMDGPU_MAX_GFX_RINGS];
+	struct drm_gpu_scheduler	*gfx_sched[AMDGPU_MAX_GFX_RINGS];
+	uint32_t			num_gfx_sched;
 	unsigned			num_gfx_rings;
 	struct amdgpu_ring		compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
+	struct drm_gpu_scheduler	*compute_sched[AMDGPU_MAX_COMPUTE_RINGS];
+	uint32_t			num_compute_sched;
 	unsigned			num_compute_rings;
 	struct amdgpu_irq_src		eop_irq;
 	struct amdgpu_irq_src		priv_reg_irq;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index a12f33c0f5df..5884ab590486 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -223,7 +223,7 @@ void amdgpu_gmc_agp_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
 	u64 size_af, size_bf;
 
 	if (amdgpu_sriov_vf(adev)) {
-		mc->agp_start = 0xffffffff;
+		mc->agp_start = 0xffffffffffff;
 		mc->agp_end = 0x0;
 		mc->agp_size = 0;
 
@@ -333,3 +333,43 @@ void amdgpu_gmc_ras_fini(struct amdgpu_device *adev)
 	amdgpu_mmhub_ras_fini(adev);
 	amdgpu_xgmi_ras_fini(adev);
 }
+
+	/*
+	 * The latest engine allocation on gfx9/10 is:
+	 * Engine 2, 3: firmware
+	 * Engine 0, 1, 4~16: amdgpu ring,
+	 *                    subject to change when ring number changes
+	 * Engine 17: Gart flushes
+	 */
+#define GFXHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
+#define MMHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
+
+int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	unsigned vm_inv_engs[AMDGPU_MAX_VMHUBS] =
+		{GFXHUB_FREE_VM_INV_ENGS_BITMAP, MMHUB_FREE_VM_INV_ENGS_BITMAP,
+		GFXHUB_FREE_VM_INV_ENGS_BITMAP};
+	unsigned i;
+	unsigned vmhub, inv_eng;
+
+	for (i = 0; i < adev->num_rings; ++i) {
+		ring = adev->rings[i];
+		vmhub = ring->funcs->vmhub;
+
+		inv_eng = ffs(vm_inv_engs[vmhub]);
+		if (!inv_eng) {
+			dev_err(adev->dev, "no VM inv eng for ring %s\n",
+				ring->name);
+			return -EINVAL;
+		}
+
+		ring->vm_inv_eng = inv_eng - 1;
+		vm_inv_engs[vmhub] &= ~(1 << ring->vm_inv_eng);
+
+		dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
+			 ring->name, ring->vm_inv_eng, ring->funcs->vmhub);
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index b499a3de8bb6..86267baca07c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -60,6 +60,11 @@
  */
 #define AMDGPU_GMC_FAULT_TIMEOUT	5000ULL
 
+/*
+ * Default stolen memory size, 1024 * 768 * 4
+ */
+#define AMDGPU_STOLEN_BIST_TRAINING_DEFAULT_SIZE	0x300000ULL
+
 struct firmware;
 
 /*
@@ -92,6 +97,9 @@ struct amdgpu_gmc_funcs {
 	/* flush the vm tlb via mmio */
 	void (*flush_gpu_tlb)(struct amdgpu_device *adev, uint32_t vmid,
 				uint32_t vmhub, uint32_t flush_type);
+	/* flush the vm tlb via pasid */
+	int (*flush_gpu_tlb_pasid)(struct amdgpu_device *adev, uint16_t pasid,
+					uint32_t flush_type, bool all_hub);
 	/* flush the vm tlb via ring */
 	uint64_t (*emit_flush_gpu_tlb)(struct amdgpu_ring *ring, unsigned vmid,
 				       uint64_t pd_addr);
@@ -216,6 +224,9 @@ struct amdgpu_gmc {
 };
 
 #define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type)))
+#define amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, type, allhub) \
+	((adev)->gmc.gmc_funcs->flush_gpu_tlb_pasid \
+	((adev), (pasid), (type), (allhub)))
 #define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (addr))
 #define amdgpu_gmc_emit_pasid_mapping(r, vmid, pasid) (r)->adev->gmc.gmc_funcs->emit_pasid_mapping((r), (vmid), (pasid))
 #define amdgpu_gmc_map_mtype(adev, flags) (adev)->gmc.gmc_funcs->map_mtype((adev),(flags))
@@ -267,5 +278,6 @@ bool amdgpu_gmc_filter_faults(struct amdgpu_device *adev, uint64_t addr,
 			      uint16_t pasid, uint64_t timestamp);
 int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev);
 void amdgpu_gmc_ras_fini(struct amdgpu_device *adev);
+int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 6f9289735e31..3a67f6c046d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -206,7 +206,7 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm,
 	int r;
 
 	if (ring->vmid_wait && !dma_fence_is_signaled(ring->vmid_wait))
-		return amdgpu_sync_fence(adev, sync, ring->vmid_wait, false);
+		return amdgpu_sync_fence(sync, ring->vmid_wait, false);
 
 	fences = kmalloc_array(sizeof(void *), id_mgr->num_ids, GFP_KERNEL);
 	if (!fences)
@@ -241,7 +241,7 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm,
 			return -ENOMEM;
 		}
 
-		r = amdgpu_sync_fence(adev, sync, &array->base, false);
+		r = amdgpu_sync_fence(sync, &array->base, false);
 		dma_fence_put(ring->vmid_wait);
 		ring->vmid_wait = &array->base;
 		return r;
@@ -294,7 +294,7 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
 		tmp = amdgpu_sync_peek_fence(&(*id)->active, ring);
 		if (tmp) {
 			*id = NULL;
-			r = amdgpu_sync_fence(adev, sync, tmp, false);
+			r = amdgpu_sync_fence(sync, tmp, false);
 			return r;
 		}
 		needs_flush = true;
@@ -303,7 +303,7 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
 	/* Good we can use this VMID. Remember this submission as
 	* user of the VMID.
 	*/
-	r = amdgpu_sync_fence(ring->adev, &(*id)->active, fence, false);
+	r = amdgpu_sync_fence(&(*id)->active, fence, false);
 	if (r)
 		return r;
 
@@ -375,7 +375,7 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm,
 		/* Good, we can use this VMID. Remember this submission as
 		 * user of the VMID.
 		 */
-		r = amdgpu_sync_fence(ring->adev, &(*id)->active, fence, false);
+		r = amdgpu_sync_fence(&(*id)->active, fence, false);
 		if (r)
 			return r;
 
@@ -435,8 +435,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 			id = idle;
 
 			/* Remember this submission as user of the VMID */
-			r = amdgpu_sync_fence(ring->adev, &id->active,
-					      fence, false);
+			r = amdgpu_sync_fence(&id->active, fence, false);
 			if (r)
 				goto error;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index 6d8f05511aba..111a301ce878 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -66,7 +66,6 @@ int amdgpu_ih_ring_init(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih,
 		if (ih->ring == NULL)
 			return -ENOMEM;
 
-		memset((void *)ih->ring, 0, ih->ring_size + 8);
 		ih->gpu_addr = dma_addr;
 		ih->wptr_addr = dma_addr + ih->ring_size;
 		ih->wptr_cpu = &ih->ring[ih->ring_size / 4];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 30d540d23b77..5ed4227f304b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -55,6 +55,7 @@
 #include "amdgpu_connectors.h"
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
+#include "amdgpu_ras.h"
 
 #include <linux/pm_runtime.h>
 
@@ -162,13 +163,15 @@ irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 	 * register to check whether the interrupt is triggered or not, and properly
 	 * ack the interrupt if it is there
 	 */
-	if (adev->nbio.funcs &&
-	    adev->nbio.funcs->handle_ras_controller_intr_no_bifring)
-		adev->nbio.funcs->handle_ras_controller_intr_no_bifring(adev);
-
-	if (adev->nbio.funcs &&
-	    adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring)
-		adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring(adev);
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__PCIE_BIF)) {
+		if (adev->nbio.funcs &&
+		    adev->nbio.funcs->handle_ras_controller_intr_no_bifring)
+			adev->nbio.funcs->handle_ras_controller_intr_no_bifring(adev);
+
+		if (adev->nbio.funcs &&
+		    adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring)
+			adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring(adev);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4fb20e870e63..d42be880a236 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -153,7 +153,6 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 	if (r)
 		return r;
 
-	job->owner = owner;
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
 	priority = job->base.s_priority;
@@ -193,8 +192,7 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 	fence = amdgpu_sync_get_fence(&job->sync, &explicit);
 	if (fence && explicit) {
 		if (drm_sched_dependency_optimized(fence, s_entity)) {
-			r = amdgpu_sync_fence(ring->adev, &job->sched_sync,
-					      fence, false);
+			r = amdgpu_sync_fence(&job->sched_sync, fence, false);
 			if (r)
 				DRM_ERROR("Error adding fence (%d)\n", r);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index dc7ee9358dcd..3f7b8433d179 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -49,7 +49,6 @@ struct amdgpu_job {
 	uint32_t		preamble_status;
 	uint32_t                preemption_status;
 	uint32_t		num_ibs;
-	void			*owner;
 	bool                    vm_needs_flush;
 	uint64_t		vm_pd_addr;
 	unsigned		vmid;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
new file mode 100644
index 000000000000..5727f00afc8e
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -0,0 +1,211 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, 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 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 NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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.
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_jpeg.h"
+#include "amdgpu_pm.h"
+#include "soc15d.h"
+#include "soc15_common.h"
+
+#define JPEG_IDLE_TIMEOUT	msecs_to_jiffies(1000)
+
+static void amdgpu_jpeg_idle_work_handler(struct work_struct *work);
+
+int amdgpu_jpeg_sw_init(struct amdgpu_device *adev)
+{
+	INIT_DELAYED_WORK(&adev->jpeg.idle_work, amdgpu_jpeg_idle_work_handler);
+
+	return 0;
+}
+
+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;
+
+		amdgpu_ring_fini(&adev->jpeg.inst[i].ring_dec);
+	}
+
+	return 0;
+}
+
+int amdgpu_jpeg_suspend(struct amdgpu_device *adev)
+{
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
+
+	return 0;
+}
+
+int amdgpu_jpeg_resume(struct amdgpu_device *adev)
+{
+	return 0;
+}
+
+static void amdgpu_jpeg_idle_work_handler(struct work_struct *work)
+{
+	struct amdgpu_device *adev =
+		container_of(work, struct amdgpu_device, jpeg.idle_work.work);
+	unsigned int fences = 0;
+	unsigned int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		fences += amdgpu_fence_count_emitted(&adev->jpeg.inst[i].ring_dec);
+	}
+
+	if (fences == 0)
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
+						       AMD_PG_STATE_GATE);
+	else
+		schedule_delayed_work(&adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
+}
+
+void amdgpu_jpeg_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	bool set_clocks = !cancel_delayed_work_sync(&adev->jpeg.idle_work);
+
+	if (set_clocks)
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
+						       AMD_PG_STATE_UNGATE);
+}
+
+void amdgpu_jpeg_ring_end_use(struct amdgpu_ring *ring)
+{
+	schedule_delayed_work(&ring->adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
+}
+
+int amdgpu_jpeg_dec_ring_test_ring(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	int r;
+
+	WREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch, 0xCAFEDEAD);
+	r = amdgpu_ring_alloc(ring, 3);
+	if (r)
+		return r;
+
+	amdgpu_ring_write(ring, PACKET0(adev->jpeg.internal.jpeg_pitch, 0));
+	amdgpu_ring_write(ring, 0xDEADBEEF);
+	amdgpu_ring_commit(ring);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch);
+		if (tmp == 0xDEADBEEF)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
+	return r;
+}
+
+static int amdgpu_jpeg_dec_set_reg(struct amdgpu_ring *ring, uint32_t handle,
+		struct dma_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_job *job;
+	struct amdgpu_ib *ib;
+	struct dma_fence *f = NULL;
+	const unsigned ib_size_dw = 16;
+	int i, r;
+
+	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
+	if (r)
+		return r;
+
+	ib = &job->ibs[0];
+
+	ib->ptr[0] = PACKETJ(adev->jpeg.internal.jpeg_pitch, 0, 0, PACKETJ_TYPE0);
+	ib->ptr[1] = 0xDEADBEEF;
+	for (i = 2; i < 16; i += 2) {
+		ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
+		ib->ptr[i+1] = 0;
+	}
+	ib->length_dw = 16;
+
+	r = amdgpu_job_submit_direct(job, ring, &f);
+	if (r)
+		goto err;
+
+	if (fence)
+		*fence = dma_fence_get(f);
+	dma_fence_put(f);
+
+	return 0;
+
+err:
+	amdgpu_job_free(job);
+	return r;
+}
+
+int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	struct dma_fence *fence = NULL;
+	long r = 0;
+
+	r = amdgpu_jpeg_dec_set_reg(ring, 1, &fence);
+	if (r)
+		goto error;
+
+	r = dma_fence_wait_timeout(fence, false, timeout);
+	if (r == 0) {
+		r = -ETIMEDOUT;
+		goto error;
+	} else if (r < 0) {
+		goto error;
+	} else {
+		r = 0;
+	}
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch);
+		if (tmp == 0xDEADBEEF)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
+	dma_fence_put(fence);
+error:
+	return r;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
new file mode 100644
index 000000000000..bd9ef9cc86de
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __AMDGPU_JPEG_H__
+#define __AMDGPU_JPEG_H__
+
+#define AMDGPU_MAX_JPEG_INSTANCES	2
+
+#define AMDGPU_JPEG_HARVEST_JPEG0 (1 << 0)
+#define AMDGPU_JPEG_HARVEST_JPEG1 (1 << 1)
+
+struct amdgpu_jpeg_reg{
+	unsigned jpeg_pitch;
+};
+
+struct amdgpu_jpeg_inst {
+	struct amdgpu_ring ring_dec;
+	struct amdgpu_irq_src irq;
+	struct amdgpu_jpeg_reg external;
+};
+
+struct amdgpu_jpeg {
+	uint8_t	num_jpeg_inst;
+	struct amdgpu_jpeg_inst inst[AMDGPU_MAX_JPEG_INSTANCES];
+	struct amdgpu_jpeg_reg internal;
+	struct drm_gpu_scheduler *jpeg_sched[AMDGPU_MAX_JPEG_INSTANCES];
+	uint32_t num_jpeg_sched;
+	unsigned harvest_config;
+	struct delayed_work idle_work;
+	enum amd_powergating_state cur_state;
+};
+
+int amdgpu_jpeg_sw_init(struct amdgpu_device *adev);
+int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev);
+int amdgpu_jpeg_suspend(struct amdgpu_device *adev);
+int amdgpu_jpeg_resume(struct amdgpu_device *adev);
+
+void amdgpu_jpeg_ring_begin_use(struct amdgpu_ring *ring);
+void amdgpu_jpeg_ring_end_use(struct amdgpu_ring *ring);
+
+int amdgpu_jpeg_dec_ring_test_ring(struct amdgpu_ring *ring);
+int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout);
+
+#endif /*__AMDGPU_JPEG_H__*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index b6db28a570c2..60591dbc2097 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -91,7 +91,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_request_full_gpu(adev, false);
 
-	if (amdgpu_device_is_px(dev)) {
+	if (adev->runpm) {
 		pm_runtime_get_sync(dev->dev);
 		pm_runtime_forbid(dev->dev);
 	}
@@ -150,8 +150,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	}
 	dev->dev_private = (void *)adev;
 
-	if ((amdgpu_runtime_pm != 0) &&
-	    amdgpu_has_atpx() &&
+	if (amdgpu_has_atpx() &&
 	    (amdgpu_is_atpx_hybrid() ||
 	     amdgpu_has_atpx_dgpu_power_cntl()) &&
 	    ((flags & AMD_IS_APU) == 0) &&
@@ -170,6 +169,13 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		goto out;
 	}
 
+	if (amdgpu_device_supports_boco(dev) &&
+	    (amdgpu_runtime_pm != 0)) /* enable runpm by default */
+		adev->runpm = true;
+	else if (amdgpu_device_supports_baco(dev) &&
+		 (amdgpu_runtime_pm > 0)) /* enable runpm if runpm=1 */
+		adev->runpm = true;
+
 	/* Call ACPI methods: require modeset init
 	 * but failure is not fatal
 	 */
@@ -180,7 +186,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 				"Error during ACPI methods call\n");
 	}
 
-	if (amdgpu_device_is_px(dev)) {
+	if (adev->runpm) {
 		dev_pm_set_driver_flags(dev->dev, DPM_FLAG_NEVER_SKIP);
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
@@ -193,7 +199,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 out:
 	if (r) {
 		/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
-		if (adev->rmmio && amdgpu_device_is_px(dev))
+		if (adev->rmmio && adev->runpm)
 			pm_runtime_put_noidle(dev->dev);
 		amdgpu_driver_unload_kms(dev);
 	}
@@ -293,6 +299,10 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->ver = adev->dm.dmcu_fw_version;
 		fw_info->feature = 0;
 		break;
+	case AMDGPU_INFO_FW_DMCUB:
+		fw_info->ver = adev->dm.dmcub_fw_version;
+		fw_info->feature = 0;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -396,12 +406,14 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev,
 		ib_size_alignment = 1;
 		break;
 	case AMDGPU_HW_IP_VCN_JPEG:
-		type = AMD_IP_BLOCK_TYPE_VCN;
-		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-			if (adev->uvd.harvest_config & (1 << i))
+		type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ?
+			AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN;
+
+		for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+			if (adev->jpeg.harvest_config & (1 << i))
 				continue;
 
-			if (adev->vcn.inst[i].ring_jpeg.sched.ready)
+			if (adev->jpeg.inst[i].ring_dec.sched.ready)
 				++num_rings;
 		}
 		ib_start_alignment = 16;
@@ -517,9 +529,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
 		case AMDGPU_HW_IP_VCN_ENC:
-		case AMDGPU_HW_IP_VCN_JPEG:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			break;
+		case AMDGPU_HW_IP_VCN_JPEG:
+			type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ?
+				AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -688,10 +703,6 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (adev->pm.dpm_enabled) {
 			dev_info.max_engine_clock = amdgpu_dpm_get_sclk(adev, false) * 10;
 			dev_info.max_memory_clock = amdgpu_dpm_get_mclk(adev, false) * 10;
-		} else if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev) &&
-			   adev->virt.ops->get_pp_clk) {
-			dev_info.max_engine_clock = amdgpu_virt_get_sclk(adev, false) * 10;
-			dev_info.max_memory_clock = amdgpu_virt_get_mclk(adev, false) * 10;
 		} else {
 			dev_info.max_engine_clock = adev->clock.default_sclk * 10;
 			dev_info.max_memory_clock = adev->clock.default_mclk * 10;
@@ -1394,6 +1405,14 @@ static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data)
 	seq_printf(m, "DMCU feature version: %u, firmware version: 0x%08x\n",
 		   fw_info.feature, fw_info.ver);
 
+	/* DMCUB */
+	query_fw.fw_type = AMDGPU_INFO_FW_DMCUB;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "DMCUB feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
 
 	seq_printf(m, "VBIOS version: %s\n", ctx->vbios_version);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index f205f56e3358..b03b1eb7ba04 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -37,6 +37,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/nospec.h>
+#include <linux/pm_runtime.h>
 #include "hwmgr.h"
 #define WIDTH_4K 3840
 
@@ -158,6 +159,14 @@ static ssize_t amdgpu_get_dpm_state(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	enum amd_pm_state_type pm;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		if (adev->smu.ppt_funcs->get_current_power_state)
@@ -170,6 +179,9 @@ static ssize_t amdgpu_get_dpm_state(struct device *dev,
 		pm = adev->pm.dpm.user_state;
 	}
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE, "%s\n",
 			(pm == POWER_STATE_TYPE_BATTERY) ? "battery" :
 			(pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance");
@@ -183,6 +195,10 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	enum amd_pm_state_type  state;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
 
 	if (strncmp("battery", buf, strlen("battery")) == 0)
 		state = POWER_STATE_TYPE_BATTERY;
@@ -190,10 +206,12 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev,
 		state = POWER_STATE_TYPE_BALANCED;
 	else if (strncmp("performance", buf, strlen("performance")) == 0)
 		state = POWER_STATE_TYPE_PERFORMANCE;
-	else {
-		count = -EINVAL;
-		goto fail;
-	}
+	else
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		mutex_lock(&adev->pm.mutex);
@@ -206,12 +224,11 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev,
 		adev->pm.dpm.user_state = state;
 		mutex_unlock(&adev->pm.mutex);
 
-		/* Can't set dpm state when the card is off */
-		if (!(adev->flags & AMD_IS_PX) ||
-		    (ddev->switch_power_state == DRM_SWITCH_POWER_ON))
-			amdgpu_pm_compute_clocks(adev);
+		amdgpu_pm_compute_clocks(adev);
 	}
-fail:
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return count;
 }
 
@@ -282,13 +299,14 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	enum amd_dpm_forced_level level = 0xff;
+	int ret;
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return 0;
 
-	if ((adev->flags & AMD_IS_PX) &&
-	    (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return snprintf(buf, PAGE_SIZE, "off\n");
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
 		level = smu_get_performance_level(&adev->smu);
@@ -297,6 +315,9 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev,
 	else
 		level = adev->pm.dpm.forced_level;
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE, "%s\n",
 			(level == AMD_DPM_FORCED_LEVEL_AUTO) ? "auto" :
 			(level == AMD_DPM_FORCED_LEVEL_LOW) ? "low" :
@@ -320,9 +341,7 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	enum amd_dpm_forced_level current_level = 0xff;
 	int ret = 0;
 
-	/* Can't force performance level when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return -EINVAL;
 
 	if (strncmp("low", buf, strlen("low")) == 0) {
@@ -344,30 +363,23 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	} else if (strncmp("profile_peak", buf, strlen("profile_peak")) == 0) {
 		level = AMD_DPM_FORCED_LEVEL_PROFILE_PEAK;
 	}  else {
-		count = -EINVAL;
-		goto fail;
+		return -EINVAL;
 	}
 
-	/* handle sriov case here */
-	if (amdgpu_sriov_vf(adev)) {
-		if (amdgim_is_hwperf(adev) &&
-		    adev->virt.ops->force_dpm_level) {
-			mutex_lock(&adev->pm.mutex);
-			adev->virt.ops->force_dpm_level(adev, level);
-			mutex_unlock(&adev->pm.mutex);
-			return count;
-		} else {
-			return -EINVAL;
-		}
-	}
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
 		current_level = smu_get_performance_level(&adev->smu);
 	else if (adev->powerplay.pp_funcs->get_performance_level)
 		current_level = amdgpu_dpm_get_performance_level(adev);
 
-	if (current_level == level)
+	if (current_level == level) {
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 		return count;
+	}
 
 	/* profile_exit setting is valid only when current mode is in profile mode */
 	if (!(current_level & (AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
@@ -376,29 +388,40 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	    AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)) &&
 	    (level == AMD_DPM_FORCED_LEVEL_PROFILE_EXIT)) {
 		pr_err("Currently not in any profile mode!\n");
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 		return -EINVAL;
 	}
 
 	if (is_support_sw_smu(adev)) {
 		ret = smu_force_performance_level(&adev->smu, level);
-		if (ret)
-			count = -EINVAL;
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
+			return -EINVAL;
+		}
 	} else if (adev->powerplay.pp_funcs->force_performance_level) {
 		mutex_lock(&adev->pm.mutex);
 		if (adev->pm.dpm.thermal_active) {
-			count = -EINVAL;
 			mutex_unlock(&adev->pm.mutex);
-			goto fail;
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
+			return -EINVAL;
 		}
 		ret = amdgpu_dpm_force_performance_level(adev, level);
-		if (ret)
-			count = -EINVAL;
-		else
+		if (ret) {
+			mutex_unlock(&adev->pm.mutex);
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
+			return -EINVAL;
+		} else {
 			adev->pm.dpm.forced_level = level;
+		}
 		mutex_unlock(&adev->pm.mutex);
 	}
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
-fail:
 	return count;
 }
 
@@ -411,6 +434,10 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev,
 	struct pp_states_info data;
 	int i, buf_len, ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		ret = smu_get_power_num_states(&adev->smu, &data);
 		if (ret)
@@ -418,6 +445,9 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev,
 	} else if (adev->powerplay.pp_funcs->get_pp_num_states)
 		amdgpu_dpm_get_pp_num_states(adev, &data);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	buf_len = snprintf(buf, PAGE_SIZE, "states: %d\n", data.nums);
 	for (i = 0; i < data.nums; i++)
 		buf_len += snprintf(buf + buf_len, PAGE_SIZE, "%d %s\n", i,
@@ -440,6 +470,13 @@ static ssize_t amdgpu_get_pp_cur_state(struct device *dev,
 	enum amd_pm_state_type pm = 0;
 	int i = 0, ret = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		pm = smu_get_current_power_state(smu);
 		ret = smu_get_power_num_states(smu, &data);
@@ -451,6 +488,9 @@ static ssize_t amdgpu_get_pp_cur_state(struct device *dev,
 		amdgpu_dpm_get_pp_num_states(adev, &data);
 	}
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	for (i = 0; i < data.nums; i++) {
 		if (pm == data.states[i])
 			break;
@@ -469,6 +509,9 @@ static ssize_t amdgpu_get_pp_force_state(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
 	if (adev->pp_force_state_enabled)
 		return amdgpu_get_pp_cur_state(dev, attr, buf);
 	else
@@ -486,6 +529,9 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 	unsigned long idx;
 	int ret;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
 	if (strlen(buf) == 1)
 		adev->pp_force_state_enabled = false;
 	else if (is_support_sw_smu(adev))
@@ -495,14 +541,18 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 		struct pp_states_info data;
 
 		ret = kstrtoul(buf, 0, &idx);
-		if (ret || idx >= ARRAY_SIZE(data.states)) {
-			count = -EINVAL;
-			goto fail;
-		}
+		if (ret || idx >= ARRAY_SIZE(data.states))
+			return -EINVAL;
+
 		idx = array_index_nospec(idx, ARRAY_SIZE(data.states));
 
 		amdgpu_dpm_get_pp_num_states(adev, &data);
 		state = data.states[idx];
+
+		ret = pm_runtime_get_sync(ddev->dev);
+		if (ret < 0)
+			return ret;
+
 		/* only set user selected power states */
 		if (state != POWER_STATE_TYPE_INTERNAL_BOOT &&
 		    state != POWER_STATE_TYPE_DEFAULT) {
@@ -510,8 +560,10 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 					AMD_PP_TASK_ENABLE_USER_STATE, &state);
 			adev->pp_force_state_enabled = true;
 		}
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 	}
-fail:
+
 	return count;
 }
 
@@ -533,17 +585,32 @@ static ssize_t amdgpu_get_pp_table(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	char *table = NULL;
-	int size;
+	int size, ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		size = smu_sys_get_pp_table(&adev->smu, (void **)&table);
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 		if (size < 0)
 			return size;
-	}
-	else if (adev->powerplay.pp_funcs->get_pp_table)
+	} else if (adev->powerplay.pp_funcs->get_pp_table) {
 		size = amdgpu_dpm_get_pp_table(adev, &table);
-	else
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
+		if (size < 0)
+			return size;
+	} else {
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 		return 0;
+	}
 
 	if (size >= PAGE_SIZE)
 		size = PAGE_SIZE - 1;
@@ -562,13 +629,26 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		ret = smu_sys_set_pp_table(&adev->smu, (void *)buf, count);
-		if (ret)
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
 			return ret;
+		}
 	} else if (adev->powerplay.pp_funcs->set_pp_table)
 		amdgpu_dpm_set_pp_table(adev, buf, count);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return count;
 }
 
@@ -654,6 +734,9 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 	const char delimiter[3] = {' ', '\n', '\0'};
 	uint32_t type;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	if (count > 127)
 		return -EINVAL;
 
@@ -689,18 +772,28 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 			tmp_str++;
 	}
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		ret = smu_od_edit_dpm_table(&adev->smu, type,
 					    parameter, parameter_size);
 
-		if (ret)
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
 			return -EINVAL;
+		}
 	} else {
 		if (adev->powerplay.pp_funcs->odn_edit_dpm_table) {
 			ret = amdgpu_dpm_odn_edit_dpm_table(adev, type,
 						parameter, parameter_size);
-			if (ret)
+			if (ret) {
+				pm_runtime_mark_last_busy(ddev->dev);
+				pm_runtime_put_autosuspend(ddev->dev);
 				return -EINVAL;
+			}
 		}
 
 		if (type == PP_OD_COMMIT_DPM_TABLE) {
@@ -708,12 +801,18 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 				amdgpu_dpm_dispatch_task(adev,
 						AMD_PP_TASK_READJUST_POWER_STATE,
 						NULL);
+				pm_runtime_mark_last_busy(ddev->dev);
+				pm_runtime_put_autosuspend(ddev->dev);
 				return count;
 			} else {
+				pm_runtime_mark_last_busy(ddev->dev);
+				pm_runtime_put_autosuspend(ddev->dev);
 				return -EINVAL;
 			}
 		}
 	}
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	return count;
 }
@@ -724,24 +823,33 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
-	uint32_t size = 0;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		size = smu_print_clk_levels(&adev->smu, SMU_OD_SCLK, buf);
 		size += smu_print_clk_levels(&adev->smu, SMU_OD_MCLK, buf+size);
 		size += smu_print_clk_levels(&adev->smu, SMU_OD_VDDC_CURVE, buf+size);
 		size += smu_print_clk_levels(&adev->smu, SMU_OD_RANGE, buf+size);
-		return size;
 	} else if (adev->powerplay.pp_funcs->print_clock_levels) {
 		size = amdgpu_dpm_print_clock_levels(adev, OD_SCLK, buf);
 		size += amdgpu_dpm_print_clock_levels(adev, OD_MCLK, buf+size);
 		size += amdgpu_dpm_print_clock_levels(adev, OD_VDDC_CURVE, buf+size);
 		size += amdgpu_dpm_print_clock_levels(adev, OD_RANGE, buf+size);
-		return size;
 	} else {
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
 	}
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
+	return size;
 }
 
 /**
@@ -770,21 +878,36 @@ static ssize_t amdgpu_set_pp_feature_status(struct device *dev,
 	uint64_t featuremask;
 	int ret;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	ret = kstrtou64(buf, 0, &featuremask);
 	if (ret)
 		return -EINVAL;
 
 	pr_debug("featuremask = 0x%llx\n", featuremask);
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		ret = smu_sys_set_pp_feature_mask(&adev->smu, featuremask);
-		if (ret)
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
 			return -EINVAL;
+		}
 	} else if (adev->powerplay.pp_funcs->set_ppfeature_status) {
 		ret = amdgpu_dpm_set_ppfeature_status(adev, featuremask);
-		if (ret)
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
 			return -EINVAL;
+		}
 	}
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	return count;
 }
@@ -795,13 +918,27 @@ static ssize_t amdgpu_get_pp_feature_status(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
 
-	if (is_support_sw_smu(adev)) {
-		return smu_sys_get_pp_feature_mask(&adev->smu, buf);
-	} else if (adev->powerplay.pp_funcs->get_ppfeature_status)
-		return amdgpu_dpm_get_ppfeature_status(adev, buf);
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
+	if (is_support_sw_smu(adev))
+		size = smu_sys_get_pp_feature_mask(&adev->smu, buf);
+	else if (adev->powerplay.pp_funcs->get_ppfeature_status)
+		size = amdgpu_dpm_get_ppfeature_status(adev, buf);
+	else
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
-	return snprintf(buf, PAGE_SIZE, "\n");
+	return size;
 }
 
 /**
@@ -840,17 +977,27 @@ static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
 
-	if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev) &&
-	    adev->virt.ops->get_pp_clk)
-		return adev->virt.ops->get_pp_clk(adev, PP_SCLK, buf);
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_SCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_SCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_SCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_SCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 /*
@@ -899,18 +1046,25 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
-	if (amdgpu_sriov_vf(adev))
-		return 0;
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_SCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (ret)
 		return -EINVAL;
 
@@ -923,17 +1077,27 @@ static ssize_t amdgpu_get_pp_dpm_mclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
 
-	if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev) &&
-	    adev->virt.ops->get_pp_clk)
-		return adev->virt.ops->get_pp_clk(adev, PP_MCLK, buf);
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_MCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_MCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_MCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_MCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
@@ -943,21 +1107,28 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
-	int ret;
 	uint32_t mask = 0;
+	int ret;
 
-	if (amdgpu_sriov_vf(adev))
-		return 0;
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+			return -EINVAL;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_MCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (ret)
 		return -EINVAL;
 
@@ -970,13 +1141,27 @@ static ssize_t amdgpu_get_pp_dpm_socclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_SOCCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_SOCCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_SOCCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_SOCCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_socclk(struct device *dev,
@@ -989,14 +1174,26 @@ static ssize_t amdgpu_set_pp_dpm_socclk(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_SOCCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_SOCCLK, mask);
+	else
+		ret = 0;
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1010,13 +1207,27 @@ static ssize_t amdgpu_get_pp_dpm_fclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_FCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_FCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_FCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_FCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_fclk(struct device *dev,
@@ -1029,14 +1240,26 @@ static ssize_t amdgpu_set_pp_dpm_fclk(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_FCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_FCLK, mask);
+	else
+		ret = 0;
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1050,13 +1273,27 @@ static ssize_t amdgpu_get_pp_dpm_dcefclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_DCEFCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_DCEFCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_DCEFCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_DCEFCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_dcefclk(struct device *dev,
@@ -1069,14 +1306,26 @@ static ssize_t amdgpu_set_pp_dpm_dcefclk(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_DCEFCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_DCEFCLK, mask);
+	else
+		ret = 0;
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1090,13 +1339,27 @@ static ssize_t amdgpu_get_pp_dpm_pcie(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_PCIE, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_PCIE, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_PCIE, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_PCIE, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
@@ -1109,14 +1372,26 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_PCIE, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
+	else
+		ret = 0;
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1131,12 +1406,23 @@ static ssize_t amdgpu_get_pp_sclk_od(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	uint32_t value = 0;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
 		value = smu_get_od_percentage(&(adev->smu), SMU_OD_SCLK);
 	else if (adev->powerplay.pp_funcs->get_sclk_od)
 		value = amdgpu_dpm_get_sclk_od(adev);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE, "%d\n", value);
 }
 
@@ -1150,12 +1436,17 @@ static ssize_t amdgpu_set_pp_sclk_od(struct device *dev,
 	int ret;
 	long int value;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	ret = kstrtol(buf, 0, &value);
 
-	if (ret) {
-		count = -EINVAL;
-		goto fail;
-	}
+	if (ret)
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		value = smu_set_od_percentage(&(adev->smu), SMU_OD_SCLK, (uint32_t)value);
@@ -1171,7 +1462,9 @@ static ssize_t amdgpu_set_pp_sclk_od(struct device *dev,
 		}
 	}
 
-fail:
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return count;
 }
 
@@ -1182,12 +1475,23 @@ static ssize_t amdgpu_get_pp_mclk_od(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	uint32_t value = 0;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
 		value = smu_get_od_percentage(&(adev->smu), SMU_OD_MCLK);
 	else if (adev->powerplay.pp_funcs->get_mclk_od)
 		value = amdgpu_dpm_get_mclk_od(adev);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE, "%d\n", value);
 }
 
@@ -1201,12 +1505,17 @@ static ssize_t amdgpu_set_pp_mclk_od(struct device *dev,
 	int ret;
 	long int value;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	ret = kstrtol(buf, 0, &value);
 
-	if (ret) {
-		count = -EINVAL;
-		goto fail;
-	}
+	if (ret)
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		value = smu_set_od_percentage(&(adev->smu), SMU_OD_MCLK, (uint32_t)value);
@@ -1222,7 +1531,9 @@ static ssize_t amdgpu_set_pp_mclk_od(struct device *dev,
 		}
 	}
 
-fail:
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return count;
 }
 
@@ -1252,13 +1563,27 @@ static ssize_t amdgpu_get_pp_power_profile_mode(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_get_power_profile_mode(&adev->smu, buf);
+		size = smu_get_power_profile_mode(&adev->smu, buf);
 	else if (adev->powerplay.pp_funcs->get_power_profile_mode)
-		return amdgpu_dpm_get_power_profile_mode(adev, buf);
+		size = amdgpu_dpm_get_power_profile_mode(adev, buf);
+	else
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
-	return snprintf(buf, PAGE_SIZE, "\n");
+	return size;
 }
 
 
@@ -1283,7 +1608,10 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 	tmp[1] = '\0';
 	ret = kstrtol(tmp, 0, &profile_mode);
 	if (ret)
-		goto fail;
+		return -EINVAL;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
 
 	if (profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) {
 		if (count < 2 || count > 127)
@@ -1295,23 +1623,30 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 		while (tmp_str[0]) {
 			sub_str = strsep(&tmp_str, delimiter);
 			ret = kstrtol(sub_str, 0, &parameter[parameter_size]);
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
+			if (ret)
+				return -EINVAL;
 			parameter_size++;
 			while (isspace(*tmp_str))
 				tmp_str++;
 		}
 	}
 	parameter[parameter_size] = profile_mode;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_set_power_profile_mode(&adev->smu, parameter, parameter_size, true);
 	else if (adev->powerplay.pp_funcs->set_power_profile_mode)
 		ret = amdgpu_dpm_set_power_profile_mode(adev, parameter, parameter_size);
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (!ret)
 		return count;
-fail:
+
 	return -EINVAL;
 }
 
@@ -1331,10 +1666,20 @@ static ssize_t amdgpu_get_busy_percent(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int r, value, size = sizeof(value);
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	r = pm_runtime_get_sync(ddev->dev);
+	if (r < 0)
+		return r;
+
 	/* read the IP busy sensor */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_LOAD,
 				   (void *)&value, &size);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1357,10 +1702,20 @@ static ssize_t amdgpu_get_memory_busy_percent(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int r, value, size = sizeof(value);
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	r = pm_runtime_get_sync(ddev->dev);
+	if (r < 0)
+		return r;
+
 	/* read the IP busy sensor */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MEM_LOAD,
 				   (void *)&value, &size);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1386,8 +1741,20 @@ static ssize_t amdgpu_get_pcie_bw(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	uint64_t count0, count1;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	amdgpu_asic_get_pcie_usage(adev, &count0, &count1);
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE,	"%llu %llu %i\n",
 			count0, count1, pcie_get_mps(adev->pdev));
 }
@@ -1409,6 +1776,9 @@ static ssize_t amdgpu_get_unique_id(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
 	if (adev->unique_id)
 		return snprintf(buf, PAGE_SIZE, "%016llx\n", adev->unique_id);
 
@@ -1472,42 +1842,43 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 				      char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	int channel = to_sensor_dev_attr(attr)->index;
 	int r, temp = 0, size = sizeof(temp);
 
-	/* Can't get temperature when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
-
 	if (channel >= PP_TEMP_MAX)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	switch (channel) {
 	case PP_TEMP_JUNCTION:
 		/* get current junction temperature */
 		r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_HOTSPOT_TEMP,
 					   (void *)&temp, &size);
-		if (r)
-			return r;
 		break;
 	case PP_TEMP_EDGE:
 		/* get current edge temperature */
 		r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_EDGE_TEMP,
 					   (void *)&temp, &size);
-		if (r)
-			return r;
 		break;
 	case PP_TEMP_MEM:
 		/* get current memory temperature */
 		r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MEM_TEMP,
 					   (void *)&temp, &size);
-		if (r)
-			return r;
+		break;
+	default:
+		r = -EINVAL;
 		break;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (r)
+		return r;
+
 	return snprintf(buf, PAGE_SIZE, "%d\n", temp);
 }
 
@@ -1603,15 +1974,27 @@ static ssize_t amdgpu_hwmon_get_pwm1_enable(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	u32 pwm_mode = 0;
+	int ret;
+
+	ret = pm_runtime_get_sync(adev->ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	} else {
-		if (!adev->powerplay.pp_funcs->get_fan_control_mode)
+		if (!adev->powerplay.pp_funcs->get_fan_control_mode) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return sprintf(buf, "%i\n", pwm_mode);
 }
 
@@ -1621,27 +2004,32 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
 					    size_t count)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	int err;
+	int err, ret;
 	int value;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
-
 	err = kstrtoint(buf, 10, &value);
 	if (err)
 		return err;
 
+	ret = pm_runtime_get_sync(adev->ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		smu_set_fan_control_mode(&adev->smu, value);
 	} else {
-		if (!adev->powerplay.pp_funcs->set_fan_control_mode)
+		if (!adev->powerplay.pp_funcs->set_fan_control_mode) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 
 		amdgpu_dpm_set_fan_control_mode(adev, value);
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return count;
 }
 
@@ -1668,34 +2056,43 @@ static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev,
 	u32 value;
 	u32 pwm_mode;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
+
 	if (is_support_sw_smu(adev))
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	else
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
+
 	if (pwm_mode != AMD_FAN_CTRL_MANUAL) {
 		pr_info("manual fan speed control should be enabled first\n");
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 		return -EINVAL;
 	}
 
 	err = kstrtou32(buf, 10, &value);
-	if (err)
+	if (err) {
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 		return err;
+	}
 
 	value = (value * 100) / 255;
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_set_fan_speed_percent(&adev->smu, value);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->set_fan_speed_percent) {
+	else if (adev->powerplay.pp_funcs->set_fan_speed_percent)
 		err = amdgpu_dpm_set_fan_speed_percent(adev, value);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	return count;
 }
@@ -1708,20 +2105,22 @@ static ssize_t amdgpu_hwmon_get_pwm1(struct device *dev,
 	int err;
 	u32 speed = 0;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_get_fan_speed_percent(&adev->smu, &speed);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->get_fan_speed_percent) {
+	else if (adev->powerplay.pp_funcs->get_fan_speed_percent)
 		err = amdgpu_dpm_get_fan_speed_percent(adev, &speed);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	speed = (speed * 255) / 100;
 
@@ -1736,20 +2135,22 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev,
 	int err;
 	u32 speed = 0;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_get_fan_speed_rpm(&adev->smu, &speed);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) {
+	else if (adev->powerplay.pp_funcs->get_fan_speed_rpm)
 		err = amdgpu_dpm_get_fan_speed_rpm(adev, &speed);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	return sprintf(buf, "%i\n", speed);
 }
@@ -1763,8 +2164,16 @@ static ssize_t amdgpu_hwmon_get_fan1_min(struct device *dev,
 	u32 size = sizeof(min_rpm);
 	int r;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MIN_FAN_RPM,
 				   (void *)&min_rpm, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1780,8 +2189,16 @@ static ssize_t amdgpu_hwmon_get_fan1_max(struct device *dev,
 	u32 size = sizeof(max_rpm);
 	int r;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MAX_FAN_RPM,
 				   (void *)&max_rpm, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1796,20 +2213,22 @@ static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev,
 	int err;
 	u32 rpm = 0;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_get_fan_speed_rpm(&adev->smu, &rpm);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) {
+	else if (adev->powerplay.pp_funcs->get_fan_speed_rpm)
 		err = amdgpu_dpm_get_fan_speed_rpm(adev, &rpm);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	return sprintf(buf, "%i\n", rpm);
 }
@@ -1823,32 +2242,40 @@ static ssize_t amdgpu_hwmon_set_fan1_target(struct device *dev,
 	u32 value;
 	u32 pwm_mode;
 
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
+
 	if (is_support_sw_smu(adev))
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	else
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 
-	if (pwm_mode != AMD_FAN_CTRL_MANUAL)
+	if (pwm_mode != AMD_FAN_CTRL_MANUAL) {
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 		return -ENODATA;
-
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	}
 
 	err = kstrtou32(buf, 10, &value);
-	if (err)
+	if (err) {
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 		return err;
+	}
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_set_fan_speed_rpm(&adev->smu, value);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->set_fan_speed_rpm) {
+	else if (adev->powerplay.pp_funcs->set_fan_speed_rpm)
 		err = amdgpu_dpm_set_fan_speed_rpm(adev, value);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	return count;
 }
@@ -1859,15 +2286,27 @@ static ssize_t amdgpu_hwmon_get_fan1_enable(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	u32 pwm_mode = 0;
+	int ret;
+
+	ret = pm_runtime_get_sync(adev->ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	} else {
-		if (!adev->powerplay.pp_funcs->get_fan_control_mode)
+		if (!adev->powerplay.pp_funcs->get_fan_control_mode) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 	}
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return sprintf(buf, "%i\n", pwm_mode == AMD_FAN_CTRL_AUTO ? 0 : 1);
 }
 
@@ -1881,12 +2320,6 @@ static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
 	int value;
 	u32 pwm_mode;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
-
-
 	err = kstrtoint(buf, 10, &value);
 	if (err)
 		return err;
@@ -1898,14 +2331,24 @@ static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
 	else
 		return -EINVAL;
 
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
+
 	if (is_support_sw_smu(adev)) {
 		smu_set_fan_control_mode(&adev->smu, pwm_mode);
 	} else {
-		if (!adev->powerplay.pp_funcs->set_fan_control_mode)
+		if (!adev->powerplay.pp_funcs->set_fan_control_mode) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 		amdgpu_dpm_set_fan_control_mode(adev, pwm_mode);
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return count;
 }
 
@@ -1914,18 +2357,20 @@ static ssize_t amdgpu_hwmon_show_vddgfx(struct device *dev,
 					char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	u32 vddgfx;
 	int r, size = sizeof(vddgfx);
 
-	/* Can't get voltage when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the voltage */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDGFX,
 				   (void *)&vddgfx, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1944,7 +2389,6 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev,
 				       char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	u32 vddnb;
 	int r, size = sizeof(vddnb);
 
@@ -1952,14 +2396,17 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev,
 	if  (!(adev->flags & AMD_IS_APU))
 		return -EINVAL;
 
-	/* Can't get voltage when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the voltage */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDNB,
 				   (void *)&vddnb, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1978,19 +2425,21 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev,
 					   char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	u32 query = 0;
 	int r, size = sizeof(u32);
 	unsigned uw;
 
-	/* Can't get power when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the voltage */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_POWER,
 				   (void *)&query, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -2013,16 +2462,27 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	uint32_t limit = 0;
+	ssize_t size;
+	int r;
+
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	if (is_support_sw_smu(adev)) {
 		smu_get_power_limit(&adev->smu, &limit, true, true);
-		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
+		size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_power_limit) {
 		adev->powerplay.pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, true);
-		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
+		size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else {
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
 	}
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
@@ -2031,16 +2491,27 @@ static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	uint32_t limit = 0;
+	ssize_t size;
+	int r;
+
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	if (is_support_sw_smu(adev)) {
 		smu_get_power_limit(&adev->smu, &limit, false,  true);
-		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
+		size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_power_limit) {
 		adev->powerplay.pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, false);
-		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
+		size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else {
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
 	}
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	return size;
 }
 
 
@@ -2053,19 +2524,29 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
 	int err;
 	u32 value;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	err = kstrtou32(buf, 10, &value);
 	if (err)
 		return err;
 
 	value = value / 1000000; /* convert to Watt */
 
-	if (is_support_sw_smu(adev)) {
+
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
+
+	if (is_support_sw_smu(adev))
 		err = smu_set_power_limit(&adev->smu, value);
-	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->set_power_limit) {
+	else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->set_power_limit)
 		err = adev->powerplay.pp_funcs->set_power_limit(adev->powerplay.pp_handle, value);
-	} else {
+	else
 		err = -EINVAL;
-	}
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
 
 	if (err)
 		return err;
@@ -2078,18 +2559,20 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev,
 				      char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	uint32_t sclk;
 	int r, size = sizeof(sclk);
 
-	/* Can't get voltage when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the sclk */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GFX_SCLK,
 				   (void *)&sclk, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -2108,18 +2591,20 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev,
 				      char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	uint32_t mclk;
 	int r, size = sizeof(mclk);
 
-	/* Can't get voltage when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the sclk */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GFX_MCLK,
 				   (void *)&mclk, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -2299,6 +2784,23 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	umode_t effective_mode = attr->mode;
 
+	/* under multi-vf mode, the hwmon attributes are all not supported */
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	/* there is no fan under pp one vf mode */
+	if (amdgpu_sriov_is_pp_one_vf(adev) &&
+	    (attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
+	     attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr ||
+	     attr == &sensor_dev_attr_pwm1_max.dev_attr.attr ||
+	     attr == &sensor_dev_attr_pwm1_min.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_input.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_min.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_max.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_target.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_enable.dev_attr.attr))
+		return 0;
+
 	/* Skip fan attributes if fan is not present */
 	if (adev->pm.no_fan && (attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
 	    attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr ||
@@ -2666,17 +3168,12 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev)
 void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 {
 	int ret = 0;
-	if (is_support_sw_smu(adev)) {
-	    ret = smu_dpm_set_power_gate(&adev->smu, AMD_IP_BLOCK_TYPE_UVD, enable);
-	    if (ret)
-		DRM_ERROR("[SW SMU]: dpm enable uvd failed, state = %s, ret = %d. \n",
-			  enable ? "true" : "false", ret);
-	} else if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
-		/* enable/disable UVD */
-		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
-		mutex_unlock(&adev->pm.mutex);
-	}
+
+	ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
+	if (ret)
+		DRM_ERROR("Dpm %s uvd failed, ret = %d. \n",
+			  enable ? "enable" : "disable", ret);
+
 	/* enable/disable Low Memory PState for UVD (4k videos) */
 	if (adev->asic_type == CHIP_STONEY &&
 		adev->uvd.decode_image_width >= WIDTH_4K) {
@@ -2693,17 +3190,11 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable)
 {
 	int ret = 0;
-	if (is_support_sw_smu(adev)) {
-	    ret = smu_dpm_set_power_gate(&adev->smu, AMD_IP_BLOCK_TYPE_VCE, enable);
-	    if (ret)
-		DRM_ERROR("[SW SMU]: dpm enable vce failed, state = %s, ret = %d. \n",
-			  enable ? "true" : "false", ret);
-	} else if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
-		/* enable/disable VCE */
-		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
-		mutex_unlock(&adev->pm.mutex);
-	}
+
+	ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
+	if (ret)
+		DRM_ERROR("Dpm %s vce failed, ret = %d. \n",
+			  enable ? "enable" : "disable", ret);
 }
 
 void amdgpu_pm_print_power_states(struct amdgpu_device *adev)
@@ -2718,42 +3209,14 @@ void amdgpu_pm_print_power_states(struct amdgpu_device *adev)
 
 }
 
-int amdgpu_pm_virt_sysfs_init(struct amdgpu_device *adev)
+void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable)
 {
 	int ret = 0;
 
-	if (!(amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev)))
-		return ret;
-
-	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_sclk);
-	if (ret) {
-		DRM_ERROR("failed to create device file pp_dpm_sclk\n");
-		return ret;
-	}
-
-	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_mclk);
-	if (ret) {
-		DRM_ERROR("failed to create device file pp_dpm_mclk\n");
-		return ret;
-	}
-
-	ret = device_create_file(adev->dev, &dev_attr_power_dpm_force_performance_level);
-	if (ret) {
-		DRM_ERROR("failed to create device file for dpm state\n");
-		return ret;
-	}
-
-	return ret;
-}
-
-void amdgpu_pm_virt_sysfs_fini(struct amdgpu_device *adev)
-{
-	if (!(amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev)))
-		return;
-
-	device_remove_file(adev->dev, &dev_attr_power_dpm_force_performance_level);
-	device_remove_file(adev->dev, &dev_attr_pp_dpm_sclk);
-	device_remove_file(adev->dev, &dev_attr_pp_dpm_mclk);
+	ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_JPEG, !enable);
+	if (ret)
+		DRM_ERROR("Dpm %s jpeg failed, ret = %d. \n",
+			  enable ? "enable" : "disable", ret);
 }
 
 int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_version)
@@ -3163,8 +3626,12 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct drm_device *ddev = adev->ddev;
 	u32 flags = 0;
+	int r;
+
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
 
 	amdgpu_device_ip_get_clockgating_state(adev, &flags);
 	seq_printf(m, "Clock Gating Flags Mask: 0x%x\n", flags);
@@ -3173,23 +3640,28 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 
 	if (!adev->pm.dpm_enabled) {
 		seq_printf(m, "dpm not enabled\n");
+		pm_runtime_mark_last_busy(dev->dev);
+		pm_runtime_put_autosuspend(dev->dev);
 		return 0;
 	}
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
-		seq_printf(m, "PX asic powered off\n");
-	} else if (!is_support_sw_smu(adev) && adev->powerplay.pp_funcs->debugfs_print_current_performance_level) {
+
+	if (!is_support_sw_smu(adev) &&
+	    adev->powerplay.pp_funcs->debugfs_print_current_performance_level) {
 		mutex_lock(&adev->pm.mutex);
 		if (adev->powerplay.pp_funcs->debugfs_print_current_performance_level)
 			adev->powerplay.pp_funcs->debugfs_print_current_performance_level(adev, m);
 		else
 			seq_printf(m, "Debugfs support not implemented for this asic\n");
 		mutex_unlock(&adev->pm.mutex);
+		r = 0;
 	} else {
-		return amdgpu_debugfs_pm_info_pp(m, adev);
+		r = amdgpu_debugfs_pm_info_pp(m, adev);
 	}
 
-	return 0;
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
+	return r;
 }
 
 static const struct drm_info_list amdgpu_pm_info_list[] = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h
index ef31448ee8d8..3da1da277805 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h
@@ -41,5 +41,6 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev);
 void amdgpu_dpm_thermal_work_handler(struct work_struct *work);
 void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable);
 void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable);
+void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
index 0e6dba9f60f0..07914e34bc25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
@@ -74,9 +74,9 @@ static void amdgpu_perf_start(struct perf_event *event, int flags)
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
 		if (!(flags & PERF_EF_RELOAD))
-			pe->adev->df_funcs->pmc_start(pe->adev, hwc->conf, 1);
+			pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1);
 
-		pe->adev->df_funcs->pmc_start(pe->adev, hwc->conf, 0);
+		pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 0);
 		break;
 	default:
 		break;
@@ -101,13 +101,13 @@ static void amdgpu_perf_read(struct perf_event *event)
 
 		switch (pe->pmu_perf_type) {
 		case PERF_TYPE_AMDGPU_DF:
-			pe->adev->df_funcs->pmc_get_count(pe->adev, hwc->conf,
+			pe->adev->df.funcs->pmc_get_count(pe->adev, hwc->conf,
 							  &count);
 			break;
 		default:
 			count = 0;
 			break;
-		};
+		}
 	} while (local64_cmpxchg(&hwc->prev_count, prev, count) != prev);
 
 	local64_add(count - prev, &event->count);
@@ -126,11 +126,11 @@ static void amdgpu_perf_stop(struct perf_event *event, int flags)
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		pe->adev->df_funcs->pmc_stop(pe->adev, hwc->conf, 0);
+		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 0);
 		break;
 	default:
 		break;
-	};
+	}
 
 	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 	hwc->state |= PERF_HES_STOPPED;
@@ -156,11 +156,11 @@ static int amdgpu_perf_add(struct perf_event *event, int flags)
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		retval = pe->adev->df_funcs->pmc_start(pe->adev, hwc->conf, 1);
+		retval = pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1);
 		break;
 	default:
 		return 0;
-	};
+	}
 
 	if (retval)
 		return retval;
@@ -184,11 +184,11 @@ static void amdgpu_perf_del(struct perf_event *event, int flags)
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		pe->adev->df_funcs->pmc_stop(pe->adev, hwc->conf, 1);
+		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 1);
 		break;
 	default:
 		break;
-	};
+	}
 
 	perf_event_update_userpage(event);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index e1b8d8daeafc..3a1570dafe34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -158,7 +158,7 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	memcpy(psp->cmd_buf_mem, cmd, sizeof(struct psp_gfx_cmd_resp));
 
 	index = atomic_inc_return(&psp->fence_value);
-	ret = psp_cmd_submit(psp, psp->cmd_buf_mc_addr, fence_mc_addr, index);
+	ret = psp_ring_cmd_submit(psp, psp->cmd_buf_mc_addr, fence_mc_addr, index);
 	if (ret) {
 		atomic_dec(&psp->fence_value);
 		mutex_unlock(&psp->mutex);
@@ -191,9 +191,9 @@ psp_cmd_submit_buf(struct psp_context *psp,
 		if (ucode)
 			DRM_WARN("failed to load ucode id (%d) ",
 				  ucode->ucode_id);
-		DRM_DEBUG_DRIVER("psp command (0x%X) failed and response status is (0x%X)\n",
+		DRM_WARN("psp command (0x%X) failed and response status is (0x%X)\n",
 			 psp->cmd_buf_mem->cmd_id,
-			 psp->cmd_buf_mem->resp.status & GFX_CMD_STATUS_MASK);
+			 psp->cmd_buf_mem->resp.status);
 		if (!timeout) {
 			mutex_unlock(&psp->mutex);
 			return -EINVAL;
@@ -318,35 +318,17 @@ static int psp_tmr_load(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_asd_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-				 uint64_t asd_mc, uint64_t asd_mc_shared,
-				 uint32_t size, uint32_t shared_size)
+static void psp_prep_asd_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+				uint64_t asd_mc, uint32_t size)
 {
 	cmd->cmd_id = GFX_CMD_ID_LOAD_ASD;
 	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(asd_mc);
 	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(asd_mc);
 	cmd->cmd.cmd_load_ta.app_len = size;
 
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(asd_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(asd_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
-}
-
-static int psp_asd_init(struct psp_context *psp)
-{
-	int ret;
-
-	/*
-	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
-	 * physical) for shared ASD <-> Driver
-	 */
-	ret = amdgpu_bo_create_kernel(psp->adev, PSP_ASD_SHARED_MEM_SIZE,
-				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->asd_shared_bo,
-				      &psp->asd_shared_mc_addr,
-				      &psp->asd_shared_buf);
-
-	return ret;
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = 0;
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = 0;
+	cmd->cmd.cmd_load_ta.cmd_buf_len = 0;
 }
 
 static int psp_asd_load(struct psp_context *psp)
@@ -368,11 +350,49 @@ static int psp_asd_load(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->asd_start_addr, psp->asd_ucode_size);
 
-	psp_prep_asd_cmd_buf(cmd, psp->fw_pri_mc_addr, psp->asd_shared_mc_addr,
-			     psp->asd_ucode_size, PSP_ASD_SHARED_MEM_SIZE);
+	psp_prep_asd_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
+				  psp->asd_ucode_size);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd,
+				 psp->fence_buf_mc_addr);
+	if (!ret) {
+		psp->asd_context.asd_initialized = true;
+		psp->asd_context.session_id = cmd->resp.session_id;
+	}
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static void psp_prep_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+				       uint32_t session_id)
+{
+	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
+	cmd->cmd.cmd_unload_ta.session_id = session_id;
+}
+
+static int psp_asd_unload(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (!psp->asd_context.asd_initialized)
+		return 0;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_ta_unload_cmd_buf(cmd, psp->asd_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
+	if (!ret)
+		psp->asd_context.asd_initialized = false;
 
 	kfree(cmd);
 
@@ -407,18 +427,20 @@ int psp_reg_program(struct psp_context *psp, enum psp_reg_prog_id reg,
 	return ret;
 }
 
-static void psp_prep_xgmi_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					  uint64_t xgmi_ta_mc, uint64_t xgmi_mc_shared,
-					  uint32_t xgmi_ta_size, uint32_t shared_size)
+static void psp_prep_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+				     uint64_t ta_bin_mc,
+				     uint32_t ta_bin_size,
+				     uint64_t ta_shared_mc,
+				     uint32_t ta_shared_size)
 {
-        cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
-        cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(xgmi_ta_mc);
-        cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(xgmi_ta_mc);
-        cmd->cmd.cmd_load_ta.app_len = xgmi_ta_size;
+	cmd->cmd_id 				= GFX_CMD_ID_LOAD_TA;
+	cmd->cmd.cmd_load_ta.app_phy_addr_lo 	= lower_32_bits(ta_bin_mc);
+	cmd->cmd.cmd_load_ta.app_phy_addr_hi 	= upper_32_bits(ta_bin_mc);
+	cmd->cmd.cmd_load_ta.app_len 		= ta_bin_size;
 
-        cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(xgmi_mc_shared);
-        cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(xgmi_mc_shared);
-        cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(ta_shared_mc);
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(ta_shared_mc);
+	cmd->cmd.cmd_load_ta.cmd_buf_len 	 = ta_shared_size;
 }
 
 static int psp_xgmi_init_shared_buf(struct psp_context *psp)
@@ -438,6 +460,36 @@ static int psp_xgmi_init_shared_buf(struct psp_context *psp)
 	return ret;
 }
 
+static void psp_prep_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+				       uint32_t ta_cmd_id,
+				       uint32_t session_id)
+{
+	cmd->cmd_id 				= GFX_CMD_ID_INVOKE_CMD;
+	cmd->cmd.cmd_invoke_cmd.session_id 	= session_id;
+	cmd->cmd.cmd_invoke_cmd.ta_cmd_id 	= ta_cmd_id;
+}
+
+int psp_ta_invoke(struct psp_context *psp,
+		  uint32_t ta_cmd_id,
+		  uint32_t session_id)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_ta_invoke_cmd_buf(cmd, ta_cmd_id, session_id);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd,
+				 psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
 static int psp_xgmi_load(struct psp_context *psp)
 {
 	int ret;
@@ -446,8 +498,6 @@ static int psp_xgmi_load(struct psp_context *psp)
 	/*
 	 * TODO: bypass the loading in sriov for now
 	 */
-	if (amdgpu_sriov_vf(psp->adev))
-		return 0;
 
 	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!cmd)
@@ -456,9 +506,11 @@ static int psp_xgmi_load(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->ta_xgmi_start_addr, psp->ta_xgmi_ucode_size);
 
-	psp_prep_xgmi_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-				      psp->xgmi_context.xgmi_shared_mc_addr,
-				      psp->ta_xgmi_ucode_size, PSP_XGMI_SHARED_MEM_SIZE);
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_xgmi_ucode_size,
+				 psp->xgmi_context.xgmi_shared_mc_addr,
+				 PSP_XGMI_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
@@ -473,29 +525,25 @@ static int psp_xgmi_load(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_xgmi_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					    uint32_t xgmi_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
-	cmd->cmd.cmd_unload_ta.session_id = xgmi_session_id;
-}
-
 static int psp_xgmi_unload(struct psp_context *psp)
 {
 	int ret;
 	struct psp_gfx_cmd_resp *cmd;
+	struct amdgpu_device *adev = psp->adev;
+
+	/* XGMI TA unload currently is not supported on Arcturus */
+	if (adev->asic_type == CHIP_ARCTURUS)
+		return 0;
 
 	/*
 	 * TODO: bypass the unloading in sriov for now
 	 */
-	if (amdgpu_sriov_vf(psp->adev))
-		return 0;
 
 	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!cmd)
 		return -ENOMEM;
 
-	psp_prep_xgmi_ta_unload_cmd_buf(cmd, psp->xgmi_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->xgmi_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
@@ -505,40 +553,9 @@ static int psp_xgmi_unload(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_xgmi_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					    uint32_t ta_cmd_id,
-					    uint32_t xgmi_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
-	cmd->cmd.cmd_invoke_cmd.session_id = xgmi_session_id;
-	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
-	/* Note: cmd_invoke_cmd.buf is not used for now */
-}
-
 int psp_xgmi_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	/*
-	 * TODO: bypass the loading in sriov for now
-	*/
-	if (amdgpu_sriov_vf(psp->adev))
-		return 0;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_xgmi_ta_invoke_cmd_buf(cmd, ta_cmd_id,
-					psp->xgmi_context.session_id);
-
-	ret = psp_cmd_submit_buf(psp, NULL, cmd,
-				 psp->fence_buf_mc_addr);
-
-	kfree(cmd);
-
-        return ret;
+	return psp_ta_invoke(psp, ta_cmd_id, psp->xgmi_context.session_id);
 }
 
 static int psp_xgmi_terminate(struct psp_context *psp)
@@ -594,20 +611,6 @@ static int psp_xgmi_initialize(struct psp_context *psp)
 }
 
 // ras begin
-static void psp_prep_ras_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-		uint64_t ras_ta_mc, uint64_t ras_mc_shared,
-		uint32_t ras_ta_size, uint32_t shared_size)
-{
-	cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
-	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(ras_ta_mc);
-	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(ras_ta_mc);
-	cmd->cmd.cmd_load_ta.app_len = ras_ta_size;
-
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(ras_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(ras_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
-}
-
 static int psp_ras_init_shared_buf(struct psp_context *psp)
 {
 	int ret;
@@ -643,15 +646,17 @@ static int psp_ras_load(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->ta_ras_start_addr, psp->ta_ras_ucode_size);
 
-	psp_prep_ras_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-			psp->ras.ras_shared_mc_addr,
-			psp->ta_ras_ucode_size, PSP_RAS_SHARED_MEM_SIZE);
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_ras_ucode_size,
+				 psp->ras.ras_shared_mc_addr,
+				 PSP_RAS_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 			psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->ras.ras_initialized = 1;
+		psp->ras.ras_initialized = true;
 		psp->ras.session_id = cmd->resp.session_id;
 	}
 
@@ -660,13 +665,6 @@ static int psp_ras_load(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_ras_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-						uint32_t ras_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
-	cmd->cmd.cmd_unload_ta.session_id = ras_session_id;
-}
-
 static int psp_ras_unload(struct psp_context *psp)
 {
 	int ret;
@@ -682,7 +680,7 @@ static int psp_ras_unload(struct psp_context *psp)
 	if (!cmd)
 		return -ENOMEM;
 
-	psp_prep_ras_ta_unload_cmd_buf(cmd, psp->ras.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->ras.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 			psp->fence_buf_mc_addr);
@@ -692,40 +690,15 @@ static int psp_ras_unload(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_ras_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-		uint32_t ta_cmd_id,
-		uint32_t ras_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
-	cmd->cmd.cmd_invoke_cmd.session_id = ras_session_id;
-	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
-	/* Note: cmd_invoke_cmd.buf is not used for now */
-}
-
 int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
 	/*
 	 * TODO: bypass the loading in sriov for now
 	 */
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_ras_ta_invoke_cmd_buf(cmd, ta_cmd_id,
-			psp->ras.session_id);
-
-	ret = psp_cmd_submit_buf(psp, NULL, cmd,
-			psp->fence_buf_mc_addr);
-
-	kfree(cmd);
-
-	return ret;
+	return psp_ta_invoke(psp, ta_cmd_id, psp->ras.session_id);
 }
 
 int psp_ras_enable_features(struct psp_context *psp,
@@ -771,7 +744,7 @@ static int psp_ras_terminate(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	psp->ras.ras_initialized = 0;
+	psp->ras.ras_initialized = false;
 
 	/* free ras shared memory */
 	amdgpu_bo_free_kernel(&psp->ras.ras_shared_bo,
@@ -812,24 +785,6 @@ static int psp_ras_initialize(struct psp_context *psp)
 // ras end
 
 // HDCP start
-static void psp_prep_hdcp_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					  uint64_t hdcp_ta_mc,
-					  uint64_t hdcp_mc_shared,
-					  uint32_t hdcp_ta_size,
-					  uint32_t shared_size)
-{
-	cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
-	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(hdcp_ta_mc);
-	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(hdcp_ta_mc);
-	cmd->cmd.cmd_load_ta.app_len = hdcp_ta_size;
-
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo =
-		lower_32_bits(hdcp_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi =
-		upper_32_bits(hdcp_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
-}
-
 static int psp_hdcp_init_shared_buf(struct psp_context *psp)
 {
 	int ret;
@@ -866,15 +821,16 @@ static int psp_hdcp_load(struct psp_context *psp)
 	memcpy(psp->fw_pri_buf, psp->ta_hdcp_start_addr,
 	       psp->ta_hdcp_ucode_size);
 
-	psp_prep_hdcp_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-				      psp->hdcp_context.hdcp_shared_mc_addr,
-				      psp->ta_hdcp_ucode_size,
-				      PSP_HDCP_SHARED_MEM_SIZE);
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_hdcp_ucode_size,
+				 psp->hdcp_context.hdcp_shared_mc_addr,
+				 PSP_HDCP_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->hdcp_context.hdcp_initialized = 1;
+		psp->hdcp_context.hdcp_initialized = true;
 		psp->hdcp_context.session_id = cmd->resp.session_id;
 	}
 
@@ -910,12 +866,6 @@ static int psp_hdcp_initialize(struct psp_context *psp)
 
 	return 0;
 }
-static void psp_prep_hdcp_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					    uint32_t hdcp_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
-	cmd->cmd.cmd_unload_ta.session_id = hdcp_session_id;
-}
 
 static int psp_hdcp_unload(struct psp_context *psp)
 {
@@ -932,7 +882,7 @@ static int psp_hdcp_unload(struct psp_context *psp)
 	if (!cmd)
 		return -ENOMEM;
 
-	psp_prep_hdcp_ta_unload_cmd_buf(cmd, psp->hdcp_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->hdcp_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
@@ -941,39 +891,15 @@ static int psp_hdcp_unload(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_hdcp_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					    uint32_t ta_cmd_id,
-					    uint32_t hdcp_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
-	cmd->cmd.cmd_invoke_cmd.session_id = hdcp_session_id;
-	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
-	/* Note: cmd_invoke_cmd.buf is not used for now */
-}
-
 int psp_hdcp_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
 	/*
 	 * TODO: bypass the loading in sriov for now
 	 */
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_hdcp_ta_invoke_cmd_buf(cmd, ta_cmd_id,
-					psp->hdcp_context.session_id);
-
-	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
-
-	kfree(cmd);
-
-	return ret;
+	return psp_ta_invoke(psp, ta_cmd_id, psp->hdcp_context.session_id);
 }
 
 static int psp_hdcp_terminate(struct psp_context *psp)
@@ -993,7 +919,7 @@ static int psp_hdcp_terminate(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	psp->hdcp_context.hdcp_initialized = 0;
+	psp->hdcp_context.hdcp_initialized = false;
 
 	/* free hdcp shared memory */
 	amdgpu_bo_free_kernel(&psp->hdcp_context.hdcp_shared_bo,
@@ -1005,22 +931,6 @@ static int psp_hdcp_terminate(struct psp_context *psp)
 // HDCP end
 
 // DTM start
-static void psp_prep_dtm_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					 uint64_t dtm_ta_mc,
-					 uint64_t dtm_mc_shared,
-					 uint32_t dtm_ta_size,
-					 uint32_t shared_size)
-{
-	cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
-	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(dtm_ta_mc);
-	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(dtm_ta_mc);
-	cmd->cmd.cmd_load_ta.app_len = dtm_ta_size;
-
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(dtm_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(dtm_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
-}
-
 static int psp_dtm_init_shared_buf(struct psp_context *psp)
 {
 	int ret;
@@ -1056,15 +966,16 @@ static int psp_dtm_load(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->ta_dtm_start_addr, psp->ta_dtm_ucode_size);
 
-	psp_prep_dtm_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-				     psp->dtm_context.dtm_shared_mc_addr,
-				     psp->ta_dtm_ucode_size,
-				     PSP_DTM_SHARED_MEM_SIZE);
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_dtm_ucode_size,
+				 psp->dtm_context.dtm_shared_mc_addr,
+				 PSP_DTM_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->dtm_context.dtm_initialized = 1;
+		psp->dtm_context.dtm_initialized = true;
 		psp->dtm_context.session_id = cmd->resp.session_id;
 	}
 
@@ -1102,39 +1013,15 @@ static int psp_dtm_initialize(struct psp_context *psp)
 	return 0;
 }
 
-static void psp_prep_dtm_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					   uint32_t ta_cmd_id,
-					   uint32_t dtm_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
-	cmd->cmd.cmd_invoke_cmd.session_id = dtm_session_id;
-	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
-	/* Note: cmd_invoke_cmd.buf is not used for now */
-}
-
 int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
 	/*
 	 * TODO: bypass the loading in sriov for now
 	 */
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_dtm_ta_invoke_cmd_buf(cmd, ta_cmd_id,
-				       psp->dtm_context.session_id);
-
-	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
-
-	kfree(cmd);
-
-	return ret;
+	return psp_ta_invoke(psp, ta_cmd_id, psp->dtm_context.session_id);
 }
 
 static int psp_dtm_terminate(struct psp_context *psp)
@@ -1154,7 +1041,7 @@ static int psp_dtm_terminate(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	psp->dtm_context.dtm_initialized = 0;
+	psp->dtm_context.dtm_initialized = false;
 
 	/* free hdcp shared memory */
 	amdgpu_bo_free_kernel(&psp->dtm_context.dtm_shared_bo,
@@ -1211,45 +1098,6 @@ static int psp_hw_start(struct psp_context *psp)
 		return ret;
 	}
 
-	ret = psp_asd_init(psp);
-	if (ret) {
-		DRM_ERROR("PSP asd init failed!\n");
-		return ret;
-	}
-
-	ret = psp_asd_load(psp);
-	if (ret) {
-		DRM_ERROR("PSP load asd failed!\n");
-		return ret;
-	}
-
-	if (adev->gmc.xgmi.num_physical_nodes > 1) {
-		ret = psp_xgmi_initialize(psp);
-		/* Warning the XGMI seesion initialize failure
-		 * Instead of stop driver initialization
-		 */
-		if (ret)
-			dev_err(psp->adev->dev,
-				"XGMI: Failed to initialize XGMI session\n");
-	}
-
-	if (psp->adev->psp.ta_fw) {
-		ret = psp_ras_initialize(psp);
-		if (ret)
-			dev_err(psp->adev->dev,
-					"RAS: Failed to initialize RAS\n");
-
-		ret = psp_hdcp_initialize(psp);
-		if (ret)
-			dev_err(psp->adev->dev,
-				"HDCP: Failed to initialize HDCP\n");
-
-		ret = psp_dtm_initialize(psp);
-		if (ret)
-			dev_err(psp->adev->dev,
-				"DTM: Failed to initialize DTM\n");
-	}
-
 	return 0;
 }
 
@@ -1329,6 +1177,9 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode,
 	case AMDGPU_UCODE_ID_VCN:
 		*type = GFX_FW_TYPE_VCN;
 		break;
+	case AMDGPU_UCODE_ID_VCN1:
+		*type = GFX_FW_TYPE_VCN1;
+		break;
 	case AMDGPU_UCODE_ID_DMCU_ERAM:
 		*type = GFX_FW_TYPE_DMCU_ERAM;
 		break;
@@ -1341,6 +1192,9 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode,
 	case AMDGPU_UCODE_ID_VCN1_RAM:
 		*type = GFX_FW_TYPE_VCN1_RAM;
 		break;
+	case AMDGPU_UCODE_ID_DMCUB:
+		*type = GFX_FW_TYPE_DMUB;
+		break;
 	case AMDGPU_UCODE_ID_MAXIMUM:
 	default:
 		return -EINVAL;
@@ -1470,7 +1324,8 @@ out:
                     || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_G
 	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL
 	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM
-	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM))
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_SMC))
 			/*skip ucode loading in SRIOV VF */
 			continue;
 
@@ -1519,16 +1374,13 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	if (!psp->cmd)
 		return -ENOMEM;
 
-	/* this fw pri bo is not used under SRIOV */
-	if (!amdgpu_sriov_vf(psp->adev)) {
-		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-					      AMDGPU_GEM_DOMAIN_GTT,
-					      &psp->fw_pri_bo,
-					      &psp->fw_pri_mc_addr,
-					      &psp->fw_pri_buf);
-		if (ret)
-			goto failed;
-	}
+	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
+					AMDGPU_GEM_DOMAIN_GTT,
+					&psp->fw_pri_bo,
+					&psp->fw_pri_mc_addr,
+					&psp->fw_pri_buf);
+	if (ret)
+		goto failed;
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE,
 					AMDGPU_GEM_DOMAIN_VRAM,
@@ -1562,6 +1414,39 @@ skip_memalloc:
 	if (ret)
 		goto failed;
 
+	ret = psp_asd_load(psp);
+	if (ret) {
+		DRM_ERROR("PSP load asd failed!\n");
+		return ret;
+	}
+
+	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+		ret = psp_xgmi_initialize(psp);
+		/* Warning the XGMI seesion initialize failure
+		 * Instead of stop driver initialization
+		 */
+		if (ret)
+			dev_err(psp->adev->dev,
+				"XGMI: Failed to initialize XGMI session\n");
+	}
+
+	if (psp->adev->psp.ta_fw) {
+		ret = psp_ras_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+					"RAS: Failed to initialize RAS\n");
+
+		ret = psp_hdcp_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"HDCP: Failed to initialize HDCP\n");
+
+		ret = psp_dtm_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"DTM: Failed to initialize DTM\n");
+	}
+
 	return 0;
 
 failed:
@@ -1619,6 +1504,8 @@ static int psp_hw_fini(void *handle)
 		psp_hdcp_terminate(psp);
 	}
 
+	psp_asd_unload(psp);
+
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
 	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
@@ -1627,8 +1514,6 @@ static int psp_hw_fini(void *handle)
 			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
 	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
 			      &psp->fence_buf_mc_addr, &psp->fence_buf);
-	amdgpu_bo_free_kernel(&psp->asd_shared_bo, &psp->asd_shared_mc_addr,
-			      &psp->asd_shared_buf);
 	amdgpu_bo_free_kernel(&psp->cmd_buf_bo, &psp->cmd_buf_mc_addr,
 			      (void **)&psp->cmd_buf_mem);
 
@@ -1704,6 +1589,39 @@ static int psp_resume(void *handle)
 	if (ret)
 		goto failed;
 
+	ret = psp_asd_load(psp);
+	if (ret) {
+		DRM_ERROR("PSP load asd failed!\n");
+		goto failed;
+	}
+
+	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+		ret = psp_xgmi_initialize(psp);
+		/* Warning the XGMI seesion initialize failure
+		 * Instead of stop driver initialization
+		 */
+		if (ret)
+			dev_err(psp->adev->dev,
+				"XGMI: Failed to initialize XGMI session\n");
+	}
+
+	if (psp->adev->psp.ta_fw) {
+		ret = psp_ras_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+					"RAS: Failed to initialize RAS\n");
+
+		ret = psp_hdcp_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"HDCP: Failed to initialize HDCP\n");
+
+		ret = psp_dtm_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"DTM: Failed to initialize DTM\n");
+	}
+
 	mutex_unlock(&adev->firmware.mutex);
 
 	return 0;
@@ -1758,6 +1676,56 @@ int psp_update_vcn_sram(struct amdgpu_device *adev, int inst_idx,
 	return psp_execute_np_fw_load(&adev->psp, &ucode);
 }
 
+int psp_ring_cmd_submit(struct psp_context *psp,
+			uint64_t cmd_buf_mc_addr,
+			uint64_t fence_mc_addr,
+			int index)
+{
+	unsigned int psp_write_ptr_reg = 0;
+	struct psp_gfx_rb_frame *write_frame;
+	struct psp_ring *ring = &psp->km_ring;
+	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
+	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
+		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
+	struct amdgpu_device *adev = psp->adev;
+	uint32_t ring_size_dw = ring->ring_size / 4;
+	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
+
+	/* KM (GPCOM) prepare write pointer */
+	psp_write_ptr_reg = psp_ring_get_wptr(psp);
+
+	/* Update KM RB frame pointer to new frame */
+	/* write_frame ptr increments by size of rb_frame in bytes */
+	/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
+	if ((psp_write_ptr_reg % ring_size_dw) == 0)
+		write_frame = ring_buffer_start;
+	else
+		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
+	/* Check invalid write_frame ptr address */
+	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
+		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
+			  ring_buffer_start, ring_buffer_end, write_frame);
+		DRM_ERROR("write_frame is pointing to address out of bounds\n");
+		return -EINVAL;
+	}
+
+	/* Initialize KM RB frame */
+	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
+
+	/* Update KM RB frame */
+	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
+	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
+	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
+	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
+	write_frame->fence_value = index;
+	amdgpu_asic_flush_hdp(adev, NULL);
+
+	/* Update the write Pointer in DWORDs */
+	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
+	psp_ring_set_wptr(psp, psp_write_ptr_reg);
+	return 0;
+}
+
 static bool psp_check_fw_loading_status(struct amdgpu_device *adev,
 					enum AMDGPU_UCODE_ID ucode_type)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 09c5474ebcc3..3265487b859f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -32,7 +32,6 @@
 
 #define PSP_FENCE_BUFFER_SIZE	0x1000
 #define PSP_CMD_BUFFER_SIZE	0x1000
-#define PSP_ASD_SHARED_MEM_SIZE 0x4000
 #define PSP_XGMI_SHARED_MEM_SIZE 0x4000
 #define PSP_RAS_SHARED_MEM_SIZE 0x4000
 #define PSP_1_MEG		0x100000
@@ -94,9 +93,6 @@ struct psp_funcs
 			    enum psp_ring_type ring_type);
 	int (*ring_destroy)(struct psp_context *psp,
 			    enum psp_ring_type ring_type);
-	int (*cmd_submit)(struct psp_context *psp,
-			  uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-			  int index);
 	bool (*compare_sram_data)(struct psp_context *psp,
 				  struct amdgpu_firmware_info *ucode,
 				  enum AMDGPU_UCODE_ID ucode_type);
@@ -116,6 +112,8 @@ struct psp_funcs
 	int (*mem_training_init)(struct psp_context *psp);
 	void (*mem_training_fini)(struct psp_context *psp);
 	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);
 };
 
 #define AMDGPU_XGMI_MAX_CONNECTED_NODES		64
@@ -131,6 +129,11 @@ struct psp_xgmi_topology_info {
 	struct psp_xgmi_node_info	nodes[AMDGPU_XGMI_MAX_CONNECTED_NODES];
 };
 
+struct psp_asd_context {
+	bool			asd_initialized;
+	uint32_t		session_id;
+};
+
 struct psp_xgmi_context {
 	uint8_t				initialized;
 	uint32_t			session_id;
@@ -199,7 +202,6 @@ struct psp_memory_training_context {
 
 	/*vram offset of the p2c training data*/
 	u64 p2c_train_data_offset;
-	struct amdgpu_bo *p2c_bo;
 
 	/*vram offset of the c2p training data*/
 	u64 c2p_train_data_offset;
@@ -239,15 +241,12 @@ struct psp_context
 	struct amdgpu_bo		*tmr_bo;
 	uint64_t			tmr_mc_addr;
 
-	/* asd firmware and buffer */
+	/* asd firmware */
 	const struct firmware		*asd_fw;
 	uint32_t			asd_fw_version;
 	uint32_t			asd_feature_version;
 	uint32_t			asd_ucode_size;
 	uint8_t				*asd_start_addr;
-	struct amdgpu_bo		*asd_shared_bo;
-	uint64_t			asd_shared_mc_addr;
-	void				*asd_shared_buf;
 
 	/* fence buffer */
 	struct amdgpu_bo		*fence_buf_bo;
@@ -282,6 +281,7 @@ struct psp_context
 	uint32_t			ta_dtm_ucode_size;
 	uint8_t				*ta_dtm_start_addr;
 
+	struct psp_asd_context		asd_context;
 	struct psp_xgmi_context		xgmi_context;
 	struct psp_ras_context		ras;
 	struct psp_hdcp_context 	hdcp_context;
@@ -300,8 +300,6 @@ struct amdgpu_psp_funcs {
 #define psp_ring_create(psp, type) (psp)->funcs->ring_create((psp), (type))
 #define psp_ring_stop(psp, type) (psp)->funcs->ring_stop((psp), (type))
 #define psp_ring_destroy(psp, type) ((psp)->funcs->ring_destroy((psp), (type)))
-#define psp_cmd_submit(psp, cmd_mc, fence_mc, index) \
-		(psp)->funcs->cmd_submit((psp), (cmd_mc), (fence_mc), (index))
 #define psp_compare_sram_data(psp, ucode, type) \
 		(psp)->funcs->compare_sram_data((psp), (ucode), (type))
 #define psp_init_microcode(psp) \
@@ -346,6 +344,9 @@ struct amdgpu_psp_funcs {
 	((psp)->funcs->ras_cure_posion ? \
 	(psp)->funcs->ras_cure_posion(psp, (addr)) : -EINVAL)
 
+#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))
+
 extern const struct amd_ip_funcs psp_ip_funcs;
 
 extern const struct amdgpu_ip_block_version psp_v3_1_ip_block;
@@ -372,4 +373,8 @@ int psp_rlc_autoload_start(struct psp_context *psp);
 extern const struct amdgpu_ip_block_version psp_v11_0_ip_block;
 int psp_reg_program(struct psp_context *psp, enum psp_reg_prog_id reg,
 		uint32_t value);
+int psp_ring_cmd_submit(struct psp_context *psp,
+			uint64_t cmd_buf_mc_addr,
+			uint64_t fence_mc_addr,
+			int index);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 404483437bd3..766be7f18282 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -198,9 +198,6 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 	return 0;
 }
 
-static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
-		struct ras_common_if *head);
-
 /**
  * DOC: AMDGPU RAS debugfs control interface
  *
@@ -318,7 +315,7 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 	default:
 		ret = -EINVAL;
 		break;
-	};
+	}
 
 	if (ret)
 		return -EINVAL;
@@ -445,7 +442,7 @@ static struct ras_manager *amdgpu_ras_create_obj(struct amdgpu_device *adev,
 }
 
 /* return an obj equal to head, or the first when head is NULL */
-static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
+struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
 		struct ras_common_if *head)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -689,6 +686,7 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
 {
 	struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
 	struct ras_err_data err_data = {0, 0, 0, NULL};
+	int i;
 
 	if (!obj)
 		return -EINVAL;
@@ -703,6 +701,13 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
 		if (adev->umc.funcs->query_ras_error_address)
 			adev->umc.funcs->query_ras_error_address(adev, &err_data);
 		break;
+	case AMDGPU_RAS_BLOCK__SDMA:
+		if (adev->sdma.funcs->query_ras_error_count) {
+			for (i = 0; i < adev->sdma.num_instances; i++)
+				adev->sdma.funcs->query_ras_error_count(adev, i,
+									&err_data);
+		}
+		break;
 	case AMDGPU_RAS_BLOCK__GFX:
 		if (adev->gfx.funcs->query_ras_error_count)
 			adev->gfx.funcs->query_ras_error_count(adev, &err_data);
@@ -1314,6 +1319,7 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 	data = con->eh_data;
 	if (!data || data->count == 0) {
 		*bps = NULL;
+		ret = -EINVAL;
 		goto out;
 	}
 
@@ -1347,7 +1353,8 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 	struct amdgpu_ras *ras =
 		container_of(work, struct amdgpu_ras, recovery_work);
 
-	amdgpu_device_gpu_recover(ras->adev, 0);
+	if (amdgpu_device_should_recover_gpu(ras->adev))
+		amdgpu_device_gpu_recover(ras->adev, 0);
 	atomic_set(&ras->in_recovery, 0);
 }
 
@@ -1687,7 +1694,8 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev,
 	*supported = 0;
 
 	if (amdgpu_sriov_vf(adev) ||
-			adev->asic_type != CHIP_VEGA20)
+	    (adev->asic_type != CHIP_VEGA20 &&
+	     adev->asic_type != CHIP_ARCTURUS))
 		return;
 
 	if (adev->is_atom_fw &&
@@ -1872,7 +1880,7 @@ void amdgpu_ras_resume(struct amdgpu_device *adev)
 		 * See feature_enable_on_boot
 		 */
 		amdgpu_ras_disable_all_features(adev, 1);
-		amdgpu_ras_reset_gpu(adev, 0);
+		amdgpu_ras_reset_gpu(adev);
 	}
 }
 
@@ -1935,6 +1943,6 @@ void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
 	if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
 		DRM_WARN("RAS event of type ERREVENT_ATHUB_INTERRUPT detected!\n");
 
-		amdgpu_ras_reset_gpu(adev, false);
+		amdgpu_ras_reset_gpu(adev);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index f80fd3428c98..a5fe29a9373e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -494,8 +494,7 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 
 int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev);
 
-static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev,
-		bool is_baco)
+static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
@@ -611,6 +610,9 @@ int amdgpu_ras_interrupt_remove_handler(struct amdgpu_device *adev,
 int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev,
 		struct ras_dispatch_if *info);
 
+struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
+		struct ras_common_if *head);
+
 extern atomic_t amdgpu_ras_in_intr;
 
 static inline bool amdgpu_ras_intr_triggered(void)
@@ -618,6 +620,11 @@ static inline bool amdgpu_ras_intr_triggered(void)
 	return !!atomic_read(&amdgpu_ras_in_intr);
 }
 
+static inline void amdgpu_ras_intr_cleared(void)
+{
+	atomic_set(&amdgpu_ras_in_intr, 0);
+}
+
 void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 6010999d9020..a2ee30b16212 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -160,7 +160,7 @@ int amdgpu_sdma_process_ras_data_cb(struct amdgpu_device *adev,
 		struct amdgpu_iv_entry *entry)
 {
 	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
-	amdgpu_ras_reset_gpu(adev, 0);
+	amdgpu_ras_reset_gpu(adev);
 
 	return AMDGPU_RAS_SUCCESS;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index 761ff8be6314..485335267d78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -50,8 +50,18 @@ struct amdgpu_sdma_instance {
 	bool			burst_nop;
 };
 
+struct amdgpu_sdma_ras_funcs {
+	int (*ras_late_init)(struct amdgpu_device *adev,
+			void *ras_ih_info);
+	void (*ras_fini)(struct amdgpu_device *adev);
+	int (*query_ras_error_count)(struct amdgpu_device *adev,
+			uint32_t instance, void *ras_error_status);
+};
+
 struct amdgpu_sdma {
 	struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES];
+	struct drm_gpu_scheduler    *sdma_sched[AMDGPU_MAX_SDMA_INSTANCES];
+	uint32_t		    num_sdma_sched;
 	struct amdgpu_irq_src	trap_irq;
 	struct amdgpu_irq_src	illegal_inst_irq;
 	struct amdgpu_irq_src	ecc_irq;
@@ -59,6 +69,7 @@ struct amdgpu_sdma {
 	uint32_t                    srbm_soft_reset;
 	bool			has_page_queue;
 	struct ras_common_if	*ras_if;
+	const struct amdgpu_sdma_ras_funcs	*funcs;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index 95e5e93edd18..a09b6b9c27d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -129,7 +129,8 @@ static void amdgpu_sync_keep_later(struct dma_fence **keep,
  * Tries to add the fence to an existing hash entry. Returns true when an entry
  * was found, false otherwise.
  */
-static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f, bool explicit)
+static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f,
+				  bool explicit)
 {
 	struct amdgpu_sync_entry *e;
 
@@ -151,19 +152,18 @@ static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f,
  * amdgpu_sync_fence - remember to sync to this fence
  *
  * @sync: sync object to add fence to
- * @fence: fence to sync to
+ * @f: fence to sync to
+ * @explicit: if this is an explicit dependency
  *
+ * Add the fence to the sync object.
  */
-int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
-		      struct dma_fence *f, bool explicit)
+int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f,
+		      bool explicit)
 {
 	struct amdgpu_sync_entry *e;
 
 	if (!f)
 		return 0;
-	if (amdgpu_sync_same_dev(adev, f) &&
-	    amdgpu_sync_get_owner(f) == AMDGPU_FENCE_OWNER_VM)
-		amdgpu_sync_keep_later(&sync->last_vm_update, f);
 
 	if (amdgpu_sync_add_later(sync, f, explicit))
 		return 0;
@@ -180,6 +180,24 @@ int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
 }
 
 /**
+ * amdgpu_sync_vm_fence - remember to sync to this VM fence
+ *
+ * @adev: amdgpu device
+ * @sync: sync object to add fence to
+ * @fence: the VM fence to add
+ *
+ * Add the fence to the sync object and remember it as VM update.
+ */
+int amdgpu_sync_vm_fence(struct amdgpu_sync *sync, struct dma_fence *fence)
+{
+	if (!fence)
+		return 0;
+
+	amdgpu_sync_keep_later(&sync->last_vm_update, fence);
+	return amdgpu_sync_fence(sync, fence, false);
+}
+
+/**
  * amdgpu_sync_resv - sync to a reservation object
  *
  * @sync: sync object to add fences from reservation object to
@@ -204,7 +222,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 
 	/* always sync to the exclusive fence */
 	f = dma_resv_get_excl(resv);
-	r = amdgpu_sync_fence(adev, sync, f, false);
+	r = amdgpu_sync_fence(sync, f, false);
 
 	flist = dma_resv_get_list(resv);
 	if (!flist || r)
@@ -222,13 +240,11 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 			continue;
 
 		if (amdgpu_sync_same_dev(adev, f)) {
-			/* VM updates are only interesting
-			 * for other VM updates and moves.
+			/* VM updates only sync with moves but not with user
+			 * command submissions or KFD evictions fences
 			 */
-			if ((owner != AMDGPU_FENCE_OWNER_UNDEFINED) &&
-			    (fence_owner != AMDGPU_FENCE_OWNER_UNDEFINED) &&
-			    ((owner == AMDGPU_FENCE_OWNER_VM) !=
-			     (fence_owner == AMDGPU_FENCE_OWNER_VM)))
+			if (owner == AMDGPU_FENCE_OWNER_VM &&
+			    fence_owner != AMDGPU_FENCE_OWNER_UNDEFINED)
 				continue;
 
 			/* Ignore fence from the same owner and explicit one as
@@ -239,7 +255,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 				continue;
 		}
 
-		r = amdgpu_sync_fence(adev, sync, f, false);
+		r = amdgpu_sync_fence(sync, f, false);
 		if (r)
 			break;
 	}
@@ -340,7 +356,7 @@ int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone)
 	hash_for_each_safe(source->fences, i, tmp, e, node) {
 		f = e->fence;
 		if (!dma_fence_is_signaled(f)) {
-			r = amdgpu_sync_fence(NULL, clone, f, e->explicit);
+			r = amdgpu_sync_fence(clone, f, e->explicit);
 			if (r)
 				return r;
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
index b5f1778a2319..d62c2b81d92b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
@@ -40,8 +40,9 @@ struct amdgpu_sync {
 };
 
 void amdgpu_sync_create(struct amdgpu_sync *sync);
-int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
-		      struct dma_fence *f, bool explicit);
+int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f,
+		      bool explicit);
+int amdgpu_sync_vm_fence(struct amdgpu_sync *sync, struct dma_fence *fence);
 int amdgpu_sync_resv(struct amdgpu_device *adev,
 		     struct amdgpu_sync *sync,
 		     struct dma_resv *resv,
@@ -49,7 +50,8 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 		     bool explicit_sync);
 struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
 				     struct amdgpu_ring *ring);
-struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync, bool *explicit);
+struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync,
+					bool *explicit);
 int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone);
 int amdgpu_sync_wait(struct amdgpu_sync *sync, bool intr);
 void amdgpu_sync_free(struct amdgpu_sync *sync);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 2616e2eafdeb..dee446278417 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -41,6 +41,7 @@
 #include <linux/swap.h>
 #include <linux/swiotlb.h>
 #include <linux/dma-buf.h>
+#include <linux/sizes.h>
 
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
@@ -1522,11 +1523,8 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 	struct dma_fence *f;
 	int i;
 
-	/* Don't evict VM page tables while they are busy, otherwise we can't
-	 * cleanly handle page faults.
-	 */
 	if (bo->type == ttm_bo_type_kernel &&
-	    !dma_resv_test_signaled_rcu(bo->base.resv, true))
+	    !amdgpu_vm_evictable(ttm_to_amdgpu_bo(bo)))
 		return false;
 
 	/* If bo is a KFD BO, check if the bo belongs to the current process.
@@ -1717,12 +1715,17 @@ static int amdgpu_ttm_training_reserve_vram_fini(struct amdgpu_device *adev)
 	amdgpu_bo_free_kernel(&ctx->c2p_bo, NULL, NULL);
 	ctx->c2p_bo = NULL;
 
-	amdgpu_bo_free_kernel(&ctx->p2c_bo, NULL, NULL);
-	ctx->p2c_bo = NULL;
-
 	return 0;
 }
 
+static u64 amdgpu_ttm_training_get_c2p_offset(u64 vram_size)
+{
+       if ((vram_size & (SZ_1M - 1)) < (SZ_4K + 1) )
+               vram_size -= SZ_1M;
+
+       return ALIGN(vram_size, SZ_1M);
+}
+
 /**
  * amdgpu_ttm_training_reserve_vram_init - create bo vram reservation from memory training
  *
@@ -1741,7 +1744,7 @@ static int amdgpu_ttm_training_reserve_vram_init(struct amdgpu_device *adev)
 		return 0;
 	}
 
-	ctx->c2p_train_data_offset = adev->fw_vram_usage.mem_train_fb_loc;
+	ctx->c2p_train_data_offset = amdgpu_ttm_training_get_c2p_offset(adev->gmc.mc_vram_size);
 	ctx->p2c_train_data_offset = (adev->gmc.mc_vram_size - GDDR6_MEM_TRAINING_OFFSET);
 	ctx->train_data_size = GDDR6_MEM_TRAINING_DATA_SIZE_IN_BYTES;
 
@@ -1751,17 +1754,6 @@ static int amdgpu_ttm_training_reserve_vram_init(struct amdgpu_device *adev)
 		  ctx->c2p_train_data_offset);
 
 	ret = amdgpu_bo_create_kernel_at(adev,
-					 ctx->p2c_train_data_offset,
-					 ctx->train_data_size,
-					 AMDGPU_GEM_DOMAIN_VRAM,
-					 &ctx->p2c_bo,
-					 NULL);
-	if (ret) {
-		DRM_ERROR("alloc p2c_bo failed(%d)!\n", ret);
-		goto Err_out;
-	}
-
-	ret = amdgpu_bo_create_kernel_at(adev,
 					 ctx->c2p_train_data_offset,
 					 ctx->train_data_size,
 					 AMDGPU_GEM_DOMAIN_VRAM,
@@ -1769,15 +1761,12 @@ static int amdgpu_ttm_training_reserve_vram_init(struct amdgpu_device *adev)
 					 NULL);
 	if (ret) {
 		DRM_ERROR("alloc c2p_bo failed(%d)!\n", ret);
-		goto Err_out;
+		amdgpu_ttm_training_reserve_vram_fini(adev);
+		return ret;
 	}
 
 	ctx->init = PSP_MEM_TRAIN_RESERVE_SUCCESS;
 	return 0;
-
-Err_out:
-	amdgpu_ttm_training_reserve_vram_fini(adev);
-	return ret;
 }
 
 /**
@@ -1990,11 +1979,13 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 
 	if (enable) {
 		struct amdgpu_ring *ring;
-		struct drm_sched_rq *rq;
+		struct drm_gpu_scheduler *sched;
 
 		ring = adev->mman.buffer_funcs_ring;
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-		r = drm_sched_entity_init(&adev->mman.entity, &rq, 1, NULL);
+		sched = &ring->sched;
+		r = drm_sched_entity_init(&adev->mman.entity,
+				          DRM_SCHED_PRIORITY_KERNEL, &sched,
+					  1, NULL);
 		if (r) {
 			DRM_ERROR("Failed setting up TTM BO move entity (%d)\n",
 				  r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 833fc4b68940..9ef312428231 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -447,6 +447,7 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 	const struct common_firmware_header *header = NULL;
 	const struct gfx_firmware_header_v1_0 *cp_hdr = NULL;
 	const struct dmcu_firmware_header_v1_0 *dmcu_hdr = NULL;
+	const struct dmcub_firmware_header_v1_0 *dmcub_hdr = NULL;
 
 	if (NULL == ucode->fw)
 		return 0;
@@ -460,6 +461,7 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 	header = (const struct common_firmware_header *)ucode->fw->data;
 	cp_hdr = (const struct gfx_firmware_header_v1_0 *)ucode->fw->data;
 	dmcu_hdr = (const struct dmcu_firmware_header_v1_0 *)ucode->fw->data;
+	dmcub_hdr = (const struct dmcub_firmware_header_v1_0 *)ucode->fw->data;
 
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP ||
 	    (ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC1 &&
@@ -470,7 +472,8 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM &&
 	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM &&
 		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_ERAM &&
-		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_INTV)) {
+		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_INTV &&
+		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCUB)) {
 		ucode->ucode_size = le32_to_cpu(header->ucode_size_bytes);
 
 		memcpy(ucode->kaddr, (void *)((uint8_t *)ucode->fw->data +
@@ -506,6 +509,12 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 					      le32_to_cpu(header->ucode_array_offset_bytes) +
 					      le32_to_cpu(dmcu_hdr->intv_offset_bytes)),
 		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_DMCUB) {
+		ucode->ucode_size = le32_to_cpu(dmcub_hdr->inst_const_bytes);
+		memcpy(ucode->kaddr,
+		       (void *)((uint8_t *)ucode->fw->data +
+				le32_to_cpu(header->ucode_array_offset_bytes)),
+		       ucode->ucode_size);
 	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL) {
 		ucode->ucode_size = adev->gfx.rlc.save_restore_list_cntl_size_bytes;
 		memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_cntl,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 914acecda5cf..b0e656409c03 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -251,6 +251,13 @@ struct dmcu_firmware_header_v1_0 {
 	uint32_t intv_size_bytes;  /* size of interrupt vectors, in bytes */
 };
 
+/* version_major=1, version_minor=0 */
+struct dmcub_firmware_header_v1_0 {
+	struct common_firmware_header header;
+	uint32_t inst_const_bytes; /* size of instruction region, in bytes */
+	uint32_t bss_data_bytes; /* size of bss/data region, in bytes */
+};
+
 /* header is fixed size */
 union amdgpu_firmware_header {
 	struct common_firmware_header common;
@@ -268,6 +275,7 @@ union amdgpu_firmware_header {
 	struct sdma_firmware_header_v1_1 sdma_v1_1;
 	struct gpu_info_firmware_header_v1_0 gpu_info;
 	struct dmcu_firmware_header_v1_0 dmcu;
+	struct dmcub_firmware_header_v1_0 dmcub;
 	uint8_t raw[0x100];
 };
 
@@ -307,6 +315,7 @@ enum AMDGPU_UCODE_ID {
 	AMDGPU_UCODE_ID_DMCU_INTV,
 	AMDGPU_UCODE_ID_VCN0_RAM,
 	AMDGPU_UCODE_ID_VCN1_RAM,
+	AMDGPU_UCODE_ID_DMCUB,
 	AMDGPU_UCODE_ID_MAXIMUM,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index d4fb9cf27e21..f4d40855147b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -95,13 +95,6 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
 
-	/* When “Full RAS” is enabled, the per-IP interrupt sources should
-	 * be disabled and the driver should only look for the aggregated
-	 * interrupt via sync flood
-	 */
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
-		return AMDGPU_RAS_SUCCESS;
-
 	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
 	if (adev->umc.funcs &&
 	    adev->umc.funcs->query_ras_error_count)
@@ -113,6 +106,7 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 		err_data->err_addr =
 			kcalloc(adev->umc.max_ras_err_cnt_per_query,
 				sizeof(struct eeprom_table_record), GFP_KERNEL);
+
 		/* still call query_ras_error_address to clear error status
 		 * even NOMEM error is encountered
 		 */
@@ -132,7 +126,7 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 						err_data->err_addr_cnt))
 			DRM_WARN("Failed to add ras bad page!\n");
 
-		amdgpu_ras_reset_gpu(adev, 0);
+		amdgpu_ras_reset_gpu(adev);
 	}
 
 	kfree(err_data->err_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index 3283032a78e5..a615a1eb750b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -21,38 +21,6 @@
 #ifndef __AMDGPU_UMC_H__
 #define __AMDGPU_UMC_H__
 
-/* implement 64 bits REG operations via 32 bits interface */
-#define RREG64_UMC(reg)	(RREG32(reg) | \
-				((uint64_t)RREG32((reg) + 1) << 32))
-#define WREG64_UMC(reg, v)	\
-	do {	\
-		WREG32((reg), lower_32_bits(v));	\
-		WREG32((reg) + 1, upper_32_bits(v));	\
-	} while (0)
-
-/*
- * void (*func)(struct amdgpu_device *adev, struct ras_err_data *err_data,
- *				uint32_t umc_reg_offset, uint32_t channel_index)
- */
-#define amdgpu_umc_for_each_channel(func)	\
-	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;	\
-	uint32_t umc_inst, channel_inst, umc_reg_offset, channel_index;	\
-	for (umc_inst = 0; umc_inst < adev->umc.umc_inst_num; umc_inst++) {	\
-		/* enable the index mode to query eror count per channel */	\
-		adev->umc.funcs->enable_umc_index_mode(adev, umc_inst);	\
-		for (channel_inst = 0;	\
-			channel_inst < adev->umc.channel_inst_num;	\
-			channel_inst++) {	\
-			/* calc the register offset according to channel instance */	\
-			umc_reg_offset = adev->umc.channel_offs * channel_inst;	\
-			/* get channel index of interleaved memory */	\
-			channel_index = adev->umc.channel_idx_tbl[	\
-				umc_inst * adev->umc.channel_inst_num + channel_inst];	\
-			(func)(adev, err_data, umc_reg_offset, channel_index);	\
-		}	\
-	}	\
-	adev->umc.funcs->disable_umc_index_mode(adev);
-
 struct amdgpu_umc_funcs {
 	void (*err_cnt_init)(struct amdgpu_device *adev);
 	int (*ras_late_init)(struct amdgpu_device *adev);
@@ -60,9 +28,6 @@ struct amdgpu_umc_funcs {
 					void *ras_error_status);
 	void (*query_ras_error_address)(struct amdgpu_device *adev,
 					void *ras_error_status);
-	void (*enable_umc_index_mode)(struct amdgpu_device *adev,
-					uint32_t umc_instance);
-	void (*disable_umc_index_mode)(struct amdgpu_device *adev);
 	void (*init_registers)(struct amdgpu_device *adev);
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index e324bfe6c58f..a92f3b18e657 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -330,12 +330,13 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 int amdgpu_uvd_entity_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
+	struct drm_gpu_scheduler *sched;
 	int r;
 
 	ring = &adev->uvd.inst[0].ring;
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&adev->uvd.entity, &rq, 1, NULL);
+	sched = &ring->sched;
+	r = drm_sched_entity_init(&adev->uvd.entity, DRM_SCHED_PRIORITY_NORMAL,
+				  &sched, 1, NULL);
 	if (r) {
 		DRM_ERROR("Failed setting up UVD kernel entity.\n");
 		return r;
@@ -349,6 +350,7 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	unsigned size;
 	void *ptr;
 	int i, j;
+	bool in_ras_intr = amdgpu_ras_intr_triggered();
 
 	cancel_delayed_work_sync(&adev->uvd.idle_work);
 
@@ -376,13 +378,15 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 			return -ENOMEM;
 
 		/* re-write 0 since err_event_athub will corrupt VCPU buffer */
-		if (amdgpu_ras_intr_triggered()) {
-			DRM_WARN("UVD VCPU state may lost due to RAS ERREVENT_ATHUB_INTERRUPT\n");
+		if (in_ras_intr)
 			memset(adev->uvd.inst[j].saved_bo, 0, size);
-		} else {
+		else
 			memcpy_fromio(adev->uvd.inst[j].saved_bo, ptr, size);
-		}
 	}
+
+	if (in_ras_intr)
+		DRM_WARN("UVD VCPU state may lost due to RAS ERREVENT_ATHUB_INTERRUPT\n");
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 46b590af2fd2..ceb0dbf685f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -240,12 +240,13 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 int amdgpu_vce_entity_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
+	struct drm_gpu_scheduler *sched;
 	int r;
 
 	ring = &adev->vce.ring[0];
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL);
+	sched = &ring->sched;
+	r = drm_sched_entity_init(&adev->vce.entity, DRM_SCHED_PRIORITY_NORMAL,
+				  &sched, 1, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCE run queue.\n");
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 9d870444d7d6..f96464e2c157 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -28,19 +28,10 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 
-#include <drm/drm.h>
-
 #include "amdgpu.h"
 #include "amdgpu_pm.h"
 #include "amdgpu_vcn.h"
 #include "soc15d.h"
-#include "soc15_common.h"
-
-#include "vcn/vcn_1_0_offset.h"
-#include "vcn/vcn_1_0_sh_mask.h"
-
-/* 1 second timeout */
-#define VCN_IDLE_TIMEOUT	msecs_to_jiffies(1000)
 
 /* Firmware Names */
 #define FIRMWARE_RAVEN		"amdgpu/raven_vcn.bin"
@@ -84,6 +75,9 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		break;
 	case CHIP_ARCTURUS:
 		fw_name = FIRMWARE_ARCTURUS;
+		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
+		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
+			adev->vcn.indirect_sram = true;
 		break;
 	case CHIP_RENOIR:
 		fw_name = FIRMWARE_RENOIR;
@@ -174,15 +168,15 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 			dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r);
 			return r;
 		}
-	}
 
-	if (adev->vcn.indirect_sram) {
-		r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE,
-			    AMDGPU_GEM_DOMAIN_VRAM, &adev->vcn.dpg_sram_bo,
-			    &adev->vcn.dpg_sram_gpu_addr, &adev->vcn.dpg_sram_cpu_addr);
-		if (r) {
-			dev_err(adev->dev, "(%d) failed to allocate DPG bo\n", r);
-			return r;
+		if (adev->vcn.indirect_sram) {
+			r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE,
+					AMDGPU_GEM_DOMAIN_VRAM, &adev->vcn.inst[i].dpg_sram_bo,
+					&adev->vcn.inst[i].dpg_sram_gpu_addr, &adev->vcn.inst[i].dpg_sram_cpu_addr);
+			if (r) {
+				dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r);
+				return r;
+			}
 		}
 	}
 
@@ -195,15 +189,14 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 
 	cancel_delayed_work_sync(&adev->vcn.idle_work);
 
-	if (adev->vcn.indirect_sram) {
-		amdgpu_bo_free_kernel(&adev->vcn.dpg_sram_bo,
-				      &adev->vcn.dpg_sram_gpu_addr,
-				      (void **)&adev->vcn.dpg_sram_cpu_addr);
-	}
-
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
+		if (adev->vcn.indirect_sram) {
+			amdgpu_bo_free_kernel(&adev->vcn.inst[j].dpg_sram_bo,
+						  &adev->vcn.inst[j].dpg_sram_gpu_addr,
+						  (void **)&adev->vcn.inst[j].dpg_sram_cpu_addr);
+		}
 		kvfree(adev->vcn.inst[j].saved_bo);
 
 		amdgpu_bo_free_kernel(&adev->vcn.inst[j].vcpu_bo,
@@ -214,8 +207,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->vcn.inst[j].ring_enc[i]);
-
-		amdgpu_ring_fini(&adev->vcn.inst[j].ring_jpeg);
 	}
 
 	release_firmware(adev->vcn.fw);
@@ -296,6 +287,7 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
+
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
 			fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);
 		}
@@ -308,26 +300,17 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 			else
 				new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
 
-			if (amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_jpeg))
-				new_state.jpeg = VCN_DPG_STATE__PAUSE;
-			else
-				new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
-
-			adev->vcn.pause_dpg_mode(adev, &new_state);
+			adev->vcn.pause_dpg_mode(adev, j, &new_state);
 		}
 
-		fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_jpeg);
 		fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_dec);
 		fences += fence[j];
 	}
 
 	if (fences == 0) {
 		amdgpu_gfx_off_ctrl(adev, true);
-		if (adev->asic_type < CHIP_ARCTURUS && adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_uvd(adev, false);
-		else
-			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
-							       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+		       AMD_PG_STATE_GATE);
 	} else {
 		schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
 	}
@@ -340,11 +323,8 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 
 	if (set_clocks) {
 		amdgpu_gfx_off_ctrl(adev, false);
-		if (adev->asic_type < CHIP_ARCTURUS && adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_uvd(adev, true);
-		else
-			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
-							       AMD_PG_STATE_UNGATE);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+		       AMD_PG_STATE_UNGATE);
 	}
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
@@ -360,17 +340,10 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 		else
 			new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
 
-		if (amdgpu_fence_count_emitted(&adev->vcn.inst[ring->me].ring_jpeg))
-			new_state.jpeg = VCN_DPG_STATE__PAUSE;
-		else
-			new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
-
 		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
 			new_state.fw_based = VCN_DPG_STATE__PAUSE;
-		else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
-			new_state.jpeg = VCN_DPG_STATE__PAUSE;
 
-		adev->vcn.pause_dpg_mode(adev, &new_state);
+		adev->vcn.pause_dpg_mode(adev, ring->me, &new_state);
 	}
 }
 
@@ -520,9 +493,14 @@ static int amdgpu_vcn_dec_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 
 int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
+	struct amdgpu_device *adev = ring->adev;
 	struct dma_fence *fence;
 	long r;
 
+	/* temporarily disable ib test for sriov */
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	r = amdgpu_vcn_dec_get_create_msg(ring, 1, NULL);
 	if (r)
 		goto error;
@@ -678,10 +656,15 @@ err:
 
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
+	struct amdgpu_device *adev = ring->adev;
 	struct dma_fence *fence = NULL;
 	struct amdgpu_bo *bo = NULL;
 	long r;
 
+	/* temporarily disable ib test for sriov */
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
 				      AMDGPU_GEM_DOMAIN_VRAM,
 				      &bo, NULL, NULL);
@@ -708,108 +691,3 @@ error:
 	amdgpu_bo_unref(&bo);
 	return r;
 }
-
-int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t tmp = 0;
-	unsigned i;
-	int r;
-
-	WREG32(adev->vcn.inst[ring->me].external.jpeg_pitch, 0xCAFEDEAD);
-	r = amdgpu_ring_alloc(ring, 3);
-	if (r)
-		return r;
-
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.jpeg_pitch, 0));
-	amdgpu_ring_write(ring, 0xDEADBEEF);
-	amdgpu_ring_commit(ring);
-
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(adev->vcn.inst[ring->me].external.jpeg_pitch);
-		if (tmp == 0xDEADBEEF)
-			break;
-		udelay(1);
-	}
-
-	if (i >= adev->usec_timeout)
-		r = -ETIMEDOUT;
-
-	return r;
-}
-
-static int amdgpu_vcn_jpeg_set_reg(struct amdgpu_ring *ring, uint32_t handle,
-		struct dma_fence **fence)
-{
-	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_job *job;
-	struct amdgpu_ib *ib;
-	struct dma_fence *f = NULL;
-	const unsigned ib_size_dw = 16;
-	int i, r;
-
-	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
-	if (r)
-		return r;
-
-	ib = &job->ibs[0];
-
-	ib->ptr[0] = PACKETJ(adev->vcn.internal.jpeg_pitch, 0, 0, PACKETJ_TYPE0);
-	ib->ptr[1] = 0xDEADBEEF;
-	for (i = 2; i < 16; i += 2) {
-		ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
-		ib->ptr[i+1] = 0;
-	}
-	ib->length_dw = 16;
-
-	r = amdgpu_job_submit_direct(job, ring, &f);
-	if (r)
-		goto err;
-
-	if (fence)
-		*fence = dma_fence_get(f);
-	dma_fence_put(f);
-
-	return 0;
-
-err:
-	amdgpu_job_free(job);
-	return r;
-}
-
-int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t tmp = 0;
-	unsigned i;
-	struct dma_fence *fence = NULL;
-	long r = 0;
-
-	r = amdgpu_vcn_jpeg_set_reg(ring, 1, &fence);
-	if (r)
-		goto error;
-
-	r = dma_fence_wait_timeout(fence, false, timeout);
-	if (r == 0) {
-		r = -ETIMEDOUT;
-		goto error;
-	} else if (r < 0) {
-		goto error;
-	} else {
-		r = 0;
-	}
-
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(adev->vcn.inst[ring->me].external.jpeg_pitch);
-		if (tmp == 0xDEADBEEF)
-			break;
-		udelay(1);
-	}
-
-	if (i >= adev->usec_timeout)
-		r = -ETIMEDOUT;
-
-	dma_fence_put(fence);
-error:
-	return r;
-}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index dface275c81a..c4984c5fb2db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -31,6 +31,7 @@
 #define AMDGPU_VCN_MAX_ENC_RINGS	3
 
 #define AMDGPU_MAX_VCN_INSTANCES	2
+#define AMDGPU_MAX_VCN_ENC_RINGS  AMDGPU_VCN_MAX_ENC_RINGS * AMDGPU_MAX_VCN_INSTANCES
 
 #define AMDGPU_VCN_HARVEST_VCN0 (1 << 0)
 #define AMDGPU_VCN_HARVEST_VCN1 (1 << 1)
@@ -56,6 +57,14 @@
 #define VCN_VID_IP_ADDRESS_2_0		0x0
 #define VCN_AON_IP_ADDRESS_2_0		0x30000
 
+#define mmUVD_RBC_XX_IB_REG_CHECK 					0x026b
+#define mmUVD_RBC_XX_IB_REG_CHECK_BASE_IDX 				1
+#define mmUVD_REG_XX_MASK 						0x026c
+#define mmUVD_REG_XX_MASK_BASE_IDX 					1
+
+/* 1 second timeout */
+#define VCN_IDLE_TIMEOUT	msecs_to_jiffies(1000)
+
 #define RREG32_SOC15_DPG_MODE(ip, inst, reg, mask, sram_sel) 				\
 	({	WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_MASK, mask); 			\
 		WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_CTL, 				\
@@ -100,27 +109,27 @@
 		internal_reg_offset >>= 2;							\
 	})
 
-#define RREG32_SOC15_DPG_MODE_2_0(offset, mask_en) 						\
-	({ 											\
-		WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_CTL, 					\
-			(0x0 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT | 				\
-			mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT | 				\
-			offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT)); 			\
-		RREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_DATA); 					\
+#define RREG32_SOC15_DPG_MODE_2_0(inst_idx, offset, mask_en) 					\
+	({											\
+		WREG32_SOC15(VCN, inst, mmUVD_DPG_LMA_CTL, 					\
+			(0x0 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT |				\
+			mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT |				\
+			offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT));			\
+		RREG32_SOC15(VCN, inst_idx, mmUVD_DPG_LMA_DATA);				\
 	})
 
-#define WREG32_SOC15_DPG_MODE_2_0(offset, value, mask_en, indirect)				\
-	do { 											\
-		if (!indirect) { 								\
-			WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_DATA, value); 			\
-			WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_CTL, 				\
-				(0x1 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT | 			\
-				 mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT | 			\
-				 offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT)); 		\
-		} else { 									\
-			*adev->vcn.dpg_sram_curr_addr++ = offset; 				\
-			*adev->vcn.dpg_sram_curr_addr++ = value; 				\
-		} 										\
+#define WREG32_SOC15_DPG_MODE_2_0(inst_idx, offset, value, mask_en, indirect)			\
+	do {											\
+		if (!indirect) {								\
+			WREG32_SOC15(VCN, inst_idx, mmUVD_DPG_LMA_DATA, value);			\
+			WREG32_SOC15(VCN, inst_idx, mmUVD_DPG_LMA_CTL, 				\
+				(0x1 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT |			\
+				 mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT |			\
+				 offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT));		\
+		} else {									\
+			*adev->vcn.inst[inst_idx].dpg_sram_curr_addr++ = offset;		\
+			*adev->vcn.inst[inst_idx].dpg_sram_curr_addr++ = value;			\
+		}										\
 	} while (0)
 
 enum engine_status_constants {
@@ -158,7 +167,6 @@ struct amdgpu_vcn_reg{
 	unsigned	ib_size;
 	unsigned	gp_scratch8;
 	unsigned	scratch9;
-	unsigned	jpeg_pitch;
 };
 
 struct amdgpu_vcn_inst {
@@ -168,9 +176,12 @@ struct amdgpu_vcn_inst {
 	void			*saved_bo;
 	struct amdgpu_ring	ring_dec;
 	struct amdgpu_ring	ring_enc[AMDGPU_VCN_MAX_ENC_RINGS];
-	struct amdgpu_ring	ring_jpeg;
 	struct amdgpu_irq_src	irq;
 	struct amdgpu_vcn_reg	external;
+	struct amdgpu_bo	*dpg_sram_bo;
+	void			*dpg_sram_cpu_addr;
+	uint64_t		dpg_sram_gpu_addr;
+	uint32_t		*dpg_sram_curr_addr;
 };
 
 struct amdgpu_vcn {
@@ -182,18 +193,18 @@ struct amdgpu_vcn {
 	struct dpg_pause_state pause_state;
 
 	bool			indirect_sram;
-	struct amdgpu_bo	*dpg_sram_bo;
-	void			*dpg_sram_cpu_addr;
-	uint64_t		dpg_sram_gpu_addr;
-	uint32_t		*dpg_sram_curr_addr;
 
 	uint8_t	num_vcn_inst;
-	struct amdgpu_vcn_inst	inst[AMDGPU_MAX_VCN_INSTANCES];
-	struct amdgpu_vcn_reg	internal;
+	struct amdgpu_vcn_inst	 inst[AMDGPU_MAX_VCN_INSTANCES];
+	struct amdgpu_vcn_reg	 internal;
+	struct drm_gpu_scheduler *vcn_enc_sched[AMDGPU_MAX_VCN_ENC_RINGS];
+	struct drm_gpu_scheduler *vcn_dec_sched[AMDGPU_MAX_VCN_INSTANCES];
+	uint32_t		 num_vcn_enc_sched;
+	uint32_t		 num_vcn_dec_sched;
 
 	unsigned	harvest_config;
 	int (*pause_dpg_mode)(struct amdgpu_device *adev,
-		struct dpg_pause_state *new_state);
+		int inst_idx, struct dpg_pause_state *new_state);
 };
 
 int amdgpu_vcn_sw_init(struct amdgpu_device *adev);
@@ -209,7 +220,4 @@ int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring);
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 
-int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring);
-int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout);
-
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index e32ae906d797..103033f96f13 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -379,54 +379,3 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 		}
 	}
 }
-
-static uint32_t parse_clk(char *buf, bool min)
-{
-        char *ptr = buf;
-        uint32_t clk = 0;
-
-        do {
-                ptr = strchr(ptr, ':');
-                if (!ptr)
-                        break;
-                ptr+=2;
-		if (kstrtou32(ptr, 10, &clk))
-			return 0;
-        } while (!min);
-
-        return clk * 100;
-}
-
-uint32_t amdgpu_virt_get_sclk(struct amdgpu_device *adev, bool lowest)
-{
-	char *buf = NULL;
-	uint32_t clk = 0;
-
-	buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	adev->virt.ops->get_pp_clk(adev, PP_SCLK, buf);
-	clk = parse_clk(buf, lowest);
-
-	kfree(buf);
-
-	return clk;
-}
-
-uint32_t amdgpu_virt_get_mclk(struct amdgpu_device *adev, bool lowest)
-{
-	char *buf = NULL;
-	uint32_t clk = 0;
-
-	buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	adev->virt.ops->get_pp_clk(adev, PP_MCLK, buf);
-	clk = parse_clk(buf, lowest);
-
-	kfree(buf);
-
-	return clk;
-}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b0b2bdc750df..4d1ac7612967 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -57,8 +57,6 @@ struct amdgpu_virt_ops {
 	int (*reset_gpu)(struct amdgpu_device *adev);
 	int (*wait_reset)(struct amdgpu_device *adev);
 	void (*trans_msg)(struct amdgpu_device *adev, u32 req, u32 data1, u32 data2, u32 data3);
-	int (*get_pp_clk)(struct amdgpu_device *adev, u32 type, char *buf);
-	int (*force_dpm_level)(struct amdgpu_device *adev, u32 level);
 };
 
 /*
@@ -85,8 +83,8 @@ enum AMDGIM_FEATURE_FLAG {
 	AMDGIM_FEATURE_GIM_LOAD_UCODES   = 0x2,
 	/* VRAM LOST by GIM */
 	AMDGIM_FEATURE_GIM_FLR_VRAMLOST = 0x4,
-	/* HW PERF SIM in GIM */
-	AMDGIM_FEATURE_HW_PERF_SIMULATION = (1 << 3),
+	/* PP ONE VF MODE in GIM */
+	AMDGIM_FEATURE_PP_ONE_VF = (1 << 4),
 };
 
 struct amd_sriov_msg_pf2vf_info_header {
@@ -257,8 +255,6 @@ struct amdgpu_virt {
 	struct amdgpu_vf_error_buffer   vf_errors;
 	struct amdgpu_virt_fw_reserve	fw_reserve;
 	uint32_t gim_feature;
-	/* protect DPM events to GIM */
-	struct mutex                    dpm_mutex;
 	uint32_t reg_access_mode;
 };
 
@@ -286,8 +282,8 @@ static inline bool is_virtual_machine(void)
 #endif
 }
 
-#define amdgim_is_hwperf(adev) \
-	((adev)->virt.gim_feature & AMDGIM_FEATURE_HW_PERF_SIMULATION)
+#define amdgpu_sriov_is_pp_one_vf(adev) \
+	((adev)->virt.gim_feature & AMDGIM_FEATURE_PP_ONE_VF)
 
 bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev);
 void amdgpu_virt_init_setting(struct amdgpu_device *adev);
@@ -306,6 +302,4 @@ int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
 					unsigned int key,
 					unsigned int chksum);
 void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev);
-uint32_t amdgpu_virt_get_sclk(struct amdgpu_device *adev, bool lowest);
-uint32_t amdgpu_virt_get_mclk(struct amdgpu_device *adev, bool lowest);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 598c24505c73..d16231d6a790 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -83,6 +83,32 @@ struct amdgpu_prt_cb {
 };
 
 /**
+ * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS
+ * happens while holding this lock anywhere to prevent deadlocks when
+ * an MMU notifier runs in reclaim-FS context.
+ */
+static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm)
+{
+	mutex_lock(&vm->eviction_lock);
+	vm->saved_flags = memalloc_nofs_save();
+}
+
+static inline int amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm)
+{
+	if (mutex_trylock(&vm->eviction_lock)) {
+		vm->saved_flags = memalloc_nofs_save();
+		return 1;
+	}
+	return 0;
+}
+
+static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm)
+{
+	memalloc_nofs_restore(vm->saved_flags);
+	mutex_unlock(&vm->eviction_lock);
+}
+
+/**
  * amdgpu_vm_level_shift - return the addr shift for each level
  *
  * @adev: amdgpu_device pointer
@@ -562,8 +588,8 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 {
 	entry->priority = 0;
 	entry->tv.bo = &vm->root.base.bo->tbo;
-	/* One for the VM updates, one for TTM and one for the CS job */
-	entry->tv.num_shared = 3;
+	/* One for TTM and one for the CS job */
+	entry->tv.num_shared = 2;
 	entry->user_pages = NULL;
 	list_add(&entry->tv.head, validated);
 }
@@ -656,7 +682,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      void *param)
 {
 	struct amdgpu_vm_bo_base *bo_base, *tmp;
-	int r = 0;
+	int r;
 
 	vm->bulk_moveable &= list_empty(&vm->evicted);
 
@@ -665,7 +691,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 		r = validate(param, bo);
 		if (r)
-			break;
+			return r;
 
 		if (bo->tbo.type != ttm_bo_type_kernel) {
 			amdgpu_vm_bo_moved(bo_base);
@@ -678,7 +704,11 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		}
 	}
 
-	return r;
+	amdgpu_vm_eviction_lock(vm);
+	vm->evicting = false;
+	amdgpu_vm_eviction_unlock(vm);
+
+	return 0;
 }
 
 /**
@@ -1555,15 +1585,25 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	if (!(flags & AMDGPU_PTE_VALID))
 		owner = AMDGPU_FENCE_OWNER_KFD;
 
+	amdgpu_vm_eviction_lock(vm);
+	if (vm->evicting) {
+		r = -EBUSY;
+		goto error_unlock;
+	}
+
 	r = vm->update_funcs->prepare(&params, owner, exclusive);
 	if (r)
-		return r;
+		goto error_unlock;
 
 	r = amdgpu_vm_update_ptes(&params, start, last + 1, addr, flags);
 	if (r)
-		return r;
+		goto error_unlock;
+
+	r = vm->update_funcs->commit(&params, fence);
 
-	return vm->update_funcs->commit(&params, fence);
+error_unlock:
+	amdgpu_vm_eviction_unlock(vm);
+	return r;
 }
 
 /**
@@ -2500,6 +2540,41 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 }
 
 /**
+ * amdgpu_vm_evictable - check if we can evict a VM
+ *
+ * @bo: A page table of the VM.
+ *
+ * Check if it is possible to evict a VM.
+ */
+bool amdgpu_vm_evictable(struct amdgpu_bo *bo)
+{
+	struct amdgpu_vm_bo_base *bo_base = bo->vm_bo;
+
+	/* Page tables of a destroyed VM can go away immediately */
+	if (!bo_base || !bo_base->vm)
+		return true;
+
+	/* Don't evict VM page tables while they are busy */
+	if (!dma_resv_test_signaled_rcu(bo->tbo.base.resv, true))
+		return false;
+
+	/* Try to block ongoing updates */
+	if (!amdgpu_vm_eviction_trylock(bo_base->vm))
+		return false;
+
+	/* Don't evict VM page tables while they are updated */
+	if (!dma_fence_is_signaled(bo_base->vm->last_direct) ||
+	    !dma_fence_is_signaled(bo_base->vm->last_delayed)) {
+		amdgpu_vm_eviction_unlock(bo_base->vm);
+		return false;
+	}
+
+	bo_base->vm->evicting = true;
+	amdgpu_vm_eviction_unlock(bo_base->vm);
+	return true;
+}
+
+/**
  * amdgpu_vm_bo_invalidate - mark the bo as invalid
  *
  * @adev: amdgpu_device pointer
@@ -2661,8 +2736,16 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size,
  */
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
 {
-	return dma_resv_wait_timeout_rcu(vm->root.base.bo->tbo.base.resv,
-						   true, true, timeout);
+	timeout = dma_resv_wait_timeout_rcu(vm->root.base.bo->tbo.base.resv,
+					    true, true, timeout);
+	if (timeout <= 0)
+		return timeout;
+
+	timeout = dma_fence_wait_timeout(vm->last_direct, true, timeout);
+	if (timeout <= 0)
+		return timeout;
+
+	return dma_fence_wait_timeout(vm->last_delayed, true, timeout);
 }
 
 /**
@@ -2696,18 +2779,22 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	spin_lock_init(&vm->invalidated_lock);
 	INIT_LIST_HEAD(&vm->freed);
 
+
 	/* create scheduler entities for page table updates */
-	r = drm_sched_entity_init(&vm->direct, adev->vm_manager.vm_pte_rqs,
-				  adev->vm_manager.vm_pte_num_rqs, NULL);
+	r = drm_sched_entity_init(&vm->direct, DRM_SCHED_PRIORITY_NORMAL,
+				  adev->vm_manager.vm_pte_scheds,
+				  adev->vm_manager.vm_pte_num_scheds, NULL);
 	if (r)
 		return r;
 
-	r = drm_sched_entity_init(&vm->delayed, adev->vm_manager.vm_pte_rqs,
-				  adev->vm_manager.vm_pte_num_rqs, NULL);
+	r = drm_sched_entity_init(&vm->delayed, DRM_SCHED_PRIORITY_NORMAL,
+				  adev->vm_manager.vm_pte_scheds,
+				  adev->vm_manager.vm_pte_num_scheds, NULL);
 	if (r)
 		goto error_free_direct;
 
 	vm->pte_support_ats = false;
+	vm->is_compute_context = false;
 
 	if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE) {
 		vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
@@ -2730,6 +2817,11 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	else
 		vm->update_funcs = &amdgpu_vm_sdma_funcs;
 	vm->last_update = NULL;
+	vm->last_direct = dma_fence_get_stub();
+	vm->last_delayed = dma_fence_get_stub();
+
+	mutex_init(&vm->eviction_lock);
+	vm->evicting = false;
 
 	amdgpu_vm_bo_param(adev, vm, adev->vm_manager.root_level, false, &bp);
 	if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE)
@@ -2780,6 +2872,8 @@ error_free_root:
 	vm->root.base.bo = NULL;
 
 error_free_delayed:
+	dma_fence_put(vm->last_direct);
+	dma_fence_put(vm->last_delayed);
 	drm_sched_entity_destroy(&vm->delayed);
 
 error_free_direct:
@@ -2893,6 +2987,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		vm->update_funcs = &amdgpu_vm_sdma_funcs;
 	dma_fence_put(vm->last_update);
 	vm->last_update = NULL;
+	vm->is_compute_context = true;
 
 	if (vm->pasid) {
 		unsigned long flags;
@@ -2947,6 +3042,7 @@ void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 	}
 	vm->pasid = 0;
+	vm->is_compute_context = false;
 }
 
 /**
@@ -2978,6 +3074,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		vm->pasid = 0;
 	}
 
+	dma_fence_wait(vm->last_direct, false);
+	dma_fence_put(vm->last_direct);
+	dma_fence_wait(vm->last_delayed, false);
+	dma_fence_put(vm->last_delayed);
+
 	list_for_each_entry_safe(mapping, tmp, &vm->freed, list) {
 		if (mapping->flags & AMDGPU_PTE_PRT && prt_fini_needed) {
 			amdgpu_vm_prt_fini(adev, vm);
@@ -3194,11 +3295,20 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
 	flags = AMDGPU_PTE_VALID | AMDGPU_PTE_SNOOPED |
 		AMDGPU_PTE_SYSTEM;
 
-	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
+	if (vm->is_compute_context) {
+		/* Intentionally setting invalid PTE flag
+		 * combination to force a no-retry-fault
+		 */
+		flags = AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE |
+			AMDGPU_PTE_TF;
+		value = 0;
+
+	} else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
 		/* Redirect the access to the dummy page */
 		value = adev->dummy_page_addr;
 		flags |= AMDGPU_PTE_EXECUTABLE | AMDGPU_PTE_READABLE |
 			AMDGPU_PTE_WRITEABLE;
+
 	} else {
 		/* Let the hw retry silently on the PTE */
 		value = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 4dbbe1b6b413..b4640ab38c95 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -30,6 +30,7 @@
 #include <drm/gpu_scheduler.h>
 #include <drm/drm_file.h>
 #include <drm/ttm/ttm_bo_driver.h>
+#include <linux/sched/mm.h>
 
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
@@ -239,6 +240,13 @@ struct amdgpu_vm {
 	/* tree of virtual addresses mapped */
 	struct rb_root_cached	va;
 
+	/* Lock to prevent eviction while we are updating page tables
+	 * use vm_eviction_lock/unlock(vm)
+	 */
+	struct mutex		eviction_lock;
+	bool			evicting;
+	unsigned int		saved_flags;
+
 	/* BOs who needs a validation */
 	struct list_head	evicted;
 
@@ -266,6 +274,10 @@ struct amdgpu_vm {
 	struct drm_sched_entity	direct;
 	struct drm_sched_entity	delayed;
 
+	/* Last submission to the scheduler entities */
+	struct dma_fence	*last_direct;
+	struct dma_fence	*last_delayed;
+
 	unsigned int		pasid;
 	/* dedicated to vm */
 	struct amdgpu_vmid	*reserved_vmid[AMDGPU_MAX_VMHUBS];
@@ -298,6 +310,8 @@ struct amdgpu_vm {
 	struct ttm_lru_bulk_move lru_bulk_move;
 	/* mark whether can do the bulk move */
 	bool			bulk_moveable;
+	/* Flag to indicate if VM is used for compute */
+	bool			is_compute_context;
 };
 
 struct amdgpu_vm_manager {
@@ -317,8 +331,8 @@ struct amdgpu_vm_manager {
 	u64					vram_base_offset;
 	/* vm pte handling */
 	const struct amdgpu_vm_pte_funcs	*vm_pte_funcs;
-	struct drm_sched_rq			*vm_pte_rqs[AMDGPU_MAX_RINGS];
-	unsigned				vm_pte_num_rqs;
+	struct drm_gpu_scheduler		*vm_pte_scheds[AMDGPU_MAX_RINGS];
+	unsigned				vm_pte_num_scheds;
 	struct amdgpu_ring			*page_fault;
 
 	/* partial resident texture handling */
@@ -376,6 +390,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			struct amdgpu_bo_va *bo_va,
 			bool clear);
+bool amdgpu_vm_evictable(struct amdgpu_bo *bo);
 void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 			     struct amdgpu_bo *bo, bool evicted);
 uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index 832db59f441e..19b7f80758f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -71,7 +71,7 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
 	p->num_dw_left = ndw;
 
 	/* Wait for moves to be completed */
-	r = amdgpu_sync_fence(p->adev, &p->job->sync, exclusive, false);
+	r = amdgpu_sync_fence(&p->job->sync, exclusive, false);
 	if (r)
 		return r;
 
@@ -95,11 +95,10 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
 static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
 				 struct dma_fence **fence)
 {
-	struct amdgpu_bo *root = p->vm->root.base.bo;
 	struct amdgpu_ib *ib = p->job->ibs;
 	struct drm_sched_entity *entity;
+	struct dma_fence *f, *tmp;
 	struct amdgpu_ring *ring;
-	struct dma_fence *f;
 	int r;
 
 	entity = p->direct ? &p->vm->direct : &p->vm->delayed;
@@ -112,7 +111,13 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
 	if (r)
 		goto error;
 
-	amdgpu_bo_fence(root, f, true);
+	tmp = dma_fence_get(f);
+	if (p->direct)
+		swap(p->vm->last_direct, tmp);
+	else
+		swap(p->vm->last_delayed, tmp);
+	dma_fence_put(tmp);
+
 	if (fence && !p->direct)
 		swap(*fence, f);
 	dma_fence_put(f);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 61d13d8b7b20..a97af422575a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -146,16 +146,16 @@ static ssize_t amdgpu_xgmi_show_error(struct device *dev,
 	ficaa_pie_ctl_in = AMDGPU_XGMI_SET_FICAA(0x200);
 	ficaa_pie_status_in = AMDGPU_XGMI_SET_FICAA(0x208);
 
-	fica_out = adev->df_funcs->get_fica(adev, ficaa_pie_ctl_in);
+	fica_out = adev->df.funcs->get_fica(adev, ficaa_pie_ctl_in);
 	if (fica_out != 0x1f)
 		pr_err("xGMI error counters not enabled!\n");
 
-	fica_out = adev->df_funcs->get_fica(adev, ficaa_pie_status_in);
+	fica_out = adev->df.funcs->get_fica(adev, ficaa_pie_status_in);
 
 	if ((fica_out & 0xffff) == 2)
 		error_count = ((fica_out >> 62) & 0x1) + (fica_out >> 63);
 
-	adev->df_funcs->set_fica(adev, ficaa_pie_status_in, 0, 0);
+	adev->df.funcs->set_fica(adev, ficaa_pie_status_in, 0, 0);
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", error_count);
 }
@@ -261,6 +261,7 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lo
 	INIT_LIST_HEAD(&tmp->device_list);
 	mutex_init(&tmp->hive_lock);
 	mutex_init(&tmp->reset_lock);
+	task_barrier_init(&tmp->tb);
 
 	if (lock)
 		mutex_lock(&tmp->hive_lock);
@@ -290,13 +291,7 @@ int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
 
 	dev_dbg(adev->dev, "Set xgmi pstate %d.\n", pstate);
 
-	if (is_support_sw_smu_xgmi(adev))
-		ret = smu_set_xgmi_pstate(&adev->smu, pstate);
-	else if (adev->powerplay.pp_funcs &&
-		 adev->powerplay.pp_funcs->set_xgmi_pstate)
-		ret = adev->powerplay.pp_funcs->set_xgmi_pstate(adev->powerplay.pp_handle,
-								pstate);
-
+	ret = amdgpu_dpm_set_xgmi_pstate(adev, pstate);
 	if (ret) {
 		dev_err(adev->dev,
 			"XGMI: Set pstate failure on device %llx, hive %llx, ret %d",
@@ -408,6 +403,8 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	top_info->num_nodes = count;
 	hive->number_devices = count;
 
+	task_barrier_add_task(&hive->tb);
+
 	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
 		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
 			/* update node list for other device in the hive */
@@ -470,6 +467,7 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 		mutex_destroy(&hive->hive_lock);
 		mutex_destroy(&hive->reset_lock);
 	} else {
+		task_barrier_rem_task(&hive->tb);
 		amdgpu_xgmi_sysfs_rem_dev_info(adev, hive);
 		mutex_unlock(&hive->hive_lock);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index bbf504ff7051..74011fbc2251 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -22,6 +22,7 @@
 #ifndef __AMDGPU_XGMI_H__
 #define __AMDGPU_XGMI_H__
 
+#include <drm/task_barrier.h>
 #include "amdgpu_psp.h"
 
 struct amdgpu_hive_info {
@@ -33,6 +34,7 @@ struct amdgpu_hive_info {
 	struct device_attribute dev_attr;
 	struct amdgpu_device *adev;
 	int pstate; /*0 -- low , 1 -- high , -1 unknown*/
+	struct task_barrier tb;
 };
 
 struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
index 6858cde9fc5d..ea702a64f807 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
@@ -361,7 +361,6 @@ int amdgpu_atombios_dp_get_panel_mode(struct drm_encoder *encoder,
 			       struct drm_connector *connector)
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
-	struct amdgpu_connector_atom_dig *dig_connector;
 	int panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
 	u16 dp_bridge = amdgpu_connector_encoder_get_dp_bridge_encoder_id(connector);
 	u8 tmp;
@@ -369,8 +368,6 @@ int amdgpu_atombios_dp_get_panel_mode(struct drm_encoder *encoder,
 	if (!amdgpu_connector->con_priv)
 		return panel_mode;
 
-	dig_connector = amdgpu_connector->con_priv;
-
 	if (dp_bridge != ENCODER_OBJECT_ID_NONE) {
 		/* DP bridge chips */
 		if (drm_dp_dpcd_readb(&amdgpu_connector->ddc_bus->aux,
@@ -713,7 +710,6 @@ void amdgpu_atombios_dp_link_train(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
-	struct amdgpu_encoder_atom_dig *dig;
 	struct amdgpu_connector *amdgpu_connector;
 	struct amdgpu_connector_atom_dig *dig_connector;
 	struct amdgpu_atombios_dp_link_train_info dp_info;
@@ -721,7 +717,6 @@ void amdgpu_atombios_dp_link_train(struct drm_encoder *encoder,
 
 	if (!amdgpu_encoder->enc_priv)
 		return;
-	dig = amdgpu_encoder->enc_priv;
 
 	amdgpu_connector = to_amdgpu_connector(connector);
 	if (!amdgpu_connector->con_priv)
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
index 980c363b1a0a..b4cc7c55fa16 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
@@ -76,11 +76,6 @@ static int amdgpu_atombios_i2c_process_i2c_ch(struct amdgpu_i2c_chan *chan,
 		}
 		args.lpI2CDataOut = cpu_to_le16(out);
 	} else {
-		if (num > ATOM_MAX_HW_I2C_READ) {
-			DRM_ERROR("hw i2c: tried to read too many bytes (%d vs 255)\n", num);
-			r = -EINVAL;
-			goto done;
-		}
 		args.ucRegIndex = 0;
 		args.lpI2CDataOut = 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 1befdee9f0f1..006f21ef7ddf 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1310,6 +1310,17 @@ static int cik_asic_pci_config_reset(struct amdgpu_device *adev)
 	return r;
 }
 
+static bool cik_asic_supports_baco(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+		return amdgpu_dpm_is_baco_supported(adev);
+	default:
+		return false;
+	}
+}
+
 static enum amd_reset_method
 cik_asic_reset_method(struct amdgpu_device *adev)
 {
@@ -1349,7 +1360,7 @@ static int cik_asic_reset(struct amdgpu_device *adev)
 	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 		if (!adev->in_suspend)
 			amdgpu_inc_vram_lost(adev);
-		r = smu7_asic_baco_reset(adev);
+		r = amdgpu_dpm_baco_reset(adev);
 	} else {
 		r = cik_asic_pci_config_reset(adev);
 	}
@@ -1927,6 +1938,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.get_pcie_usage = &cik_get_pcie_usage,
 	.need_reset_on_init = &cik_need_reset_on_init,
 	.get_pcie_replay_count = &cik_get_pcie_replay_count,
+	.supports_baco = &cik_asic_supports_baco,
 };
 
 static int cik_common_early_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.h b/drivers/gpu/drm/amd/amdgpu/cik.h
index 9870bf27870e..f91ab4c246b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.h
+++ b/drivers/gpu/drm/amd/amdgpu/cik.h
@@ -31,7 +31,5 @@ void cik_srbm_select(struct amdgpu_device *adev,
 int cik_set_ip_blocks(struct amdgpu_device *adev);
 
 void legacy_doorbell_index_init(struct amdgpu_device *adev);
-int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap);
-int smu7_asic_baco_reset(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index c45304f1047c..580d3f93d670 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -228,7 +228,7 @@ static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
 	u32 extra_bits = vmid & 0xf;
 
 	/* IB packet must end on a 8 DW boundary */
-	cik_sdma_ring_insert_nop(ring, (12 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	cik_sdma_ring_insert_nop(ring, (4 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
 	amdgpu_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
@@ -811,7 +811,7 @@ static void cik_sdma_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1372,16 +1372,14 @@ static const struct amdgpu_vm_pte_funcs cik_sdma_vm_pte_funcs = {
 
 static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	adev->vm_manager.vm_pte_funcs = &cik_sdma_vm_pte_funcs;
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] =
+			&adev->sdma.instance[i].ring.sched;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version cik_sdma_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
index d6221298b477..d6aca1c08068 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
@@ -31,6 +31,9 @@ static u32 df_v1_7_channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
 
 static void df_v1_7_sw_init(struct amdgpu_device *adev)
 {
+	adev->df.hash_status.hash_64k = false;
+	adev->df.hash_status.hash_2m = false;
+	adev->df.hash_status.hash_1g = false;
 }
 
 static void df_v1_7_sw_fini(struct amdgpu_device *adev)
@@ -66,7 +69,7 @@ static u32 df_v1_7_get_hbm_channel_number(struct amdgpu_device *adev)
 {
 	int fb_channel_number;
 
-	fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
+	fb_channel_number = adev->df.funcs->get_fb_channel_number(adev);
 
 	return df_v1_7_channel_number[fb_channel_number];
 }
@@ -77,7 +80,7 @@ static void df_v1_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 	u32 tmp;
 
 	/* Put DF on broadcast mode */
-	adev->df_funcs->enable_broadcast_mode(adev, true);
+	adev->df.funcs->enable_broadcast_mode(adev, true);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) {
 		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
@@ -92,7 +95,7 @@ static void df_v1_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 	}
 
 	/* Exit boradcast mode */
-	adev->df_funcs->enable_broadcast_mode(adev, false);
+	adev->df.funcs->enable_broadcast_mode(adev, false);
 }
 
 static void df_v1_7_get_clockgating_state(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index 4043ebcea5de..f51326598a8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -183,6 +183,61 @@ static void df_v3_6_perfmon_wreg(struct amdgpu_device *adev, uint32_t lo_addr,
 	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
 }
 
+/* same as perfmon_wreg but return status on write value check */
+static int df_v3_6_perfmon_arm_with_status(struct amdgpu_device *adev,
+					  uint32_t lo_addr, uint32_t lo_val,
+					  uint32_t hi_addr, uint32_t  hi_val)
+{
+	unsigned long flags, address, data;
+	uint32_t lo_val_rb, hi_val_rb;
+
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	WREG32(address, lo_addr);
+	WREG32(data, lo_val);
+	WREG32(address, hi_addr);
+	WREG32(data, hi_val);
+
+	WREG32(address, lo_addr);
+	lo_val_rb = RREG32(data);
+	WREG32(address, hi_addr);
+	hi_val_rb = RREG32(data);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+
+	if (!(lo_val == lo_val_rb && hi_val == hi_val_rb))
+		return -EBUSY;
+
+	return 0;
+}
+
+
+/*
+ * retry arming counters every 100 usecs within 1 millisecond interval.
+ * if retry fails after time out, return error.
+ */
+#define ARM_RETRY_USEC_TIMEOUT	1000
+#define ARM_RETRY_USEC_INTERVAL	100
+static int df_v3_6_perfmon_arm_with_retry(struct amdgpu_device *adev,
+					  uint32_t lo_addr, uint32_t lo_val,
+					  uint32_t hi_addr, uint32_t  hi_val)
+{
+	int countdown = ARM_RETRY_USEC_TIMEOUT;
+
+	while (countdown) {
+
+		if (!df_v3_6_perfmon_arm_with_status(adev, lo_addr, lo_val,
+						     hi_addr, hi_val))
+			break;
+
+		countdown -= ARM_RETRY_USEC_INTERVAL;
+		udelay(ARM_RETRY_USEC_INTERVAL);
+	}
+
+	return countdown > 0 ? 0 : -ETIME;
+}
+
 /* get the number of df counters available */
 static ssize_t df_v3_6_get_df_cntr_avail(struct device *dev,
 		struct device_attribute *attr,
@@ -207,6 +262,32 @@ static ssize_t df_v3_6_get_df_cntr_avail(struct device *dev,
 /* device attr for available perfmon counters */
 static DEVICE_ATTR(df_cntr_avail, S_IRUGO, df_v3_6_get_df_cntr_avail, NULL);
 
+static void df_v3_6_query_hashes(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	adev->df.hash_status.hash_64k = false;
+	adev->df.hash_status.hash_2m = false;
+	adev->df.hash_status.hash_1g = false;
+
+	if (adev->asic_type != CHIP_ARCTURUS)
+		return;
+
+	/* encoding for hash-enabled on Arcturus */
+	if (adev->df.funcs->get_fb_channel_number(adev) == 0xe) {
+		tmp = RREG32_SOC15(DF, 0, mmDF_CS_UMC_AON0_DfGlobalCtrl);
+		adev->df.hash_status.hash_64k = REG_GET_FIELD(tmp,
+						DF_CS_UMC_AON0_DfGlobalCtrl,
+						GlbHashIntlvCtl64K);
+		adev->df.hash_status.hash_2m = REG_GET_FIELD(tmp,
+						DF_CS_UMC_AON0_DfGlobalCtrl,
+						GlbHashIntlvCtl2M);
+		adev->df.hash_status.hash_1g = REG_GET_FIELD(tmp,
+						DF_CS_UMC_AON0_DfGlobalCtrl,
+						GlbHashIntlvCtl1G);
+	}
+}
+
 /* init perfmons */
 static void df_v3_6_sw_init(struct amdgpu_device *adev)
 {
@@ -218,6 +299,8 @@ static void df_v3_6_sw_init(struct amdgpu_device *adev)
 
 	for (i = 0; i < AMDGPU_MAX_DF_PERFMONS; i++)
 		adev->df_perfmon_config_assign_mask[i] = 0;
+
+	df_v3_6_query_hashes(adev);
 }
 
 static void df_v3_6_sw_fini(struct amdgpu_device *adev)
@@ -256,7 +339,7 @@ static u32 df_v3_6_get_hbm_channel_number(struct amdgpu_device *adev)
 {
 	int fb_channel_number;
 
-	fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
+	fb_channel_number = adev->df.funcs->get_fb_channel_number(adev);
 	if (fb_channel_number >= ARRAY_SIZE(df_v3_6_channel_number))
 		fb_channel_number = 0;
 
@@ -270,7 +353,7 @@ static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG) {
 		/* Put DF on broadcast mode */
-		adev->df_funcs->enable_broadcast_mode(adev, true);
+		adev->df.funcs->enable_broadcast_mode(adev, true);
 
 		if (enable) {
 			tmp = RREG32_SOC15(DF, 0,
@@ -289,7 +372,7 @@ static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 		}
 
 		/* Exit broadcast mode */
-		adev->df_funcs->enable_broadcast_mode(adev, false);
+		adev->df.funcs->enable_broadcast_mode(adev, false);
 	}
 }
 
@@ -334,20 +417,20 @@ static void df_v3_6_pmc_get_addr(struct amdgpu_device *adev,
 	switch (target_cntr) {
 
 	case 0:
-		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo0 : smnPerfMonCtrLo0;
-		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi0 : smnPerfMonCtrHi0;
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo4 : smnPerfMonCtrLo4;
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi4 : smnPerfMonCtrHi4;
 		break;
 	case 1:
-		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo1 : smnPerfMonCtrLo1;
-		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi1 : smnPerfMonCtrHi1;
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo5 : smnPerfMonCtrLo5;
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi5 : smnPerfMonCtrHi5;
 		break;
 	case 2:
-		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo2 : smnPerfMonCtrLo2;
-		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi2 : smnPerfMonCtrHi2;
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo6 : smnPerfMonCtrLo6;
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi6 : smnPerfMonCtrHi6;
 		break;
 	case 3:
-		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo3 : smnPerfMonCtrLo3;
-		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi3 : smnPerfMonCtrHi3;
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo7 : smnPerfMonCtrLo7;
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi7 : smnPerfMonCtrHi7;
 		break;
 
 	}
@@ -422,6 +505,44 @@ static int df_v3_6_pmc_add_cntr(struct amdgpu_device *adev,
 	return -ENOSPC;
 }
 
+#define DEFERRED_ARM_MASK	(1 << 31)
+static int df_v3_6_pmc_set_deferred(struct amdgpu_device *adev,
+				    uint64_t config, bool is_deferred)
+{
+	int target_cntr;
+
+	target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
+
+	if (target_cntr < 0)
+		return -EINVAL;
+
+	if (is_deferred)
+		adev->df_perfmon_config_assign_mask[target_cntr] |=
+							DEFERRED_ARM_MASK;
+	else
+		adev->df_perfmon_config_assign_mask[target_cntr] &=
+							~DEFERRED_ARM_MASK;
+
+	return 0;
+}
+
+static bool df_v3_6_pmc_is_deferred(struct amdgpu_device *adev,
+				    uint64_t config)
+{
+	int target_cntr;
+
+	target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
+
+	/*
+	 * we never get target_cntr < 0 since this funciton is only called in
+	 * pmc_count for now but we should check anyways.
+	 */
+	return (target_cntr >= 0 &&
+			(adev->df_perfmon_config_assign_mask[target_cntr]
+			& DEFERRED_ARM_MASK));
+
+}
+
 /* release performance counter */
 static void df_v3_6_pmc_release_cntr(struct amdgpu_device *adev,
 				     uint64_t config)
@@ -451,29 +572,33 @@ static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
 			     int is_enable)
 {
 	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
-	int ret = 0;
+	int err = 0, ret = 0;
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
+		if (is_enable)
+			return df_v3_6_pmc_add_cntr(adev, config);
 
 		df_v3_6_reset_perfmon_cntr(adev, config);
 
-		if (is_enable) {
-			ret = df_v3_6_pmc_add_cntr(adev, config);
-		} else {
-			ret = df_v3_6_pmc_get_ctrl_settings(adev,
+		ret = df_v3_6_pmc_get_ctrl_settings(adev,
 					config,
 					&lo_base_addr,
 					&hi_base_addr,
 					&lo_val,
 					&hi_val);
 
-			if (ret)
-				return ret;
+		if (ret)
+			return ret;
 
-			df_v3_6_perfmon_wreg(adev, lo_base_addr, lo_val,
-					hi_base_addr, hi_val);
-		}
+		err = df_v3_6_perfmon_arm_with_retry(adev,
+						     lo_base_addr,
+						     lo_val,
+						     hi_base_addr,
+						     hi_val);
+
+		if (err)
+			ret = df_v3_6_pmc_set_deferred(adev, config, true);
 
 		break;
 	default:
@@ -501,7 +626,7 @@ static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config,
 		if (ret)
 			return ret;
 
-		df_v3_6_perfmon_wreg(adev, lo_base_addr, 0, hi_base_addr, 0);
+		df_v3_6_reset_perfmon_cntr(adev, config);
 
 		if (is_disable)
 			df_v3_6_pmc_release_cntr(adev, config);
@@ -518,18 +643,29 @@ static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
 				  uint64_t config,
 				  uint64_t *count)
 {
-	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
+	uint32_t lo_base_addr, hi_base_addr, lo_val = 0, hi_val = 0;
 	*count = 0;
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
-
 		df_v3_6_pmc_get_read_settings(adev, config, &lo_base_addr,
 				      &hi_base_addr);
 
 		if ((lo_base_addr == 0) || (hi_base_addr == 0))
 			return;
 
+		/* rearm the counter or throw away count value on failure */
+		if (df_v3_6_pmc_is_deferred(adev, config)) {
+			int rearm_err = df_v3_6_perfmon_arm_with_status(adev,
+							lo_base_addr, lo_val,
+							hi_base_addr, hi_val);
+
+			if (rearm_err)
+				return;
+
+			df_v3_6_pmc_set_deferred(adev, config, false);
+		}
+
 		df_v3_6_perfmon_rreg(adev, lo_base_addr, &lo_val,
 				hi_base_addr, &hi_val);
 
@@ -542,7 +678,6 @@ static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
 			 config, lo_base_addr, hi_base_addr, lo_val, hi_val);
 
 		break;
-
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ba9e53a1abc3..874f641de281 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -40,6 +40,7 @@
 #include "ivsrcid/gfx/irqsrcs_gfx_10_1.h"
 
 #include "soc15.h"
+#include "soc15d.h"
 #include "soc15_common.h"
 #include "clearstate_gfx10.h"
 #include "v10_structs.h"
@@ -50,9 +51,6 @@
  * Navi10 has two graphic rings to share each graphic pipe.
  * 1. Primary ring
  * 2. Async ring
- *
- * In bring-up phase, it just used primary ring so set gfx ring number as 1 at
- * first.
  */
 #define GFX10_NUM_GFX_RINGS	2
 #define GFX10_MEC_HPD_SIZE	2048
@@ -123,7 +121,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000800, 0x00000820),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL, 0x001f0000, 0x00070104),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x001f0000, 0x00070104),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000100, 0x00000130),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
@@ -171,7 +169,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000800, 0x00000820),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL, 0x001f0000, 0x00070105),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x001f0000, 0x00070105),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000133, 0x00000130),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
@@ -348,15 +346,29 @@ static void gfx10_kiq_query_status(struct amdgpu_ring *kiq_ring,
 	amdgpu_ring_write(kiq_ring, upper_32_bits(seq));
 }
 
+static void gfx10_kiq_invalidate_tlbs(struct amdgpu_ring *kiq_ring,
+				uint16_t pasid, uint32_t flush_type,
+				bool all_hub)
+{
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
+			PACKET3_INVALIDATE_TLBS_ALL_HUB(all_hub) |
+			PACKET3_INVALIDATE_TLBS_PASID(pasid) |
+			PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(flush_type));
+}
+
 static const struct kiq_pm4_funcs gfx_v10_0_kiq_pm4_funcs = {
 	.kiq_set_resources = gfx10_kiq_set_resources,
 	.kiq_map_queues = gfx10_kiq_map_queues,
 	.kiq_unmap_queues = gfx10_kiq_unmap_queues,
 	.kiq_query_status = gfx10_kiq_query_status,
+	.kiq_invalidate_tlbs = gfx10_kiq_invalidate_tlbs,
 	.set_resources_size = 8,
 	.map_queues_size = 7,
 	.unmap_queues_size = 6,
 	.query_status_size = 7,
+	.invalidate_tlbs_size = 12,
 };
 
 static void gfx_v10_0_set_kiq_pm4_funcs(struct amdgpu_device *adev)
@@ -474,18 +486,10 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)
 		else
 			udelay(1);
 	}
-	if (i < adev->usec_timeout) {
-		if (amdgpu_emu_mode == 1)
-			DRM_INFO("ring test on %d succeeded in %d msecs\n",
-				 ring->idx, i);
-		else
-			DRM_INFO("ring test on %d succeeded in %d usecs\n",
-				 ring->idx, i);
-	} else {
-		DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
-			  ring->idx, scratch, tmp);
-		r = -EINVAL;
-	}
+
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
 	amdgpu_gfx_scratch_free(adev, scratch);
 
 	return r;
@@ -535,14 +539,10 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 
 	tmp = RREG32(scratch);
-	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+	if (tmp == 0xDEADBEEF)
 		r = 0;
-	} else {
-		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
-			  scratch, tmp);
+	else
 		r = -EINVAL;
-	}
 err2:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
@@ -591,8 +591,7 @@ static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev)
 	}
 
 	if (adev->gfx.cp_fw_write_wait == false)
-		DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
-			      GRBM requires 1-cycle delay in cp firmware\n");
+		DRM_WARN_ONCE("CP firmware version too old, please update!");
 }
 
 
@@ -617,11 +616,29 @@ static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
 			le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
 }
 
+static bool gfx_v10_0_navi10_gfxoff_should_enable(struct amdgpu_device *adev)
+{
+	bool ret = false;
+
+	switch (adev->pdev->revision) {
+	case 0xc2:
+	case 0xc3:
+		ret = true;
+		break;
+	default:
+		ret = false;
+		break;
+	}
+
+	return ret ;
+}
+
 static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
-		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+		if (!gfx_v10_0_navi10_gfxoff_should_enable(adev))
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		break;
 	default:
 		break;
@@ -805,10 +822,11 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G];
 		info->ucode_id = AMDGPU_UCODE_ID_RLC_G;
 		info->fw = adev->gfx.rlc_fw;
-		header = (const struct common_firmware_header *)info->fw->data;
-		adev->firmware.fw_size +=
-			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
-
+		if (info->fw) {
+			header = (const struct common_firmware_header *)info->fw->data;
+			adev->firmware.fw_size +=
+				ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+		}
 		if (adev->gfx.rlc.is_rlc_v2_1 &&
 		    adev->gfx.rlc.save_restore_list_cntl_size_bytes &&
 		    adev->gfx.rlc.save_restore_list_gpm_size_bytes &&
@@ -1948,7 +1966,7 @@ static int gfx_v10_0_parse_rlc_toc(struct amdgpu_device *adev)
 		rlc_autoload_info[rlc_toc->id].size = rlc_toc->size * 4;
 
 		rlc_toc++;
-	};
+	}
 
 	return 0;
 }
@@ -3319,8 +3337,11 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_ring *ring)
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
-	/* activate the queue */
-	mqd->cp_hqd_active = 1;
+	/* map_queues packet doesn't need activate the queue,
+	 * so only kiq need set this field.
+	 */
+	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+		mqd->cp_hqd_active = 1;
 
 	return 0;
 }
@@ -3591,23 +3612,16 @@ static int gfx_v10_0_cp_resume(struct amdgpu_device *adev)
 
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
 		ring = &adev->gfx.gfx_ring[i];
-		DRM_INFO("gfx %d ring me %d pipe %d q %d\n",
-			 i, ring->me, ring->pipe, ring->queue);
-		r = amdgpu_ring_test_ring(ring);
-		if (r) {
-			ring->sched.ready = false;
+		r = amdgpu_ring_test_helper(ring);
+		if (r)
 			return r;
-		}
 	}
 
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		ring = &adev->gfx.compute_ring[i];
-		ring->sched.ready = true;
-		DRM_INFO("compute ring %d mec %d pipe %d q %d\n",
-			 i, ring->me, ring->pipe, ring->queue);
-		r = amdgpu_ring_test_ring(ring);
+		r = amdgpu_ring_test_helper(ring);
 		if (r)
-			ring->sched.ready = false;
+			return r;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 7f0a63628c43..31f44d05e606 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -1576,7 +1576,7 @@ static void gfx_v6_0_config_init(struct amdgpu_device *adev)
 static void gfx_v6_0_constants_init(struct amdgpu_device *adev)
 {
 	u32 gb_addr_config = 0;
-	u32 mc_shared_chmap, mc_arb_ramcfg;
+	u32 mc_arb_ramcfg;
 	u32 sx_debug_1;
 	u32 hdp_host_path_cntl;
 	u32 tmp;
@@ -1678,7 +1678,6 @@ static void gfx_v6_0_constants_init(struct amdgpu_device *adev)
 
 	WREG32(mmBIF_FB_EN, BIF_FB_EN__FB_READ_EN_MASK | BIF_FB_EN__FB_WRITE_EN_MASK);
 
-	mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
 	adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
 	mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index d92e92e5d50b..8f20a5dd44fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4258,7 +4258,7 @@ static int gfx_v7_0_late_init(void *handle)
 static void gfx_v7_0_gpu_early_init(struct amdgpu_device *adev)
 {
 	u32 gb_addr_config;
-	u32 mc_shared_chmap, mc_arb_ramcfg;
+	u32 mc_arb_ramcfg;
 	u32 dimm00_addr_map, dimm01_addr_map, dimm10_addr_map, dimm11_addr_map;
 	u32 tmp;
 
@@ -4335,7 +4335,6 @@ static void gfx_v7_0_gpu_early_init(struct amdgpu_device *adev)
 		break;
 	}
 
-	mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
 	adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
 	mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 52a647d7022d..46f0533ba43f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1677,7 +1677,7 @@ fail:
 static int gfx_v8_0_gpu_early_init(struct amdgpu_device *adev)
 {
 	u32 gb_addr_config;
-	u32 mc_shared_chmap, mc_arb_ramcfg;
+	u32 mc_arb_ramcfg;
 	u32 dimm00_addr_map, dimm01_addr_map, dimm10_addr_map, dimm11_addr_map;
 	u32 tmp;
 	int ret;
@@ -1817,7 +1817,6 @@ static int gfx_v8_0_gpu_early_init(struct amdgpu_device *adev)
 		break;
 	}
 
-	mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
 	adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
 	mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
 
@@ -4559,8 +4558,11 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_eop_wptr_mem = RREG32(mmCP_HQD_EOP_WPTR_MEM);
 	mqd->cp_hqd_eop_dones = RREG32(mmCP_HQD_EOP_DONES);
 
-	/* activate the queue */
-	mqd->cp_hqd_active = 1;
+	/* map_queues packet doesn't need activate the queue,
+	 * so only kiq need set this field.
+	 */
+	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+		mqd->cp_hqd_active = 1;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 97105a5bb246..46ab46757b25 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -131,18 +131,6 @@ MODULE_FIRMWARE("amdgpu/renoir_rlc.bin");
 #define mmTCP_CHAN_STEER_5_ARCT								0x0b0c
 #define mmTCP_CHAN_STEER_5_ARCT_BASE_IDX							0
 
-struct ras_gfx_subblock_reg {
-	const char *name;
-	uint32_t hwip;
-	uint32_t inst;
-	uint32_t seg;
-	uint32_t reg_offset;
-	uint32_t sec_count_mask;
-	uint32_t sec_count_shift;
-	uint32_t ded_count_mask;
-	uint32_t ded_count_shift;
-};
-
 enum ta_ras_gfx_subblock {
 	/*CPC*/
 	TA_RAS_BLOCK__GFX_CPC_INDEX_START = 0,
@@ -751,6 +739,134 @@ static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 static int gfx_v9_0_ras_error_inject(struct amdgpu_device *adev,
 				     void *inject_if);
 
+static void gfx_v9_0_kiq_set_resources(struct amdgpu_ring *kiq_ring,
+				uint64_t queue_mask)
+{
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
+	amdgpu_ring_write(kiq_ring,
+		PACKET3_SET_RESOURCES_VMID_MASK(0) |
+		/* vmid_mask:0* queue_type:0 (KIQ) */
+		PACKET3_SET_RESOURCES_QUEUE_TYPE(0));
+	amdgpu_ring_write(kiq_ring,
+			lower_32_bits(queue_mask));	/* queue mask lo */
+	amdgpu_ring_write(kiq_ring,
+			upper_32_bits(queue_mask));	/* queue mask hi */
+	amdgpu_ring_write(kiq_ring, 0);	/* gws mask lo */
+	amdgpu_ring_write(kiq_ring, 0);	/* gws mask hi */
+	amdgpu_ring_write(kiq_ring, 0);	/* oac mask */
+	amdgpu_ring_write(kiq_ring, 0);	/* gds heap base:0, gds heap size:0 */
+}
+
+static void gfx_v9_0_kiq_map_queues(struct amdgpu_ring *kiq_ring,
+				 struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = kiq_ring->adev;
+	uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
+	uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
+	/* Q_sel:0, vmid:0, vidmem: 1, engine:0, num_Q:1*/
+	amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
+			 PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
+			 PACKET3_MAP_QUEUES_VMID(0) | /* VMID */
+			 PACKET3_MAP_QUEUES_QUEUE(ring->queue) |
+			 PACKET3_MAP_QUEUES_PIPE(ring->pipe) |
+			 PACKET3_MAP_QUEUES_ME((ring->me == 1 ? 0 : 1)) |
+			 /*queue_type: normal compute queue */
+			 PACKET3_MAP_QUEUES_QUEUE_TYPE(0) |
+			 /* alloc format: all_on_one_pipe */
+			 PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) |
+			 PACKET3_MAP_QUEUES_ENGINE_SEL(eng_sel) |
+			 /* num_queues: must be 1 */
+			 PACKET3_MAP_QUEUES_NUM_QUEUES(1));
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_MAP_QUEUES_DOORBELL_OFFSET(ring->doorbell_index));
+	amdgpu_ring_write(kiq_ring, lower_32_bits(mqd_addr));
+	amdgpu_ring_write(kiq_ring, upper_32_bits(mqd_addr));
+	amdgpu_ring_write(kiq_ring, lower_32_bits(wptr_addr));
+	amdgpu_ring_write(kiq_ring, upper_32_bits(wptr_addr));
+}
+
+static void gfx_v9_0_kiq_unmap_queues(struct amdgpu_ring *kiq_ring,
+				   struct amdgpu_ring *ring,
+				   enum amdgpu_unmap_queues_action action,
+				   u64 gpu_addr, u64 seq)
+{
+	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_UNMAP_QUEUES, 4));
+	amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
+			  PACKET3_UNMAP_QUEUES_ACTION(action) |
+			  PACKET3_UNMAP_QUEUES_QUEUE_SEL(0) |
+			  PACKET3_UNMAP_QUEUES_ENGINE_SEL(eng_sel) |
+			  PACKET3_UNMAP_QUEUES_NUM_QUEUES(1));
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_UNMAP_QUEUES_DOORBELL_OFFSET0(ring->doorbell_index));
+
+	if (action == PREEMPT_QUEUES_NO_UNMAP) {
+		amdgpu_ring_write(kiq_ring, lower_32_bits(gpu_addr));
+		amdgpu_ring_write(kiq_ring, upper_32_bits(gpu_addr));
+		amdgpu_ring_write(kiq_ring, seq);
+	} else {
+		amdgpu_ring_write(kiq_ring, 0);
+		amdgpu_ring_write(kiq_ring, 0);
+		amdgpu_ring_write(kiq_ring, 0);
+	}
+}
+
+static void gfx_v9_0_kiq_query_status(struct amdgpu_ring *kiq_ring,
+				   struct amdgpu_ring *ring,
+				   u64 addr,
+				   u64 seq)
+{
+	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_QUERY_STATUS, 5));
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_QUERY_STATUS_CONTEXT_ID(0) |
+			  PACKET3_QUERY_STATUS_INTERRUPT_SEL(0) |
+			  PACKET3_QUERY_STATUS_COMMAND(2));
+	/* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_QUERY_STATUS_DOORBELL_OFFSET(ring->doorbell_index) |
+			PACKET3_QUERY_STATUS_ENG_SEL(eng_sel));
+	amdgpu_ring_write(kiq_ring, lower_32_bits(addr));
+	amdgpu_ring_write(kiq_ring, upper_32_bits(addr));
+	amdgpu_ring_write(kiq_ring, lower_32_bits(seq));
+	amdgpu_ring_write(kiq_ring, upper_32_bits(seq));
+}
+
+static void gfx_v9_0_kiq_invalidate_tlbs(struct amdgpu_ring *kiq_ring,
+				uint16_t pasid, uint32_t flush_type,
+				bool all_hub)
+{
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
+			PACKET3_INVALIDATE_TLBS_ALL_HUB(all_hub) |
+			PACKET3_INVALIDATE_TLBS_PASID(pasid) |
+			PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(flush_type));
+}
+
+static const struct kiq_pm4_funcs gfx_v9_0_kiq_pm4_funcs = {
+	.kiq_set_resources = gfx_v9_0_kiq_set_resources,
+	.kiq_map_queues = gfx_v9_0_kiq_map_queues,
+	.kiq_unmap_queues = gfx_v9_0_kiq_unmap_queues,
+	.kiq_query_status = gfx_v9_0_kiq_query_status,
+	.kiq_invalidate_tlbs = gfx_v9_0_kiq_invalidate_tlbs,
+	.set_resources_size = 8,
+	.map_queues_size = 7,
+	.unmap_queues_size = 6,
+	.query_status_size = 7,
+	.invalidate_tlbs_size = 12,
+};
+
+static void gfx_v9_0_set_kiq_pm4_funcs(struct amdgpu_device *adev)
+{
+	adev->gfx.kiq.pmf = &gfx_v9_0_kiq_pm4_funcs;
+}
+
 static void gfx_v9_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
@@ -991,8 +1107,7 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev)
 	    (adev->gfx.mec_feature_version < 46) ||
 	    (adev->gfx.pfp_fw_version < 0x000000b7) ||
 	    (adev->gfx.pfp_feature_version < 46))
-		DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
-			      GRBM requires 1-cycle delay in cp firmware\n");
+		DRM_WARN_ONCE("CP firmware version too old, please update!");
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
@@ -3119,74 +3234,6 @@ static void gfx_v9_0_kiq_setting(struct amdgpu_ring *ring)
 	WREG32_SOC15_RLC(GC, 0, mmRLC_CP_SCHEDULERS, tmp);
 }
 
-static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev)
-{
-	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
-	uint64_t queue_mask = 0;
-	int r, i;
-
-	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
-		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
-			continue;
-
-		/* This situation may be hit in the future if a new HW
-		 * generation exposes more than 64 queues. If so, the
-		 * definition of queue_mask needs updating */
-		if (WARN_ON(i >= (sizeof(queue_mask)*8))) {
-			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
-			break;
-		}
-
-		queue_mask |= (1ull << i);
-	}
-
-	r = amdgpu_ring_alloc(kiq_ring, (7 * adev->gfx.num_compute_rings) + 8);
-	if (r) {
-		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
-		return r;
-	}
-
-	/* set resources */
-	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
-	amdgpu_ring_write(kiq_ring, PACKET3_SET_RESOURCES_VMID_MASK(0) |
-			  PACKET3_SET_RESOURCES_QUEUE_TYPE(0));	/* vmid_mask:0 queue_type:0 (KIQ) */
-	amdgpu_ring_write(kiq_ring, lower_32_bits(queue_mask));	/* queue mask lo */
-	amdgpu_ring_write(kiq_ring, upper_32_bits(queue_mask));	/* queue mask hi */
-	amdgpu_ring_write(kiq_ring, 0);	/* gws mask lo */
-	amdgpu_ring_write(kiq_ring, 0);	/* gws mask hi */
-	amdgpu_ring_write(kiq_ring, 0);	/* oac mask */
-	amdgpu_ring_write(kiq_ring, 0);	/* gds heap base:0, gds heap size:0 */
-	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
-		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
-		uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
-		uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
-
-		amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
-		/* Q_sel:0, vmid:0, vidmem: 1, engine:0, num_Q:1*/
-		amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
-				  PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
-				  PACKET3_MAP_QUEUES_VMID(0) | /* VMID */
-				  PACKET3_MAP_QUEUES_QUEUE(ring->queue) |
-				  PACKET3_MAP_QUEUES_PIPE(ring->pipe) |
-				  PACKET3_MAP_QUEUES_ME((ring->me == 1 ? 0 : 1)) |
-				  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
-				  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
-				  PACKET3_MAP_QUEUES_ENGINE_SEL(0) | /* engine_sel: compute */
-				  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
-		amdgpu_ring_write(kiq_ring, PACKET3_MAP_QUEUES_DOORBELL_OFFSET(ring->doorbell_index));
-		amdgpu_ring_write(kiq_ring, lower_32_bits(mqd_addr));
-		amdgpu_ring_write(kiq_ring, upper_32_bits(mqd_addr));
-		amdgpu_ring_write(kiq_ring, lower_32_bits(wptr_addr));
-		amdgpu_ring_write(kiq_ring, upper_32_bits(wptr_addr));
-	}
-
-	r = amdgpu_ring_test_helper(kiq_ring);
-	if (r)
-		DRM_ERROR("KCQ enable failed\n");
-
-	return r;
-}
-
 static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -3323,8 +3370,11 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
-	/* activate the queue */
-	mqd->cp_hqd_active = 1;
+	/* map_queues packet doesn't need activate the queue,
+	 * so only kiq need set this field.
+	 */
+	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+		mqd->cp_hqd_active = 1;
 
 	return 0;
 }
@@ -3593,7 +3643,7 @@ static int gfx_v9_0_kcq_resume(struct amdgpu_device *adev)
 			goto done;
 	}
 
-	r = gfx_v9_0_kiq_kcq_enable(adev);
+	r = amdgpu_gfx_enable_kcq(adev);
 done:
 	return r;
 }
@@ -3650,6 +3700,23 @@ static int gfx_v9_0_cp_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
+static void gfx_v9_0_init_tcp_config(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	if (adev->asic_type != CHIP_ARCTURUS)
+		return;
+
+	tmp = RREG32_SOC15(GC, 0, mmTCP_ADDR_CONFIG);
+	tmp = REG_SET_FIELD(tmp, TCP_ADDR_CONFIG, ENABLE64KHASH,
+				adev->df.hash_status.hash_64k);
+	tmp = REG_SET_FIELD(tmp, TCP_ADDR_CONFIG, ENABLE2MHASH,
+				adev->df.hash_status.hash_2m);
+	tmp = REG_SET_FIELD(tmp, TCP_ADDR_CONFIG, ENABLE1GHASH,
+				adev->df.hash_status.hash_1g);
+	WREG32_SOC15(GC, 0, mmTCP_ADDR_CONFIG, tmp);
+}
+
 static void gfx_v9_0_cp_enable(struct amdgpu_device *adev, bool enable)
 {
 	if (adev->asic_type != CHIP_ARCTURUS)
@@ -3667,6 +3734,8 @@ static int gfx_v9_0_hw_init(void *handle)
 
 	gfx_v9_0_constants_init(adev);
 
+	gfx_v9_0_init_tcp_config(adev);
+
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
 		return r;
@@ -3678,36 +3747,6 @@ static int gfx_v9_0_hw_init(void *handle)
 	return r;
 }
 
-static int gfx_v9_0_kcq_disable(struct amdgpu_device *adev)
-{
-	int r, i;
-	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
-
-	r = amdgpu_ring_alloc(kiq_ring, 6 * adev->gfx.num_compute_rings);
-	if (r)
-		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
-
-	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
-		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
-
-		amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_UNMAP_QUEUES, 4));
-		amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
-						PACKET3_UNMAP_QUEUES_ACTION(1) | /* RESET_QUEUES */
-						PACKET3_UNMAP_QUEUES_QUEUE_SEL(0) |
-						PACKET3_UNMAP_QUEUES_ENGINE_SEL(0) |
-						PACKET3_UNMAP_QUEUES_NUM_QUEUES(1));
-		amdgpu_ring_write(kiq_ring, PACKET3_UNMAP_QUEUES_DOORBELL_OFFSET0(ring->doorbell_index));
-		amdgpu_ring_write(kiq_ring, 0);
-		amdgpu_ring_write(kiq_ring, 0);
-		amdgpu_ring_write(kiq_ring, 0);
-	}
-	r = amdgpu_ring_test_helper(kiq_ring);
-	if (r)
-		DRM_ERROR("KCQ disable failed\n");
-
-	return r;
-}
-
 static int gfx_v9_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -3719,7 +3758,7 @@ static int gfx_v9_0_hw_fini(void *handle)
 	/* DF freeze and kcq disable will fail */
 	if (!amdgpu_ras_intr_triggered())
 		/* disable KCQ to avoid CPC touch memory not valid anymore */
-		gfx_v9_0_kcq_disable(adev);
+		amdgpu_gfx_disable_kcq(adev);
 
 	if (amdgpu_sriov_vf(adev)) {
 		gfx_v9_0_cp_gfx_enable(adev, false);
@@ -3936,30 +3975,58 @@ static const u32 sgpr_init_compute_shader[] =
 	0xbe800080, 0xbf810000,
 };
 
+/* When below register arrays changed, please update gpr_reg_size,
+  and sec_ded_counter_reg_size in function gfx_v9_0_do_edc_gpr_workarounds,
+  to cover all gfx9 ASICs */
 static const struct soc15_reg_entry vgpr_init_regs[] = {
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x0000000 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 0x40 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 4 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Z), 1 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x3f },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x400000 },  /* 64KB LDS */
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0xffffffff },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0xffffffff },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE2), 0xffffffff },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE3), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x1000000 }, /* CU_GROUP_COUNT=1 */
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 256*2 },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 1 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE4), 0xffffffff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE5), 0xffffffff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE6), 0xffffffff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE7), 0xffffffff },
+};
+
+static const struct soc15_reg_entry sgpr1_init_regs[] = {
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x0000000 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 0x40 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 8 },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Z), 1 },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x100007f }, /* VGPRS=15 (256 logical VGPRs, SGPRS=1 (16 SGPRs, BULKY=1 */
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x400000 },  /* 64KB LDS */
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x240 }, /* (80 GPRS) */
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x0 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE2), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE3), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE4), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE5), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE6), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE7), 0x000000ff },
 };
 
-static const struct soc15_reg_entry sgpr_init_regs[] = {
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE2), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE3), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x1000000 }, /* CU_GROUP_COUNT=1 */
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 256*2 },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 1 },
+static const struct soc15_reg_entry sgpr2_init_regs[] = {
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x0000000 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 0x40 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 8 },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Z), 1 },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x340 }, /* SGPRS=13 (112 GPRS) */
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x240 }, /* (80 GPRS) */
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x0 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE2), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE3), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE4), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE5), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE6), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE7), 0x0000ff00 },
 };
 
 static const struct soc15_reg_entry sec_ded_counter_registers[] = {
@@ -3996,6 +4063,7 @@ static const struct soc15_reg_entry sec_ded_counter_registers[] = {
    { SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2), 0, 1, 16},
    { SOC15_REG_ENTRY(GC, 0, mmTCA_EDC_CNT), 0, 1, 2},
    { SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 0, 4, 6},
+   { SOC15_REG_ENTRY(HDP, 0, mmHDP_EDC_CNT), 0, 1, 1},
 };
 
 static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)
@@ -4054,6 +4122,12 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 	unsigned total_size, vgpr_offset, sgpr_offset;
 	u64 gpu_addr;
 
+	int compute_dim_x = adev->gfx.config.max_shader_engines *
+						adev->gfx.config.max_cu_per_sh *
+						adev->gfx.config.max_sh_per_se;
+	int sgpr_work_group_size = 5;
+	int gpr_reg_size = compute_dim_x / 16 + 6;
+
 	/* only support when RAS is enabled */
 	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
 		return 0;
@@ -4063,9 +4137,11 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 		return 0;
 
 	total_size =
-		((ARRAY_SIZE(vgpr_init_regs) * 3) + 4 + 5 + 2) * 4;
+		(gpr_reg_size * 3 + 4 + 5 + 2) * 4; /* VGPRS */
 	total_size +=
-		((ARRAY_SIZE(sgpr_init_regs) * 3) + 4 + 5 + 2) * 4;
+		(gpr_reg_size * 3 + 4 + 5 + 2) * 4; /* SGPRS1 */
+	total_size +=
+		(gpr_reg_size * 3 + 4 + 5 + 2) * 4; /* SGPRS2 */
 	total_size = ALIGN(total_size, 256);
 	vgpr_offset = total_size;
 	total_size += ALIGN(sizeof(vgpr_init_compute_shader), 256);
@@ -4092,7 +4168,7 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 
 	/* VGPR */
 	/* write the register state for the compute dispatch */
-	for (i = 0; i < ARRAY_SIZE(vgpr_init_regs); i++) {
+	for (i = 0; i < gpr_reg_size; i++) {
 		ib.ptr[ib.length_dw++] = PACKET3(PACKET3_SET_SH_REG, 1);
 		ib.ptr[ib.length_dw++] = SOC15_REG_ENTRY_OFFSET(vgpr_init_regs[i])
 								- PACKET3_SET_SH_REG_START;
@@ -4108,7 +4184,35 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 
 	/* write dispatch packet */
 	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_DISPATCH_DIRECT, 3);
-	ib.ptr[ib.length_dw++] = 128; /* x */
+	ib.ptr[ib.length_dw++] = compute_dim_x; /* x */
+	ib.ptr[ib.length_dw++] = 1; /* y */
+	ib.ptr[ib.length_dw++] = 1; /* z */
+	ib.ptr[ib.length_dw++] =
+		REG_SET_FIELD(0, COMPUTE_DISPATCH_INITIATOR, COMPUTE_SHADER_EN, 1);
+
+	/* write CS partial flush packet */
+	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_EVENT_WRITE, 0);
+	ib.ptr[ib.length_dw++] = EVENT_TYPE(7) | EVENT_INDEX(4);
+
+	/* SGPR1 */
+	/* write the register state for the compute dispatch */
+	for (i = 0; i < gpr_reg_size; i++) {
+		ib.ptr[ib.length_dw++] = PACKET3(PACKET3_SET_SH_REG, 1);
+		ib.ptr[ib.length_dw++] = SOC15_REG_ENTRY_OFFSET(sgpr1_init_regs[i])
+								- PACKET3_SET_SH_REG_START;
+		ib.ptr[ib.length_dw++] = sgpr1_init_regs[i].reg_value;
+	}
+	/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */
+	gpu_addr = (ib.gpu_addr + (u64)sgpr_offset) >> 8;
+	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_SET_SH_REG, 2);
+	ib.ptr[ib.length_dw++] = SOC15_REG_OFFSET(GC, 0, mmCOMPUTE_PGM_LO)
+							- PACKET3_SET_SH_REG_START;
+	ib.ptr[ib.length_dw++] = lower_32_bits(gpu_addr);
+	ib.ptr[ib.length_dw++] = upper_32_bits(gpu_addr);
+
+	/* write dispatch packet */
+	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_DISPATCH_DIRECT, 3);
+	ib.ptr[ib.length_dw++] = compute_dim_x / 2 * sgpr_work_group_size; /* x */
 	ib.ptr[ib.length_dw++] = 1; /* y */
 	ib.ptr[ib.length_dw++] = 1; /* z */
 	ib.ptr[ib.length_dw++] =
@@ -4118,13 +4222,13 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_EVENT_WRITE, 0);
 	ib.ptr[ib.length_dw++] = EVENT_TYPE(7) | EVENT_INDEX(4);
 
-	/* SGPR */
+	/* SGPR2 */
 	/* write the register state for the compute dispatch */
-	for (i = 0; i < ARRAY_SIZE(sgpr_init_regs); i++) {
+	for (i = 0; i < gpr_reg_size; i++) {
 		ib.ptr[ib.length_dw++] = PACKET3(PACKET3_SET_SH_REG, 1);
-		ib.ptr[ib.length_dw++] = SOC15_REG_ENTRY_OFFSET(sgpr_init_regs[i])
+		ib.ptr[ib.length_dw++] = SOC15_REG_ENTRY_OFFSET(sgpr2_init_regs[i])
 								- PACKET3_SET_SH_REG_START;
-		ib.ptr[ib.length_dw++] = sgpr_init_regs[i].reg_value;
+		ib.ptr[ib.length_dw++] = sgpr2_init_regs[i].reg_value;
 	}
 	/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */
 	gpu_addr = (ib.gpu_addr + (u64)sgpr_offset) >> 8;
@@ -4136,7 +4240,7 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 
 	/* write dispatch packet */
 	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_DISPATCH_DIRECT, 3);
-	ib.ptr[ib.length_dw++] = 128; /* x */
+	ib.ptr[ib.length_dw++] = compute_dim_x / 2 * sgpr_work_group_size; /* x */
 	ib.ptr[ib.length_dw++] = 1; /* y */
 	ib.ptr[ib.length_dw++] = 1; /* z */
 	ib.ptr[ib.length_dw++] =
@@ -4189,6 +4293,7 @@ static int gfx_v9_0_early_init(void *handle)
 	else
 		adev->gfx.num_gfx_rings = GFX9_NUM_GFX_RINGS;
 	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	gfx_v9_0_set_kiq_pm4_funcs(adev);
 	gfx_v9_0_set_ring_funcs(adev);
 	gfx_v9_0_set_irq_funcs(adev);
 	gfx_v9_0_set_gds_init(adev);
@@ -4202,10 +4307,6 @@ static int gfx_v9_0_ecc_late_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int r;
 
-	r = amdgpu_gfx_ras_late_init(adev);
-	if (r)
-		return r;
-
 	r = gfx_v9_0_do_edc_gds_workarounds(adev);
 	if (r)
 		return r;
@@ -4215,6 +4316,10 @@ static int gfx_v9_0_ecc_late_init(void *handle)
 	if (r)
 		return r;
 
+	r = amdgpu_gfx_ras_late_init(adev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -5440,7 +5545,7 @@ static int gfx_v9_0_priv_inst_irq(struct amdgpu_device *adev,
 }
 
 
-static const struct ras_gfx_subblock_reg ras_subblock_regs[] = {
+static const struct soc15_ras_field_entry gc_ras_fields_vg20[] = {
 	{ "CPC_SCRATCH", SOC15_REG_ENTRY(GC, 0, mmCPC_EDC_SCRATCH_CNT),
 	  SOC15_REG_FIELD(CPC_EDC_SCRATCH_CNT, SEC_COUNT),
 	  SOC15_REG_FIELD(CPC_EDC_SCRATCH_CNT, DED_COUNT)
@@ -6099,29 +6204,29 @@ static int __get_ras_error_count(const struct soc15_reg_entry *reg,
 	uint32_t i;
 	uint32_t sec_cnt, ded_cnt;
 
-	for (i = 0; i < ARRAY_SIZE(ras_subblock_regs); i++) {
-		if(ras_subblock_regs[i].reg_offset != reg->reg_offset ||
-			ras_subblock_regs[i].seg != reg->seg ||
-			ras_subblock_regs[i].inst != reg->inst)
+	for (i = 0; i < ARRAY_SIZE(gc_ras_fields_vg20); i++) {
+		if(gc_ras_fields_vg20[i].reg_offset != reg->reg_offset ||
+			gc_ras_fields_vg20[i].seg != reg->seg ||
+			gc_ras_fields_vg20[i].inst != reg->inst)
 			continue;
 
 		sec_cnt = (value &
-				ras_subblock_regs[i].sec_count_mask) >>
-				ras_subblock_regs[i].sec_count_shift;
+				gc_ras_fields_vg20[i].sec_count_mask) >>
+				gc_ras_fields_vg20[i].sec_count_shift;
 		if (sec_cnt) {
 			DRM_INFO("GFX SubBlock %s, Instance[%d][%d], SEC %d\n",
-				ras_subblock_regs[i].name,
+				gc_ras_fields_vg20[i].name,
 				se_id, inst_id,
 				sec_cnt);
 			*sec_count += sec_cnt;
 		}
 
 		ded_cnt = (value &
-				ras_subblock_regs[i].ded_count_mask) >>
-				ras_subblock_regs[i].ded_count_shift;
+				gc_ras_fields_vg20[i].ded_count_mask) >>
+				gc_ras_fields_vg20[i].ded_count_shift;
 		if (ded_cnt) {
 			DRM_INFO("GFX SubBlock %s, Instance[%d][%d], DED %d\n",
-				ras_subblock_regs[i].name,
+				gc_ras_fields_vg20[i].name,
 				se_id, inst_id,
 				ded_cnt);
 			*ded_count += ded_cnt;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index e91bd7945777..1a2f18b908fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -75,40 +75,45 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
 	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
 
-	/* Program the system aperture low logical page number. */
-	WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
-		     min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
-
-	if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8)
-		/*
-		 * Raven2 has a HW issue that it is unable to use the vram which
-		 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
-		 * workaround that increase system aperture high address (add 1)
-		 * to get rid of the VM fault and hardware hang.
-		 */
-		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     max((adev->gmc.fb_end >> 18) + 0x1,
-				 adev->gmc.agp_end >> 18));
-	else
-		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
-
-	/* Set default page address. */
-	value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start
-		+ adev->vm_manager.vram_base_offset;
-	WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB,
-		     (u32)(value >> 12));
-	WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB,
-		     (u32)(value >> 44));
-
-	/* Program "protection fault". */
-	WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
-		     (u32)(adev->dummy_page_addr >> 12));
-	WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
-		     (u32)((u64)adev->dummy_page_addr >> 44));
-
-	WREG32_FIELD15(GC, 0, VM_L2_PROTECTION_FAULT_CNTL2,
-		       ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY, 1);
+	if (!amdgpu_sriov_vf(adev) || adev->asic_type <= CHIP_VEGA10) {
+		/* Program the system aperture low logical page number. */
+		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
+			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
+
+		if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8)
+			/*
+			* Raven2 has a HW issue that it is unable to use the
+			* vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR.
+			* So here is the workaround that increase system
+			* aperture high address (add 1) to get rid of the VM
+			* fault and hardware hang.
+			*/
+			WREG32_SOC15_RLC(GC, 0,
+					 mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+					 max((adev->gmc.fb_end >> 18) + 0x1,
+					     adev->gmc.agp_end >> 18));
+		else
+			WREG32_SOC15_RLC(
+				GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+				max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
+
+		/* Set default page address. */
+		value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start +
+			adev->vm_manager.vram_base_offset;
+		WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB,
+			     (u32)(value >> 12));
+		WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB,
+			     (u32)(value >> 44));
+
+		/* Program "protection fault". */
+		WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
+			     (u32)(adev->dummy_page_addr >> 12));
+		WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
+			     (u32)((u64)adev->dummy_page_addr >> 44));
+
+		WREG32_FIELD15(GC, 0, VM_L2_PROTECTION_FAULT_CNTL2,
+			       ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY, 1);
+	}
 }
 
 static void gfxhub_v1_0_init_tlb_regs(struct amdgpu_device *adev)
@@ -264,7 +269,7 @@ static void gfxhub_v1_0_program_invalidation(struct amdgpu_device *adev)
 
 int gfxhub_v1_0_gart_enable(struct amdgpu_device *adev)
 {
-	if (amdgpu_sriov_vf(adev)) {
+	if (amdgpu_sriov_vf(adev) && adev->asic_type != CHIP_ARCTURUS) {
 		/*
 		 * MC_VM_FB_LOCATION_BASE/TOP is NULL for VF, becuase they are
 		 * VF copy registers so vbios post doesn't program them, for
@@ -280,10 +285,12 @@ int gfxhub_v1_0_gart_enable(struct amdgpu_device *adev)
 	gfxhub_v1_0_init_gart_aperture_regs(adev);
 	gfxhub_v1_0_init_system_aperture_regs(adev);
 	gfxhub_v1_0_init_tlb_regs(adev);
-	gfxhub_v1_0_init_cache_regs(adev);
+	if (!amdgpu_sriov_vf(adev))
+		gfxhub_v1_0_init_cache_regs(adev);
 
 	gfxhub_v1_0_enable_system_domain(adev);
-	gfxhub_v1_0_disable_identity_aperture(adev);
+	if (!amdgpu_sriov_vf(adev))
+		gfxhub_v1_0_disable_identity_aperture(adev);
 	gfxhub_v1_0_setup_vmid_config(adev);
 	gfxhub_v1_0_program_invalidation(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index f5725336a5f2..bbede09983e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -30,6 +30,8 @@
 #include "hdp/hdp_5_0_0_sh_mask.h"
 #include "gc/gc_10_1_0_sh_mask.h"
 #include "mmhub/mmhub_2_0_0_sh_mask.h"
+#include "athub/athub_2_0_0_sh_mask.h"
+#include "athub/athub_2_0_0_offset.h"
 #include "dcn/dcn_2_0_0_offset.h"
 #include "dcn/dcn_2_0_0_sh_mask.h"
 #include "oss/osssys_5_0_0_offset.h"
@@ -37,6 +39,7 @@
 #include "navi10_enum.h"
 
 #include "soc15.h"
+#include "soc15d.h"
 #include "soc15_common.h"
 
 #include "nbio_v2_3.h"
@@ -234,6 +237,19 @@ static bool gmc_v10_0_use_invalidate_semaphore(struct amdgpu_device *adev,
 		(!amdgpu_sriov_vf(adev)));
 }
 
+static bool gmc_v10_0_get_atc_vmid_pasid_mapping_info(
+					struct amdgpu_device *adev,
+					uint8_t vmid, uint16_t *p_pasid)
+{
+	uint32_t value;
+
+	value = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
+		     + vmid);
+	*p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+
+	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -380,6 +396,63 @@ error_alloc:
 	DRM_ERROR("Error flushing GPU TLB using the SDMA (%d)!\n", r);
 }
 
+/**
+ * gmc_v10_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+					uint16_t pasid, uint32_t flush_type,
+					bool all_hub)
+{
+	int vmid, i;
+	signed long r;
+	uint32_t seq;
+	uint16_t queried_pasid;
+	bool ret;
+	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
+
+	if (amdgpu_emu_mode == 0 && ring->sched.ready) {
+		spin_lock(&adev->gfx.kiq.ring_lock);
+		amdgpu_ring_alloc(ring, kiq->pmf->invalidate_tlbs_size);
+		kiq->pmf->kiq_invalidate_tlbs(ring,
+					pasid, flush_type, all_hub);
+		amdgpu_fence_emit_polling(ring, &seq);
+		amdgpu_ring_commit(ring);
+		spin_unlock(&adev->gfx.kiq.ring_lock);
+		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		if (r < 1) {
+			DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+			return -ETIME;
+		}
+
+		return 0;
+	}
+
+	for (vmid = 1; vmid < 16; vmid++) {
+
+		ret = gmc_v10_0_get_atc_vmid_pasid_mapping_info(adev, vmid,
+				&queried_pasid);
+		if (ret	&& queried_pasid == pasid) {
+			if (all_hub) {
+				for (i = 0; i < adev->num_vmhubs; i++)
+					gmc_v10_0_flush_gpu_tlb(adev, vmid,
+							i, 0);
+			} else {
+				gmc_v10_0_flush_gpu_tlb(adev, vmid,
+						AMDGPU_GFXHUB_0, 0);
+			}
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 					     unsigned vmid, uint64_t pd_addr)
 {
@@ -531,6 +604,7 @@ static void gmc_v10_0_get_vm_pte(struct amdgpu_device *adev,
 
 static const struct amdgpu_gmc_funcs gmc_v10_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v10_0_flush_gpu_tlb,
+	.flush_gpu_tlb_pasid = gmc_v10_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v10_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v10_0_emit_pasid_mapping,
 	.map_mtype = gmc_v10_0_map_mtype,
@@ -564,22 +638,18 @@ static int gmc_v10_0_early_init(void *handle)
 static int gmc_v10_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	unsigned vm_inv_eng[AMDGPU_MAX_VMHUBS] = { 4, 4 };
-	unsigned i;
-
-	for(i = 0; i < adev->num_rings; ++i) {
-		struct amdgpu_ring *ring = adev->rings[i];
-		unsigned vmhub = ring->funcs->vmhub;
+	int r;
 
-		ring->vm_inv_eng = vm_inv_eng[vmhub]++;
-		dev_info(adev->dev, "ring %u(%s) uses VM inv eng %u on hub %u\n",
-			 ring->idx, ring->name, ring->vm_inv_eng,
-			 ring->funcs->vmhub);
-	}
+	/*
+	 * Can't free the stolen VGA memory when it might be used for memory
+	 * training again.
+	 */
+	if (!adev->fw_vram_usage.mem_train_support)
+		amdgpu_bo_late_init(adev);
 
-	/* Engine 17 is used for GART flushes */
-	for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i)
-		BUG_ON(vm_inv_eng[i] > 17);
+	r = amdgpu_gmc_allocate_vm_inv_eng(adev);
+	if (r)
+		return r;
 
 	return amdgpu_irq_get(adev, &adev->gmc.vm_fault, 0);
 }
@@ -731,6 +801,10 @@ static int gmc_v10_0_sw_init(void *handle)
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC,
 			      VMC_1_0__SRCID__VM_FAULT,
 			      &adev->gmc.vm_fault);
+
+	if (r)
+		return r;
+
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2,
 			      UTCL2_1_0__SRCID__FAULT,
 			      &adev->gmc.vm_fault);
@@ -743,15 +817,6 @@ static int gmc_v10_0_sw_init(void *handle)
 	 */
 	adev->gmc.mc_mask = 0xffffffffffffULL; /* 48 bit MC */
 
-	/*
-	 * Reserve 8M stolen memory for navi10 like vega10
-	 * TODO: will check if it's really needed on asic.
-	 */
-	if (amdgpu_emu_mode == 1)
-		adev->gmc.stolen_size = 0;
-	else
-		adev->gmc.stolen_size = 9 * 1024 *1024;
-
 	r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(44));
 	if (r) {
 		printk(KERN_WARNING "amdgpu: No suitable DMA available.\n");
@@ -764,6 +829,19 @@ static int gmc_v10_0_sw_init(void *handle)
 
 	adev->gmc.stolen_size = gmc_v10_0_get_vbios_fb_size(adev);
 
+	/*
+	 * In dual GPUs scenario, stolen_size is assigned to zero on the
+	 * secondary GPU, since there is no pre-OS console using that memory.
+	 * Then the bottom region of VRAM was allocated as GTT, unfortunately a
+	 * small region of bottom VRAM was encroached by UMC firmware during
+	 * GDDR6 BIST training, this cause page fault.
+	 * The page fault can be fixed by forcing stolen_size to 3MB, then the
+	 * bottom region of VRAM was allocated as stolen memory, GTT corruption
+	 * avoid.
+	 */
+	adev->gmc.stolen_size = max(adev->gmc.stolen_size,
+				    AMDGPU_STOLEN_BIST_TRAINING_DEFAULT_SIZE);
+
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
 	if (r)
@@ -803,6 +881,13 @@ static void gmc_v10_0_gart_fini(struct amdgpu_device *adev)
 static int gmc_v10_0_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	void *stolen_vga_buf;
+
+	/*
+	 * Free the stolen memory if it wasn't already freed in late_init
+	 * because of memory training.
+	 */
+	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf);
 
 	amdgpu_vm_manager_fini(adev);
 	gmc_v10_0_gart_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index f08e5330642d..19d5b133e1d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -418,6 +418,38 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * gmc_v7_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v7_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+					uint16_t pasid, uint32_t flush_type,
+					bool all_hub)
+{
+	int vmid;
+	unsigned int tmp;
+
+	if (adev->in_gpu_reset)
+		return -EIO;
+
+	for (vmid = 1; vmid < 16; vmid++) {
+
+		tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
+		if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
+			(tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
+			WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
+			RREG32(mmVM_INVALIDATE_RESPONSE);
+			break;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -1333,6 +1365,7 @@ static const struct amd_ip_funcs gmc_v7_0_ip_funcs = {
 
 static const struct amdgpu_gmc_funcs gmc_v7_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v7_0_flush_gpu_tlb,
+	.flush_gpu_tlb_pasid = gmc_v7_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v7_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v7_0_emit_pasid_mapping,
 	.set_prt = gmc_v7_0_set_prt,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 6d96d40fbcb8..27d83204fa2b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -620,6 +620,39 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * gmc_v8_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v8_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+					uint16_t pasid, uint32_t flush_type,
+					bool all_hub)
+{
+	int vmid;
+	unsigned int tmp;
+
+	if (adev->in_gpu_reset)
+		return -EIO;
+
+	for (vmid = 1; vmid < 16; vmid++) {
+
+		tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
+		if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
+			(tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
+			WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
+			RREG32(mmVM_INVALIDATE_RESPONSE);
+			break;
+		}
+	}
+
+	return 0;
+
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -1700,6 +1733,7 @@ static const struct amd_ip_funcs gmc_v8_0_ip_funcs = {
 
 static const struct amdgpu_gmc_funcs gmc_v8_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v8_0_flush_gpu_tlb,
+	.flush_gpu_tlb_pasid = gmc_v8_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v8_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v8_0_emit_pasid_mapping,
 	.set_prt = gmc_v8_0_set_prt,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index a5b68b5e452f..40a496804356 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -38,10 +38,12 @@
 #include "dce/dce_12_0_sh_mask.h"
 #include "vega10_enum.h"
 #include "mmhub/mmhub_1_0_offset.h"
+#include "athub/athub_1_0_sh_mask.h"
 #include "athub/athub_1_0_offset.h"
 #include "oss/osssys_4_0_offset.h"
 
 #include "soc15.h"
+#include "soc15d.h"
 #include "soc15_common.h"
 #include "umc/umc_6_0_sh_mask.h"
 
@@ -207,6 +209,11 @@ static int gmc_v9_0_ecc_interrupt_state(struct amdgpu_device *adev,
 {
 	u32 bits, i, tmp, reg;
 
+	/* Devices newer then VEGA10/12 shall have these programming
+	     sequences performed by PSP BL */
+	if (adev->asic_type >= CHIP_VEGA20)
+		return 0;
+
 	bits = 0x7f;
 
 	switch (state) {
@@ -393,8 +400,10 @@ static void gmc_v9_0_set_irq_funcs(struct amdgpu_device *adev)
 	adev->gmc.vm_fault.num_types = 1;
 	adev->gmc.vm_fault.funcs = &gmc_v9_0_irq_funcs;
 
-	adev->gmc.ecc_irq.num_types = 1;
-	adev->gmc.ecc_irq.funcs = &gmc_v9_0_ecc_funcs;
+	if (!amdgpu_sriov_vf(adev)) {
+		adev->gmc.ecc_irq.num_types = 1;
+		adev->gmc.ecc_irq.funcs = &gmc_v9_0_ecc_funcs;
+	}
 }
 
 static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid,
@@ -434,6 +443,18 @@ static bool gmc_v9_0_use_invalidate_semaphore(struct amdgpu_device *adev,
 		   adev->pdev->device == 0x15d8)));
 }
 
+static bool gmc_v9_0_get_atc_vmid_pasid_mapping_info(struct amdgpu_device *adev,
+					uint8_t vmid, uint16_t *p_pasid)
+{
+	uint32_t value;
+
+	value = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
+		     + vmid);
+	*p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+
+	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -532,6 +553,67 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	DRM_ERROR("Timeout waiting for VM flush ACK!\n");
 }
 
+/**
+ * gmc_v9_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+					uint16_t pasid, uint32_t flush_type,
+					bool all_hub)
+{
+	int vmid, i;
+	signed long r;
+	uint32_t seq;
+	uint16_t queried_pasid;
+	bool ret;
+	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
+
+	if (adev->in_gpu_reset)
+		return -EIO;
+
+	if (ring->sched.ready) {
+		spin_lock(&adev->gfx.kiq.ring_lock);
+		amdgpu_ring_alloc(ring, kiq->pmf->invalidate_tlbs_size);
+		kiq->pmf->kiq_invalidate_tlbs(ring,
+					pasid, flush_type, all_hub);
+		amdgpu_fence_emit_polling(ring, &seq);
+		amdgpu_ring_commit(ring);
+		spin_unlock(&adev->gfx.kiq.ring_lock);
+		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		if (r < 1) {
+			DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+			return -ETIME;
+		}
+
+		return 0;
+	}
+
+	for (vmid = 1; vmid < 16; vmid++) {
+
+		ret = gmc_v9_0_get_atc_vmid_pasid_mapping_info(adev, vmid,
+				&queried_pasid);
+		if (ret && queried_pasid == pasid) {
+			if (all_hub) {
+				for (i = 0; i < adev->num_vmhubs; i++)
+					gmc_v9_0_flush_gpu_tlb(adev, vmid,
+							i, 0);
+			} else {
+				gmc_v9_0_flush_gpu_tlb(adev, vmid,
+						AMDGPU_GFXHUB_0, 0);
+			}
+			break;
+		}
+	}
+
+	return 0;
+
+}
+
 static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 					    unsigned vmid, uint64_t pd_addr)
 {
@@ -693,6 +775,7 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev,
 
 static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v9_0_flush_gpu_tlb,
+	.flush_gpu_tlb_pasid = gmc_v9_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v9_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v9_0_emit_pasid_mapping,
 	.map_mtype = gmc_v9_0_map_mtype,
@@ -715,7 +798,15 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)
 		adev->umc.max_ras_err_cnt_per_query = UMC_V6_1_TOTAL_CHANNEL_NUM;
 		adev->umc.channel_inst_num = UMC_V6_1_CHANNEL_INSTANCE_NUM;
 		adev->umc.umc_inst_num = UMC_V6_1_UMC_INSTANCE_NUM;
-		adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET;
+		adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET_VG20;
+		adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0];
+		adev->umc.funcs = &umc_v6_1_funcs;
+		break;
+	case CHIP_ARCTURUS:
+		adev->umc.max_ras_err_cnt_per_query = UMC_V6_1_TOTAL_CHANNEL_NUM;
+		adev->umc.channel_inst_num = UMC_V6_1_CHANNEL_INSTANCE_NUM;
+		adev->umc.umc_inst_num = UMC_V6_1_UMC_INSTANCE_NUM;
+		adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET_ARCT;
 		adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0];
 		adev->umc.funcs = &umc_v6_1_funcs;
 		break;
@@ -730,6 +821,9 @@ static void gmc_v9_0_set_mmhub_funcs(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		adev->mmhub.funcs = &mmhub_v1_0_funcs;
 		break;
+	case CHIP_ARCTURUS:
+		adev->mmhub.funcs = &mmhub_v9_4_funcs;
+		break;
 	default:
 		break;
 	}
@@ -779,36 +873,6 @@ static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev)
 	}
 }
 
-static int gmc_v9_0_allocate_vm_inv_eng(struct amdgpu_device *adev)
-{
-	struct amdgpu_ring *ring;
-	unsigned vm_inv_engs[AMDGPU_MAX_VMHUBS] =
-		{GFXHUB_FREE_VM_INV_ENGS_BITMAP, MMHUB_FREE_VM_INV_ENGS_BITMAP,
-		GFXHUB_FREE_VM_INV_ENGS_BITMAP};
-	unsigned i;
-	unsigned vmhub, inv_eng;
-
-	for (i = 0; i < adev->num_rings; ++i) {
-		ring = adev->rings[i];
-		vmhub = ring->funcs->vmhub;
-
-		inv_eng = ffs(vm_inv_engs[vmhub]);
-		if (!inv_eng) {
-			dev_err(adev->dev, "no VM inv eng for ring %s\n",
-				ring->name);
-			return -EINVAL;
-		}
-
-		ring->vm_inv_eng = inv_eng - 1;
-		vm_inv_engs[vmhub] &= ~(1 << ring->vm_inv_eng);
-
-		dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
-			 ring->name, ring->vm_inv_eng, ring->funcs->vmhub);
-	}
-
-	return 0;
-}
-
 static int gmc_v9_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -817,7 +881,7 @@ static int gmc_v9_0_late_init(void *handle)
 	if (!gmc_v9_0_keep_stolen_memory(adev))
 		amdgpu_bo_late_init(adev);
 
-	r = gmc_v9_0_allocate_vm_inv_eng(adev);
+	r = amdgpu_gmc_allocate_vm_inv_eng(adev);
 	if (r)
 		return r;
 	/* Check if ecc is available */
@@ -825,11 +889,12 @@ static int gmc_v9_0_late_init(void *handle)
 		switch (adev->asic_type) {
 		case CHIP_VEGA10:
 		case CHIP_VEGA20:
+		case CHIP_ARCTURUS:
 			r = amdgpu_atomfirmware_mem_ecc_supported(adev);
 			if (!r) {
 				DRM_INFO("ECC is not present.\n");
-				if (adev->df_funcs->enable_ecc_force_par_wr_rmw)
-					adev->df_funcs->enable_ecc_force_par_wr_rmw(adev, false);
+				if (adev->df.funcs->enable_ecc_force_par_wr_rmw)
+					adev->df.funcs->enable_ecc_force_par_wr_rmw(adev, false);
 			} else {
 				DRM_INFO("ECC is active.\n");
 			}
@@ -1034,7 +1099,7 @@ static int gmc_v9_0_sw_init(void *handle)
 		else
 			chansize = 128;
 
-		numchan = adev->df_funcs->get_hbm_channel_number(adev);
+		numchan = adev->df.funcs->get_hbm_channel_number(adev);
 		adev->gmc.vram_width = numchan * chansize;
 	}
 
@@ -1100,11 +1165,13 @@ static int gmc_v9_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	/* interrupt sent to DF. */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DF, 0,
-			&adev->gmc.ecc_irq);
-	if (r)
-		return r;
+	if (!amdgpu_sriov_vf(adev)) {
+		/* interrupt sent to DF. */
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DF, 0,
+				      &adev->gmc.ecc_irq);
+		if (r)
+			return r;
+	}
 
 	/* Set the internal MC address mask
 	 * This is the max address of the GPU's
@@ -1290,12 +1357,13 @@ static int gmc_v9_0_hw_init(void *handle)
 	else
 		value = true;
 
-	gfxhub_v1_0_set_fault_enable_default(adev, value);
-	if (adev->asic_type == CHIP_ARCTURUS)
-		mmhub_v9_4_set_fault_enable_default(adev, value);
-	else
-		mmhub_v1_0_set_fault_enable_default(adev, value);
-
+	if (!amdgpu_sriov_vf(adev)) {
+		gfxhub_v1_0_set_fault_enable_default(adev, value);
+		if (adev->asic_type == CHIP_ARCTURUS)
+			mmhub_v9_4_set_fault_enable_default(adev, value);
+		else
+			mmhub_v1_0_set_fault_enable_default(adev, value);
+	}
 	for (i = 0; i < adev->num_vmhubs; ++i)
 		gmc_v9_0_flush_gpu_tlb(adev, 0, i, 0);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
index 971c0840358f..e0585e8c6c1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
@@ -24,24 +24,6 @@
 #ifndef __GMC_V9_0_H__
 #define __GMC_V9_0_H__
 
-	/*
-	 * The latest engine allocation on gfx9 is:
-	 * Engine 2, 3: firmware
-	 * Engine 0, 1, 4~16: amdgpu ring,
-	 *                    subject to change when ring number changes
-	 * Engine 17: Gart flushes
-	 */
-#define GFXHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
-#define MMHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
-
 extern const struct amd_ip_funcs gmc_v9_0_ip_funcs;
 extern const struct amdgpu_ip_block_version gmc_v9_0_ip_block;
-
-/* amdgpu_amdkfd*.c */
-void gfxhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t value);
-void mmhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t value);
-void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, int hubid,
-				uint32_t vmid, uint64_t value);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
new file mode 100644
index 000000000000..0debfd9f428c
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
@@ -0,0 +1,586 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_jpeg.h"
+#include "soc15.h"
+#include "soc15d.h"
+#include "vcn_v1_0.h"
+
+#include "vcn/vcn_1_0_offset.h"
+#include "vcn/vcn_1_0_sh_mask.h"
+
+static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
+static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev);
+
+static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
+{
+	struct amdgpu_device *adev = ring->adev;
+	ring->ring[(*ptr)++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		ring->ring[(*ptr)++] = 0;
+		ring->ring[(*ptr)++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0);
+	} else {
+		ring->ring[(*ptr)++] = reg_offset;
+		ring->ring[(*ptr)++] = PACKETJ(0, 0, 0, PACKETJ_TYPE0);
+	}
+	ring->ring[(*ptr)++] = val;
+}
+
+static void jpeg_v1_0_decode_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	uint32_t reg, reg_offset, val, mask, i;
+
+	// 1st: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW);
+	reg_offset = (reg << 2);
+	val = lower_32_bits(ring->gpu_addr);
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 2nd: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH);
+	reg_offset = (reg << 2);
+	val = upper_32_bits(ring->gpu_addr);
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 3rd to 5th: issue MEM_READ commands
+	for (i = 0; i <= 2; i++) {
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE2);
+		ring->ring[ptr++] = 0;
+	}
+
+	// 6th: program mmUVD_JRBC_RB_CNTL register to enable NO_FETCH and RPTR write ability
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x13;
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 7th: program mmUVD_JRBC_RB_REF_DATA
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA);
+	reg_offset = (reg << 2);
+	val = 0x1;
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 8th: issue conditional register read mmUVD_JRBC_RB_CNTL
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x1;
+	mask = 0x1;
+
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0);
+	ring->ring[ptr++] = 0x01400200;
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0);
+	ring->ring[ptr++] = val;
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		ring->ring[ptr++] = 0;
+		ring->ring[ptr++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3);
+	} else {
+		ring->ring[ptr++] = reg_offset;
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE3);
+	}
+	ring->ring[ptr++] = mask;
+
+	//9th to 21st: insert no-op
+	for (i = 0; i <= 12; i++) {
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
+		ring->ring[ptr++] = 0;
+	}
+
+	//22nd: reset mmUVD_JRBC_RB_RPTR
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_RPTR);
+	reg_offset = (reg << 2);
+	val = 0;
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	//23rd: program mmUVD_JRBC_RB_CNTL to disable no_fetch
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x12;
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t jpeg_v1_0_decode_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t jpeg_v1_0_decode_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void jpeg_v1_0_decode_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+}
+
+/**
+ * jpeg_v1_0_decode_ring_insert_start - insert a start command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a start command to the ring.
+ */
+static void jpeg_v1_0_decode_ring_insert_start(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x80010000);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_insert_end - insert a end command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a end command to the ring.
+ */
+static void jpeg_v1_0_decode_ring_insert_end(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x00010000);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_emit_fence - emit an fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+static void jpeg_v1_0_decode_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				     unsigned flags)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_DATA0), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_DATA1), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_CMD), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x8);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_CMD), 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0xffffffff);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x3fbc);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x1);
+
+	/* emit trap */
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
+	amdgpu_ring_write(ring, 0);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_emit_ib - execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write ring commands to execute the indirect buffer.
+ */
+static void jpeg_v1_0_decode_ring_emit_ib(struct amdgpu_ring *ring,
+					struct amdgpu_job *job,
+					struct amdgpu_ib *ib,
+					uint32_t flags)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_IB_SIZE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, ib->length_dw);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_STATUS), 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
+	amdgpu_ring_write(ring, 0x2);
+}
+
+static void jpeg_v1_0_decode_ring_emit_reg_wait(struct amdgpu_ring *ring,
+					    uint32_t reg, uint32_t val,
+					    uint32_t mask)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, val);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,
+			PACKETJ(0, 0, 0, PACKETJ_TYPE3));
+	}
+	amdgpu_ring_write(ring, mask);
+}
+
+static void jpeg_v1_0_decode_ring_emit_vm_flush(struct amdgpu_ring *ring,
+		unsigned vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
+	uint32_t data0, data1, mask;
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for register write */
+	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+	data1 = lower_32_bits(pd_addr);
+	mask = 0xffffffff;
+	jpeg_v1_0_decode_ring_emit_reg_wait(ring, data0, data1, mask);
+}
+
+static void jpeg_v1_0_decode_ring_emit_wreg(struct amdgpu_ring *ring,
+					uint32_t reg, uint32_t val)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+			((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,
+			PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	}
+	amdgpu_ring_write(ring, val);
+}
+
+static void jpeg_v1_0_decode_ring_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
+static int jpeg_v1_0_set_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	return 0;
+}
+
+static int jpeg_v1_0_process_interrupt(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	DRM_DEBUG("IH: JPEG decode TRAP\n");
+
+	switch (entry->src_id) {
+	case 126:
+		amdgpu_fence_process(&adev->jpeg.inst->ring_dec);
+		break;
+	default:
+		DRM_ERROR("Unhandled interrupt: %d %d\n",
+			  entry->src_id, entry->src_data[0]);
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v1_0_early_init - set function pointers
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Set ring and irq function pointers
+ */
+int jpeg_v1_0_early_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	adev->jpeg.num_jpeg_inst = 1;
+
+	jpeg_v1_0_set_dec_ring_funcs(adev);
+	jpeg_v1_0_set_irq_funcs(adev);
+
+	return 0;
+}
+
+/**
+ * jpeg_v1_0_sw_init - sw init for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ */
+int jpeg_v1_0_sw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring;
+	int r;
+
+	/* JPEG TRAP */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 126, &adev->jpeg.inst->irq);
+	if (r)
+		return r;
+
+	ring = &adev->jpeg.inst->ring_dec;
+	sprintf(ring->name, "jpeg_dec");
+	r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, 0);
+	if (r)
+		return r;
+
+	adev->jpeg.internal.jpeg_pitch = adev->jpeg.inst->external.jpeg_pitch =
+		SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_PITCH);
+
+	return 0;
+}
+
+/**
+ * jpeg_v1_0_sw_fini - sw fini for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * JPEG free up sw allocation
+ */
+void jpeg_v1_0_sw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	amdgpu_ring_fini(&adev->jpeg.inst[0].ring_dec);
+}
+
+/**
+ * jpeg_v1_0_start - start JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Setup and start the JPEG block
+ */
+void jpeg_v1_0_start(struct amdgpu_device *adev, int mode)
+{
+	struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec;
+
+	if (mode == 0) {
+		WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
+				UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
+		WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr));
+		WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR, 0);
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, 0);
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
+	}
+
+	/* initialize wptr */
+	ring->wptr = RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
+
+	/* copy patch commands to the jpeg ring */
+	jpeg_v1_0_decode_ring_set_patch_ring(ring,
+		(ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+}
+
+static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_JPEG,
+	.align_mask = 0xf,
+	.nop = PACKET0(0x81ff, 0),
+	.support_64bit_ptrs = false,
+	.no_user_fence = true,
+	.vmhub = AMDGPU_MMHUB_0,
+	.extra_dw = 64,
+	.get_rptr = jpeg_v1_0_decode_ring_get_rptr,
+	.get_wptr = jpeg_v1_0_decode_ring_get_wptr,
+	.set_wptr = jpeg_v1_0_decode_ring_set_wptr,
+	.emit_frame_size =
+		6 + 6 + /* hdp invalidate / flush */
+		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+		8 + /* jpeg_v1_0_decode_ring_emit_vm_flush */
+		26 + 26 + /* jpeg_v1_0_decode_ring_emit_fence x2 vm fence */
+		6,
+	.emit_ib_size = 22, /* jpeg_v1_0_decode_ring_emit_ib */
+	.emit_ib = jpeg_v1_0_decode_ring_emit_ib,
+	.emit_fence = jpeg_v1_0_decode_ring_emit_fence,
+	.emit_vm_flush = jpeg_v1_0_decode_ring_emit_vm_flush,
+	.test_ring = amdgpu_jpeg_dec_ring_test_ring,
+	.test_ib = amdgpu_jpeg_dec_ring_test_ib,
+	.insert_nop = jpeg_v1_0_decode_ring_nop,
+	.insert_start = jpeg_v1_0_decode_ring_insert_start,
+	.insert_end = jpeg_v1_0_decode_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = vcn_v1_0_ring_begin_use,
+	.end_use = amdgpu_vcn_ring_end_use,
+	.emit_wreg = jpeg_v1_0_decode_ring_emit_wreg,
+	.emit_reg_wait = jpeg_v1_0_decode_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+};
+
+static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev)
+{
+	adev->jpeg.inst->ring_dec.funcs = &jpeg_v1_0_decode_ring_vm_funcs;
+	DRM_INFO("JPEG decode is enabled in VM mode\n");
+}
+
+static const struct amdgpu_irq_src_funcs jpeg_v1_0_irq_funcs = {
+	.set = jpeg_v1_0_set_interrupt_state,
+	.process = jpeg_v1_0_process_interrupt,
+};
+
+static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev)
+{
+	adev->jpeg.inst->irq.funcs = &jpeg_v1_0_irq_funcs;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h
new file mode 100644
index 000000000000..bbf33a6a3972
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __JPEG_V1_0_H__
+#define __JPEG_V1_0_H__
+
+int jpeg_v1_0_early_init(void *handle);
+int jpeg_v1_0_sw_init(void *handle);
+void jpeg_v1_0_sw_fini(void *handle);
+void jpeg_v1_0_start(struct amdgpu_device *adev, int mode);
+
+#endif /*__JPEG_V1_0_H__*/
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
new file mode 100644
index 000000000000..a78292d84854
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -0,0 +1,827 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_jpeg.h"
+#include "amdgpu_pm.h"
+#include "soc15.h"
+#include "soc15d.h"
+
+#include "vcn/vcn_2_0_0_offset.h"
+#include "vcn/vcn_2_0_0_sh_mask.h"
+#include "ivsrcid/vcn/irqsrcs_vcn_2_0.h"
+
+#define mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET 			0x1bfff
+#define mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET				0x4029
+#define mmUVD_JPEG_GPCOM_DATA0_INTERNAL_OFFSET				0x402a
+#define mmUVD_JPEG_GPCOM_DATA1_INTERNAL_OFFSET				0x402b
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET		0x40ea
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x40eb
+#define mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET				0x40cf
+#define mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET				0x40d1
+#define mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET 		0x40e8
+#define mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET		0x40e9
+#define mmUVD_JRBC_IB_SIZE_INTERNAL_OFFSET				0x4082
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET		0x40ec
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x40ed
+#define mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET			0x4085
+#define mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET				0x4084
+#define mmUVD_JRBC_STATUS_INTERNAL_OFFSET				0x4089
+#define mmUVD_JPEG_PITCH_INTERNAL_OFFSET				0x401f
+
+#define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR				0x18000
+
+static void jpeg_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev);
+static void jpeg_v2_0_set_irq_funcs(struct amdgpu_device *adev);
+static int jpeg_v2_0_set_powergating_state(void *handle,
+				enum amd_powergating_state state);
+
+/**
+ * jpeg_v2_0_early_init - set function pointers
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Set ring and irq function pointers
+ */
+static int jpeg_v2_0_early_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	adev->jpeg.num_jpeg_inst = 1;
+
+	jpeg_v2_0_set_dec_ring_funcs(adev);
+	jpeg_v2_0_set_irq_funcs(adev);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_sw_init - sw init for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Load firmware and sw initialization
+ */
+static int jpeg_v2_0_sw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring;
+	int r;
+
+	/* JPEG TRAP */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
+		VCN_2_0__SRCID__JPEG_DECODE, &adev->jpeg.inst->irq);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_sw_init(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_resume(adev);
+	if (r)
+		return r;
+
+	ring = &adev->jpeg.inst->ring_dec;
+	ring->use_doorbell = true;
+	ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1;
+	sprintf(ring->name, "jpeg_dec");
+	r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, 0);
+	if (r)
+		return r;
+
+	adev->jpeg.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
+	adev->jpeg.inst->external.jpeg_pitch = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_PITCH);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_sw_fini - sw fini for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * JPEG suspend and free up sw allocation
+ */
+static int jpeg_v2_0_sw_fini(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_jpeg_suspend(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_sw_fini(adev);
+
+	return r;
+}
+
+/**
+ * jpeg_v2_0_hw_init - start and test JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ */
+static int jpeg_v2_0_hw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec;
+	int r;
+
+	adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+		(adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0);
+
+	r = amdgpu_ring_test_helper(ring);
+	if (!r)
+		DRM_INFO("JPEG decode initialized successfully.\n");
+
+	return r;
+}
+
+/**
+ * jpeg_v2_0_hw_fini - stop the hardware block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Stop the JPEG block, mark ring as not ready any more
+ */
+static int jpeg_v2_0_hw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec;
+
+	if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
+	      RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS))
+		jpeg_v2_0_set_powergating_state(adev, AMD_PG_STATE_GATE);
+
+	ring->sched.ready = false;
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_suspend - suspend JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * HW fini and suspend JPEG block
+ */
+static int jpeg_v2_0_suspend(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = jpeg_v2_0_hw_fini(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_suspend(adev);
+
+	return r;
+}
+
+/**
+ * jpeg_v2_0_resume - resume JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Resume firmware and hw init JPEG block
+ */
+static int jpeg_v2_0_resume(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_jpeg_resume(adev);
+	if (r)
+		return r;
+
+	r = jpeg_v2_0_hw_init(adev);
+
+	return r;
+}
+
+static int jpeg_v2_0_disable_power_gating(struct amdgpu_device *adev)
+{
+	uint32_t data;
+	int r = 0;
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_JPEG) {
+		data = 1 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT;
+		WREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_PGFSM_CONFIG), data);
+
+		SOC15_WAIT_ON_RREG(JPEG, 0,
+			mmUVD_PGFSM_STATUS, UVD_PGFSM_STATUS_UVDJ_PWR_ON,
+			UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK, r);
+
+		if (r) {
+			DRM_ERROR("amdgpu: JPEG disable power gating failed\n");
+			return r;
+		}
+	}
+
+	/* Removing the anti hang mechanism to indicate the UVDJ tile is ON */
+	data = RREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_POWER_STATUS)) & ~0x1;
+	WREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_POWER_STATUS), data);
+
+	return 0;
+}
+
+static int jpeg_v2_0_enable_power_gating(struct amdgpu_device* adev)
+{
+	if (adev->pg_flags & AMD_PG_SUPPORT_JPEG) {
+		uint32_t data;
+		int r = 0;
+
+		data = RREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_POWER_STATUS));
+		data &= ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK;
+		data |=  0x1; //UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_TILES_OFF;
+		WREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_POWER_STATUS), data);
+
+		data = 2 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT;
+		WREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_PGFSM_CONFIG), data);
+
+		SOC15_WAIT_ON_RREG(JPEG, 0, mmUVD_PGFSM_STATUS,
+			(2 << UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT),
+			UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK, r);
+
+		if (r) {
+			DRM_ERROR("amdgpu: JPEG enable power gating failed\n");
+			return r;
+		}
+	}
+
+	return 0;
+}
+
+static void jpeg_v2_0_disable_clock_gating(struct amdgpu_device* adev)
+{
+	uint32_t data;
+
+	data = RREG32_SOC15(JPEG, 0, mmJPEG_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_JPEG_MGCG)
+		data |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data &= ~JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+
+	data |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(JPEG, 0, mmJPEG_CGC_CTRL, data);
+
+	data = RREG32_SOC15(JPEG, 0, mmJPEG_CGC_GATE);
+	data &= ~(JPEG_CGC_GATE__JPEG_DEC_MASK
+		| JPEG_CGC_GATE__JPEG2_DEC_MASK
+		| JPEG_CGC_GATE__JPEG_ENC_MASK
+		| JPEG_CGC_GATE__JMCIF_MASK
+		| JPEG_CGC_GATE__JRBBM_MASK);
+	WREG32_SOC15(JPEG, 0, mmJPEG_CGC_GATE, data);
+}
+
+static void jpeg_v2_0_enable_clock_gating(struct amdgpu_device* adev)
+{
+	uint32_t data;
+
+	data = RREG32_SOC15(JPEG, 0, mmJPEG_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_JPEG_MGCG)
+		data |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data |= 0 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+
+	data |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(JPEG, 0, mmJPEG_CGC_CTRL, data);
+
+	data = RREG32_SOC15(JPEG, 0, mmJPEG_CGC_GATE);
+	data |= (JPEG_CGC_GATE__JPEG_DEC_MASK
+		|JPEG_CGC_GATE__JPEG2_DEC_MASK
+		|JPEG_CGC_GATE__JPEG_ENC_MASK
+		|JPEG_CGC_GATE__JMCIF_MASK
+		|JPEG_CGC_GATE__JRBBM_MASK);
+	WREG32_SOC15(JPEG, 0, mmJPEG_CGC_GATE, data);
+}
+
+/**
+ * jpeg_v2_0_start - start JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Setup and start the JPEG block
+ */
+static int jpeg_v2_0_start(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec;
+	int r;
+
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_jpeg(adev, true);
+
+	/* disable power gating */
+	r = jpeg_v2_0_disable_power_gating(adev);
+	if (r)
+		return r;
+
+	/* JPEG disable CGC */
+	jpeg_v2_0_disable_clock_gating(adev);
+
+	WREG32_SOC15(JPEG, 0, mmJPEG_DEC_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+
+	/* enable JMI channel */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JMI_CNTL), 0,
+		~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+	/* enable System Interrupt for JRBC */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, 0, mmJPEG_SYS_INT_EN),
+		JPEG_SYS_INT_EN__DJRBC_MASK,
+		~JPEG_SYS_INT_EN__DJRBC_MASK);
+
+	WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
+	WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
+		lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
+		upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR, 0);
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, 0);
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
+	ring->wptr = RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_stop - stop JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * stop the JPEG block
+ */
+static int jpeg_v2_0_stop(struct amdgpu_device *adev)
+{
+	int r;
+
+	/* reset JMI */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JMI_CNTL),
+		UVD_JMI_CNTL__SOFT_RESET_MASK,
+		~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+	/* enable JPEG CGC */
+	jpeg_v2_0_enable_clock_gating(adev);
+
+	/* enable power gating */
+	r = jpeg_v2_0_enable_power_gating(adev);
+	if (r)
+		return r;
+
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_jpeg(adev, false);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_dec_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t jpeg_v2_0_dec_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t jpeg_v2_0_dec_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->use_doorbell)
+		return adev->wb.wb[ring->wptr_offs];
+	else
+		return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void jpeg_v2_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->use_doorbell) {
+		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
+	} else {
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+	}
+}
+
+/**
+ * jpeg_v2_0_dec_ring_insert_start - insert a start command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a start command to the ring.
+ */
+void jpeg_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x80010000);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_insert_end - insert a end command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a end command to the ring.
+ */
+void jpeg_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x00010000);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_emit_fence - emit an fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+void jpeg_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				unsigned flags)
+{
+	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JPEG_GPCOM_DATA0_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_DATA1_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x8);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET,
+		0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x3fbc);
+
+	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x1);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
+	amdgpu_ring_write(ring, 0);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_emit_ib - execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write ring commands to execute the indirect buffer.
+ */
+void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
+				struct amdgpu_job *job,
+				struct amdgpu_ib *ib,
+				uint32_t flags)
+{
+	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_IB_SIZE_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, ib->length_dw);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x2);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_STATUS_INTERNAL_OFFSET,
+		0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
+	amdgpu_ring_write(ring, 0x2);
+}
+
+void jpeg_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask)
+{
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, val);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,	PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+			0, 0, PACKETJ_TYPE3));
+	}
+	amdgpu_ring_write(ring, mask);
+}
+
+void jpeg_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
+	uint32_t data0, data1, mask;
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for register write */
+	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+	data1 = lower_32_bits(pd_addr);
+	mask = 0xffffffff;
+	jpeg_v2_0_dec_ring_emit_reg_wait(ring, data0, data1, mask);
+}
+
+void jpeg_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
+{
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,	PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+			0, 0, PACKETJ_TYPE0));
+	}
+	amdgpu_ring_write(ring, val);
+}
+
+void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
+static bool jpeg_v2_0_is_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	return ((RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS) &
+		UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
+		UVD_JRBC_STATUS__RB_JOB_DONE_MASK);
+}
+
+static int jpeg_v2_0_wait_for_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int ret = 0;
+
+	SOC15_WAIT_ON_RREG(JPEG, 0, mmUVD_JRBC_STATUS, UVD_JRBC_STATUS__RB_JOB_DONE_MASK,
+		UVD_JRBC_STATUS__RB_JOB_DONE_MASK, ret);
+
+	return ret;
+}
+
+static int jpeg_v2_0_set_clockgating_state(void *handle,
+					  enum amd_clockgating_state state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+
+	if (enable) {
+		if (jpeg_v2_0_is_idle(handle))
+			return -EBUSY;
+		jpeg_v2_0_enable_clock_gating(adev);
+	} else {
+		jpeg_v2_0_disable_clock_gating(adev);
+	}
+
+	return 0;
+}
+
+static int jpeg_v2_0_set_powergating_state(void *handle,
+					enum amd_powergating_state state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int ret;
+
+	if (state == adev->jpeg.cur_state)
+		return 0;
+
+	if (state == AMD_PG_STATE_GATE)
+		ret = jpeg_v2_0_stop(adev);
+	else
+		ret = jpeg_v2_0_start(adev);
+
+	if (!ret)
+		adev->jpeg.cur_state = state;
+
+	return ret;
+}
+
+static int jpeg_v2_0_set_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	return 0;
+}
+
+static int jpeg_v2_0_process_interrupt(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	DRM_DEBUG("IH: JPEG TRAP\n");
+
+	switch (entry->src_id) {
+	case VCN_2_0__SRCID__JPEG_DECODE:
+		amdgpu_fence_process(&adev->jpeg.inst->ring_dec);
+		break;
+	default:
+		DRM_ERROR("Unhandled interrupt: %d %d\n",
+			  entry->src_id, entry->src_data[0]);
+		break;
+	}
+
+	return 0;
+}
+
+static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = {
+	.name = "jpeg_v2_0",
+	.early_init = jpeg_v2_0_early_init,
+	.late_init = NULL,
+	.sw_init = jpeg_v2_0_sw_init,
+	.sw_fini = jpeg_v2_0_sw_fini,
+	.hw_init = jpeg_v2_0_hw_init,
+	.hw_fini = jpeg_v2_0_hw_fini,
+	.suspend = jpeg_v2_0_suspend,
+	.resume = jpeg_v2_0_resume,
+	.is_idle = jpeg_v2_0_is_idle,
+	.wait_for_idle = jpeg_v2_0_wait_for_idle,
+	.check_soft_reset = NULL,
+	.pre_soft_reset = NULL,
+	.soft_reset = NULL,
+	.post_soft_reset = NULL,
+	.set_clockgating_state = jpeg_v2_0_set_clockgating_state,
+	.set_powergating_state = jpeg_v2_0_set_powergating_state,
+};
+
+static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_JPEG,
+	.align_mask = 0xf,
+	.vmhub = AMDGPU_MMHUB_0,
+	.get_rptr = jpeg_v2_0_dec_ring_get_rptr,
+	.get_wptr = jpeg_v2_0_dec_ring_get_wptr,
+	.set_wptr = jpeg_v2_0_dec_ring_set_wptr,
+	.emit_frame_size =
+		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+		8 + /* jpeg_v2_0_dec_ring_emit_vm_flush */
+		18 + 18 + /* jpeg_v2_0_dec_ring_emit_fence x2 vm fence */
+		8 + 16,
+	.emit_ib_size = 22, /* jpeg_v2_0_dec_ring_emit_ib */
+	.emit_ib = jpeg_v2_0_dec_ring_emit_ib,
+	.emit_fence = jpeg_v2_0_dec_ring_emit_fence,
+	.emit_vm_flush = jpeg_v2_0_dec_ring_emit_vm_flush,
+	.test_ring = amdgpu_jpeg_dec_ring_test_ring,
+	.test_ib = amdgpu_jpeg_dec_ring_test_ib,
+	.insert_nop = jpeg_v2_0_dec_ring_nop,
+	.insert_start = jpeg_v2_0_dec_ring_insert_start,
+	.insert_end = jpeg_v2_0_dec_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_jpeg_ring_begin_use,
+	.end_use = amdgpu_jpeg_ring_end_use,
+	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
+	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+};
+
+static void jpeg_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev)
+{
+	adev->jpeg.inst->ring_dec.funcs = &jpeg_v2_0_dec_ring_vm_funcs;
+	DRM_INFO("JPEG decode is enabled in VM mode\n");
+}
+
+static const struct amdgpu_irq_src_funcs jpeg_v2_0_irq_funcs = {
+	.set = jpeg_v2_0_set_interrupt_state,
+	.process = jpeg_v2_0_process_interrupt,
+};
+
+static void jpeg_v2_0_set_irq_funcs(struct amdgpu_device *adev)
+{
+	adev->jpeg.inst->irq.num_types = 1;
+	adev->jpeg.inst->irq.funcs = &jpeg_v2_0_irq_funcs;
+}
+
+const struct amdgpu_ip_block_version jpeg_v2_0_ip_block =
+{
+		.type = AMD_IP_BLOCK_TYPE_JPEG,
+		.major = 2,
+		.minor = 0,
+		.rev = 0,
+		.funcs = &jpeg_v2_0_ip_funcs,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
new file mode 100644
index 000000000000..15a344ed340f
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __JPEG_V2_0_H__
+#define __JPEG_V2_0_H__
+
+void jpeg_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring);
+void jpeg_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring);
+void jpeg_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				unsigned flags);
+void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_job *job,
+				struct amdgpu_ib *ib, uint32_t flags);
+void jpeg_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask);
+void jpeg_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned vmid, uint64_t pd_addr);
+void jpeg_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
+void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count);
+
+extern const struct amdgpu_ip_block_version jpeg_v2_0_ip_block;
+
+#endif /* __JPEG_V2_0_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
new file mode 100644
index 000000000000..2c58939e6ad0
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -0,0 +1,641 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_jpeg.h"
+#include "soc15.h"
+#include "soc15d.h"
+#include "jpeg_v2_0.h"
+
+#include "vcn/vcn_2_5_offset.h"
+#include "vcn/vcn_2_5_sh_mask.h"
+#include "ivsrcid/vcn/irqsrcs_vcn_2_0.h"
+
+#define mmUVD_JPEG_PITCH_INTERNAL_OFFSET			0x401f
+
+#define JPEG25_MAX_HW_INSTANCES_ARCTURUS			2
+
+static void jpeg_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev);
+static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev);
+static int jpeg_v2_5_set_powergating_state(void *handle,
+				enum amd_powergating_state state);
+
+static int amdgpu_ih_clientid_jpeg[] = {
+	SOC15_IH_CLIENTID_VCN,
+	SOC15_IH_CLIENTID_VCN1
+};
+
+/**
+ * jpeg_v2_5_early_init - set function pointers
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Set ring and irq function pointers
+ */
+static int jpeg_v2_5_early_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		u32 harvest;
+		int i;
+
+		adev->jpeg.num_jpeg_inst = JPEG25_MAX_HW_INSTANCES_ARCTURUS;
+		for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+			harvest = RREG32_SOC15(JPEG, i, mmCC_UVD_HARVESTING);
+			if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
+				adev->jpeg.harvest_config |= 1 << i;
+		}
+
+		if (adev->jpeg.harvest_config == (AMDGPU_JPEG_HARVEST_JPEG0 |
+						 AMDGPU_JPEG_HARVEST_JPEG1))
+			return -ENOENT;
+	} else
+		adev->jpeg.num_jpeg_inst = 1;
+
+	jpeg_v2_5_set_dec_ring_funcs(adev);
+	jpeg_v2_5_set_irq_funcs(adev);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_sw_init - sw init for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Load firmware and sw initialization
+ */
+static int jpeg_v2_5_sw_init(void *handle)
+{
+	struct amdgpu_ring *ring;
+	int i, r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		/* JPEG TRAP */
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i],
+				VCN_2_0__SRCID__JPEG_DECODE, &adev->jpeg.inst[i].irq);
+		if (r)
+			return r;
+	}
+
+	r = amdgpu_jpeg_sw_init(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_resume(adev);
+	if (r)
+		return r;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = &adev->jpeg.inst[i].ring_dec;
+		ring->use_doorbell = true;
+		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1 + 8 * i;
+		sprintf(ring->name, "jpeg_dec_%d", i);
+		r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst[i].irq, 0);
+		if (r)
+			return r;
+
+		adev->jpeg.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
+		adev->jpeg.inst[i].external.jpeg_pitch = SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_PITCH);
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_sw_fini - sw fini for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * JPEG suspend and free up sw allocation
+ */
+static int jpeg_v2_5_sw_fini(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_jpeg_suspend(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_sw_fini(adev);
+
+	return r;
+}
+
+/**
+ * jpeg_v2_5_hw_init - start and test JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ */
+static int jpeg_v2_5_hw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring;
+	int i, r;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = &adev->jpeg.inst[i].ring_dec;
+		adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+			(adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i, i);
+
+		r = amdgpu_ring_test_helper(ring);
+		if (r)
+			return r;
+	}
+
+	DRM_INFO("JPEG decode initialized successfully.\n");
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_hw_fini - stop the hardware block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Stop the JPEG block, mark ring as not ready any more
+ */
+static int jpeg_v2_5_hw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring;
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = &adev->jpeg.inst[i].ring_dec;
+		if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
+		      RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS))
+			jpeg_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
+
+		ring->sched.ready = false;
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_suspend - suspend JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * HW fini and suspend JPEG block
+ */
+static int jpeg_v2_5_suspend(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = jpeg_v2_5_hw_fini(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_suspend(adev);
+
+	return r;
+}
+
+/**
+ * jpeg_v2_5_resume - resume JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Resume firmware and hw init JPEG block
+ */
+static int jpeg_v2_5_resume(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = amdgpu_jpeg_resume(adev);
+	if (r)
+		return r;
+
+	r = jpeg_v2_5_hw_init(adev);
+
+	return r;
+}
+
+static void jpeg_v2_5_disable_clock_gating(struct amdgpu_device* adev, int inst)
+{
+	uint32_t data;
+
+	data = RREG32_SOC15(JPEG, inst, mmJPEG_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_JPEG_MGCG)
+		data |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data &= ~JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+
+	data |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_CTRL, data);
+
+	data = RREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE);
+	data &= ~(JPEG_CGC_GATE__JPEG_DEC_MASK
+		| JPEG_CGC_GATE__JPEG2_DEC_MASK
+		| JPEG_CGC_GATE__JPEG_ENC_MASK
+		| JPEG_CGC_GATE__JMCIF_MASK
+		| JPEG_CGC_GATE__JRBBM_MASK);
+	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE, data);
+
+	data = RREG32_SOC15(JPEG, inst, mmJPEG_CGC_CTRL);
+	data &= ~(JPEG_CGC_CTRL__JPEG_DEC_MODE_MASK
+		| JPEG_CGC_CTRL__JPEG2_DEC_MODE_MASK
+		| JPEG_CGC_CTRL__JMCIF_MODE_MASK
+		| JPEG_CGC_CTRL__JRBBM_MODE_MASK);
+	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_CTRL, data);
+}
+
+static void jpeg_v2_5_enable_clock_gating(struct amdgpu_device* adev, int inst)
+{
+	uint32_t data;
+
+	data = RREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE);
+	data |= (JPEG_CGC_GATE__JPEG_DEC_MASK
+		|JPEG_CGC_GATE__JPEG2_DEC_MASK
+		|JPEG_CGC_GATE__JPEG_ENC_MASK
+		|JPEG_CGC_GATE__JMCIF_MASK
+		|JPEG_CGC_GATE__JRBBM_MASK);
+	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE, data);
+}
+
+/**
+ * jpeg_v2_5_start - start JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Setup and start the JPEG block
+ */
+static int jpeg_v2_5_start(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = &adev->jpeg.inst[i].ring_dec;
+		/* disable anti hang mechanism */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_POWER_STATUS), 0,
+			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+
+		/* JPEG disable CGC */
+		jpeg_v2_5_disable_clock_gating(adev, i);
+
+		/* MJPEG global tiling registers */
+		WREG32_SOC15(JPEG, i, mmJPEG_DEC_GFX8_ADDR_CONFIG,
+			adev->gfx.config.gb_addr_config);
+		WREG32_SOC15(JPEG, i, mmJPEG_DEC_GFX10_ADDR_CONFIG,
+			adev->gfx.config.gb_addr_config);
+
+		/* enable JMI channel */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JMI_CNTL), 0,
+			~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+		/* enable System Interrupt for JRBC */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmJPEG_SYS_INT_EN),
+			JPEG_SYS_INT_EN__DJRBC_MASK,
+			~JPEG_SYS_INT_EN__DJRBC_MASK);
+
+		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_VMID, 0);
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
+		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
+			lower_32_bits(ring->gpu_addr));
+		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
+			upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_RPTR, 0);
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_WPTR, 0);
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
+		ring->wptr = RREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_WPTR);
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_stop - stop JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * stop the JPEG block
+ */
+static int jpeg_v2_5_stop(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		/* reset JMI */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JMI_CNTL),
+			UVD_JMI_CNTL__SOFT_RESET_MASK,
+			~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+		jpeg_v2_5_enable_clock_gating(adev, i);
+
+		/* enable anti hang mechanism */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_POWER_STATUS),
+			UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
+			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_dec_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t jpeg_v2_5_dec_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(JPEG, ring->me, mmUVD_JRBC_RB_RPTR);
+}
+
+/**
+ * jpeg_v2_5_dec_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t jpeg_v2_5_dec_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->use_doorbell)
+		return adev->wb.wb[ring->wptr_offs];
+	else
+		return RREG32_SOC15(JPEG, ring->me, mmUVD_JRBC_RB_WPTR);
+}
+
+/**
+ * jpeg_v2_5_dec_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void jpeg_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->use_doorbell) {
+		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
+	} else {
+		WREG32_SOC15(JPEG, ring->me, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+	}
+}
+
+static bool jpeg_v2_5_is_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i, ret = 1;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ret &= (((RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS) &
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK));
+	}
+
+	return ret;
+}
+
+static int jpeg_v2_5_wait_for_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i, ret = 0;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		SOC15_WAIT_ON_RREG(JPEG, i, mmUVD_JRBC_STATUS,
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK,
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK, ret);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int jpeg_v2_5_set_clockgating_state(void *handle,
+					  enum amd_clockgating_state state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		if (enable) {
+			if (jpeg_v2_5_is_idle(handle))
+				return -EBUSY;
+			jpeg_v2_5_enable_clock_gating(adev, i);
+		} else {
+			jpeg_v2_5_disable_clock_gating(adev, i);
+		}
+	}
+
+	return 0;
+}
+
+static int jpeg_v2_5_set_powergating_state(void *handle,
+					  enum amd_powergating_state state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int ret;
+
+	if(state == adev->jpeg.cur_state)
+		return 0;
+
+	if (state == AMD_PG_STATE_GATE)
+		ret = jpeg_v2_5_stop(adev);
+	else
+		ret = jpeg_v2_5_start(adev);
+
+	if(!ret)
+		adev->jpeg.cur_state = state;
+
+	return ret;
+}
+
+static int jpeg_v2_5_set_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	return 0;
+}
+
+static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	uint32_t ip_instance;
+
+	switch (entry->client_id) {
+	case SOC15_IH_CLIENTID_VCN:
+		ip_instance = 0;
+		break;
+	case SOC15_IH_CLIENTID_VCN1:
+		ip_instance = 1;
+		break;
+	default:
+		DRM_ERROR("Unhandled client id: %d\n", entry->client_id);
+		return 0;
+	}
+
+	DRM_DEBUG("IH: JPEG TRAP\n");
+
+	switch (entry->src_id) {
+	case VCN_2_0__SRCID__JPEG_DECODE:
+		amdgpu_fence_process(&adev->jpeg.inst[ip_instance].ring_dec);
+		break;
+	default:
+		DRM_ERROR("Unhandled interrupt: %d %d\n",
+			  entry->src_id, entry->src_data[0]);
+		break;
+	}
+
+	return 0;
+}
+
+static const struct amd_ip_funcs jpeg_v2_5_ip_funcs = {
+	.name = "jpeg_v2_5",
+	.early_init = jpeg_v2_5_early_init,
+	.late_init = NULL,
+	.sw_init = jpeg_v2_5_sw_init,
+	.sw_fini = jpeg_v2_5_sw_fini,
+	.hw_init = jpeg_v2_5_hw_init,
+	.hw_fini = jpeg_v2_5_hw_fini,
+	.suspend = jpeg_v2_5_suspend,
+	.resume = jpeg_v2_5_resume,
+	.is_idle = jpeg_v2_5_is_idle,
+	.wait_for_idle = jpeg_v2_5_wait_for_idle,
+	.check_soft_reset = NULL,
+	.pre_soft_reset = NULL,
+	.soft_reset = NULL,
+	.post_soft_reset = NULL,
+	.set_clockgating_state = jpeg_v2_5_set_clockgating_state,
+	.set_powergating_state = jpeg_v2_5_set_powergating_state,
+};
+
+static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_JPEG,
+	.align_mask = 0xf,
+	.vmhub = AMDGPU_MMHUB_1,
+	.get_rptr = jpeg_v2_5_dec_ring_get_rptr,
+	.get_wptr = jpeg_v2_5_dec_ring_get_wptr,
+	.set_wptr = jpeg_v2_5_dec_ring_set_wptr,
+	.emit_frame_size =
+		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+		8 + /* jpeg_v2_5_dec_ring_emit_vm_flush */
+		18 + 18 + /* jpeg_v2_5_dec_ring_emit_fence x2 vm fence */
+		8 + 16,
+	.emit_ib_size = 22, /* jpeg_v2_5_dec_ring_emit_ib */
+	.emit_ib = jpeg_v2_0_dec_ring_emit_ib,
+	.emit_fence = jpeg_v2_0_dec_ring_emit_fence,
+	.emit_vm_flush = jpeg_v2_0_dec_ring_emit_vm_flush,
+	.test_ring = amdgpu_jpeg_dec_ring_test_ring,
+	.test_ib = amdgpu_jpeg_dec_ring_test_ib,
+	.insert_nop = jpeg_v2_0_dec_ring_nop,
+	.insert_start = jpeg_v2_0_dec_ring_insert_start,
+	.insert_end = jpeg_v2_0_dec_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_jpeg_ring_begin_use,
+	.end_use = amdgpu_jpeg_ring_end_use,
+	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
+	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+};
+
+static void jpeg_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		adev->jpeg.inst[i].ring_dec.funcs = &jpeg_v2_5_dec_ring_vm_funcs;
+		adev->jpeg.inst[i].ring_dec.me = i;
+		DRM_INFO("JPEG(%d) JPEG decode is enabled in VM mode\n", i);
+	}
+}
+
+static const struct amdgpu_irq_src_funcs jpeg_v2_5_irq_funcs = {
+	.set = jpeg_v2_5_set_interrupt_state,
+	.process = jpeg_v2_5_process_interrupt,
+};
+
+static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		adev->jpeg.inst[i].irq.num_types = 1;
+		adev->jpeg.inst[i].irq.funcs = &jpeg_v2_5_irq_funcs;
+	}
+}
+
+const struct amdgpu_ip_block_version jpeg_v2_5_ip_block =
+{
+		.type = AMD_IP_BLOCK_TYPE_JPEG,
+		.major = 2,
+		.minor = 5,
+		.rev = 0,
+		.funcs = &jpeg_v2_5_ip_funcs,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/gp102.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.h
index fde6328c6d71..2b4087c02620 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/gp102.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
+ * Copyright 2019 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -14,17 +14,16 @@
  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
+ * 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 "priv.h"
+#ifndef __JPEG_V2_5_H__
+#define __JPEG_V2_5_H__
+
+extern const struct amdgpu_ip_block_version jpeg_v2_5_ip_block;
 
-int
-gp102_nvdec_new(struct nvkm_device *device, int index,
-		struct nvkm_nvdec **pnvdec)
-{
-	return nvkm_nvdec_new_(device, index, pnvdec);
-}
+#endif /* __JPEG_V2_5_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 28105e4af507..adfd8a6171eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -27,17 +27,13 @@
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
 #include "mmhub/mmhub_1_0_default.h"
-#include "mmhub/mmhub_9_4_0_offset.h"
 #include "vega10_enum.h"
-
+#include "soc15.h"
 #include "soc15_common.h"
 
 #define mmDAGB0_CNTL_MISC2_RV 0x008f
 #define mmDAGB0_CNTL_MISC2_RV_BASE_IDX 0
 
-#define EA_EDC_CNT_MASK 0x3
-#define EA_EDC_CNT_SHIFT 0x2
-
 u64 mmhub_v1_0_get_fb_location(struct amdgpu_device *adev)
 {
 	u64 base = RREG32_SOC15(MMHUB, 0, mmMC_VM_FB_LOCATION_BASE);
@@ -564,59 +560,191 @@ void mmhub_v1_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
 
+static const struct soc15_ras_field_entry mmhub_v1_0_ras_fields[] = {
+	{ "MMEA0_DRAMRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_RRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, RRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, RRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA0_WRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, WRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, WRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, IORD_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, IOWR_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, IOWR_DATAMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_GMIRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_DRAMRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_RRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, RRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, RRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA1_WRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, WRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, WRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, IORD_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, IOWR_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, IOWR_DATAMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_GMIRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	}
+};
+
+static const struct soc15_reg_entry mmhub_v1_0_edc_cnt_regs[] = {
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20), 0, 0, 0},
+};
+
+static int mmhub_v1_0_get_ras_error_count(const struct soc15_reg_entry *reg,
+	uint32_t value, uint32_t *sec_count, uint32_t *ded_count)
+{
+	uint32_t i;
+	uint32_t sec_cnt, ded_cnt;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v1_0_ras_fields); i++) {
+		if(mmhub_v1_0_ras_fields[i].reg_offset != reg->reg_offset)
+			continue;
+
+		sec_cnt = (value &
+				mmhub_v1_0_ras_fields[i].sec_count_mask) >>
+				mmhub_v1_0_ras_fields[i].sec_count_shift;
+		if (sec_cnt) {
+			DRM_INFO("MMHUB SubBlock %s, SEC %d\n",
+				mmhub_v1_0_ras_fields[i].name,
+				sec_cnt);
+			*sec_count += sec_cnt;
+		}
+
+		ded_cnt = (value &
+				mmhub_v1_0_ras_fields[i].ded_count_mask) >>
+				mmhub_v1_0_ras_fields[i].ded_count_shift;
+		if (ded_cnt) {
+			DRM_INFO("MMHUB SubBlock %s, DED %d\n",
+				mmhub_v1_0_ras_fields[i].name,
+				ded_cnt);
+			*ded_count += ded_cnt;
+		}
+	}
+
+	return 0;
+}
+
 static void mmhub_v1_0_query_ras_error_count(struct amdgpu_device *adev,
 					   void *ras_error_status)
 {
-	int i;
-	uint32_t ea0_edc_cnt, ea0_edc_cnt2;
-	uint32_t ea1_edc_cnt, ea1_edc_cnt2;
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
-
-	/* EDC CNT will be cleared automatically after read */
-	ea0_edc_cnt = RREG32_SOC15(MMHUB, 0, mmMMEA0_EDC_CNT_VG20);
-	ea0_edc_cnt2 = RREG32_SOC15(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20);
-	ea1_edc_cnt = RREG32_SOC15(MMHUB, 0, mmMMEA1_EDC_CNT_VG20);
-	ea1_edc_cnt2 = RREG32_SOC15(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20);
-
-	/* error count of each error type is recorded by 2 bits,
-	 * ce and ue count in EDC_CNT
-	 */
-	for (i = 0; i < 5; i++) {
-		err_data->ce_count += (ea0_edc_cnt & EA_EDC_CNT_MASK);
-		err_data->ce_count += (ea1_edc_cnt & EA_EDC_CNT_MASK);
-		ea0_edc_cnt >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt >>= EA_EDC_CNT_SHIFT;
-		err_data->ue_count += (ea0_edc_cnt & EA_EDC_CNT_MASK);
-		err_data->ue_count += (ea1_edc_cnt & EA_EDC_CNT_MASK);
-		ea0_edc_cnt >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt >>= EA_EDC_CNT_SHIFT;
-	}
-	/* successive ue count in EDC_CNT */
-	for (i = 0; i < 5; i++) {
-		err_data->ue_count += (ea0_edc_cnt & EA_EDC_CNT_MASK);
-		err_data->ue_count += (ea1_edc_cnt & EA_EDC_CNT_MASK);
-		ea0_edc_cnt >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt >>= EA_EDC_CNT_SHIFT;
+	uint32_t sec_count = 0, ded_count = 0;
+	uint32_t i;
+	uint32_t reg_value;
+
+	err_data->ue_count = 0;
+	err_data->ce_count = 0;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v1_0_edc_cnt_regs); i++) {
+		reg_value =
+			RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v1_0_edc_cnt_regs[i]));
+		if (reg_value)
+			mmhub_v1_0_get_ras_error_count(&mmhub_v1_0_edc_cnt_regs[i],
+				reg_value, &sec_count, &ded_count);
 	}
 
-	/* ce and ue count in EDC_CNT2 */
-	for (i = 0; i < 3; i++) {
-		err_data->ce_count += (ea0_edc_cnt2 & EA_EDC_CNT_MASK);
-		err_data->ce_count += (ea1_edc_cnt2 & EA_EDC_CNT_MASK);
-		ea0_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-		err_data->ue_count += (ea0_edc_cnt2 & EA_EDC_CNT_MASK);
-		err_data->ue_count += (ea1_edc_cnt2 & EA_EDC_CNT_MASK);
-		ea0_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-	}
-	/* successive ue count in EDC_CNT2 */
-	for (i = 0; i < 6; i++) {
-		err_data->ue_count += (ea0_edc_cnt2 & EA_EDC_CNT_MASK);
-		err_data->ue_count += (ea1_edc_cnt2 & EA_EDC_CNT_MASK);
-		ea0_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-	}
+	err_data->ce_count += sec_count;
+	err_data->ue_count += ded_count;
 }
 
 const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 66efe2f7bd76..5c42387c9274 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -21,6 +21,7 @@
  *
  */
 #include "amdgpu.h"
+#include "amdgpu_ras.h"
 #include "mmhub_v9_4.h"
 
 #include "mmhub/mmhub_9_4_1_offset.h"
@@ -29,7 +30,7 @@
 #include "athub/athub_1_0_offset.h"
 #include "athub/athub_1_0_sh_mask.h"
 #include "vega10_enum.h"
-
+#include "soc15.h"
 #include "soc15_common.h"
 
 #define MMHUB_NUM_INSTANCES			2
@@ -53,7 +54,7 @@ u64 mmhub_v9_4_get_fb_location(struct amdgpu_device *adev)
 	return base;
 }
 
-void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, int hubid,
+static void mmhub_v9_4_setup_hubid_vm_pt_regs(struct amdgpu_device *adev, int hubid,
 				uint32_t vmid, uint64_t value)
 {
 	/* two registers distance between mmVML2VC0_VM_CONTEXT0_* to
@@ -79,7 +80,7 @@ static void mmhub_v9_4_init_gart_aperture_regs(struct amdgpu_device *adev,
 {
 	uint64_t pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
 
-	mmhub_v9_4_setup_vm_pt_regs(adev, hubid, 0, pt_base);
+	mmhub_v9_4_setup_hubid_vm_pt_regs(adev, hubid, 0, pt_base);
 
 	WREG32_SOC15_OFFSET(MMHUB, 0,
 			    mmVML2VC0_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32,
@@ -100,6 +101,16 @@ static void mmhub_v9_4_init_gart_aperture_regs(struct amdgpu_device *adev,
 			    (u32)(adev->gmc.gart_end >> 44));
 }
 
+void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base)
+{
+	int i;
+
+	for (i = 0; i < MMHUB_NUM_INSTANCES; i++)
+		mmhub_v9_4_setup_hubid_vm_pt_regs(adev, i, vmid,
+				page_table_base);
+}
+
 static void mmhub_v9_4_init_system_aperture_regs(struct amdgpu_device *adev,
 					         int hubid)
 {
@@ -117,45 +128,53 @@ static void mmhub_v9_4_init_system_aperture_regs(struct amdgpu_device *adev,
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
 			    adev->gmc.agp_start >> 24);
 
-	/* Program the system aperture low logical page number. */
-	WREG32_SOC15_OFFSET(MMHUB, 0,
-			    mmVMSHAREDVC0_MC_VM_SYSTEM_APERTURE_LOW_ADDR,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
-			    min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
-	WREG32_SOC15_OFFSET(MMHUB, 0,
-			    mmVMSHAREDVC0_MC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
-			    max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
+	if (!amdgpu_sriov_vf(adev)) {
+		/* Program the system aperture low logical page number. */
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0, mmVMSHAREDVC0_MC_VM_SYSTEM_APERTURE_LOW_ADDR,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0, mmVMSHAREDVC0_MC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+			max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
 
-	/* Set default page address. */
-	value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start +
-		adev->vm_manager.vram_base_offset;
-	WREG32_SOC15_OFFSET(MMHUB, 0,
+		/* Set default page address. */
+		value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start +
+			adev->vm_manager.vram_base_offset;
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0,
 			mmVMSHAREDPF0_MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB,
 			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
 			(u32)(value >> 12));
-	WREG32_SOC15_OFFSET(MMHUB, 0,
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0,
 			mmVMSHAREDPF0_MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB,
 			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
 			(u32)(value >> 44));
 
-	/* Program "protection fault". */
-	WREG32_SOC15_OFFSET(MMHUB, 0,
-			    mmVML2PF0_VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
-			    (u32)(adev->dummy_page_addr >> 12));
-	WREG32_SOC15_OFFSET(MMHUB, 0,
-			    mmVML2PF0_VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
-			    (u32)((u64)adev->dummy_page_addr >> 44));
+		/* Program "protection fault". */
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0,
+			mmVML2PF0_VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+			(u32)(adev->dummy_page_addr >> 12));
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0,
+			mmVML2PF0_VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+			(u32)((u64)adev->dummy_page_addr >> 44));
 
-	tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
-				  mmVML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
-				  hubid * MMHUB_INSTANCE_REGISTER_OFFSET);
-	tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
-			    ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY, 1);
-	WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
+		tmp = RREG32_SOC15_OFFSET(
+			MMHUB, 0, mmVML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET);
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
+				    ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY, 1);
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+				    mmVML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
+				    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+				    tmp);
+	}
 }
 
 static void mmhub_v9_4_init_tlb_regs(struct amdgpu_device *adev, int hubid)
@@ -313,7 +332,8 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 				    adev->vm_manager.block_size - 9);
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
-				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
+				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
+				    !amdgpu_noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL,
 				    hubid * MMHUB_INSTANCE_REGISTER_OFFSET + i,
 				    tmp);
@@ -356,30 +376,16 @@ int mmhub_v9_4_gart_enable(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < MMHUB_NUM_INSTANCES; i++) {
-		if (amdgpu_sriov_vf(adev)) {
-			/*
-			 * MC_VM_FB_LOCATION_BASE/TOP is NULL for VF, becuase
-			 * they are VF copy registers so vbios post doesn't
-			 * program them, for SRIOV driver need to program them
-			 */
-			WREG32_SOC15_OFFSET(MMHUB, 0,
-				     mmVMSHAREDVC0_MC_VM_FB_LOCATION_BASE,
-				     i * MMHUB_INSTANCE_REGISTER_OFFSET,
-				     adev->gmc.vram_start >> 24);
-			WREG32_SOC15_OFFSET(MMHUB, 0,
-				     mmVMSHAREDVC0_MC_VM_FB_LOCATION_TOP,
-				     i * MMHUB_INSTANCE_REGISTER_OFFSET,
-				     adev->gmc.vram_end >> 24);
-		}
-
 		/* GART Enable. */
 		mmhub_v9_4_init_gart_aperture_regs(adev, i);
 		mmhub_v9_4_init_system_aperture_regs(adev, i);
 		mmhub_v9_4_init_tlb_regs(adev, i);
-		mmhub_v9_4_init_cache_regs(adev, i);
+		if (!amdgpu_sriov_vf(adev))
+			mmhub_v9_4_init_cache_regs(adev, i);
 
 		mmhub_v9_4_enable_system_domain(adev, i);
-		mmhub_v9_4_disable_identity_aperture(adev, i);
+		if (!amdgpu_sriov_vf(adev))
+			mmhub_v9_4_disable_identity_aperture(adev, i);
 		mmhub_v9_4_setup_vmid_config(adev, i);
 		mmhub_v9_4_program_invalidation(adev, i);
 	}
@@ -655,3 +661,253 @@ void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 	if (data & ATCL2_0_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK)
 		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
+
+static const struct soc15_ras_field_entry mmhub_v9_4_ras_fields[] = {
+	{ "MMEA0_DRAMRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_RRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, RRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, RRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA0_WRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, WRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, WRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, IORD_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, IOWR_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, IOWR_DATAMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_GMIRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, DRAMRD_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, DRAMWR_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA0_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, IORD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, IOWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, IOWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, GMIRD_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, GMIWR_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_RRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, RRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, RRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA1_WRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, WRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, WRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, IORD_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, IOWR_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, IOWR_DATAMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_GMIRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, DRAMRD_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, DRAMWR_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA1_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, IORD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, IOWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, IOWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, GMIRD_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, GMIWR_PAGEMEM_DED_COUNT),
+	}
+};
+
+static const struct soc15_reg_entry mmhub_v9_4_edc_cnt_regs[] = {
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3), 0, 0, 0},
+};
+
+static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg,
+	uint32_t value, uint32_t *sec_count, uint32_t *ded_count)
+{
+	uint32_t i;
+	uint32_t sec_cnt, ded_cnt;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_ras_fields); i++) {
+		if(mmhub_v9_4_ras_fields[i].reg_offset != reg->reg_offset)
+			continue;
+
+		sec_cnt = (value &
+				mmhub_v9_4_ras_fields[i].sec_count_mask) >>
+				mmhub_v9_4_ras_fields[i].sec_count_shift;
+		if (sec_cnt) {
+			DRM_INFO("MMHUB SubBlock %s, SEC %d\n",
+				mmhub_v9_4_ras_fields[i].name,
+				sec_cnt);
+			*sec_count += sec_cnt;
+		}
+
+		ded_cnt = (value &
+				mmhub_v9_4_ras_fields[i].ded_count_mask) >>
+				mmhub_v9_4_ras_fields[i].ded_count_shift;
+		if (ded_cnt) {
+			DRM_INFO("MMHUB SubBlock %s, DED %d\n",
+				mmhub_v9_4_ras_fields[i].name,
+				ded_cnt);
+			*ded_count += ded_cnt;
+		}
+	}
+
+	return 0;
+}
+
+static void mmhub_v9_4_query_ras_error_count(struct amdgpu_device *adev,
+					   void *ras_error_status)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+	uint32_t sec_count = 0, ded_count = 0;
+	uint32_t i;
+	uint32_t reg_value;
+
+	err_data->ue_count = 0;
+	err_data->ce_count = 0;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_edc_cnt_regs); i++) {
+		reg_value =
+			RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_edc_cnt_regs[i]));
+		if (reg_value)
+			mmhub_v9_4_get_ras_error_count(&mmhub_v9_4_edc_cnt_regs[i],
+				reg_value, &sec_count, &ded_count);
+	}
+
+	err_data->ce_count += sec_count;
+	err_data->ue_count += ded_count;
+}
+
+const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = {
+	.ras_late_init = amdgpu_mmhub_ras_late_init,
+	.query_ras_error_count = mmhub_v9_4_query_ras_error_count,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
index d435cfcec1a8..1b979773776c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
@@ -23,6 +23,8 @@
 #ifndef __MMHUB_V9_4_H__
 #define __MMHUB_V9_4_H__
 
+extern const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs;
+
 u64 mmhub_v9_4_get_fb_location(struct amdgpu_device *adev);
 int mmhub_v9_4_gart_enable(struct amdgpu_device *adev);
 void mmhub_v9_4_gart_disable(struct amdgpu_device *adev);
@@ -32,5 +34,7 @@ void mmhub_v9_4_init(struct amdgpu_device *adev);
 int mmhub_v9_4_set_clockgating(struct amdgpu_device *adev,
 			       enum amd_clockgating_state state);
 void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u32 *flags);
+void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h b/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
index 8af0bddf85e4..20958639b601 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
@@ -47,6 +47,18 @@ struct mmsch_v1_0_init_header {
 	uint32_t uvd_table_size;
 };
 
+struct mmsch_vf_eng_init_header {
+	uint32_t init_status;
+	uint32_t table_offset;
+	uint32_t table_size;
+};
+
+struct mmsch_v1_1_init_header {
+	uint32_t version;
+	uint32_t total_size;
+	struct mmsch_vf_eng_init_header eng[2];
+};
+
 struct mmsch_v1_0_cmd_direct_reg_header {
 	uint32_t reg_offset   : 28;
 	uint32_t command_type : 4;
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index cc5bf595f9b1..5fd67e1cc2a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -158,82 +158,6 @@ static void xgpu_ai_mailbox_trans_msg (struct amdgpu_device *adev,
 	xgpu_ai_mailbox_set_valid(adev, false);
 }
 
-static int xgpu_ai_get_pp_clk(struct amdgpu_device *adev, u32 type, char *buf)
-{
-        int r = 0;
-        u32 req, val, size;
-
-        if (!amdgim_is_hwperf(adev) || buf == NULL)
-                return -EBADRQC;
-
-        switch(type) {
-        case PP_SCLK:
-                req = IDH_IRQ_GET_PP_SCLK;
-                break;
-        case PP_MCLK:
-                req = IDH_IRQ_GET_PP_MCLK;
-                break;
-        default:
-                return -EBADRQC;
-        }
-
-        mutex_lock(&adev->virt.dpm_mutex);
-
-        xgpu_ai_mailbox_trans_msg(adev, req, 0, 0, 0);
-
-        r = xgpu_ai_poll_msg(adev, IDH_SUCCESS);
-        if (!r && adev->fw_vram_usage.va != NULL) {
-                val = RREG32_NO_KIQ(
-                        SOC15_REG_OFFSET(NBIO, 0,
-                                         mmBIF_BX_PF0_MAILBOX_MSGBUF_RCV_DW1));
-                size = strnlen((((char *)adev->virt.fw_reserve.p_pf2vf) +
-                                val), PAGE_SIZE);
-
-                if (size < PAGE_SIZE)
-                        strcpy(buf,((char *)adev->virt.fw_reserve.p_pf2vf + val));
-                else
-                        size = 0;
-
-                r = size;
-                goto out;
-        }
-
-        r = xgpu_ai_poll_msg(adev, IDH_FAIL);
-        if(r)
-                pr_info("%s DPM request failed",
-                        (type == PP_SCLK)? "SCLK" : "MCLK");
-
-out:
-        mutex_unlock(&adev->virt.dpm_mutex);
-        return r;
-}
-
-static int xgpu_ai_force_dpm_level(struct amdgpu_device *adev, u32 level)
-{
-        int r = 0;
-        u32 req = IDH_IRQ_FORCE_DPM_LEVEL;
-
-        if (!amdgim_is_hwperf(adev))
-                return -EBADRQC;
-
-        mutex_lock(&adev->virt.dpm_mutex);
-        xgpu_ai_mailbox_trans_msg(adev, req, level, 0, 0);
-
-        r = xgpu_ai_poll_msg(adev, IDH_SUCCESS);
-        if (!r)
-                goto out;
-
-        r = xgpu_ai_poll_msg(adev, IDH_FAIL);
-        if (!r)
-                pr_info("DPM request failed");
-        else
-                pr_info("Mailbox is broken");
-
-out:
-        mutex_unlock(&adev->virt.dpm_mutex);
-        return r;
-}
-
 static int xgpu_ai_send_access_requests(struct amdgpu_device *adev,
 					enum idh_request req)
 {
@@ -326,7 +250,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	 */
 	locked = mutex_trylock(&adev->lock_reset);
 	if (locked)
-		adev->in_gpu_reset = 1;
+		adev->in_gpu_reset = true;
 
 	do {
 		if (xgpu_ai_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@@ -338,7 +262,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 
 flr_done:
 	if (locked) {
-		adev->in_gpu_reset = 0;
+		adev->in_gpu_reset = false;
 		mutex_unlock(&adev->lock_reset);
 	}
 
@@ -455,6 +379,4 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = {
 	.reset_gpu = xgpu_ai_request_reset,
 	.wait_reset = NULL,
 	.trans_msg = xgpu_ai_mailbox_trans_msg,
-	.get_pp_clk = xgpu_ai_get_pp_clk,
-	.force_dpm_level = xgpu_ai_force_dpm_level,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
index 077e91a33d62..37dbe0f2142f 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
@@ -35,10 +35,6 @@ enum idh_request {
 	IDH_REL_GPU_FINI_ACCESS,
 	IDH_REQ_GPU_RESET_ACCESS,
 
-	IDH_IRQ_FORCE_DPM_LEVEL = 10,
-	IDH_IRQ_GET_PP_SCLK,
-	IDH_IRQ_GET_PP_MCLK,
-
 	IDH_LOG_VF_ERROR       = 200,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 0d8767eb7a70..237fa5e16b7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -252,7 +252,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	 */
 	locked = mutex_trylock(&adev->lock_reset);
 	if (locked)
-		adev->in_gpu_reset = 1;
+		adev->in_gpu_reset = true;
 
 	do {
 		if (xgpu_nv_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@@ -264,12 +264,16 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 
 flr_done:
 	if (locked) {
-		adev->in_gpu_reset = 0;
+		adev->in_gpu_reset = false;
 		mutex_unlock(&adev->lock_reset);
 	}
 
 	/* Trigger recovery for world switch failure if no TDR */
-	if (amdgpu_device_should_recover_gpu(adev))
+	if (amdgpu_device_should_recover_gpu(adev)
+		&& (adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->video_timeout == MAX_SCHEDULE_TIMEOUT))
 		amdgpu_device_gpu_recover(adev, NULL);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 9af73567e716..f737ce459c28 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -110,7 +110,6 @@ static uint32_t navi10_ih_rb_cntl(struct amdgpu_ih_ring *ih, uint32_t ih_rb_cntl
 static int navi10_ih_irq_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ih_ring *ih = &adev->irq.ih;
-	int ret = 0;
 	u32 ih_rb_cntl, ih_doorbell_rtpr, ih_chicken;
 	u32 tmp;
 
@@ -179,7 +178,7 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
 	/* enable interrupts */
 	navi10_ih_enable_interrupts(adev);
 
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 0db458f9fafc..65eb378fa035 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -52,6 +52,9 @@
 #define BIF_MMSCH1_DOORBELL_RANGE__OFFSET_MASK          0x00000FFCL
 #define BIF_MMSCH1_DOORBELL_RANGE__SIZE_MASK            0x001F0000L
 
+static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
+					void *ras_error_status);
+
 static void nbio_v7_4_remap_hdp_registers(struct amdgpu_device *adev)
 {
 	WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL,
@@ -314,6 +317,7 @@ static void nbio_v7_4_init_registers(struct amdgpu_device *adev)
 static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device *adev)
 {
 	uint32_t bif_doorbell_intr_cntl;
+	struct ras_manager *obj = amdgpu_ras_find_obj(adev, adev->nbio.ras_if);
 
 	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
 	if (REG_GET_FIELD(bif_doorbell_intr_cntl,
@@ -324,7 +328,18 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 						RAS_CNTLR_INTERRUPT_CLEAR, 1);
 		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
 
-		amdgpu_ras_global_ras_isr(adev);
+		/*
+		 * clear error status after ras_controller_intr according to
+		 * hw team and count ue number for query
+		 */
+		nbio_v7_4_query_ras_error_count(adev, &obj->err_data);
+
+		DRM_WARN("RAS controller interrupt triggered by NBIF error\n");
+
+		/* ras_controller_int is dedicated for nbif ras error,
+		 * not the global interrupt for sync flood
+		 */
+		amdgpu_ras_reset_gpu(adev);
 	}
 }
 
@@ -441,10 +456,8 @@ static int nbio_v7_4_init_ras_controller_interrupt (struct amdgpu_device *adev)
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF,
 			      NBIF_7_4__SRCID__RAS_CONTROLLER_INTERRUPT,
 			      &adev->nbio.ras_controller_irq);
-	if (r)
-		return r;
 
-	return 0;
+	return r;
 }
 
 static int nbio_v7_4_init_ras_err_event_athub_interrupt (struct amdgpu_device *adev)
@@ -461,16 +474,16 @@ static int nbio_v7_4_init_ras_err_event_athub_interrupt (struct amdgpu_device *a
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF,
 			      NBIF_7_4__SRCID__ERREVENT_ATHUB_INTERRUPT,
 			      &adev->nbio.ras_err_event_athub_irq);
-	if (r)
-		return r;
 
-	return 0;
+	return r;
 }
 
+#define smnPARITY_ERROR_STATUS_UNCORR_GRP2	0x13a20030
+
 static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 					void *ras_error_status)
 {
-	uint32_t global_sts, central_sts, int_eoi;
+	uint32_t global_sts, central_sts, int_eoi, parity_sts;
 	uint32_t corr, fatal, non_fatal;
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
 
@@ -479,6 +492,7 @@ static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 	fatal = REG_GET_FIELD(global_sts, RAS_GLOBAL_STATUS_LO, ParityErrFatal);
 	non_fatal = REG_GET_FIELD(global_sts, RAS_GLOBAL_STATUS_LO,
 				ParityErrNonFatal);
+	parity_sts = RREG32_PCIE(smnPARITY_ERROR_STATUS_UNCORR_GRP2);
 
 	if (corr)
 		err_data->ce_count++;
@@ -490,6 +504,11 @@ static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 		/* clear error status register */
 		WREG32_PCIE(smnRAS_GLOBAL_STATUS_LO, global_sts);
 
+		if (fatal)
+			/* clear parity fatal error indication field */
+			WREG32_PCIE(smnPARITY_ERROR_STATUS_UNCORR_GRP2,
+				    parity_sts);
+
 		if (REG_GET_FIELD(central_sts, BIFL_RAS_CENTRAL_STATUS,
 				BIFL_RasContller_Intr_Recv)) {
 			/* clear interrupt status register */
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 0ba66bef5746..2e0f8933410e 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -53,6 +53,7 @@
 #include "gfx_v10_0.h"
 #include "sdma_v5_0.h"
 #include "vcn_v2_0.h"
+#include "jpeg_v2_0.h"
 #include "dce_virtual.h"
 #include "mes_v10_1.h"
 #include "mxgpu_nv.h"
@@ -314,6 +315,16 @@ static int nv_asic_mode1_reset(struct amdgpu_device *adev)
 	return ret;
 }
 
+static bool nv_asic_supports_baco(struct amdgpu_device *adev)
+{
+	struct smu_context *smu = &adev->smu;
+
+	if (smu_baco_is_support(smu))
+		return true;
+	else
+		return false;
+}
+
 static enum amd_reset_method
 nv_asic_reset_method(struct amdgpu_device *adev)
 {
@@ -342,7 +353,12 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 	if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 		if (!adev->in_suspend)
 			amdgpu_inc_vram_lost(adev);
-		ret = smu_baco_reset(smu);
+		ret = smu_baco_enter(smu);
+		if (ret)
+			return ret;
+		ret = smu_baco_exit(smu);
+		if (ret)
+			return ret;
 	} else {
 		if (!adev->in_suspend)
 			amdgpu_inc_vram_lost(adev);
@@ -462,7 +478,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP &&
-		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
+		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -473,9 +489,10 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
-		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
+		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		if (adev->enable_mes)
 			amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block);
 		break;
@@ -485,7 +502,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP &&
-		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
+		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -496,9 +513,10 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
-		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
+		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		break;
 	default:
 		return -EINVAL;
@@ -617,6 +635,7 @@ static const struct amdgpu_asic_funcs nv_asic_funcs =
 	.get_pcie_usage = &nv_get_pcie_usage,
 	.need_reset_on_init = &nv_need_reset_on_init,
 	.get_pcie_replay_count = &nv_get_pcie_replay_count,
+	.supports_baco = &nv_asic_supports_baco,
 };
 
 static int nv_common_early_init(void *handle)
@@ -656,10 +675,12 @@ static int nv_common_early_init(void *handle)
 			AMD_CG_SUPPORT_ATHUB_MGCG |
 			AMD_CG_SUPPORT_ATHUB_LS |
 			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG |
 			AMD_CG_SUPPORT_BIF_MGCG |
 			AMD_CG_SUPPORT_BIF_LS;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_ATHUB;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
@@ -676,9 +697,11 @@ static int nv_common_early_init(void *handle)
 			AMD_CG_SUPPORT_ATHUB_MGCG |
 			AMD_CG_SUPPORT_ATHUB_LS |
 			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG |
 			AMD_CG_SUPPORT_BIF_MGCG |
 			AMD_CG_SUPPORT_BIF_LS;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
+			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_VCN_DPG;
 		adev->external_rev_id = adev->rev_id + 20;
 		break;
@@ -697,10 +720,18 @@ static int nv_common_early_init(void *handle)
 			AMD_CG_SUPPORT_MC_LS |
 			AMD_CG_SUPPORT_ATHUB_MGCG |
 			AMD_CG_SUPPORT_ATHUB_LS |
-			AMD_CG_SUPPORT_VCN_MGCG;
+			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_ATHUB;
+		/* guest vm gets 0xffffffff when reading RCC_DEV0_EPF0_STRAP0,
+		 * as a consequence, the rev_id and external_rev_id are wrong.
+		 * workaround it by hardcoding rev_id to 0 (default value).
+		 */
+		if (amdgpu_sriov_vf(adev))
+			adev->rev_id = 0;
 		adev->external_rev_id = adev->rev_id + 0xa;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index 74a9fe8e0cfb..36b65797434e 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -242,6 +242,7 @@ enum psp_gfx_fw_type {
 	GFX_FW_TYPE_SDMA5                           = 55,   /* SDMA5                    MI      */
 	GFX_FW_TYPE_SDMA6                           = 56,   /* SDMA6                    MI      */
 	GFX_FW_TYPE_SDMA7                           = 57,   /* SDMA7                    MI      */
+	GFX_FW_TYPE_VCN1                            = 58,   /* VCN1                     MI      */
 	GFX_FW_TYPE_MAX
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index b345e69ba246..7539104175e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
@@ -230,54 +230,6 @@ static int psp_v10_0_ring_destroy(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v10_0_cmd_submit(struct psp_context *psp,
-				uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-				int index)
-{
-	unsigned int psp_write_ptr_reg = 0;
-	struct psp_gfx_rb_frame * write_frame = psp->km_ring.ring_mem;
-	struct psp_ring *ring = &psp->km_ring;
-	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
-	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
-		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
-	struct amdgpu_device *adev = psp->adev;
-	uint32_t ring_size_dw = ring->ring_size / 4;
-	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
-
-	/* KM (GPCOM) prepare write pointer */
-	psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
-
-	/* Update KM RB frame pointer to new frame */
-	if ((psp_write_ptr_reg % ring_size_dw) == 0)
-		write_frame = ring_buffer_start;
-	else
-		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
-	/* Check invalid write_frame ptr address */
-	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
-		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
-			  ring_buffer_start, ring_buffer_end, write_frame);
-		DRM_ERROR("write_frame is pointing to address out of bounds\n");
-		return -EINVAL;
-	}
-
-	/* Initialize KM RB frame */
-	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
-
-	/* Update KM RB frame */
-	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
-	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
-	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
-	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
-	write_frame->fence_value = index;
-	amdgpu_asic_flush_hdp(adev, NULL);
-
-	/* Update the write Pointer in DWORDs */
-	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, psp_write_ptr_reg);
-
-	return 0;
-}
-
 static int
 psp_v10_0_sram_map(struct amdgpu_device *adev,
 		   unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
@@ -407,15 +359,30 @@ static int psp_v10_0_mode1_reset(struct psp_context *psp)
 	return -EINVAL;
 }
 
+static uint32_t psp_v10_0_ring_get_wptr(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	return RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+}
+
+static void psp_v10_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
 static const struct psp_funcs psp_v10_0_funcs = {
 	.init_microcode = psp_v10_0_init_microcode,
 	.ring_init = psp_v10_0_ring_init,
 	.ring_create = psp_v10_0_ring_create,
 	.ring_stop = psp_v10_0_ring_stop,
 	.ring_destroy = psp_v10_0_ring_destroy,
-	.cmd_submit = psp_v10_0_cmd_submit,
 	.compare_sram_data = psp_v10_0_compare_sram_data,
 	.mode1_reset = psp_v10_0_mode1_reset,
+	.ring_get_wptr = psp_v10_0_ring_get_wptr,
+	.ring_set_wptr = psp_v10_0_ring_set_wptr,
 };
 
 void psp_v10_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index ffeaa2f5588d..685dd9754c67 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -43,10 +43,13 @@ MODULE_FIRMWARE("amdgpu/vega20_asd.bin");
 MODULE_FIRMWARE("amdgpu/vega20_ta.bin");
 MODULE_FIRMWARE("amdgpu/navi10_sos.bin");
 MODULE_FIRMWARE("amdgpu/navi10_asd.bin");
+MODULE_FIRMWARE("amdgpu/navi10_ta.bin");
 MODULE_FIRMWARE("amdgpu/navi14_sos.bin");
 MODULE_FIRMWARE("amdgpu/navi14_asd.bin");
+MODULE_FIRMWARE("amdgpu/navi14_ta.bin");
 MODULE_FIRMWARE("amdgpu/navi12_sos.bin");
 MODULE_FIRMWARE("amdgpu/navi12_asd.bin");
+MODULE_FIRMWARE("amdgpu/navi12_ta.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_sos.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_asd.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_ta.bin");
@@ -186,6 +189,31 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
+		err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
+		if (err) {
+			release_firmware(adev->psp.ta_fw);
+			adev->psp.ta_fw = NULL;
+			dev_info(adev->dev,
+				 "psp v11.0: Failed to load firmware \"%s\"\n", fw_name);
+		} else {
+			err = amdgpu_ucode_validate(adev->psp.ta_fw);
+			if (err)
+				goto out2;
+
+			ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
+			adev->psp.ta_hdcp_ucode_version = le32_to_cpu(ta_hdr->ta_hdcp_ucode_version);
+			adev->psp.ta_hdcp_ucode_size = le32_to_cpu(ta_hdr->ta_hdcp_size_bytes);
+			adev->psp.ta_hdcp_start_addr = (uint8_t *)ta_hdr +
+				le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
+
+			adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
+
+			adev->psp.ta_dtm_ucode_version = le32_to_cpu(ta_hdr->ta_dtm_ucode_version);
+			adev->psp.ta_dtm_ucode_size = le32_to_cpu(ta_hdr->ta_dtm_size_bytes);
+			adev->psp.ta_dtm_start_addr = (uint8_t *)adev->psp.ta_hdcp_start_addr +
+				le32_to_cpu(ta_hdr->ta_dtm_offset_bytes);
+		}
 		break;
 	default:
 		BUG();
@@ -208,6 +236,29 @@ out:
 	return err;
 }
 
+int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	int ret;
+	int retry_loop;
+
+	for (retry_loop = 0; retry_loop < 10; retry_loop++) {
+		/* Wait for bootloader to signify that is
+		    ready having bit 31 of C2PMSG_35 set to 1 */
+		ret = psp_wait_for(psp,
+				   SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
+				   0x80000000,
+				   0x80000000,
+				   false);
+
+		if (ret == 0)
+			return 0;
+	}
+
+	return ret;
+}
+
 static bool psp_v11_0_is_sos_alive(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
@@ -233,9 +284,7 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 		return 0;
 	}
 
-	/* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 	if (ret)
 		return ret;
 
@@ -251,9 +300,7 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35,
 	       psp_gfxdrv_command_reg);
 
-	/* Wait for bootloader to signify that is ready having  bit 31 of C2PMSG_35 set to 1*/
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 
 	return ret;
 }
@@ -273,9 +320,7 @@ static int psp_v11_0_bootloader_load_sysdrv(struct psp_context *psp)
 		return 0;
 	}
 
-	/* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 	if (ret)
 		return ret;
 
@@ -294,8 +339,7 @@ static int psp_v11_0_bootloader_load_sysdrv(struct psp_context *psp)
 	/* there might be handshake issue with hardware which needs delay */
 	mdelay(20);
 
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 
 	return ret;
 }
@@ -312,9 +356,7 @@ static int psp_v11_0_bootloader_load_sos(struct psp_context *psp)
 	if (psp_v11_0_is_sos_alive(psp))
 		return 0;
 
-	/* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 	if (ret)
 		return ret;
 
@@ -519,63 +561,6 @@ static int psp_v11_0_ring_destroy(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v11_0_cmd_submit(struct psp_context *psp,
-			       uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-			       int index)
-{
-	unsigned int psp_write_ptr_reg = 0;
-	struct psp_gfx_rb_frame *write_frame = psp->km_ring.ring_mem;
-	struct psp_ring *ring = &psp->km_ring;
-	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
-	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
-		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
-	struct amdgpu_device *adev = psp->adev;
-	uint32_t ring_size_dw = ring->ring_size / 4;
-	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
-
-	/* KM (GPCOM) prepare write pointer */
-	if (psp_v11_0_support_vmr_ring(psp))
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
-	else
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
-
-	/* Update KM RB frame pointer to new frame */
-	/* write_frame ptr increments by size of rb_frame in bytes */
-	/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
-	if ((psp_write_ptr_reg % ring_size_dw) == 0)
-		write_frame = ring_buffer_start;
-	else
-		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
-	/* Check invalid write_frame ptr address */
-	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
-		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
-			  ring_buffer_start, ring_buffer_end, write_frame);
-		DRM_ERROR("write_frame is pointing to address out of bounds\n");
-		return -EINVAL;
-	}
-
-	/* Initialize KM RB frame */
-	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
-
-	/* Update KM RB frame */
-	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
-	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
-	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
-	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
-	write_frame->fence_value = index;
-	amdgpu_asic_flush_hdp(adev, NULL);
-
-	/* Update the write Pointer in DWORDs */
-	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	if (psp_v11_0_support_vmr_ring(psp)) {
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_write_ptr_reg);
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
-	} else
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, psp_write_ptr_reg);
-
-	return 0;
-}
-
 static int
 psp_v11_0_sram_map(struct amdgpu_device *adev,
 		  unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
@@ -1068,6 +1053,30 @@ static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops)
 	return 0;
 }
 
+static uint32_t psp_v11_0_ring_get_wptr(struct psp_context *psp)
+{
+	uint32_t data;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v11_0_support_vmr_ring(psp))
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
+	else
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+
+	return data;
+}
+
+static void psp_v11_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v11_0_support_vmr_ring(psp)) {
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, value);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
+	} else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
 static const struct psp_funcs psp_v11_0_funcs = {
 	.init_microcode = psp_v11_0_init_microcode,
 	.bootloader_load_kdb = psp_v11_0_bootloader_load_kdb,
@@ -1077,7 +1086,6 @@ static const struct psp_funcs psp_v11_0_funcs = {
 	.ring_create = psp_v11_0_ring_create,
 	.ring_stop = psp_v11_0_ring_stop,
 	.ring_destroy = psp_v11_0_ring_destroy,
-	.cmd_submit = psp_v11_0_cmd_submit,
 	.compare_sram_data = psp_v11_0_compare_sram_data,
 	.mode1_reset = psp_v11_0_mode1_reset,
 	.xgmi_get_topology_info = psp_v11_0_xgmi_get_topology_info,
@@ -1091,6 +1099,8 @@ static const struct psp_funcs psp_v11_0_funcs = {
 	.mem_training_init = psp_v11_0_memory_training_init,
 	.mem_training_fini = psp_v11_0_memory_training_fini,
 	.mem_training = psp_v11_0_memory_training,
+	.ring_get_wptr = psp_v11_0_ring_get_wptr,
+	.ring_set_wptr = psp_v11_0_ring_set_wptr,
 };
 
 void psp_v11_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 8f553f6f92d6..58d8b6d732e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -334,63 +334,6 @@ static int psp_v12_0_ring_destroy(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v12_0_cmd_submit(struct psp_context *psp,
-			       uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-			       int index)
-{
-	unsigned int psp_write_ptr_reg = 0;
-	struct psp_gfx_rb_frame *write_frame = psp->km_ring.ring_mem;
-	struct psp_ring *ring = &psp->km_ring;
-	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
-	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
-		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
-	struct amdgpu_device *adev = psp->adev;
-	uint32_t ring_size_dw = ring->ring_size / 4;
-	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
-
-	/* KM (GPCOM) prepare write pointer */
-	if (psp_v12_0_support_vmr_ring(psp))
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
-	else
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
-
-	/* Update KM RB frame pointer to new frame */
-	/* write_frame ptr increments by size of rb_frame in bytes */
-	/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
-	if ((psp_write_ptr_reg % ring_size_dw) == 0)
-		write_frame = ring_buffer_start;
-	else
-		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
-	/* Check invalid write_frame ptr address */
-	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
-		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
-			  ring_buffer_start, ring_buffer_end, write_frame);
-		DRM_ERROR("write_frame is pointing to address out of bounds\n");
-		return -EINVAL;
-	}
-
-	/* Initialize KM RB frame */
-	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
-
-	/* Update KM RB frame */
-	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
-	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
-	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
-	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
-	write_frame->fence_value = index;
-	amdgpu_asic_flush_hdp(adev, NULL);
-
-	/* Update the write Pointer in DWORDs */
-	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	if (psp_v12_0_support_vmr_ring(psp)) {
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_write_ptr_reg);
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
-	} else
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, psp_write_ptr_reg);
-
-	return 0;
-}
-
 static int
 psp_v12_0_sram_map(struct amdgpu_device *adev,
 		  unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
@@ -547,6 +490,30 @@ static int psp_v12_0_mode1_reset(struct psp_context *psp)
 	return 0;
 }
 
+static uint32_t psp_v12_0_ring_get_wptr(struct psp_context *psp)
+{
+	uint32_t data;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v12_0_support_vmr_ring(psp))
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
+	else
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+
+	return data;
+}
+
+static void psp_v12_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v12_0_support_vmr_ring(psp)) {
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, value);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
+	} else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
 static const struct psp_funcs psp_v12_0_funcs = {
 	.init_microcode = psp_v12_0_init_microcode,
 	.bootloader_load_sysdrv = psp_v12_0_bootloader_load_sysdrv,
@@ -555,9 +522,10 @@ static const struct psp_funcs psp_v12_0_funcs = {
 	.ring_create = psp_v12_0_ring_create,
 	.ring_stop = psp_v12_0_ring_stop,
 	.ring_destroy = psp_v12_0_ring_destroy,
-	.cmd_submit = psp_v12_0_cmd_submit,
 	.compare_sram_data = psp_v12_0_compare_sram_data,
 	.mode1_reset = psp_v12_0_mode1_reset,
+	.ring_get_wptr = psp_v12_0_ring_get_wptr,
+	.ring_set_wptr = psp_v12_0_ring_set_wptr,
 };
 
 void psp_v12_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index fdc00938327b..735c43c7daab 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -179,7 +179,7 @@ static bool psp_v3_1_match_version(struct amdgpu_device *adev, uint32_t ver)
 	 * Double check if the latest four legacy versions.
 	 * If yes, it is still the right version.
 	 */
-	for (i = 0; i < sizeof(sos_old_versions) / sizeof(uint32_t); i++) {
+	for (i = 0; i < ARRAY_SIZE(sos_old_versions); i++) {
 		if (sos_old_versions[i] == adev->psp.sos_fw_version)
 			return true;
 	}
@@ -410,65 +410,6 @@ static int psp_v3_1_ring_destroy(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v3_1_cmd_submit(struct psp_context *psp,
-			       uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-			       int index)
-{
-	unsigned int psp_write_ptr_reg = 0;
-	struct psp_gfx_rb_frame * write_frame = psp->km_ring.ring_mem;
-	struct psp_ring *ring = &psp->km_ring;
-	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
-	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
-		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
-	struct amdgpu_device *adev = psp->adev;
-	uint32_t ring_size_dw = ring->ring_size / 4;
-	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
-
-	/* KM (GPCOM) prepare write pointer */
-	if (psp_v3_1_support_vmr_ring(psp))
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
-	else
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
-
-	/* Update KM RB frame pointer to new frame */
-	/* write_frame ptr increments by size of rb_frame in bytes */
-	/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
-	if ((psp_write_ptr_reg % ring_size_dw) == 0)
-		write_frame = ring_buffer_start;
-	else
-		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
-	/* Check invalid write_frame ptr address */
-	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
-		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
-			  ring_buffer_start, ring_buffer_end, write_frame);
-		DRM_ERROR("write_frame is pointing to address out of bounds\n");
-		return -EINVAL;
-	}
-
-	/* Initialize KM RB frame */
-	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
-
-	/* Update KM RB frame */
-	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
-	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
-	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
-	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
-	write_frame->fence_value = index;
-	amdgpu_asic_flush_hdp(adev, NULL);
-
-	/* Update the write Pointer in DWORDs */
-	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	if (psp_v3_1_support_vmr_ring(psp)) {
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_write_ptr_reg);
-		/* send interrupt to PSP for SRIOV ring write pointer update */
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
-					GFX_CTRL_CMD_ID_CONSUME_CMD);
-	} else
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, psp_write_ptr_reg);
-
-	return 0;
-}
-
 static int
 psp_v3_1_sram_map(struct amdgpu_device *adev,
 		  unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
@@ -642,6 +583,31 @@ static bool psp_v3_1_support_vmr_ring(struct psp_context *psp)
 	return false;
 }
 
+static uint32_t psp_v3_1_ring_get_wptr(struct psp_context *psp)
+{
+	uint32_t data;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v3_1_support_vmr_ring(psp))
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
+	else
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+	return data;
+}
+
+static void psp_v3_1_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v3_1_support_vmr_ring(psp)) {
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, value);
+		/* send interrupt to PSP for SRIOV ring write pointer update */
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
+			GFX_CTRL_CMD_ID_CONSUME_CMD);
+	} else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
 static const struct psp_funcs psp_v3_1_funcs = {
 	.init_microcode = psp_v3_1_init_microcode,
 	.bootloader_load_sysdrv = psp_v3_1_bootloader_load_sysdrv,
@@ -650,11 +616,12 @@ static const struct psp_funcs psp_v3_1_funcs = {
 	.ring_create = psp_v3_1_ring_create,
 	.ring_stop = psp_v3_1_ring_stop,
 	.ring_destroy = psp_v3_1_ring_destroy,
-	.cmd_submit = psp_v3_1_cmd_submit,
 	.compare_sram_data = psp_v3_1_compare_sram_data,
 	.smu_reload_quirk = psp_v3_1_smu_reload_quirk,
 	.mode1_reset = psp_v3_1_mode1_reset,
 	.support_vmr_ring = psp_v3_1_support_vmr_ring,
+	.ring_get_wptr = psp_v3_1_ring_get_wptr,
+	.ring_set_wptr = psp_v3_1_ring_set_wptr,
 };
 
 void psp_v3_1_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index a10175838013..7d509a40076f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -255,7 +255,7 @@ static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v2_4_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -750,7 +750,7 @@ static void sdma_v2_4_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1260,16 +1260,14 @@ static const struct amdgpu_vm_pte_funcs sdma_v2_4_vm_pte_funcs = {
 
 static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs;
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] =
+			&adev->sdma.instance[i].ring.sched;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version sdma_v2_4_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 5f4e2c616241..b6109a99fc43 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -429,7 +429,7 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v3_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1021,7 +1021,7 @@ static void sdma_v3_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1698,16 +1698,14 @@ static const struct amdgpu_vm_pte_funcs sdma_v3_0_vm_pte_funcs = {
 
 static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	adev->vm_manager.vm_pte_funcs = &sdma_v3_0_vm_pte_funcs;
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] =
+			 &adev->sdma.instance[i].ring.sched;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version sdma_v3_0_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 2f52b7f4d25c..27c7001be1ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -82,6 +82,7 @@ static void sdma_v4_0_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v4_0_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v4_0_set_vm_pte_funcs(struct amdgpu_device *adev);
 static void sdma_v4_0_set_irq_funcs(struct amdgpu_device *adev);
+static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev);
 
 static const struct soc15_reg_golden golden_settings_sdma_4[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831d07),
@@ -257,6 +258,105 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x03fbe1fe)
 };
 
+static const struct soc15_ras_field_entry sdma_v4_0_ras_fields[] = {
+	{ "SDMA_UCODE_BUF_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_UCODE_BUF_SED),
+	0, 0,
+	},
+	{ "SDMA_RB_CMD_BUF_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_RB_CMD_BUF_SED),
+	0, 0,
+	},
+	{ "SDMA_IB_CMD_BUF_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_IB_CMD_BUF_SED),
+	0, 0,
+	},
+	{ "SDMA_UTCL1_RD_FIFO_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_UTCL1_RD_FIFO_SED),
+	0, 0,
+	},
+	{ "SDMA_UTCL1_RDBST_FIFO_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_UTCL1_RDBST_FIFO_SED),
+	0, 0,
+	},
+	{ "SDMA_DATA_LUT_FIFO_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_DATA_LUT_FIFO_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF0_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF0_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF1_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF1_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF2_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF2_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF3_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF3_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF4_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF4_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF5_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF5_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF6_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF6_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF7_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF7_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF8_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF8_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF9_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF9_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF10_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF10_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF11_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF11_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF12_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF12_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF13_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF13_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF14_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF14_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF15_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF15_SED),
+	0, 0,
+	},
+	{ "SDMA_SPLIT_DAT_BUF_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_SPLIT_DAT_BUF_SED),
+	0, 0,
+	},
+	{ "SDMA_MC_WR_ADDR_FIFO_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MC_WR_ADDR_FIFO_SED),
+	0, 0,
+	},
+};
+
 static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
 		u32 instance, u32 offset)
 {
@@ -698,7 +798,7 @@ static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v4_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v4_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1579,7 +1679,7 @@ static void sdma_v4_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1686,6 +1786,7 @@ static int sdma_v4_0_early_init(void *handle)
 	sdma_v4_0_set_buffer_funcs(adev);
 	sdma_v4_0_set_vm_pte_funcs(adev);
 	sdma_v4_0_set_irq_funcs(adev);
+	sdma_v4_0_set_ras_funcs(adev);
 
 	return 0;
 }
@@ -1700,8 +1801,18 @@ static int sdma_v4_0_late_init(void *handle)
 	struct ras_ih_if ih_info = {
 		.cb = sdma_v4_0_process_ras_data_cb,
 	};
+	int i;
 
-	return amdgpu_sdma_ras_late_init(adev, &ih_info);
+	/* read back edc counter registers to clear the counters */
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) {
+		for (i = 0; i < adev->sdma.num_instances; i++)
+			RREG32_SDMA(i, mmSDMA0_EDC_COUNTER);
+	}
+
+	if (adev->sdma.funcs && adev->sdma.funcs->ras_late_init)
+		return adev->sdma.funcs->ras_late_init(adev, &ih_info);
+	else
+		return 0;
 }
 
 static int sdma_v4_0_sw_init(void *handle)
@@ -1773,7 +1884,8 @@ static int sdma_v4_0_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int i;
 
-	amdgpu_sdma_ras_fini(adev);
+	if (adev->sdma.funcs && adev->sdma.funcs->ras_fini)
+		adev->sdma.funcs->ras_fini(adev);
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
@@ -2409,10 +2521,73 @@ static void sdma_v4_0_set_vm_pte_funcs(struct amdgpu_device *adev)
 			sched = &adev->sdma.instance[i].page.sched;
 		else
 			sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] = sched;
+	}
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
+}
+
+static void sdma_v4_0_get_ras_error_count(uint32_t value,
+					uint32_t instance,
+					uint32_t *sec_count)
+{
+	uint32_t i;
+	uint32_t sec_cnt;
+
+	/* double bits error (multiple bits) error detection is not supported */
+	for (i = 0; i < ARRAY_SIZE(sdma_v4_0_ras_fields); i++) {
+		/* the SDMA_EDC_COUNTER register in each sdma instance
+		 * shares the same sed shift_mask
+		 * */
+		sec_cnt = (value &
+			sdma_v4_0_ras_fields[i].sec_count_mask) >>
+			sdma_v4_0_ras_fields[i].sec_count_shift;
+		if (sec_cnt) {
+			DRM_INFO("Detected %s in SDMA%d, SED %d\n",
+				sdma_v4_0_ras_fields[i].name,
+				instance, sec_cnt);
+			*sec_count += sec_cnt;
+		}
+	}
+}
+
+static int sdma_v4_0_query_ras_error_count(struct amdgpu_device *adev,
+			uint32_t instance, void *ras_error_status)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+	uint32_t sec_count = 0;
+	uint32_t reg_value = 0;
+
+	reg_value = RREG32_SDMA(instance, mmSDMA0_EDC_COUNTER);
+	/* double bit error is not supported */
+	if (reg_value)
+		sdma_v4_0_get_ras_error_count(reg_value,
+				instance, &sec_count);
+	/* err_data->ce_count should be initialized to 0
+	 * before calling into this function */
+	err_data->ce_count += sec_count;
+	/* double bit error is not supported
+	 * set ue count to 0 */
+	err_data->ue_count = 0;
+
+	return 0;
+};
+
+static const struct amdgpu_sdma_ras_funcs sdma_v4_0_ras_funcs = {
+	.ras_late_init = amdgpu_sdma_ras_late_init,
+	.ras_fini = amdgpu_sdma_ras_fini,
+	.query_ras_error_count = sdma_v4_0_query_ras_error_count,
+};
+
+static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
+		adev->sdma.funcs = &sdma_v4_0_ras_funcs;
+		break;
+	default:
+		break;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version sdma_v4_0_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index f4ad2990f973..4c6bf1f8a528 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -382,8 +382,15 @@ static void sdma_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 	uint64_t csa_mc_addr = amdgpu_sdma_get_csa_mc_addr(ring, vmid);
 
-	/* IB packet must end on a 8 DW boundary */
-	sdma_v5_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	/* An IB packet must end on a 8 DW boundary--the next dword
+	 * must be on a 8-dword boundary. Our IB packet below is 6
+	 * dwords long, thus add x number of NOPs, such that, in
+	 * modular arithmetic,
+	 * wptr + 6 + x = 8k, k >= 0, which in C is,
+	 * (wptr + 6 + x) % 8 = 0.
+	 * The expression below, is a solution of x.
+	 */
+	sdma_v5_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -907,16 +914,9 @@ static int sdma_v5_0_ring_test_ring(struct amdgpu_ring *ring)
 			udelay(1);
 	}
 
-	if (i < adev->usec_timeout) {
-		if (amdgpu_emu_mode == 1)
-			DRM_INFO("ring test on %d succeeded in %d msecs\n", ring->idx, i);
-		else
-			DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
-	} else {
-		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
-			  ring->idx, tmp);
-		r = -EINVAL;
-	}
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
 	amdgpu_device_wb_free(adev, index);
 
 	return r;
@@ -981,13 +981,10 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		goto err1;
 	}
 	tmp = le32_to_cpu(adev->wb.wb[index]);
-	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+	if (tmp == 0xDEADBEEF)
 		r = 0;
-	} else {
-		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
+	else
 		r = -EINVAL;
-	}
 
 err1:
 	amdgpu_ib_free(adev, &ib, NULL);
@@ -1086,10 +1083,10 @@ static void sdma_v5_0_vm_set_pte_pde(struct amdgpu_ib *ib,
 }
 
 /**
- * sdma_v5_0_ring_pad_ib - pad the IB to the required number of dw
- *
+ * sdma_v5_0_ring_pad_ib - pad the IB
  * @ib: indirect buffer to fill with padding
  *
+ * Pad the IB with NOPs to a boundary multiple of 8.
  */
 static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
 {
@@ -1097,7 +1094,7 @@ static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 0x7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1721,17 +1718,15 @@ static const struct amdgpu_vm_pte_funcs sdma_v5_0_vm_pte_funcs = {
 
 static void sdma_v5_0_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	if (adev->vm_manager.vm_pte_funcs == NULL) {
 		adev->vm_manager.vm_pte_funcs = &sdma_v5_0_vm_pte_funcs;
 		for (i = 0; i < adev->sdma.num_instances; i++) {
-			sched = &adev->sdma.instance[i].ring.sched;
-			adev->vm_manager.vm_pte_rqs[i] =
-				&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+			adev->vm_manager.vm_pte_scheds[i] =
+				&adev->sdma.instance[i].ring.sched;
 		}
-		adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+		adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index f2d70a47a3af..4d415bfdb42f 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -1197,6 +1197,11 @@ static int si_asic_reset(struct amdgpu_device *adev)
 	return 0;
 }
 
+static bool si_asic_supports_baco(struct amdgpu_device *adev)
+{
+	return false;
+}
+
 static enum amd_reset_method
 si_asic_reset_method(struct amdgpu_device *adev)
 {
@@ -1425,6 +1430,7 @@ static const struct amdgpu_asic_funcs si_asic_funcs =
 	.get_pcie_usage = &si_get_pcie_usage,
 	.need_reset_on_init = &si_need_reset_on_init,
 	.get_pcie_replay_count = &si_get_pcie_replay_count,
+	.supports_baco = &si_asic_supports_baco,
 };
 
 static uint32_t si_get_rev_id(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index bdda8b4e03f0..9aac9f9c50bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -834,16 +834,14 @@ static const struct amdgpu_vm_pte_funcs si_dma_vm_pte_funcs = {
 
 static void si_dma_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	adev->vm_manager.vm_pte_funcs = &si_dma_vm_pte_funcs;
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] =
+			&adev->sdma.instance[i].ring.sched;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version si_dma_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
index c44723c267c9..c902f26cf50d 100644
--- a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
@@ -234,7 +234,7 @@ static uint32_t smu_v11_0_i2c_transmit(struct i2c_adapter *control,
 	DRM_DEBUG_DRIVER("I2C_Transmit(), address = %x, bytes = %d , data: ",
 		 (uint16_t)address, numbytes);
 
-	if (drm_debug & DRM_UT_DRIVER) {
+	if (drm_debug_enabled(DRM_UT_DRIVER)) {
 		print_hex_dump(KERN_INFO, "data: ", DUMP_PREFIX_NONE,
 			       16, 1, data, numbytes, false);
 	}
@@ -388,7 +388,7 @@ static uint32_t smu_v11_0_i2c_receive(struct i2c_adapter *control,
 	DRM_DEBUG_DRIVER("I2C_Receive(), address = %x, bytes = %d, data :",
 		  (uint16_t)address, bytes_received);
 
-	if (drm_debug & DRM_UT_DRIVER) {
+	if (drm_debug_enabled(DRM_UT_DRIVER)) {
 		print_hex_dump(KERN_INFO, "data: ", DUMP_PREFIX_NONE,
 			       16, 1, data, bytes_received, false);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 8e1640bc07af..317803f6a561 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -67,7 +67,9 @@
 #include "vce_v4_0.h"
 #include "vcn_v1_0.h"
 #include "vcn_v2_0.h"
+#include "jpeg_v2_0.h"
 #include "vcn_v2_5.h"
+#include "jpeg_v2_5.h"
 #include "dce_virtual.h"
 #include "mxgpu_ai.h"
 #include "amdgpu_smu.h"
@@ -477,56 +479,18 @@ static int soc15_asic_mode1_reset(struct amdgpu_device *adev)
 	return ret;
 }
 
-static int soc15_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap)
-{
-	if (is_support_sw_smu(adev)) {
-		struct smu_context *smu = &adev->smu;
-
-		*cap = smu_baco_is_support(smu);
-		return 0;
-	} else {
-		void *pp_handle = adev->powerplay.pp_handle;
-		const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-		if (!pp_funcs || !pp_funcs->get_asic_baco_capability) {
-			*cap = false;
-			return -ENOENT;
-		}
-
-		return pp_funcs->get_asic_baco_capability(pp_handle, cap);
-	}
-}
-
 static int soc15_asic_baco_reset(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	int ret = 0;
 
 	/* avoid NBIF got stuck when do RAS recovery in BACO reset */
 	if (ras && ras->supported)
 		adev->nbio.funcs->enable_doorbell_interrupt(adev, false);
 
-	dev_info(adev->dev, "GPU BACO reset\n");
-
-	if (is_support_sw_smu(adev)) {
-		struct smu_context *smu = &adev->smu;
-
-		if (smu_baco_reset(smu))
-			return -EIO;
-	} else {
-		void *pp_handle = adev->powerplay.pp_handle;
-		const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-		if (!pp_funcs ||!pp_funcs->get_asic_baco_state ||!pp_funcs->set_asic_baco_state)
-			return -ENOENT;
-
-		/* enter BACO state */
-		if (pp_funcs->set_asic_baco_state(pp_handle, 1))
-			return -EIO;
-
-		/* exit BACO state */
-		if (pp_funcs->set_asic_baco_state(pp_handle, 0))
-			return -EIO;
-	}
+	ret = amdgpu_dpm_baco_reset(adev);
+	if (ret)
+		return ret;
 
 	/* re-enable doorbell interrupt after BACO exit */
 	if (ras && ras->supported)
@@ -535,21 +499,11 @@ static int soc15_asic_baco_reset(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int soc15_mode2_reset(struct amdgpu_device *adev)
-{
-	if (is_support_sw_smu(adev))
-		return smu_mode2_reset(&adev->smu);
-	if (!adev->powerplay.pp_funcs ||
-	    !adev->powerplay.pp_funcs->asic_reset_mode_2)
-		return -ENOENT;
-
-	return adev->powerplay.pp_funcs->asic_reset_mode_2(adev->powerplay.pp_handle);
-}
-
 static enum amd_reset_method
 soc15_asic_reset_method(struct amdgpu_device *adev)
 {
-	bool baco_reset;
+	bool baco_reset = false;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
@@ -557,23 +511,21 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 		return AMD_RESET_METHOD_MODE2;
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
-		soc15_asic_get_baco_capability(adev, &baco_reset);
+	case CHIP_ARCTURUS:
+		baco_reset = amdgpu_dpm_is_baco_supported(adev);
 		break;
 	case CHIP_VEGA20:
 		if (adev->psp.sos_fw_version >= 0x80067)
-			soc15_asic_get_baco_capability(adev, &baco_reset);
-		else
-			baco_reset = false;
-		if (baco_reset) {
-			struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
-			struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+			baco_reset = amdgpu_dpm_is_baco_supported(adev);
 
-			if (hive || (ras && ras->supported))
-				baco_reset = false;
-		}
+		/*
+		 * 1. PMFW version > 0x284300: all cases use baco
+		 * 2. PMFW version <= 0x284300: only sGPU w/o RAS use baco
+		 */
+		if ((ras && ras->supported) && adev->pm.fw_version <= 0x283400)
+			baco_reset = false;
 		break;
 	default:
-		baco_reset = false;
 		break;
 	}
 
@@ -591,7 +543,7 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_baco_reset(adev);
 		case AMD_RESET_METHOD_MODE2:
-			return soc15_mode2_reset(adev);
+			return amdgpu_dpm_mode2_reset(adev);
 		default:
 			if (!adev->in_suspend)
 				amdgpu_inc_vram_lost(adev);
@@ -599,6 +551,22 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 	}
 }
 
+static bool soc15_supports_baco(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
+	case CHIP_VEGA12:
+	case CHIP_ARCTURUS:
+		return amdgpu_dpm_is_baco_supported(adev);
+	case CHIP_VEGA20:
+		if (adev->psp.sos_fw_version >= 0x80067)
+			return amdgpu_dpm_is_baco_supported(adev);
+		return false;
+	default:
+		return false;
+	}
+}
+
 /*static int soc15_set_uvd_clock(struct amdgpu_device *adev, u32 clock,
 			u32 cntl_reg, u32 status_reg)
 {
@@ -709,9 +677,9 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 	}
 
 	if (adev->asic_type == CHIP_VEGA20 || adev->asic_type == CHIP_ARCTURUS)
-		adev->df_funcs = &df_v3_6_funcs;
+		adev->df.funcs = &df_v3_6_funcs;
 	else
-		adev->df_funcs = &df_v1_7_funcs;
+		adev->df.funcs = &df_v1_7_funcs;
 
 	adev->rev_id = soc15_get_rev_id(adev);
 	adev->nbio.funcs->detect_hw_virt(adev);
@@ -746,11 +714,11 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		}
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
-		if (!amdgpu_sriov_vf(adev)) {
-			if (is_support_sw_smu(adev))
+		if (is_support_sw_smu(adev)) {
+			if (!amdgpu_sriov_vf(adev))
 				amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
-			else
-				amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		} else {
+			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		}
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -798,11 +766,16 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
-		if (!amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 
-		if (unlikely(adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT))
+		if (amdgpu_sriov_vf(adev)) {
+			if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP))
+				amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block);
+		} else {
 			amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block);
+		}
+		if (!amdgpu_sriov_vf(adev))
+			amdgpu_device_ip_block_add(adev, &jpeg_v2_5_ip_block);
 		break;
 	case CHIP_RENOIR:
 		amdgpu_device_ip_block_add(adev, &vega10_common_ip_block);
@@ -810,8 +783,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
 		if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP))
 			amdgpu_device_ip_block_add(adev, &psp_v12_0_ip_block);
-		if (is_support_sw_smu(adev))
-			amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
@@ -821,6 +793,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
                         amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		break;
 	default:
 		return -EINVAL;
@@ -999,6 +972,7 @@ static const struct amdgpu_asic_funcs soc15_asic_funcs =
 	.get_pcie_usage = &soc15_get_pcie_usage,
 	.need_reset_on_init = &soc15_need_reset_on_init,
 	.get_pcie_replay_count = &soc15_get_pcie_replay_count,
+	.supports_baco = &soc15_supports_baco,
 };
 
 static const struct amdgpu_asic_funcs vega20_asic_funcs =
@@ -1007,6 +981,7 @@ static const struct amdgpu_asic_funcs vega20_asic_funcs =
 	.read_bios_from_rom = &soc15_read_bios_from_rom,
 	.read_register = &soc15_read_register,
 	.reset = &soc15_asic_reset,
+	.reset_method = &soc15_asic_reset_method,
 	.set_vga_state = &soc15_vga_set_state,
 	.get_xclk = &soc15_get_xclk,
 	.set_uvd_clocks = &soc15_set_uvd_clocks,
@@ -1019,7 +994,7 @@ static const struct amdgpu_asic_funcs vega20_asic_funcs =
 	.get_pcie_usage = &vega20_get_pcie_usage,
 	.need_reset_on_init = &soc15_need_reset_on_init,
 	.get_pcie_replay_count = &soc15_get_pcie_replay_count,
-	.reset_method = &soc15_asic_reset_method
+	.supports_baco = &soc15_supports_baco,
 };
 
 static int soc15_common_early_init(void *handle)
@@ -1145,9 +1120,7 @@ static int soc15_common_early_init(void *handle)
 				AMD_CG_SUPPORT_SDMA_LS |
 				AMD_CG_SUPPORT_VCN_MGCG;
 
-			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
-				AMD_PG_SUPPORT_VCN |
-				AMD_PG_SUPPORT_VCN_DPG;
+			adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
 		} else if (adev->pdev->device == 0x15d8) {
 			adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				AMD_CG_SUPPORT_GFX_MGLS |
@@ -1190,9 +1163,7 @@ static int soc15_common_early_init(void *handle)
 				AMD_CG_SUPPORT_SDMA_LS |
 				AMD_CG_SUPPORT_VCN_MGCG;
 
-			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
-				AMD_PG_SUPPORT_VCN |
-				AMD_PG_SUPPORT_VCN_DPG;
+			adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
 		}
 		break;
 	case CHIP_ARCTURUS:
@@ -1208,7 +1179,9 @@ static int soc15_common_early_init(void *handle)
 			AMD_CG_SUPPORT_SDMA_LS |
 			AMD_CG_SUPPORT_MC_MGCG |
 			AMD_CG_SUPPORT_MC_LS |
-			AMD_CG_SUPPORT_IH_CG;
+			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x32;
 		break;
@@ -1229,12 +1202,14 @@ static int soc15_common_early_init(void *handle)
 				 AMD_CG_SUPPORT_HDP_LS |
 				 AMD_CG_SUPPORT_ROM_MGCG |
 				 AMD_CG_SUPPORT_VCN_MGCG |
+				 AMD_CG_SUPPORT_JPEG_MGCG |
 				 AMD_CG_SUPPORT_IH_CG |
 				 AMD_CG_SUPPORT_ATHUB_LS |
 				 AMD_CG_SUPPORT_ATHUB_MGCG |
 				 AMD_CG_SUPPORT_DF_MGCG;
 		adev->pg_flags = AMD_PG_SUPPORT_SDMA |
 				 AMD_PG_SUPPORT_VCN |
+				 AMD_PG_SUPPORT_JPEG |
 				 AMD_PG_SUPPORT_VCN_DPG;
 		adev->external_rev_id = adev->rev_id + 0x91;
 		break;
@@ -1272,7 +1247,7 @@ static int soc15_common_sw_init(void *handle)
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_add_irq_id(adev);
 
-	adev->df_funcs->sw_init(adev);
+	adev->df.funcs->sw_init(adev);
 
 	return 0;
 }
@@ -1282,7 +1257,7 @@ static int soc15_common_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_nbio_ras_fini(adev);
-	adev->df_funcs->sw_fini(adev);
+	adev->df.funcs->sw_fini(adev);
 	return 0;
 }
 
@@ -1503,7 +1478,7 @@ static int soc15_common_set_clockgating_state(void *handle,
 				state == AMD_CG_STATE_GATE ? true : false);
 		soc15_update_rom_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
-		adev->df_funcs->update_medium_grain_clock_gating(adev,
+		adev->df.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		break;
 	case CHIP_RAVEN:
@@ -1561,7 +1536,7 @@ static void soc15_common_get_clockgating_state(void *handle, u32 *flags)
 	if (!(data & CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE0_MASK))
 		*flags |= AMD_CG_SUPPORT_ROM_MGCG;
 
-	adev->df_funcs->get_clockgating_state(adev, flags);
+	adev->df.funcs->get_clockgating_state(adev, flags);
 }
 
 static int soc15_common_set_powergating_state(void *handle,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h
index 57af489a5de3..d0fb7a67c1a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.h
@@ -60,6 +60,18 @@ struct soc15_allowed_register_entry {
 	bool grbm_indexed;
 };
 
+struct soc15_ras_field_entry {
+	const char *name;
+	uint32_t hwip;
+	uint32_t inst;
+	uint32_t seg;
+	uint32_t reg_offset;
+	uint32_t sec_count_mask;
+	uint32_t sec_count_shift;
+	uint32_t ded_count_mask;
+	uint32_t ded_count_shift;
+};
+
 #define SOC15_REG_ENTRY(ip, inst, reg)	ip##_HWIP, inst, reg##_BASE_IDX, reg
 
 #define SOC15_REG_ENTRY_OFFSET(entry)	(adev->reg_offset[entry.hwip][entry.inst][entry.seg] + entry.reg_offset)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 839f186e1182..19e870c79896 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -52,6 +52,7 @@
 		uint32_t old_ = 0;	\
 		uint32_t tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
 		uint32_t loop = adev->usec_timeout;		\
+		ret = 0;					\
 		while ((tmp_ & (mask)) != (expected_value)) {	\
 			if (old_ != tmp_) {			\
 				loop = adev->usec_timeout;	\
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
index 47c4b96b14d1..793bf70e64b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
@@ -28,19 +28,24 @@
 #include "rsmu/rsmu_0_0_2_sh_mask.h"
 #include "umc/umc_6_1_1_offset.h"
 #include "umc/umc_6_1_1_sh_mask.h"
+#include "umc/umc_6_1_2_offset.h"
 
-#define smnMCA_UMC0_MCUMC_ADDRT0	0x50f10
+#define UMC_6_INST_DIST			0x40000
 
 /*
  * (addr / 256) * 8192, the higher 26 bits in ErrorAddr
  * is the index of 8KB block
  */
-#define ADDR_OF_8KB_BLOCK(addr)		(((addr) & ~0xffULL) << 5)
+#define ADDR_OF_8KB_BLOCK(addr)			(((addr) & ~0xffULL) << 5)
 /* channel index is the index of 256B block */
 #define ADDR_OF_256B_BLOCK(channel_index)	((channel_index) << 8)
 /* offset in 256B block */
 #define OFFSET_IN_256B_BLOCK(addr)		((addr) & 0xffULL)
 
+#define LOOP_UMC_INST(umc_inst) for ((umc_inst) = 0; (umc_inst) < adev->umc.umc_inst_num; (umc_inst)++)
+#define LOOP_UMC_CH_INST(ch_inst) for ((ch_inst) = 0; (ch_inst) < adev->umc.channel_inst_num; (ch_inst)++)
+#define LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) LOOP_UMC_INST((umc_inst)) LOOP_UMC_CH_INST((ch_inst))
+
 const uint32_t
 	umc_v6_1_channel_idx_tbl[UMC_V6_1_UMC_INSTANCE_NUM][UMC_V6_1_CHANNEL_INSTANCE_NUM] = {
 		{2, 18, 11, 27},	{4, 20, 13, 29},
@@ -49,24 +54,10 @@ const uint32_t
 		{9, 25, 0, 16},		{15, 31, 6, 22}
 };
 
-static void umc_v6_1_enable_umc_index_mode(struct amdgpu_device *adev,
-					   uint32_t umc_instance)
+static void umc_v6_1_enable_umc_index_mode(struct amdgpu_device *adev)
 {
-	uint32_t rsmu_umc_index;
-
-	rsmu_umc_index = RREG32_SOC15(RSMU, 0,
-			mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
-	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
-			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+	WREG32_FIELD15(RSMU, 0, RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
 			RSMU_UMC_INDEX_MODE_EN, 1);
-	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
-			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
-			RSMU_UMC_INDEX_INSTANCE, umc_instance);
-	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
-			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
-			RSMU_UMC_INDEX_WREN, 1 << umc_instance);
-	WREG32_SOC15(RSMU, 0, mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
-				rsmu_umc_index);
 }
 
 static void umc_v6_1_disable_umc_index_mode(struct amdgpu_device *adev)
@@ -75,15 +66,23 @@ static void umc_v6_1_disable_umc_index_mode(struct amdgpu_device *adev)
 			RSMU_UMC_INDEX_MODE_EN, 0);
 }
 
-static uint32_t umc_v6_1_get_umc_inst(struct amdgpu_device *adev)
+static uint32_t umc_v6_1_get_umc_index_mode_state(struct amdgpu_device *adev)
 {
 	uint32_t rsmu_umc_index;
 
 	rsmu_umc_index = RREG32_SOC15(RSMU, 0,
-				mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
+			mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
+
 	return REG_GET_FIELD(rsmu_umc_index,
-				RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
-				RSMU_UMC_INDEX_INSTANCE);
+			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+			RSMU_UMC_INDEX_MODE_EN);
+}
+
+static inline uint32_t get_umc_6_reg_offset(struct amdgpu_device *adev,
+					    uint32_t umc_inst,
+					    uint32_t ch_inst)
+{
+	return adev->umc.channel_offs*ch_inst + UMC_6_INST_DIST*umc_inst;
 }
 
 static void umc_v6_1_query_correctable_error_count(struct amdgpu_device *adev,
@@ -95,39 +94,50 @@ static void umc_v6_1_query_correctable_error_count(struct amdgpu_device *adev,
 	uint64_t mc_umc_status;
 	uint32_t mc_umc_status_addr;
 
-	ecc_err_cnt_sel_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
-	ecc_err_cnt_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
-	mc_umc_status_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		/* UMC 6_1_2 registers */
+		ecc_err_cnt_sel_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel_ARCT);
+		ecc_err_cnt_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt_ARCT);
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT);
+	} else {
+		/* UMC 6_1_1 registers */
+		ecc_err_cnt_sel_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
+		ecc_err_cnt_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	}
 
 	/* select the lower chip and check the error count */
-	ecc_err_cnt_sel = RREG32(ecc_err_cnt_sel_addr + umc_reg_offset);
+	ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4);
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrCntCsSel, 0);
-	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
-	ecc_err_cnt = RREG32(ecc_err_cnt_addr + umc_reg_offset);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+	ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4);
 	*error_count +=
 		(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) -
 		 UMC_V6_1_CE_CNT_INIT);
 	/* clear the lower chip err count */
-	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V6_1_CE_CNT_INIT);
 
 	/* select the higher chip and check the err counter */
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrCntCsSel, 1);
-	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
-	ecc_err_cnt = RREG32(ecc_err_cnt_addr + umc_reg_offset);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+	ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4);
 	*error_count +=
 		(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) -
 		 UMC_V6_1_CE_CNT_INIT);
 	/* clear the higher chip err count */
-	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V6_1_CE_CNT_INIT);
 
 	/* check for SRAM correctable error
 	  MCUMC_STATUS is a 64 bit register */
-	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
 	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, ErrorCodeExt) == 6 &&
 	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
 	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
@@ -141,11 +151,18 @@ static void umc_v6_1_querry_uncorrectable_error_count(struct amdgpu_device *adev
 	uint64_t mc_umc_status;
 	uint32_t mc_umc_status_addr;
 
-	mc_umc_status_addr =
-                SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		/* UMC 6_1_2 registers */
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT);
+	} else {
+		/* UMC 6_1_1 registers */
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	}
 
 	/* check the MCUMC_STATUS */
-	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
 	if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
 	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
 	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
@@ -155,49 +172,78 @@ static void umc_v6_1_querry_uncorrectable_error_count(struct amdgpu_device *adev
 		*error_count += 1;
 }
 
-static void umc_v6_1_query_error_count(struct amdgpu_device *adev,
-					   struct ras_err_data *err_data, uint32_t umc_reg_offset,
-					   uint32_t channel_index)
-{
-	umc_v6_1_query_correctable_error_count(adev, umc_reg_offset,
-						   &(err_data->ce_count));
-	umc_v6_1_querry_uncorrectable_error_count(adev, umc_reg_offset,
-						  &(err_data->ue_count));
-}
-
 static void umc_v6_1_query_ras_error_count(struct amdgpu_device *adev,
 					   void *ras_error_status)
 {
-	amdgpu_umc_for_each_channel(umc_v6_1_query_error_count);
+	struct ras_err_data* err_data = (struct ras_err_data*)ras_error_status;
+
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	uint32_t rsmu_umc_index_state = umc_v6_1_get_umc_index_mode_state(adev);
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_disable_umc_index_mode(adev);
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_6_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v6_1_query_correctable_error_count(adev,
+						       umc_reg_offset,
+						       &(err_data->ce_count));
+		umc_v6_1_querry_uncorrectable_error_count(adev,
+							  umc_reg_offset,
+							  &(err_data->ue_count));
+	}
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_enable_umc_index_mode(adev);
 }
 
 static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 					 struct ras_err_data *err_data,
-					 uint32_t umc_reg_offset, uint32_t channel_index)
+					 uint32_t umc_reg_offset,
+					 uint32_t ch_inst,
+					 uint32_t umc_inst)
 {
 	uint32_t lsb, mc_umc_status_addr;
-	uint64_t mc_umc_status, err_addr, retired_page;
+	uint64_t mc_umc_status, err_addr, retired_page, mc_umc_addrt0;
 	struct eeprom_table_record *err_rec;
-
-	mc_umc_status_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	uint32_t channel_index = adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst];
+
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		/* UMC 6_1_2 registers */
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT);
+		mc_umc_addrt0 =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_ADDRT0_ARCT);
+	} else {
+		/* UMC 6_1_1 registers */
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+		mc_umc_addrt0 =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_ADDRT0);
+	}
 
 	/* skip error address process if -ENOMEM */
 	if (!err_data->err_addr) {
 		/* clear umc status */
-		WREG64_UMC(mc_umc_status_addr + umc_reg_offset, 0x0ULL);
+		WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL);
 		return;
 	}
 
 	err_rec = &err_data->err_addr[err_data->err_addr_cnt];
-	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
 
 	/* calculate error address if ue/ce error is detected */
 	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
 	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
 	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) {
-		err_addr = RREG64_PCIE(smnMCA_UMC0_MCUMC_ADDRT0 + umc_reg_offset * 4);
 
+		err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4);
 		/* the lowest lsb bits should be ignored */
 		lsb = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, LSB);
 		err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr);
@@ -218,57 +264,105 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 			err_rec->err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE;
 			err_rec->cu = 0;
 			err_rec->mem_channel = channel_index;
-			err_rec->mcumc_id = umc_v6_1_get_umc_inst(adev);
+			err_rec->mcumc_id = umc_inst;
 
 			err_data->err_addr_cnt++;
 		}
 	}
 
 	/* clear umc status */
-	WREG64_UMC(mc_umc_status_addr + umc_reg_offset, 0x0ULL);
+	WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL);
 }
 
 static void umc_v6_1_query_ras_error_address(struct amdgpu_device *adev,
 					     void *ras_error_status)
 {
-	amdgpu_umc_for_each_channel(umc_v6_1_query_error_address);
+	struct ras_err_data* err_data = (struct ras_err_data*)ras_error_status;
+
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	uint32_t rsmu_umc_index_state = umc_v6_1_get_umc_index_mode_state(adev);
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_disable_umc_index_mode(adev);
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_6_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v6_1_query_error_address(adev,
+					     err_data,
+					     umc_reg_offset,
+					     ch_inst,
+					     umc_inst);
+	}
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_enable_umc_index_mode(adev);
 }
 
 static void umc_v6_1_err_cnt_init_per_channel(struct amdgpu_device *adev,
-					 struct ras_err_data *err_data,
-					 uint32_t umc_reg_offset, uint32_t channel_index)
+					      uint32_t umc_reg_offset)
 {
 	uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
 	uint32_t ecc_err_cnt_addr;
 
-	ecc_err_cnt_sel_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
-	ecc_err_cnt_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		/* UMC 6_1_2 registers */
+		ecc_err_cnt_sel_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel_ARCT);
+		ecc_err_cnt_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt_ARCT);
+	} else {
+		/* UMC 6_1_1 registers */
+		ecc_err_cnt_sel_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
+		ecc_err_cnt_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
+	}
 
 	/* select the lower chip and check the error count */
-	ecc_err_cnt_sel = RREG32(ecc_err_cnt_sel_addr + umc_reg_offset);
+	ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4);
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrCntCsSel, 0);
 	/* set ce error interrupt type to APIC based interrupt */
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrInt, 0x1);
-	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
 	/* set error count to initial value */
-	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V6_1_CE_CNT_INIT);
 
 	/* select the higher chip and check the err counter */
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrCntCsSel, 1);
-	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
-	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V6_1_CE_CNT_INIT);
 }
 
 static void umc_v6_1_err_cnt_init(struct amdgpu_device *adev)
 {
-	void *ras_error_status = NULL;
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	uint32_t rsmu_umc_index_state = umc_v6_1_get_umc_index_mode_state(adev);
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_disable_umc_index_mode(adev);
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_6_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v6_1_err_cnt_init_per_channel(adev, umc_reg_offset);
+	}
 
-	amdgpu_umc_for_each_channel(umc_v6_1_err_cnt_init_per_channel);
+	if (rsmu_umc_index_state)
+		umc_v6_1_enable_umc_index_mode(adev);
 }
 
 const struct amdgpu_umc_funcs umc_v6_1_funcs = {
@@ -276,6 +370,4 @@ const struct amdgpu_umc_funcs umc_v6_1_funcs = {
 	.ras_late_init = amdgpu_umc_ras_late_init,
 	.query_ras_error_count = umc_v6_1_query_ras_error_count,
 	.query_ras_error_address = umc_v6_1_query_ras_error_address,
-	.enable_umc_index_mode = umc_v6_1_enable_umc_index_mode,
-	.disable_umc_index_mode = umc_v6_1_disable_umc_index_mode,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h
index dab9cbd292c5..0ce1d323cfdd 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h
@@ -35,7 +35,8 @@
 /* total channel instances in one umc block */
 #define UMC_V6_1_TOTAL_CHANNEL_NUM	(UMC_V6_1_CHANNEL_INSTANCE_NUM * UMC_V6_1_UMC_INSTANCE_NUM)
 /* UMC regiser per channel offset */
-#define UMC_V6_1_PER_CHANNEL_OFFSET		0x800
+#define UMC_V6_1_PER_CHANNEL_OFFSET_VG20	0x800
+#define UMC_V6_1_PER_CHANNEL_OFFSET_ARCT	0x400
 
 /* EccErrCnt max value */
 #define UMC_V6_1_CE_CNT_MAX		0xffff
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index b4f84a820a44..e654938f6cca 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -25,6 +25,7 @@
 
 #include "amdgpu.h"
 #include "amdgpu_vcn.h"
+#include "amdgpu_pm.h"
 #include "soc15.h"
 #include "soc15d.h"
 #include "soc15_common.h"
@@ -36,21 +37,22 @@
 #include "mmhub/mmhub_9_1_sh_mask.h"
 
 #include "ivsrcid/vcn/irqsrcs_vcn_1_0.h"
+#include "jpeg_v1_0.h"
 
-#define mmUVD_RBC_XX_IB_REG_CHECK				0x05ab
-#define mmUVD_RBC_XX_IB_REG_CHECK_BASE_IDX	1
-#define mmUVD_REG_XX_MASK							0x05ac
-#define mmUVD_REG_XX_MASK_BASE_IDX				1
+#define mmUVD_RBC_XX_IB_REG_CHECK_1_0		0x05ab
+#define mmUVD_RBC_XX_IB_REG_CHECK_1_0_BASE_IDX	1
+#define mmUVD_REG_XX_MASK_1_0			0x05ac
+#define mmUVD_REG_XX_MASK_1_0_BASE_IDX		1
 
 static int vcn_v1_0_stop(struct amdgpu_device *adev);
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
-static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev);
-static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr);
 static int vcn_v1_0_set_powergating_state(void *handle, enum amd_powergating_state state);
 static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
-				struct dpg_pause_state *new_state);
+				int inst_idx, struct dpg_pause_state *new_state);
+
+static void vcn_v1_0_idle_work_handler(struct work_struct *work);
 
 /**
  * vcn_v1_0_early_init - set function pointers
@@ -68,9 +70,10 @@ static int vcn_v1_0_early_init(void *handle)
 
 	vcn_v1_0_set_dec_ring_funcs(adev);
 	vcn_v1_0_set_enc_ring_funcs(adev);
-	vcn_v1_0_set_jpeg_ring_funcs(adev);
 	vcn_v1_0_set_irq_funcs(adev);
 
+	jpeg_v1_0_early_init(handle);
+
 	return 0;
 }
 
@@ -101,15 +104,13 @@ static int vcn_v1_0_sw_init(void *handle)
 			return r;
 	}
 
-	/* VCN JPEG TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 126, &adev->vcn.inst->irq);
-	if (r)
-		return r;
-
 	r = amdgpu_vcn_sw_init(adev);
 	if (r)
 		return r;
 
+	/* Override the work func */
+	adev->vcn.idle_work.work.func = vcn_v1_0_idle_work_handler;
+
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		const struct common_firmware_header *hdr;
 		hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
@@ -149,17 +150,11 @@ static int vcn_v1_0_sw_init(void *handle)
 			return r;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	sprintf(ring->name, "vcn_jpeg");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
-	if (r)
-		return r;
-
 	adev->vcn.pause_dpg_mode = vcn_v1_0_pause_dpg_mode;
-	adev->vcn.internal.jpeg_pitch = adev->vcn.inst->external.jpeg_pitch =
-		SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH);
 
-	return 0;
+	r = jpeg_v1_0_sw_init(handle);
+
+	return r;
 }
 
 /**
@@ -178,6 +173,8 @@ static int vcn_v1_0_sw_fini(void *handle)
 	if (r)
 		return r;
 
+	jpeg_v1_0_sw_fini(handle);
+
 	r = amdgpu_vcn_sw_fini(adev);
 
 	return r;
@@ -207,7 +204,7 @@ static int vcn_v1_0_hw_init(void *handle)
 			goto done;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
+	ring = &adev->jpeg.inst->ring_dec;
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		goto done;
@@ -838,9 +835,9 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 
 	vcn_v1_0_mc_resume_spg_mode(adev);
 
-	WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK, 0x10);
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK,
-		RREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK) | 0x3);
+	WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK_1_0, 0x10);
+	WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0,
+		RREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0) | 0x3);
 
 	/* enable VCPU clock */
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CNTL, UVD_VCPU_CNTL__CLK_EN_MASK);
@@ -947,22 +944,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
-			UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
-
-	/* initialize wptr */
-	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-
-	/* copy patch commands to the jpeg ring */
-	vcn_v1_0_jpeg_ring_set_patch_ring(ring,
-		(ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+	jpeg_v1_0_start(adev, 0);
 
 	return 0;
 }
@@ -1106,13 +1088,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_RB_CNTL), 0,
 			~UVD_RBC_RB_CNTL__RB_NO_FETCH_MASK);
 
-	/* initialize JPEG wptr */
-	ring = &adev->vcn.inst->ring_jpeg;
-	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-
-	/* copy patch commands to the jpeg ring */
-	vcn_v1_0_jpeg_ring_set_patch_ring(ring,
-		(ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+	jpeg_v1_0_start(adev, 1);
 
 	return 0;
 }
@@ -1223,7 +1199,7 @@ static int vcn_v1_0_stop(struct amdgpu_device *adev)
 }
 
 static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
-				struct dpg_pause_state *new_state)
+				int inst_idx, struct dpg_pause_state *new_state)
 {
 	int ret_code;
 	uint32_t reg_data = 0;
@@ -1316,7 +1292,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
 							UVD_DPG_PAUSE__JPEG_PAUSE_DPG_ACK_MASK, ret_code);
 
 				/* Restore */
-				ring = &adev->vcn.inst->ring_jpeg;
+				ring = &adev->jpeg.inst->ring_dec;
 				WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
 				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL,
 							UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
@@ -1716,389 +1692,6 @@ static void vcn_v1_0_enc_ring_emit_wreg(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, val);
 }
 
-
-/**
- * vcn_v1_0_jpeg_ring_get_rptr - get read pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware read pointer
- */
-static uint64_t vcn_v1_0_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_get_wptr - get write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware write pointer
- */
-static uint64_t vcn_v1_0_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_set_wptr - set write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Commits the write pointer to the hardware
- */
-static void vcn_v1_0_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
-}
-
-/**
- * vcn_v1_0_jpeg_ring_insert_start - insert a start command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a start command to the ring.
- */
-static void vcn_v1_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x68e04);
-
-	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x80010000);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_insert_end - insert a end command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a end command to the ring.
- */
-static void vcn_v1_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x68e04);
-
-	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x00010000);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_emit_fence - emit an fence & trap command
- *
- * @ring: amdgpu_ring pointer
- * @fence: fence to emit
- *
- * Write a fence and a trap command to the ring.
- */
-static void vcn_v1_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
-				     unsigned flags)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA0), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA1), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x8);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
-	amdgpu_ring_write(ring, 0);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE2));
-	amdgpu_ring_write(ring, 0xffffffff);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x3fbc);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(0, 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x1);
-
-	/* emit trap */
-	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
-	amdgpu_ring_write(ring, 0);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_emit_ib - execute indirect buffer
- *
- * @ring: amdgpu_ring pointer
- * @ib: indirect buffer to execute
- *
- * Write ring commands to execute the indirect buffer.
- */
-static void vcn_v1_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
-					struct amdgpu_job *job,
-					struct amdgpu_ib *ib,
-					uint32_t flags)
-{
-	struct amdgpu_device *adev = ring->adev;
-	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_IB_SIZE), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, ib->length_dw);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
-	amdgpu_ring_write(ring, 0);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x2);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_STATUS), 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
-	amdgpu_ring_write(ring, 0x2);
-}
-
-static void vcn_v1_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring,
-					    uint32_t reg, uint32_t val,
-					    uint32_t mask)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t reg_offset = (reg << 2);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, val);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
-		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
-		amdgpu_ring_write(ring, 0);
-		amdgpu_ring_write(ring,
-			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
-	} else {
-		amdgpu_ring_write(ring, reg_offset);
-		amdgpu_ring_write(ring,
-			PACKETJ(0, 0, 0, PACKETJ_TYPE3));
-	}
-	amdgpu_ring_write(ring, mask);
-}
-
-static void vcn_v1_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
-		unsigned vmid, uint64_t pd_addr)
-{
-	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t data0, data1, mask;
-
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
-
-	/* wait for register write */
-	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
-	data1 = lower_32_bits(pd_addr);
-	mask = 0xffffffff;
-	vcn_v1_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
-}
-
-static void vcn_v1_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring,
-					uint32_t reg, uint32_t val)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t reg_offset = (reg << 2);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
-			((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
-		amdgpu_ring_write(ring, 0);
-		amdgpu_ring_write(ring,
-			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
-	} else {
-		amdgpu_ring_write(ring, reg_offset);
-		amdgpu_ring_write(ring,
-			PACKETJ(0, 0, 0, PACKETJ_TYPE0));
-	}
-	amdgpu_ring_write(ring, val);
-}
-
-static void vcn_v1_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
-{
-	int i;
-
-	WARN_ON(ring->wptr % 2 || count % 2);
-
-	for (i = 0; i < count / 2; i++) {
-		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
-		amdgpu_ring_write(ring, 0);
-	}
-}
-
-static void vcn_v1_0_jpeg_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
-{
-	struct amdgpu_device *adev = ring->adev;
-	ring->ring[(*ptr)++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
-	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
-		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
-		ring->ring[(*ptr)++] = 0;
-		ring->ring[(*ptr)++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0);
-	} else {
-		ring->ring[(*ptr)++] = reg_offset;
-		ring->ring[(*ptr)++] = PACKETJ(0, 0, 0, PACKETJ_TYPE0);
-	}
-	ring->ring[(*ptr)++] = val;
-}
-
-static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	uint32_t reg, reg_offset, val, mask, i;
-
-	// 1st: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW);
-	reg_offset = (reg << 2);
-	val = lower_32_bits(ring->gpu_addr);
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	// 2nd: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH);
-	reg_offset = (reg << 2);
-	val = upper_32_bits(ring->gpu_addr);
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	// 3rd to 5th: issue MEM_READ commands
-	for (i = 0; i <= 2; i++) {
-		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE2);
-		ring->ring[ptr++] = 0;
-	}
-
-	// 6th: program mmUVD_JRBC_RB_CNTL register to enable NO_FETCH and RPTR write ability
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
-	reg_offset = (reg << 2);
-	val = 0x13;
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	// 7th: program mmUVD_JRBC_RB_REF_DATA
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA);
-	reg_offset = (reg << 2);
-	val = 0x1;
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	// 8th: issue conditional register read mmUVD_JRBC_RB_CNTL
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
-	reg_offset = (reg << 2);
-	val = 0x1;
-	mask = 0x1;
-
-	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0);
-	ring->ring[ptr++] = 0x01400200;
-	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0);
-	ring->ring[ptr++] = val;
-	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
-	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
-		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
-		ring->ring[ptr++] = 0;
-		ring->ring[ptr++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3);
-	} else {
-		ring->ring[ptr++] = reg_offset;
-		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE3);
-	}
-	ring->ring[ptr++] = mask;
-
-	//9th to 21st: insert no-op
-	for (i = 0; i <= 12; i++) {
-		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
-		ring->ring[ptr++] = 0;
-	}
-
-	//22nd: reset mmUVD_JRBC_RB_RPTR
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_RPTR);
-	reg_offset = (reg << 2);
-	val = 0;
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	//23rd: program mmUVD_JRBC_RB_CNTL to disable no_fetch
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
-	reg_offset = (reg << 2);
-	val = 0x12;
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-}
-
 static int vcn_v1_0_set_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned type,
@@ -2123,9 +1716,6 @@ static int vcn_v1_0_process_interrupt(struct amdgpu_device *adev,
 	case 120:
 		amdgpu_fence_process(&adev->vcn.inst->ring_enc[1]);
 		break;
-	case 126:
-		amdgpu_fence_process(&adev->vcn.inst->ring_jpeg);
-		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
@@ -2174,6 +1764,86 @@ static int vcn_v1_0_set_powergating_state(void *handle,
 	return ret;
 }
 
+static void vcn_v1_0_idle_work_handler(struct work_struct *work)
+{
+	struct amdgpu_device *adev =
+		container_of(work, struct amdgpu_device, vcn.idle_work.work);
+	unsigned int fences = 0, i;
+
+	for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+		fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]);
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		struct dpg_pause_state new_state;
+
+		if (fences)
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+
+		if (amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec))
+			new_state.jpeg = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
+
+		adev->vcn.pause_dpg_mode(adev, 0, &new_state);
+	}
+
+	fences += amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec);
+	fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_dec);
+
+	if (fences == 0) {
+		amdgpu_gfx_off_ctrl(adev, true);
+		if (adev->pm.dpm_enabled)
+			amdgpu_dpm_enable_uvd(adev, false);
+		else
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+			       AMD_PG_STATE_GATE);
+	} else {
+		schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+	}
+}
+
+void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+
+	if (set_clocks) {
+		amdgpu_gfx_off_ctrl(adev, false);
+		if (adev->pm.dpm_enabled)
+			amdgpu_dpm_enable_uvd(adev, true);
+		else
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+			       AMD_PG_STATE_UNGATE);
+	}
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		struct dpg_pause_state new_state;
+		unsigned int fences = 0, i;
+
+		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+			fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]);
+
+		if (fences)
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+
+		if (amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec))
+			new_state.jpeg = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
+
+		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
+			new_state.jpeg = VCN_DPG_STATE__PAUSE;
+
+		adev->vcn.pause_dpg_mode(adev, 0, &new_state);
+	}
+}
+
 static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 	.name = "vcn_v1_0",
 	.early_init = vcn_v1_0_early_init,
@@ -2220,7 +1890,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.insert_start = vcn_v1_0_dec_ring_insert_start,
 	.insert_end = vcn_v1_0_dec_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
+	.begin_use = vcn_v1_0_ring_begin_use,
 	.end_use = amdgpu_vcn_ring_end_use,
 	.emit_wreg = vcn_v1_0_dec_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_dec_ring_emit_reg_wait,
@@ -2252,48 +1922,13 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
 	.insert_nop = amdgpu_ring_insert_nop,
 	.insert_end = vcn_v1_0_enc_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
+	.begin_use = vcn_v1_0_ring_begin_use,
 	.end_use = amdgpu_vcn_ring_end_use,
 	.emit_wreg = vcn_v1_0_enc_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-static const struct amdgpu_ring_funcs vcn_v1_0_jpeg_ring_vm_funcs = {
-	.type = AMDGPU_RING_TYPE_VCN_JPEG,
-	.align_mask = 0xf,
-	.nop = PACKET0(0x81ff, 0),
-	.support_64bit_ptrs = false,
-	.no_user_fence = true,
-	.vmhub = AMDGPU_MMHUB_0,
-	.extra_dw = 64,
-	.get_rptr = vcn_v1_0_jpeg_ring_get_rptr,
-	.get_wptr = vcn_v1_0_jpeg_ring_get_wptr,
-	.set_wptr = vcn_v1_0_jpeg_ring_set_wptr,
-	.emit_frame_size =
-		6 + 6 + /* hdp invalidate / flush */
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
-		8 + /* vcn_v1_0_jpeg_ring_emit_vm_flush */
-		26 + 26 + /* vcn_v1_0_jpeg_ring_emit_fence x2 vm fence */
-		6,
-	.emit_ib_size = 22, /* vcn_v1_0_jpeg_ring_emit_ib */
-	.emit_ib = vcn_v1_0_jpeg_ring_emit_ib,
-	.emit_fence = vcn_v1_0_jpeg_ring_emit_fence,
-	.emit_vm_flush = vcn_v1_0_jpeg_ring_emit_vm_flush,
-	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
-	.test_ib = amdgpu_vcn_jpeg_ring_test_ib,
-	.insert_nop = vcn_v1_0_jpeg_ring_nop,
-	.insert_start = vcn_v1_0_jpeg_ring_insert_start,
-	.insert_end = vcn_v1_0_jpeg_ring_insert_end,
-	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v1_0_jpeg_ring_emit_wreg,
-	.emit_reg_wait = vcn_v1_0_jpeg_ring_emit_reg_wait,
-	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
-};
-
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
 	adev->vcn.inst->ring_dec.funcs = &vcn_v1_0_dec_ring_vm_funcs;
@@ -2310,12 +1945,6 @@ static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	DRM_INFO("VCN encode is enabled in VM mode\n");
 }
 
-static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev)
-{
-	adev->vcn.inst->ring_jpeg.funcs = &vcn_v1_0_jpeg_ring_vm_funcs;
-	DRM_INFO("VCN jpeg decode is enabled in VM mode\n");
-}
-
 static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = {
 	.set = vcn_v1_0_set_interrupt_state,
 	.process = vcn_v1_0_process_interrupt,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
index 2a497a7a4840..f67d7391fc21 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
@@ -24,6 +24,8 @@
 #ifndef __VCN_V1_0_H__
 #define __VCN_V1_0_H__
 
+void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
+
 extern const struct amdgpu_ip_block_version vcn_v1_0_ip_block;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 38f787a560cb..f4db8af6536b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -47,39 +47,13 @@
 #define mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET		0x5a7
 #define mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET			0x1e2
 
-#define mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET 			0x1bfff
-#define mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET				0x4029
-#define mmUVD_JPEG_GPCOM_DATA0_INTERNAL_OFFSET				0x402a
-#define mmUVD_JPEG_GPCOM_DATA1_INTERNAL_OFFSET				0x402b
-#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET		0x40ea
-#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x40eb
-#define mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET				0x40cf
-#define mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET				0x40d1
-#define mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET 		0x40e8
-#define mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET		0x40e9
-#define mmUVD_JRBC_IB_SIZE_INTERNAL_OFFSET				0x4082
-#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET		0x40ec
-#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x40ed
-#define mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET			0x4085
-#define mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET				0x4084
-#define mmUVD_JRBC_STATUS_INTERNAL_OFFSET				0x4089
-#define mmUVD_JPEG_PITCH_INTERNAL_OFFSET				0x401f
-
-#define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR				0x18000
-
-#define mmUVD_RBC_XX_IB_REG_CHECK 					0x026b
-#define mmUVD_RBC_XX_IB_REG_CHECK_BASE_IDX 				1
-#define mmUVD_REG_XX_MASK 						0x026c
-#define mmUVD_REG_XX_MASK_BASE_IDX 					1
-
 static void vcn_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev);
-static void vcn_v2_0_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev);
 static int vcn_v2_0_set_powergating_state(void *handle,
 				enum amd_powergating_state state);
 static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
-				struct dpg_pause_state *new_state);
+				int inst_idx, struct dpg_pause_state *new_state);
 
 /**
  * vcn_v2_0_early_init - set function pointers
@@ -97,7 +71,6 @@ static int vcn_v2_0_early_init(void *handle)
 
 	vcn_v2_0_set_dec_ring_funcs(adev);
 	vcn_v2_0_set_enc_ring_funcs(adev);
-	vcn_v2_0_set_jpeg_ring_funcs(adev);
 	vcn_v2_0_set_irq_funcs(adev);
 
 	return 0;
@@ -132,12 +105,6 @@ static int vcn_v2_0_sw_init(void *handle)
 			return r;
 	}
 
-	/* VCN JPEG TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
-			      VCN_2_0__SRCID__JPEG_DECODE, &adev->vcn.inst->irq);
-	if (r)
-		return r;
-
 	r = amdgpu_vcn_sw_init(adev);
 	if (r)
 		return r;
@@ -194,19 +161,8 @@ static int vcn_v2_0_sw_init(void *handle)
 			return r;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	ring->use_doorbell = true;
-	ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1;
-	sprintf(ring->name, "vcn_jpeg");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
-	if (r)
-		return r;
-
 	adev->vcn.pause_dpg_mode = vcn_v2_0_pause_dpg_mode;
 
-	adev->vcn.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
-	adev->vcn.inst->external.jpeg_pitch = SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH);
-
 	return 0;
 }
 
@@ -258,11 +214,6 @@ static int vcn_v2_0_hw_init(void *handle)
 			goto done;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	r = amdgpu_ring_test_helper(ring);
-	if (r)
-		goto done;
-
 done:
 	if (!r)
 		DRM_INFO("VCN decode and encode initialized successfully(under %s).\n",
@@ -296,9 +247,6 @@ static int vcn_v2_0_hw_fini(void *handle)
 		ring->sched.ready = false;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	ring->sched.ready = false;
-
 	return 0;
 }
 
@@ -393,7 +341,6 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
 
 	WREG32_SOC15(UVD, 0, mmUVD_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
-	WREG32_SOC15(UVD, 0, mmJPEG_DEC_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
 }
 
 static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirect)
@@ -404,88 +351,88 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec
 	/* cache window 0: fw */
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		if (!indirect) {
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
 				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo), 0, indirect);
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
 				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_hi), 0, indirect);
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
 		} else {
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), 0, 0, indirect);
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), 0, 0, indirect);
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
 		}
 		offset = 0;
 	} else {
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
 			lower_32_bits(adev->vcn.inst->gpu_addr), 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
 			upper_32_bits(adev->vcn.inst->gpu_addr), 0, indirect);
 		offset = size;
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_OFFSET0),
 			AMDGPU_UVD_FIRMWARE_OFFSET >> 3, 0, indirect);
 	}
 
 	if (!indirect)
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_SIZE0), size, 0, indirect);
 	else
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_SIZE0), 0, 0, indirect);
 
 	/* cache window 1: stack */
 	if (!indirect) {
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
 			lower_32_bits(adev->vcn.inst->gpu_addr + offset), 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
 			upper_32_bits(adev->vcn.inst->gpu_addr + offset), 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
 	} else {
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW), 0, 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH), 0, 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
 	}
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CACHE_SIZE1), AMDGPU_VCN_STACK_SIZE, 0, indirect);
 
 	/* cache window 2: context */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
 		lower_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
 		upper_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CACHE_OFFSET2), 0, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE, 0, indirect);
 
 	/* non-cache window */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW), 0, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH), 0, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_NONCACHE_SIZE0), 0, 0, indirect);
 
 	/* VCN global tiling registers */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
 }
 
@@ -631,146 +578,23 @@ static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev,
 		 UVD_CGC_CTRL__WCB_MODE_MASK |
 		 UVD_CGC_CTRL__VCPU_MODE_MASK |
 		 UVD_CGC_CTRL__SCPU_MODE_MASK);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_CGC_CTRL), reg_data, sram_sel, indirect);
 
 	/* turn off clock gating */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_CGC_GATE), 0, sram_sel, indirect);
 
 	/* turn on SUVD clock gating */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_SUVD_CGC_GATE), 1, sram_sel, indirect);
 
 	/* turn on sw mode in UVD_SUVD_CGC_CTRL */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_SUVD_CGC_CTRL), 0, sram_sel, indirect);
 }
 
 /**
- * jpeg_v2_0_start - start JPEG block
- *
- * @adev: amdgpu_device pointer
- *
- * Setup and start the JPEG block
- */
-static int jpeg_v2_0_start(struct amdgpu_device *adev)
-{
-	struct amdgpu_ring *ring = &adev->vcn.inst->ring_jpeg;
-	uint32_t tmp;
-	int r = 0;
-
-	/* disable power gating */
-	tmp = 1 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT;
-	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_PGFSM_CONFIG), tmp);
-
-	SOC15_WAIT_ON_RREG(VCN, 0,
-		mmUVD_PGFSM_STATUS, UVD_PGFSM_STATUS_UVDJ_PWR_ON,
-		UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK, r);
-
-	if (r) {
-		DRM_ERROR("amdgpu: JPEG disable power gating failed\n");
-		return r;
-	}
-
-	/* Removing the anti hang mechanism to indicate the UVDJ tile is ON */
-	tmp = RREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_POWER_STATUS)) & ~0x1;
-	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_POWER_STATUS), tmp);
-
-	/* JPEG disable CGC */
-	tmp = RREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL);
-	tmp |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-	tmp |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-	tmp |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-	WREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL, tmp);
-
-	tmp = RREG32_SOC15(VCN, 0, mmJPEG_CGC_GATE);
-	tmp &= ~(JPEG_CGC_GATE__JPEG_DEC_MASK
-		| JPEG_CGC_GATE__JPEG2_DEC_MASK
-		| JPEG_CGC_GATE__JPEG_ENC_MASK
-		| JPEG_CGC_GATE__JMCIF_MASK
-		| JPEG_CGC_GATE__JRBBM_MASK);
-	WREG32_SOC15(VCN, 0, mmJPEG_CGC_GATE, tmp);
-
-	/* enable JMI channel */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_JMI_CNTL), 0,
-		~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-	/* enable System Interrupt for JRBC */
-	WREG32_P(SOC15_REG_OFFSET(VCN, 0, mmJPEG_SYS_INT_EN),
-		JPEG_SYS_INT_EN__DJRBC_MASK,
-		~JPEG_SYS_INT_EN__DJRBC_MASK);
-
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
-		lower_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
-		upper_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
-	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-
-	return 0;
-}
-
-/**
- * jpeg_v2_0_stop - stop JPEG block
- *
- * @adev: amdgpu_device pointer
- *
- * stop the JPEG block
- */
-static int jpeg_v2_0_stop(struct amdgpu_device *adev)
-{
-	uint32_t tmp;
-	int r = 0;
-
-	/* reset JMI */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_JMI_CNTL),
-		UVD_JMI_CNTL__SOFT_RESET_MASK,
-		~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-	/* enable JPEG CGC */
-	tmp = RREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL);
-	tmp |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-	tmp |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-	tmp |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-	WREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL, tmp);
-
-
-	tmp = RREG32_SOC15(VCN, 0, mmJPEG_CGC_GATE);
-	tmp |= (JPEG_CGC_GATE__JPEG_DEC_MASK
-		|JPEG_CGC_GATE__JPEG2_DEC_MASK
-		|JPEG_CGC_GATE__JPEG_ENC_MASK
-		|JPEG_CGC_GATE__JMCIF_MASK
-		|JPEG_CGC_GATE__JRBBM_MASK);
-	WREG32_SOC15(VCN, 0, mmJPEG_CGC_GATE, tmp);
-
-	/* enable power gating */
-	tmp = RREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_POWER_STATUS));
-	tmp &= ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK;
-	tmp |=  0x1; //UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_TILES_OFF;
-	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_POWER_STATUS), tmp);
-
-	tmp = 2 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT;
-	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_PGFSM_CONFIG), tmp);
-
-	SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS,
-		(2 << UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT),
-		UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK, r);
-
-	if (r) {
-		DRM_ERROR("amdgpu: JPEG enable power gating failed\n");
-		return r;
-	}
-
-	return r;
-}
-
-/**
  * vcn_v2_0_enable_clock_gating - enable VCN clock gating
  *
  * @adev: amdgpu_device pointer
@@ -930,7 +754,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 	WREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS, tmp);
 
 	if (indirect)
-		adev->vcn.dpg_sram_curr_addr = (uint32_t*)adev->vcn.dpg_sram_cpu_addr;
+		adev->vcn.inst->dpg_sram_curr_addr = (uint32_t*)adev->vcn.inst->dpg_sram_cpu_addr;
 
 	/* enable clock gating */
 	vcn_v2_0_clock_gating_dpg_mode(adev, 0, indirect);
@@ -939,11 +763,11 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
 	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
 	tmp |= UVD_VCPU_CNTL__MIF_WR_LOW_THRESHOLD_BP_MASK;
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CNTL), tmp, 0, indirect);
 
 	/* disable master interupt */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MASTINT_EN), 0, 0, indirect);
 
 	/* setup mmUVD_LMI_CTRL */
@@ -955,28 +779,28 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 		UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
 		(8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
 		0x00100000L);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_CTRL), tmp, 0, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MPC_CNTL),
 		0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT, 0, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MPC_SET_MUXA0),
 		((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
 		 (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
 		 (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)), 0, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MPC_SET_MUXB0),
 		((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
 		 (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
 		 (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)), 0, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MPC_SET_MUX),
 		((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
@@ -984,29 +808,29 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 
 	vcn_v2_0_mc_resume_dpg_mode(adev, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_REG_XX_MASK), 0x10, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK), 0x3, 0, indirect);
 
 	/* release VCPU reset to boot */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_SOFT_RESET), 0, 0, indirect);
 
 	/* enable LMI MC and UMC channels */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_CTRL2),
 		0x1F << UVD_LMI_CTRL2__RE_OFLD_MIF_WR_REQ_NUM__SHIFT, 0, indirect);
 
 	/* enable master interrupt */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
 	if (indirect)
-		psp_update_vcn_sram(adev, 0, adev->vcn.dpg_sram_gpu_addr,
-				    (uint32_t)((uintptr_t)adev->vcn.dpg_sram_curr_addr -
-					       (uintptr_t)adev->vcn.dpg_sram_cpu_addr));
+		psp_update_vcn_sram(adev, 0, adev->vcn.inst->dpg_sram_gpu_addr,
+				    (uint32_t)((uintptr_t)adev->vcn.inst->dpg_sram_curr_addr -
+					       (uintptr_t)adev->vcn.inst->dpg_sram_cpu_addr));
 
 	/* force RBC into idle state */
 	rb_bufsz = order_base_2(ring->ring_size);
@@ -1052,12 +876,8 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 	if (adev->pm.dpm_enabled)
 		amdgpu_dpm_enable_uvd(adev, true);
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-		r = vcn_v2_0_start_dpg_mode(adev, adev->vcn.indirect_sram);
-		if (r)
-			return r;
-		goto jpeg;
-	}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v2_0_start_dpg_mode(adev, adev->vcn.indirect_sram);
 
 	vcn_v2_0_disable_static_power_gating(adev);
 
@@ -1209,10 +1029,7 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
 
-jpeg:
-	r = jpeg_v2_0_start(adev);
-
-	return r;
+	return 0;
 }
 
 static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev)
@@ -1231,9 +1048,6 @@ static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev)
 	tmp = RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2);
 	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR2, tmp, 0xFFFFFFFF, ret_code);
 
-	tmp = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_JRBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
-
 	tmp = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF;
 	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
 
@@ -1252,10 +1066,6 @@ static int vcn_v2_0_stop(struct amdgpu_device *adev)
 	uint32_t tmp;
 	int r;
 
-	r = jpeg_v2_0_stop(adev);
-	if (r)
-		return r;
-
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
 		r = vcn_v2_0_stop_dpg_mode(adev);
 		if (r)
@@ -1320,7 +1130,7 @@ power_off:
 }
 
 static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
-				struct dpg_pause_state *new_state)
+				int inst_idx, struct dpg_pause_state *new_state)
 {
 	struct amdgpu_ring *ring;
 	uint32_t reg_data = 0;
@@ -1781,272 +1591,6 @@ void vcn_v2_0_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_
 	amdgpu_ring_write(ring, val);
 }
 
-/**
- * vcn_v2_0_jpeg_ring_get_rptr - get read pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware read pointer
- */
-static uint64_t vcn_v2_0_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_get_wptr - get write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware write pointer
- */
-static uint64_t vcn_v2_0_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
-	else
-		return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_set_wptr - set write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Commits the write pointer to the hardware
- */
-static void vcn_v2_0_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
-		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
-	} else {
-		WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
-	}
-}
-
-/**
- * vcn_v2_0_jpeg_ring_insert_start - insert a start command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a start command to the ring.
- */
-void vcn_v2_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
-{
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x68e04);
-
-	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x80010000);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_insert_end - insert a end command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a end command to the ring.
- */
-void vcn_v2_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
-{
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x68e04);
-
-	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x00010000);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_emit_fence - emit an fence & trap command
- *
- * @ring: amdgpu_ring pointer
- * @fence: fence to emit
- *
- * Write a fence and a trap command to the ring.
- */
-void vcn_v2_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
-				unsigned flags)
-{
-	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JPEG_GPCOM_DATA0_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_DATA1_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x8);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET,
-		0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
-	amdgpu_ring_write(ring, 0);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x3fbc);
-
-	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x1);
-
-	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
-	amdgpu_ring_write(ring, 0);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_emit_ib - execute indirect buffer
- *
- * @ring: amdgpu_ring pointer
- * @ib: indirect buffer to execute
- *
- * Write ring commands to execute the indirect buffer.
- */
-void vcn_v2_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
-				struct amdgpu_job *job,
-				struct amdgpu_ib *ib,
-				uint32_t flags)
-{
-	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_IB_SIZE_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, ib->length_dw);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
-	amdgpu_ring_write(ring, 0);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x2);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_STATUS_INTERNAL_OFFSET,
-		0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
-	amdgpu_ring_write(ring, 0x2);
-}
-
-void vcn_v2_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
-				uint32_t val, uint32_t mask)
-{
-	uint32_t reg_offset = (reg << 2);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, val);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
-		amdgpu_ring_write(ring, 0);
-		amdgpu_ring_write(ring,
-			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
-	} else {
-		amdgpu_ring_write(ring, reg_offset);
-		amdgpu_ring_write(ring,	PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-			0, 0, PACKETJ_TYPE3));
-	}
-	amdgpu_ring_write(ring, mask);
-}
-
-void vcn_v2_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
-				unsigned vmid, uint64_t pd_addr)
-{
-	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t data0, data1, mask;
-
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
-
-	/* wait for register write */
-	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
-	data1 = lower_32_bits(pd_addr);
-	mask = 0xffffffff;
-	vcn_v2_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
-}
-
-void vcn_v2_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
-{
-	uint32_t reg_offset = (reg << 2);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
-		amdgpu_ring_write(ring, 0);
-		amdgpu_ring_write(ring,
-			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
-	} else {
-		amdgpu_ring_write(ring, reg_offset);
-		amdgpu_ring_write(ring,	PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-			0, 0, PACKETJ_TYPE0));
-	}
-	amdgpu_ring_write(ring, val);
-}
-
-void vcn_v2_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
-{
-	int i;
-
-	WARN_ON(ring->wptr % 2 || count % 2);
-
-	for (i = 0; i < count / 2; i++) {
-		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
-		amdgpu_ring_write(ring, 0);
-	}
-}
-
 static int vcn_v2_0_set_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned type,
@@ -2071,9 +1615,6 @@ static int vcn_v2_0_process_interrupt(struct amdgpu_device *adev,
 	case VCN_2_0__SRCID__UVD_ENC_LOW_LATENCY:
 		amdgpu_fence_process(&adev->vcn.inst->ring_enc[1]);
 		break;
-	case VCN_2_0__SRCID__JPEG_DECODE:
-		amdgpu_fence_process(&adev->vcn.inst->ring_jpeg);
-		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
@@ -2219,36 +1760,6 @@ static const struct amdgpu_ring_funcs vcn_v2_0_enc_ring_vm_funcs = {
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-static const struct amdgpu_ring_funcs vcn_v2_0_jpeg_ring_vm_funcs = {
-	.type = AMDGPU_RING_TYPE_VCN_JPEG,
-	.align_mask = 0xf,
-	.vmhub = AMDGPU_MMHUB_0,
-	.get_rptr = vcn_v2_0_jpeg_ring_get_rptr,
-	.get_wptr = vcn_v2_0_jpeg_ring_get_wptr,
-	.set_wptr = vcn_v2_0_jpeg_ring_set_wptr,
-	.emit_frame_size =
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
-		8 + /* vcn_v2_0_jpeg_ring_emit_vm_flush */
-		18 + 18 + /* vcn_v2_0_jpeg_ring_emit_fence x2 vm fence */
-		8 + 16,
-	.emit_ib_size = 22, /* vcn_v2_0_jpeg_ring_emit_ib */
-	.emit_ib = vcn_v2_0_jpeg_ring_emit_ib,
-	.emit_fence = vcn_v2_0_jpeg_ring_emit_fence,
-	.emit_vm_flush = vcn_v2_0_jpeg_ring_emit_vm_flush,
-	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
-	.test_ib = amdgpu_vcn_jpeg_ring_test_ib,
-	.insert_nop = vcn_v2_0_jpeg_ring_nop,
-	.insert_start = vcn_v2_0_jpeg_ring_insert_start,
-	.insert_end = vcn_v2_0_jpeg_ring_insert_end,
-	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v2_0_jpeg_ring_emit_wreg,
-	.emit_reg_wait = vcn_v2_0_jpeg_ring_emit_reg_wait,
-	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
-};
-
 static void vcn_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
 	adev->vcn.inst->ring_dec.funcs = &vcn_v2_0_dec_ring_vm_funcs;
@@ -2265,12 +1776,6 @@ static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	DRM_INFO("VCN encode is enabled in VM mode\n");
 }
 
-static void vcn_v2_0_set_jpeg_ring_funcs(struct amdgpu_device *adev)
-{
-	adev->vcn.inst->ring_jpeg.funcs = &vcn_v2_0_jpeg_ring_vm_funcs;
-	DRM_INFO("VCN jpeg decode is enabled in VM mode\n");
-}
-
 static const struct amdgpu_irq_src_funcs vcn_v2_0_irq_funcs = {
 	.set = vcn_v2_0_set_interrupt_state,
 	.process = vcn_v2_0_process_interrupt,
@@ -2278,7 +1783,7 @@ static const struct amdgpu_irq_src_funcs vcn_v2_0_irq_funcs = {
 
 static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 2;
+	adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 1;
 	adev->vcn.inst->irq.funcs = &vcn_v2_0_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.h
index 8467292f32e5..ef749b02ded9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.h
@@ -49,19 +49,6 @@ extern void vcn_v2_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
 				unsigned int vmid, uint64_t pd_addr);
 extern void vcn_v2_0_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
 
-extern void vcn_v2_0_jpeg_ring_insert_start(struct amdgpu_ring *ring);
-extern void vcn_v2_0_jpeg_ring_insert_end(struct amdgpu_ring *ring);
-extern void vcn_v2_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
-				unsigned flags);
-extern void vcn_v2_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_job *job,
-				struct amdgpu_ib *ib, uint32_t flags);
-extern void vcn_v2_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
-				uint32_t val, uint32_t mask);
-extern void vcn_v2_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
-				unsigned vmid, uint64_t pd_addr);
-extern void vcn_v2_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
-extern void vcn_v2_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count);
-
 extern const struct amdgpu_ip_block_version vcn_v2_0_ip_block;
 
 #endif /* __VCN_V2_0_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 93edf9193a7b..c8b63d57a541 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -29,6 +29,7 @@
 #include "soc15.h"
 #include "soc15d.h"
 #include "vcn_v2_0.h"
+#include "mmsch_v1_0.h"
 
 #include "vcn/vcn_2_5_offset.h"
 #include "vcn/vcn_2_5_sh_mask.h"
@@ -47,16 +48,16 @@
 #define mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x3b5
 #define mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET			0x25c
 
-#define mmUVD_JPEG_PITCH_INTERNAL_OFFSET			0x401f
-
-#define VCN25_MAX_HW_INSTANCES_ARCTURUS				2
+#define VCN25_MAX_HW_INSTANCES_ARCTURUS			2
 
 static void vcn_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev);
-static void vcn_v2_5_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev);
 static int vcn_v2_5_set_powergating_state(void *handle,
 				enum amd_powergating_state state);
+static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev,
+				int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v2_5_sriov_start(struct amdgpu_device *adev);
 
 static int amdgpu_ih_clientid_vcns[] = {
 	SOC15_IH_CLIENTID_VCN,
@@ -91,11 +92,16 @@ static int vcn_v2_5_early_init(void *handle)
 	} else
 		adev->vcn.num_vcn_inst = 1;
 
-	adev->vcn.num_enc_rings = 2;
+	if (amdgpu_sriov_vf(adev)) {
+		adev->vcn.num_vcn_inst = 2;
+		adev->vcn.harvest_config = 0;
+		adev->vcn.num_enc_rings = 1;
+	} else {
+		adev->vcn.num_enc_rings = 2;
+	}
 
 	vcn_v2_5_set_dec_ring_funcs(adev);
 	vcn_v2_5_set_enc_ring_funcs(adev);
-	vcn_v2_5_set_jpeg_ring_funcs(adev);
 	vcn_v2_5_set_irq_funcs(adev);
 
 	return 0;
@@ -130,12 +136,6 @@ static int vcn_v2_5_sw_init(void *handle)
 			if (r)
 				return r;
 		}
-
-		/* VCN JPEG TRAP */
-		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[j],
-				VCN_2_0__SRCID__JPEG_DECODE, &adev->vcn.inst[j].irq);
-		if (r)
-			return r;
 	}
 
 	r = amdgpu_vcn_sw_init(adev);
@@ -184,12 +184,11 @@ static int vcn_v2_5_sw_init(void *handle)
 		adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
 		adev->vcn.inst[j].external.nop = SOC15_REG_OFFSET(UVD, j, mmUVD_NO_OP);
 
-		adev->vcn.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
-		adev->vcn.inst[j].external.jpeg_pitch = SOC15_REG_OFFSET(UVD, j, mmUVD_JPEG_PITCH);
-
 		ring = &adev->vcn.inst[j].ring_dec;
 		ring->use_doorbell = true;
-		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8*j;
+
+		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+				(amdgpu_sriov_vf(adev) ? 2*j : 8*j);
 		sprintf(ring->name, "vcn_dec_%d", j);
 		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[j].irq, 0);
 		if (r)
@@ -198,22 +197,26 @@ static int vcn_v2_5_sw_init(void *handle)
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
 			ring = &adev->vcn.inst[j].ring_enc[i];
 			ring->use_doorbell = true;
-			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + i + 8*j;
+
+			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+					(amdgpu_sriov_vf(adev) ? (1 + i + 2*j) : (2 + i + 8*j));
+
 			sprintf(ring->name, "vcn_enc_%d.%d", j, i);
 			r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[j].irq, 0);
 			if (r)
 				return r;
 		}
+	}
 
-		ring = &adev->vcn.inst[j].ring_jpeg;
-		ring->use_doorbell = true;
-		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1 + 8*j;
-		sprintf(ring->name, "vcn_jpeg_%d", j);
-		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[j].irq, 0);
+	if (amdgpu_sriov_vf(adev)) {
+		r = amdgpu_virt_alloc_mm_table(adev);
 		if (r)
 			return r;
 	}
 
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		adev->vcn.pause_dpg_mode = vcn_v2_5_pause_dpg_mode;
+
 	return 0;
 }
 
@@ -229,6 +232,9 @@ static int vcn_v2_5_sw_fini(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_free_mm_table(adev);
+
 	r = amdgpu_vcn_suspend(adev);
 	if (r)
 		return r;
@@ -249,35 +255,44 @@ static int vcn_v2_5_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct amdgpu_ring *ring;
-	int i, j, r;
+	int i, j, r = 0;
+
+	if (amdgpu_sriov_vf(adev))
+		r = vcn_v2_5_sriov_start(adev);
 
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
-		ring = &adev->vcn.inst[j].ring_dec;
 
-		adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
-						     ring->doorbell_index, j);
+		if (amdgpu_sriov_vf(adev)) {
+			adev->vcn.inst[j].ring_enc[0].sched.ready = true;
+			adev->vcn.inst[j].ring_enc[1].sched.ready = false;
+			adev->vcn.inst[j].ring_enc[2].sched.ready = false;
+			adev->vcn.inst[j].ring_dec.sched.ready = true;
+		} else {
 
-		r = amdgpu_ring_test_helper(ring);
-		if (r)
-			goto done;
+			ring = &adev->vcn.inst[j].ring_dec;
+
+			adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+						     ring->doorbell_index, j);
 
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-			ring = &adev->vcn.inst[j].ring_enc[i];
 			r = amdgpu_ring_test_helper(ring);
 			if (r)
 				goto done;
-		}
 
-		ring = &adev->vcn.inst[j].ring_jpeg;
-		r = amdgpu_ring_test_helper(ring);
-		if (r)
-			goto done;
+			for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+				ring = &adev->vcn.inst[j].ring_enc[i];
+				r = amdgpu_ring_test_helper(ring);
+				if (r)
+					goto done;
+			}
+		}
 	}
+
 done:
 	if (!r)
-		DRM_INFO("VCN decode and encode initialized successfully.\n");
+		DRM_INFO("VCN decode and encode initialized successfully(under %s).\n",
+			(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)?"DPG Mode":"SPG Mode");
 
 	return r;
 }
@@ -300,7 +315,9 @@ static int vcn_v2_5_hw_fini(void *handle)
 			continue;
 		ring = &adev->vcn.inst[i].ring_dec;
 
-		if (RREG32_SOC15(VCN, i, mmUVD_STATUS))
+		if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
+		    (adev->vcn.cur_state != AMD_PG_STATE_GATE &&
+		     RREG32_SOC15(VCN, i, mmUVD_STATUS)))
 			vcn_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 
 		ring->sched.ready = false;
@@ -309,9 +326,6 @@ static int vcn_v2_5_hw_fini(void *handle)
 			ring = &adev->vcn.inst[i].ring_enc[j];
 			ring->sched.ready = false;
 		}
-
-		ring = &adev->vcn.inst[i].ring_jpeg;
-		ring->sched.ready = false;
 	}
 
 	return 0;
@@ -378,9 +392,9 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
 		/* cache window 0: fw */
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo));
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo));
 			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_hi));
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi));
 			WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_OFFSET0, 0);
 			offset = 0;
 		} else {
@@ -412,6 +426,99 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
 	}
 }
 
+static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+{
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t offset;
+
+	/* cache window 0: fw */
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		if (!indirect) {
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + inst_idx].tmr_mc_addr_lo), 0, indirect);
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + inst_idx].tmr_mc_addr_hi), 0, indirect);
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
+		} else {
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), 0, 0, indirect);
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), 0, 0, indirect);
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
+		}
+		offset = 0;
+	} else {
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr), 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr), 0, indirect);
+		offset = size;
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET0),
+			AMDGPU_UVD_FIRMWARE_OFFSET >> 3, 0, indirect);
+	}
+
+	if (!indirect)
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_SIZE0), size, 0, indirect);
+	else
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_SIZE0), 0, 0, indirect);
+
+	/* cache window 1: stack */
+	if (!indirect) {
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset), 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset), 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
+	} else {
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW), 0, 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH), 0, 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
+	}
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CACHE_SIZE1), AMDGPU_VCN_STACK_SIZE, 0, indirect);
+
+	/* cache window 2: context */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
+		lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
+		upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET2), 0, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE, 0, indirect);
+
+	/* non-cache window */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW), 0, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH), 0, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_NONCACHE_SIZE0), 0, 0, indirect);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_GFX8_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+}
+
 /**
  * vcn_v2_5_disable_clock_gating - disable VCN clock gating
  *
@@ -530,6 +637,54 @@ static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev)
 	}
 }
 
+static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev,
+		uint8_t sram_sel, int inst_idx, uint8_t indirect)
+{
+	uint32_t reg_data = 0;
+
+	/* enable sw clock gating control */
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
+		reg_data = 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		reg_data = 0 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	reg_data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	reg_data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	reg_data &= ~(UVD_CGC_CTRL__UDEC_RE_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_CM_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_IT_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_DB_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_MP_MODE_MASK |
+		 UVD_CGC_CTRL__SYS_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_MODE_MASK |
+		 UVD_CGC_CTRL__MPEG2_MODE_MASK |
+		 UVD_CGC_CTRL__REGS_MODE_MASK |
+		 UVD_CGC_CTRL__RBC_MODE_MASK |
+		 UVD_CGC_CTRL__LMI_MC_MODE_MASK |
+		 UVD_CGC_CTRL__LMI_UMC_MODE_MASK |
+		 UVD_CGC_CTRL__IDCT_MODE_MASK |
+		 UVD_CGC_CTRL__MPRD_MODE_MASK |
+		 UVD_CGC_CTRL__MPC_MODE_MASK |
+		 UVD_CGC_CTRL__LBSI_MODE_MASK |
+		 UVD_CGC_CTRL__LRBBM_MODE_MASK |
+		 UVD_CGC_CTRL__WCB_MODE_MASK |
+		 UVD_CGC_CTRL__VCPU_MODE_MASK |
+		 UVD_CGC_CTRL__MMSCH_MODE_MASK);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_CGC_CTRL), reg_data, sram_sel, indirect);
+
+	/* turn off clock gating */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_CGC_GATE), 0, sram_sel, indirect);
+
+	/* turn on SUVD clock gating */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_SUVD_CGC_GATE), 1, sram_sel, indirect);
+
+	/* turn on sw mode in UVD_SUVD_CGC_CTRL */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_SUVD_CGC_CTRL), 0, sram_sel, indirect);
+}
+
 /**
  * vcn_v2_5_enable_clock_gating - enable VCN clock gating
  *
@@ -592,111 +747,134 @@ static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev)
 	}
 }
 
-/**
- * jpeg_v2_5_start - start JPEG block
- *
- * @adev: amdgpu_device pointer
- *
- * Setup and start the JPEG block
- */
-static int jpeg_v2_5_start(struct amdgpu_device *adev)
+static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
 {
 	struct amdgpu_ring *ring;
-	uint32_t tmp;
-	int i;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		ring = &adev->vcn.inst[i].ring_jpeg;
-		/* disable anti hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_JPEG_POWER_STATUS), 0,
-			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
-
-		/* JPEG disable CGC */
-		tmp = RREG32_SOC15(VCN, i, mmJPEG_CGC_CTRL);
-		tmp |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-		tmp |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-		tmp |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-		WREG32_SOC15(VCN, i, mmJPEG_CGC_CTRL, tmp);
-
-		tmp = RREG32_SOC15(VCN, i, mmJPEG_CGC_GATE);
-		tmp &= ~(JPEG_CGC_GATE__JPEG_DEC_MASK
-			| JPEG_CGC_GATE__JPEG2_DEC_MASK
-			| JPEG_CGC_GATE__JMCIF_MASK
-			| JPEG_CGC_GATE__JRBBM_MASK);
-		WREG32_SOC15(VCN, i, mmJPEG_CGC_GATE, tmp);
-
-		tmp = RREG32_SOC15(VCN, i, mmJPEG_CGC_CTRL);
-		tmp &= ~(JPEG_CGC_CTRL__JPEG_DEC_MODE_MASK
-			| JPEG_CGC_CTRL__JPEG2_DEC_MODE_MASK
-			| JPEG_CGC_CTRL__JMCIF_MODE_MASK
-			| JPEG_CGC_CTRL__JRBBM_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmJPEG_CGC_CTRL, tmp);
-
-		/* MJPEG global tiling registers */
-		WREG32_SOC15(UVD, i, mmJPEG_DEC_GFX8_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-		WREG32_SOC15(UVD, i, mmJPEG_DEC_GFX10_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-
-		/* enable JMI channel */
-		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_JMI_CNTL), 0,
-			~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-		/* enable System Interrupt for JRBC */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmJPEG_SYS_INT_EN),
-			JPEG_SYS_INT_EN__DJRBC_MASK,
-			~JPEG_SYS_INT_EN__DJRBC_MASK);
-
-		WREG32_SOC15(UVD, i, mmUVD_LMI_JRBC_RB_VMID, 0);
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
-		WREG32_SOC15(UVD, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
-			lower_32_bits(ring->gpu_addr));
-		WREG32_SOC15(UVD, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
-			upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_RPTR, 0);
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_WPTR, 0);
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_CNTL, 0x00000002L);
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
-		ring->wptr = RREG32_SOC15(UVD, i, mmUVD_JRBC_RB_WPTR);
-	}
-
-	return 0;
-}
-
-/**
- * jpeg_v2_5_stop - stop JPEG block
- *
- * @adev: amdgpu_device pointer
- *
- * stop the JPEG block
- */
-static int jpeg_v2_5_stop(struct amdgpu_device *adev)
-{
-	uint32_t tmp;
-	int i;
+	uint32_t rb_bufsz, tmp;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* reset JMI */
-		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_JMI_CNTL),
-			UVD_JMI_CNTL__SOFT_RESET_MASK,
-			~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, mmJPEG_CGC_GATE);
-		tmp |= (JPEG_CGC_GATE__JPEG_DEC_MASK
-			|JPEG_CGC_GATE__JPEG2_DEC_MASK
-			|JPEG_CGC_GATE__JMCIF_MASK
-			|JPEG_CGC_GATE__JRBBM_MASK);
-		WREG32_SOC15(VCN, i, mmJPEG_CGC_GATE, tmp);
-
-		/* enable anti hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_JPEG_POWER_STATUS),
-			UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
-			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
-	}
+	/* disable register anti-hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(UVD, inst_idx, mmUVD_POWER_STATUS), 1,
+		~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
+	/* enable dynamic power gating mode */
+	tmp = RREG32_SOC15(UVD, inst_idx, mmUVD_POWER_STATUS);
+	tmp |= UVD_POWER_STATUS__UVD_PG_MODE_MASK;
+	tmp |= UVD_POWER_STATUS__UVD_PG_EN_MASK;
+	WREG32_SOC15(UVD, inst_idx, mmUVD_POWER_STATUS, tmp);
+
+	if (indirect)
+		adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t*)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr;
+
+	/* enable clock gating */
+	vcn_v2_5_clock_gating_dpg_mode(adev, 0, inst_idx, indirect);
+
+	/* enable VCPU clock */
+	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
+	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
+	tmp |= UVD_VCPU_CNTL__BLK_RST_MASK;
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CNTL), tmp, 0, indirect);
+
+	/* disable master interupt */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MASTINT_EN), 0, 0, indirect);
+
+	/* setup mmUVD_LMI_CTRL */
+	tmp = (0x8 | UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		UVD_LMI_CTRL__REQ_MODE_MASK |
+		UVD_LMI_CTRL__CRC_RESET_MASK |
+		UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
+		(8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
+		0x00100000L);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_CTRL), tmp, 0, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MPC_CNTL),
+		0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT, 0, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MPC_SET_MUXA0),
+		((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		 (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		 (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		 (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)), 0, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MPC_SET_MUXB0),
+		((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		 (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		 (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		 (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)), 0, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MPC_SET_MUX),
+		((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect);
+
+	vcn_v2_5_mc_resume_dpg_mode(adev, inst_idx, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_REG_XX_MASK), 0x10, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_RBC_XX_IB_REG_CHECK), 0x3, 0, indirect);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_CTRL2), 0, 0, indirect);
+
+	/* unblock VCPU register access */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_RB_ARB_CTRL), 0, 0, indirect);
+
+	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
+	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CNTL), tmp, 0, indirect);
+
+	/* enable master interrupt */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MASTINT_EN),
+		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
+
+	if (indirect)
+		psp_update_vcn_sram(adev, inst_idx, adev->vcn.inst[inst_idx].dpg_sram_gpu_addr,
+				    (uint32_t)((uintptr_t)adev->vcn.inst[inst_idx].dpg_sram_curr_addr -
+					       (uintptr_t)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr));
+
+	ring = &adev->vcn.inst[inst_idx].ring_dec;
+	/* force RBC into idle state */
+	rb_bufsz = order_base_2(ring->ring_size);
+	tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_CNTL, tmp);
+
+	/* set the write pointer delay */
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_WPTR_CNTL, 0);
+
+	/* set the wb address */
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_RPTR_ADDR,
+		(upper_32_bits(ring->gpu_addr) >> 2));
+
+	/* programm the RB_BASE for ring buffer */
+	WREG32_SOC15(UVD, inst_idx, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
+		lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(UVD, inst_idx, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
+		upper_32_bits(ring->gpu_addr));
+
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_RPTR, 0);
+
+	WREG32_SOC15(UVD, inst_idx, mmUVD_SCRATCH2, 0);
+
+	ring->wptr = RREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_RPTR);
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_WPTR,
+		lower_32_bits(ring->wptr));
 
 	return 0;
 }
@@ -713,6 +891,9 @@ static int vcn_v2_5_start(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			return vcn_v2_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
+
 		/* disable register anti-hang mechanism */
 		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_POWER_STATUS), 0,
 			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
@@ -874,23 +1055,251 @@ static int vcn_v2_5_start(struct amdgpu_device *adev)
 		WREG32_SOC15(UVD, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 		WREG32_SOC15(UVD, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
 	}
-	r = jpeg_v2_5_start(adev);
 
-	return r;
+	return 0;
 }
 
-static int vcn_v2_5_stop(struct amdgpu_device *adev)
+static int vcn_v2_5_mmsch_start(struct amdgpu_device *adev,
+				struct amdgpu_mm_table *table)
+{
+	uint32_t data = 0, loop = 0, size = 0;
+	uint64_t addr = table->gpu_addr;
+	struct mmsch_v1_1_init_header *header = NULL;;
+
+	header = (struct mmsch_v1_1_init_header *)table->cpu_addr;
+	size = header->total_size;
+
+	/*
+	 * 1, write to vce_mmsch_vf_ctx_addr_lo/hi register with GPU mc addr of
+	 *  memory descriptor location
+	 */
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_CTX_ADDR_LO, lower_32_bits(addr));
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_CTX_ADDR_HI, upper_32_bits(addr));
+
+	/* 2, update vmid of descriptor */
+	data = RREG32_SOC15(UVD, 0, mmMMSCH_VF_VMID);
+	data &= ~MMSCH_VF_VMID__VF_CTX_VMID_MASK;
+	/* use domain0 for MM scheduler */
+	data |= (0 << MMSCH_VF_VMID__VF_CTX_VMID__SHIFT);
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_VMID, data);
+
+	/* 3, notify mmsch about the size of this descriptor */
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_CTX_SIZE, size);
+
+	/* 4, set resp to zero */
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_MAILBOX_RESP, 0);
+
+	/*
+	 * 5, kick off the initialization and wait until
+	 * VCE_MMSCH_VF_MAILBOX_RESP becomes non-zero
+	 */
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_MAILBOX_HOST, 0x10000001);
+
+	data = RREG32_SOC15(UVD, 0, mmMMSCH_VF_MAILBOX_RESP);
+	loop = 10;
+	while ((data & 0x10000002) != 0x10000002) {
+		udelay(100);
+		data = RREG32_SOC15(UVD, 0, mmMMSCH_VF_MAILBOX_RESP);
+		loop--;
+		if (!loop)
+			break;
+	}
+
+	if (!loop) {
+		dev_err(adev->dev,
+			"failed to init MMSCH, mmMMSCH_VF_MAILBOX_RESP = %x\n",
+			data);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int vcn_v2_5_sriov_start(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	uint32_t offset, size, tmp, i, rb_bufsz;
+	uint32_t table_size = 0;
+	struct mmsch_v1_0_cmd_direct_write direct_wt = { { 0 } };
+	struct mmsch_v1_0_cmd_direct_read_modify_write direct_rd_mod_wt = { { 0 } };
+	struct mmsch_v1_0_cmd_direct_polling direct_poll = { { 0 } };
+	struct mmsch_v1_0_cmd_end end = { { 0 } };
+	uint32_t *init_table = adev->virt.mm_table.cpu_addr;
+	struct mmsch_v1_1_init_header *header = (struct mmsch_v1_1_init_header *)init_table;
+
+	direct_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_WRITE;
+	direct_rd_mod_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_READ_MODIFY_WRITE;
+	direct_poll.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_POLLING;
+	end.cmd_header.command_type = MMSCH_COMMAND__END;
+
+	header->version = MMSCH_VERSION;
+	header->total_size = sizeof(struct mmsch_v1_1_init_header) >> 2;
+	init_table += header->total_size;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		header->eng[i].table_offset = header->total_size;
+		header->eng[i].init_status = 0;
+		header->eng[i].table_size = 0;
+
+		table_size = 0;
+
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_STATUS),
+			~UVD_STATUS__UVD_BUSY, UVD_STATUS__UVD_BUSY);
+
+		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+		/* mc resume*/
+		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i,
+					mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo);
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i,
+					mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi);
+			offset = 0;
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET0), 0);
+		} else {
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i,
+					mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				lower_32_bits(adev->vcn.inst[i].gpu_addr));
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i,
+					mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				upper_32_bits(adev->vcn.inst[i].gpu_addr));
+			offset = size;
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET0),
+				AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+		}
+
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE0),
+			size);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[i].gpu_addr + offset));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[i].gpu_addr + offset));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET1),
+			0);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE1),
+			AMDGPU_VCN_STACK_SIZE);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[i].gpu_addr + offset +
+				AMDGPU_VCN_STACK_SIZE));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[i].gpu_addr + offset +
+				AMDGPU_VCN_STACK_SIZE));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET2),
+			0);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE2),
+			AMDGPU_VCN_CONTEXT_SIZE);
+
+		ring = &adev->vcn.inst[i].ring_enc[0];
+		ring->wptr = 0;
+
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_RB_BASE_LO),
+			lower_32_bits(ring->gpu_addr));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_RB_BASE_HI),
+			upper_32_bits(ring->gpu_addr));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_RB_SIZE),
+			ring->ring_size / 4);
+
+		ring = &adev->vcn.inst[i].ring_dec;
+		ring->wptr = 0;
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_RBC_RB_64BIT_BAR_LOW),
+			lower_32_bits(ring->gpu_addr));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH),
+			upper_32_bits(ring->gpu_addr));
+
+		/* force RBC into idle state */
+		rb_bufsz = order_base_2(ring->ring_size);
+		tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_RBC_RB_CNTL), tmp);
+
+		/* add end packet */
+		memcpy((void *)init_table, &end, sizeof(struct mmsch_v1_0_cmd_end));
+		table_size += sizeof(struct mmsch_v1_0_cmd_end) / 4;
+		init_table += sizeof(struct mmsch_v1_0_cmd_end) / 4;
+
+		/* refine header */
+		header->eng[i].table_size = table_size;
+		header->total_size += table_size;
+	}
+
+	return vcn_v2_5_mmsch_start(adev, &adev->virt.mm_table);
+}
+
+static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 {
+	int ret_code = 0;
 	uint32_t tmp;
-	int i, r;
 
-	r = jpeg_v2_5_stop(adev);
-	if (r)
-		return r;
+	/* Wait for power status to be 1 */
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS, 1,
+		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+
+	/* wait for read ptr to be equal to write ptr */
+	tmp = RREG32_SOC15(UVD, inst_idx, mmUVD_RB_WPTR);
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+
+	tmp = RREG32_SOC15(UVD, inst_idx, mmUVD_RB_WPTR2);
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_RB_RPTR2, tmp, 0xFFFFFFFF, ret_code);
+
+	tmp = RREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF;
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS, 1,
+		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+
+	/* disable dynamic power gating mode */
+	WREG32_P(SOC15_REG_OFFSET(UVD, inst_idx, mmUVD_POWER_STATUS), 0,
+			~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
+
+	return 0;
+}
+
+static int vcn_v2_5_stop(struct amdgpu_device *adev)
+{
+	uint32_t tmp;
+	int i, r = 0;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+			r = vcn_v2_5_stop_dpg_mode(adev, i);
+			goto power_off;
+		}
+
 		/* wait for vcn idle */
 		SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7, r);
 		if (r)
@@ -940,12 +1349,74 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev)
 			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
 	}
 
+power_off:
 	if (adev->pm.dpm_enabled)
 		amdgpu_dpm_enable_uvd(adev, false);
 
 	return 0;
 }
 
+static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev,
+				int inst_idx, struct dpg_pause_state *new_state)
+{
+	struct amdgpu_ring *ring;
+	uint32_t reg_data = 0;
+	int ret_code;
+
+	/* pause/unpause if state is changed */
+	if (adev->vcn.pause_state.fw_based != new_state->fw_based) {
+		DRM_DEBUG("dpg pause state changed %d -> %d",
+			adev->vcn.pause_state.fw_based,	new_state->fw_based);
+		reg_data = RREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE) &
+			(~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+
+		if (new_state->fw_based == VCN_DPG_STATE__PAUSE) {
+			ret_code = 0;
+			SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS, 0x1,
+				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+
+			if (!ret_code) {
+				/* pause DPG */
+				reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+				WREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE, reg_data);
+
+				/* wait for ACK */
+				SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_DPG_PAUSE,
+					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
+					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, ret_code);
+
+				/* Restore */
+				ring = &adev->vcn.inst[inst_idx].ring_enc[0];
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_BASE_LO, ring->gpu_addr);
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_SIZE, ring->ring_size / 4);
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+
+				ring = &adev->vcn.inst[inst_idx].ring_enc[1];
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_SIZE2, ring->ring_size / 4);
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_WPTR,
+					   RREG32_SOC15(UVD, inst_idx, mmUVD_SCRATCH2) & 0x7FFFFFFF);
+
+				SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS,
+					   0x0, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+			}
+		} else {
+			/* unpause dpg, no need to wait */
+			reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+			WREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE, reg_data);
+		}
+		adev->vcn.pause_state.fw_based = new_state->fw_based;
+	}
+
+	return 0;
+}
+
 /**
  * vcn_v2_5_dec_ring_get_rptr - get read pointer
  *
@@ -988,6 +1459,10 @@ static void vcn_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		WREG32_SOC15(UVD, ring->me, mmUVD_SCRATCH2,
+			lower_32_bits(ring->wptr) | 0x80000000);
+
 	if (ring->use_doorbell) {
 		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
@@ -1125,86 +1600,6 @@ static const struct amdgpu_ring_funcs vcn_v2_5_enc_ring_vm_funcs = {
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-/**
- * vcn_v2_5_jpeg_ring_get_rptr - get read pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware read pointer
- */
-static uint64_t vcn_v2_5_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	return RREG32_SOC15(UVD, ring->me, mmUVD_JRBC_RB_RPTR);
-}
-
-/**
- * vcn_v2_5_jpeg_ring_get_wptr - get write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware write pointer
- */
-static uint64_t vcn_v2_5_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
-	else
-		return RREG32_SOC15(UVD, ring->me, mmUVD_JRBC_RB_WPTR);
-}
-
-/**
- * vcn_v2_5_jpeg_ring_set_wptr - set write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Commits the write pointer to the hardware
- */
-static void vcn_v2_5_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
-		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
-	} else {
-		WREG32_SOC15(UVD, ring->me, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
-	}
-}
-
-static const struct amdgpu_ring_funcs vcn_v2_5_jpeg_ring_vm_funcs = {
-	.type = AMDGPU_RING_TYPE_VCN_JPEG,
-	.align_mask = 0xf,
-	.vmhub = AMDGPU_MMHUB_1,
-	.get_rptr = vcn_v2_5_jpeg_ring_get_rptr,
-	.get_wptr = vcn_v2_5_jpeg_ring_get_wptr,
-	.set_wptr = vcn_v2_5_jpeg_ring_set_wptr,
-	.emit_frame_size =
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
-		8 + /* vcn_v2_0_jpeg_ring_emit_vm_flush */
-		18 + 18 + /* vcn_v2_0_jpeg_ring_emit_fence x2 vm fence */
-		8 + 16,
-	.emit_ib_size = 22, /* vcn_v2_0_jpeg_ring_emit_ib */
-	.emit_ib = vcn_v2_0_jpeg_ring_emit_ib,
-	.emit_fence = vcn_v2_0_jpeg_ring_emit_fence,
-	.emit_vm_flush = vcn_v2_0_jpeg_ring_emit_vm_flush,
-	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
-	.test_ib = amdgpu_vcn_jpeg_ring_test_ib,
-	.insert_nop = vcn_v2_0_jpeg_ring_nop,
-	.insert_start = vcn_v2_0_jpeg_ring_insert_start,
-	.insert_end = vcn_v2_0_jpeg_ring_insert_end,
-	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v2_0_jpeg_ring_emit_wreg,
-	.emit_reg_wait = vcn_v2_0_jpeg_ring_emit_reg_wait,
-	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
-};
-
 static void vcn_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
@@ -1233,19 +1628,6 @@ static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev)
 	}
 }
 
-static void vcn_v2_5_set_jpeg_ring_funcs(struct amdgpu_device *adev)
-{
-	int i;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		adev->vcn.inst[i].ring_jpeg.funcs = &vcn_v2_5_jpeg_ring_vm_funcs;
-		adev->vcn.inst[i].ring_jpeg.me = i;
-		DRM_INFO("VCN(%d) jpeg decode is enabled in VM mode\n", i);
-	}
-}
-
 static bool vcn_v2_5_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1283,6 +1665,9 @@ static int vcn_v2_5_set_clockgating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	if (enable) {
 		if (vcn_v2_5_is_idle(handle))
 			return -EBUSY;
@@ -1300,6 +1685,9 @@ static int vcn_v2_5_set_powergating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int ret;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	if(state == adev->vcn.cur_state)
 		return 0;
 
@@ -1352,9 +1740,6 @@ static int vcn_v2_5_process_interrupt(struct amdgpu_device *adev,
 	case VCN_2_0__SRCID__UVD_ENC_LOW_LATENCY:
 		amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_enc[1]);
 		break;
-	case VCN_2_0__SRCID__JPEG_DECODE:
-		amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_jpeg);
-		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
@@ -1376,7 +1761,7 @@ static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
-		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 2;
+		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1;
 		adev->vcn.inst[i].irq.funcs = &vcn_v2_5_irq_funcs;
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 5cb7e231de5f..d9e331084ea0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -234,16 +234,9 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 	WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI, (ih->gpu_addr >> 40) & 0xff);
 
 	ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL);
-	ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN);
 	ih_rb_cntl = vega10_ih_rb_cntl(ih, ih_rb_cntl);
-	if (adev->irq.ih.use_bus_addr) {
-		ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN, MC_SPACE_GPA_ENABLE, 1);
-	} else {
-		ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN, MC_SPACE_FBPA_ENABLE, 1);
-	}
 	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RPTR_REARM,
 				   !!adev->irq.msi_enabled);
-
 	if (amdgpu_sriov_vf(adev)) {
 		if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL, ih_rb_cntl)) {
 			DRM_ERROR("PSP program IH_RB_CNTL failed!\n");
@@ -253,10 +246,19 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 		WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl);
 	}
 
-	if ((adev->asic_type == CHIP_ARCTURUS
-		&& adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT)
-		|| adev->asic_type == CHIP_RENOIR)
+	if ((adev->asic_type == CHIP_ARCTURUS &&
+	     adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) ||
+	    adev->asic_type == CHIP_RENOIR) {
+		ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN);
+		if (adev->irq.ih.use_bus_addr) {
+			ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN,
+						   MC_SPACE_GPA_ENABLE, 1);
+		} else {
+			ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN,
+						   MC_SPACE_FBPA_ENABLE, 1);
+		}
 		WREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN, ih_chicken);
+	}
 
 	/* set the writeback address whether it's enabled or not */
 	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_LO,
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index f1b171e30774..78b35901643b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -689,40 +689,6 @@ static int vi_gpu_pci_config_reset(struct amdgpu_device *adev)
 	return -EINVAL;
 }
 
-int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap)
-{
-	void *pp_handle = adev->powerplay.pp_handle;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (!pp_funcs || !pp_funcs->get_asic_baco_capability) {
-		*cap = false;
-		return -ENOENT;
-	}
-
-	return pp_funcs->get_asic_baco_capability(pp_handle, cap);
-}
-
-int smu7_asic_baco_reset(struct amdgpu_device *adev)
-{
-	void *pp_handle = adev->powerplay.pp_handle;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (!pp_funcs ||!pp_funcs->get_asic_baco_state ||!pp_funcs->set_asic_baco_state)
-		return -ENOENT;
-
-	/* enter BACO state */
-	if (pp_funcs->set_asic_baco_state(pp_handle, 1))
-		return -EIO;
-
-	/* exit BACO state */
-	if (pp_funcs->set_asic_baco_state(pp_handle, 0))
-		return -EIO;
-
-	dev_info(adev->dev, "GPU BACO reset\n");
-
-	return 0;
-}
-
 /**
  * vi_asic_pci_config_reset - soft reset GPU
  *
@@ -745,6 +711,21 @@ static int vi_asic_pci_config_reset(struct amdgpu_device *adev)
 	return r;
 }
 
+static bool vi_asic_supports_baco(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_FIJI:
+	case CHIP_TONGA:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+	case CHIP_TOPAZ:
+		return amdgpu_dpm_is_baco_supported(adev);
+	default:
+		return false;
+	}
+}
+
 static enum amd_reset_method
 vi_asic_reset_method(struct amdgpu_device *adev)
 {
@@ -757,7 +738,7 @@ vi_asic_reset_method(struct amdgpu_device *adev)
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
 	case CHIP_TOPAZ:
-		smu7_asic_get_baco_capability(adev, &baco_reset);
+		baco_reset = amdgpu_dpm_is_baco_supported(adev);
 		break;
 	default:
 		baco_reset = false;
@@ -786,7 +767,7 @@ static int vi_asic_reset(struct amdgpu_device *adev)
 	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 		if (!adev->in_suspend)
 			amdgpu_inc_vram_lost(adev);
-		r = smu7_asic_baco_reset(adev);
+		r = amdgpu_dpm_baco_reset(adev);
 	} else {
 		r = vi_asic_pci_config_reset(adev);
 	}
@@ -1119,6 +1100,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.get_pcie_usage = &vi_get_pcie_usage,
 	.need_reset_on_init = &vi_need_reset_on_init,
 	.get_pcie_replay_count = &vi_get_pcie_replay_count,
+	.supports_baco = &vi_asic_supports_baco,
 };
 
 #define CZ_REV_BRISTOL(rev)	 \
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.h b/drivers/gpu/drm/amd/amdgpu/vi.h
index 40d4174913a4..defb4aaf929a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.h
+++ b/drivers/gpu/drm/amd/amdgpu/vi.h
@@ -31,7 +31,5 @@ void vi_srbm_select(struct amdgpu_device *adev,
 int vi_set_ip_blocks(struct amdgpu_device *adev);
 
 void legacy_doorbell_index_init(struct amdgpu_device *adev);
-int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap);
-int smu7_asic_baco_reset(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile
index 48155060a57c..61474627a32c 100644
--- a/drivers/gpu/drm/amd/amdkfd/Makefile
+++ b/drivers/gpu/drm/amd/amdkfd/Makefile
@@ -38,11 +38,9 @@ AMDKFD_FILES	:= $(AMDKFD_PATH)/kfd_module.o \
 		$(AMDKFD_PATH)/kfd_mqd_manager_v9.o \
 		$(AMDKFD_PATH)/kfd_mqd_manager_v10.o \
 		$(AMDKFD_PATH)/kfd_kernel_queue.o \
-		$(AMDKFD_PATH)/kfd_kernel_queue_cik.o \
-		$(AMDKFD_PATH)/kfd_kernel_queue_vi.o \
-		$(AMDKFD_PATH)/kfd_kernel_queue_v9.o \
-		$(AMDKFD_PATH)/kfd_kernel_queue_v10.o \
 		$(AMDKFD_PATH)/kfd_packet_manager.o \
+		$(AMDKFD_PATH)/kfd_packet_manager_vi.o \
+		$(AMDKFD_PATH)/kfd_packet_manager_v9.o \
 		$(AMDKFD_PATH)/kfd_process_queue_manager.o \
 		$(AMDKFD_PATH)/kfd_device_queue_manager.o \
 		$(AMDKFD_PATH)/kfd_device_queue_manager_cik.o \
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 1544007af34a..3f0300e53727 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -42,6 +42,7 @@
 
 static long kfd_ioctl(struct file *, unsigned int, unsigned long);
 static int kfd_open(struct inode *, struct file *);
+static int kfd_release(struct inode *, struct file *);
 static int kfd_mmap(struct file *, struct vm_area_struct *);
 
 static const char kfd_dev_name[] = "kfd";
@@ -51,6 +52,7 @@ static const struct file_operations kfd_fops = {
 	.unlocked_ioctl = kfd_ioctl,
 	.compat_ioctl = compat_ptr_ioctl,
 	.open = kfd_open,
+	.release = kfd_release,
 	.mmap = kfd_mmap,
 };
 
@@ -124,8 +126,13 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
-	if (kfd_is_locked())
+	if (kfd_is_locked()) {
+		kfd_unref_process(process);
 		return -EAGAIN;
+	}
+
+	/* filep now owns the reference returned by kfd_create_process */
+	filep->private_data = process;
 
 	dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n",
 		process->pasid, process->is_32bit_user_mode);
@@ -133,6 +140,16 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	return 0;
 }
 
+static int kfd_release(struct inode *inode, struct file *filep)
+{
+	struct kfd_process *process = filep->private_data;
+
+	if (process)
+		kfd_unref_process(process);
+
+	return 0;
+}
+
 static int kfd_ioctl_get_version(struct file *filep, struct kfd_process *p,
 					void *data)
 {
@@ -258,6 +275,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	unsigned int queue_id;
 	struct kfd_process_device *pdd;
 	struct queue_properties q_properties;
+	uint32_t doorbell_offset_in_process = 0;
 
 	memset(&q_properties, 0, sizeof(struct queue_properties));
 
@@ -286,7 +304,8 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 			p->pasid,
 			dev->id);
 
-	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id);
+	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id,
+			&doorbell_offset_in_process);
 	if (err != 0)
 		goto err_create_queue;
 
@@ -296,14 +315,11 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	/* Return gpu_id as doorbell offset for mmap usage */
 	args->doorbell_offset = KFD_MMAP_TYPE_DOORBELL;
 	args->doorbell_offset |= KFD_MMAP_GPU_ID(args->gpu_id);
-	args->doorbell_offset <<= PAGE_SHIFT;
 	if (KFD_IS_SOC15(dev->device_info->asic_family))
-		/* On SOC15 ASICs, doorbell allocation must be
-		 * per-device, and independent from the per-process
-		 * queue_id. Return the doorbell offset within the
-		 * doorbell aperture to user mode.
+		/* On SOC15 ASICs, include the doorbell offset within the
+		 * process doorbell frame, which is 2 pages.
 		 */
-		args->doorbell_offset |= q_properties.doorbell_off;
+		args->doorbell_offset |= doorbell_offset_in_process;
 
 	mutex_unlock(&p->mutex);
 
@@ -1312,10 +1328,9 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 	/* MMIO is mapped through kfd device
 	 * Generate a kfd mmap offset
 	 */
-	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) {
-		args->mmap_offset = KFD_MMAP_TYPE_MMIO | KFD_MMAP_GPU_ID(args->gpu_id);
-		args->mmap_offset <<= PAGE_SHIFT;
-	}
+	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP)
+		args->mmap_offset = KFD_MMAP_TYPE_MMIO
+					| KFD_MMAP_GPU_ID(args->gpu_id);
 
 	return 0;
 
@@ -1803,9 +1818,14 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 
 	dev_dbg(kfd_device, "ioctl cmd 0x%x (#0x%x), arg 0x%lx\n", cmd, nr, arg);
 
-	process = kfd_get_process(current);
-	if (IS_ERR(process)) {
-		dev_dbg(kfd_device, "no process\n");
+	/* Get the process struct from the filep. Only the process
+	 * that opened /dev/kfd can use the file descriptor. Child
+	 * processes need to create their own KFD device context.
+	 */
+	process = filep->private_data;
+	if (process->lead_thread != current->group_leader) {
+		dev_dbg(kfd_device, "Using KFD FD in wrong process\n");
+		retcode = -EBADF;
 		goto err_i1;
 	}
 
@@ -1899,20 +1919,19 @@ static int kfd_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct kfd_process *process;
 	struct kfd_dev *dev = NULL;
-	unsigned long vm_pgoff;
+	unsigned long mmap_offset;
 	unsigned int gpu_id;
 
 	process = kfd_get_process(current);
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
-	vm_pgoff = vma->vm_pgoff;
-	vma->vm_pgoff = KFD_MMAP_OFFSET_VALUE_GET(vm_pgoff);
-	gpu_id = KFD_MMAP_GPU_ID_GET(vm_pgoff);
+	mmap_offset = vma->vm_pgoff << PAGE_SHIFT;
+	gpu_id = KFD_MMAP_GET_GPU_ID(mmap_offset);
 	if (gpu_id)
 		dev = kfd_device_by_id(gpu_id);
 
-	switch (vm_pgoff & KFD_MMAP_TYPE_MASK) {
+	switch (mmap_offset & KFD_MMAP_TYPE_MASK) {
 	case KFD_MMAP_TYPE_DOORBELL:
 		if (!dev)
 			return -ENODEV;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index d59f2cd056c6..27bcc5b472f6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -72,11 +72,11 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 	 * The receive packet buff will be sitting on the Indirect Buffer
 	 * and in the PQ we put the IB packet + sync packet(s).
 	 */
-	status = kq->ops.acquire_packet_buffer(kq,
+	status = kq_acquire_packet_buffer(kq,
 				pq_packets_size_in_bytes / sizeof(uint32_t),
 				&ib_packet_buff);
 	if (status) {
-		pr_err("acquire_packet_buffer failed\n");
+		pr_err("kq_acquire_packet_buffer failed\n");
 		return status;
 	}
 
@@ -115,7 +115,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 
 	if (status) {
 		pr_err("Failed to allocate GART memory\n");
-		kq->ops.rollback_packet(kq);
+		kq_rollback_packet(kq);
 		return status;
 	}
 
@@ -151,7 +151,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 
 	rm_packet->data_lo = QUEUESTATE__ACTIVE;
 
-	kq->ops.submit_packet(kq);
+	kq_submit_packet(kq);
 
 	/* Wait till CP writes sync code: */
 	status = amdkfd_fence_wait_timeout(
@@ -185,7 +185,7 @@ static int dbgdev_register_diq(struct kfd_dbgdev *dbgdev)
 	properties.type = KFD_QUEUE_TYPE_DIQ;
 
 	status = pqm_create_queue(dbgdev->pqm, dbgdev->dev, NULL,
-				&properties, &qid);
+				&properties, &qid, NULL);
 
 	if (status) {
 		pr_err("Failed to create DIQ\n");
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index 15c523027285..511712c2e382 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -93,7 +93,7 @@ void kfd_debugfs_init(void)
 			    kfd_debugfs_hqds_by_device, &kfd_debugfs_fops);
 	debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
 			    kfd_debugfs_rls_by_device, &kfd_debugfs_fops);
-	debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
+	debugfs_create_file("hang_hws", S_IFREG | 0200, debugfs_root,
 			    NULL, &kfd_debugfs_hang_hws_fops);
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 4fa8834ce7cb..2a9e40131735 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -728,6 +728,9 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 {
 	if (!kfd->init_complete)
 		return 0;
+
+	kfd->dqm->ops.pre_reset(kfd->dqm);
+
 	kgd2kfd_suspend(kfd);
 
 	kfd_signal_reset_event(kfd);
@@ -742,7 +745,7 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 
 int kgd2kfd_post_reset(struct kfd_dev *kfd)
 {
-	int ret, count;
+	int ret;
 
 	if (!kfd->init_complete)
 		return 0;
@@ -750,7 +753,7 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
 	ret = kfd_resume(kfd);
 	if (ret)
 		return ret;
-	count = atomic_dec_return(&kfd_locked);
+	atomic_dec(&kfd_locked);
 
 	atomic_set(&kfd->sram_ecc_flag, 0);
 
@@ -822,6 +825,21 @@ dqm_start_error:
 	return err;
 }
 
+static inline void kfd_queue_work(struct workqueue_struct *wq,
+				  struct work_struct *work)
+{
+	int cpu, new_cpu;
+
+	cpu = new_cpu = smp_processor_id();
+	do {
+		new_cpu = cpumask_next(new_cpu, cpu_online_mask) % nr_cpu_ids;
+		if (cpu_to_node(new_cpu) == numa_node_id())
+			break;
+	} while (cpu != new_cpu);
+
+	queue_work_on(new_cpu, wq, work);
+}
+
 /* This is called directly from KGD at ISR. */
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 {
@@ -844,7 +862,7 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 				   patched_ihre, &is_patched)
 	    && enqueue_ih_ring_entry(kfd,
 				     is_patched ? patched_ihre : ih_ring_entry))
-		queue_work(kfd->ih_wq, &kfd->interrupt_work);
+		kfd_queue_work(kfd->ih_wq, &kfd->interrupt_work);
 
 	spin_unlock_irqrestore(&kfd->interrupt_lock, flags);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 984c2f2b24b6..2870553a2ce0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -170,7 +170,7 @@ static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 	}
 
 	q->properties.doorbell_off =
-		kfd_doorbell_id_to_offset(dev, q->process,
+		kfd_get_doorbell_dw_offset_in_bar(dev, q->process,
 					  q->doorbell_id);
 
 	return 0;
@@ -930,11 +930,11 @@ static void uninitialize(struct device_queue_manager *dqm)
 	for (i = 0 ; i < KFD_MQD_TYPE_MAX ; i++)
 		kfree(dqm->mqd_mgrs[i]);
 	mutex_destroy(&dqm->lock_hidden);
-	kfd_gtt_sa_free(dqm->dev, dqm->pipeline_mem);
 }
 
 static int start_nocpsch(struct device_queue_manager *dqm)
 {
+	pr_info("SW scheduler is used");
 	init_interrupts(dqm);
 	
 	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
@@ -947,12 +947,19 @@ static int start_nocpsch(struct device_queue_manager *dqm)
 static int stop_nocpsch(struct device_queue_manager *dqm)
 {
 	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
-		pm_uninit(&dqm->packets);
+		pm_uninit(&dqm->packets, false);
 	dqm->sched_running = false;
 
 	return 0;
 }
 
+static void pre_reset(struct device_queue_manager *dqm)
+{
+	dqm_lock(dqm);
+	dqm->is_resetting = true;
+	dqm_unlock(dqm);
+}
+
 static int allocate_sdma_queue(struct device_queue_manager *dqm,
 				struct queue *q)
 {
@@ -1100,6 +1107,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	dqm_lock(dqm);
 	/* clear hang status when driver try to start the hw scheduler */
 	dqm->is_hws_hang = false;
+	dqm->is_resetting = false;
 	dqm->sched_running = true;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	dqm_unlock(dqm);
@@ -1107,20 +1115,24 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	return 0;
 fail_allocate_vidmem:
 fail_set_sched_resources:
-	pm_uninit(&dqm->packets);
+	pm_uninit(&dqm->packets, false);
 fail_packet_manager_init:
 	return retval;
 }
 
 static int stop_cpsch(struct device_queue_manager *dqm)
 {
+	bool hanging;
+
 	dqm_lock(dqm);
-	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	if (!dqm->is_hws_hang)
+		unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	hanging = dqm->is_hws_hang || dqm->is_resetting;
 	dqm->sched_running = false;
 	dqm_unlock(dqm);
 
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
-	pm_uninit(&dqm->packets);
+	pm_uninit(&dqm->packets, hanging);
 
 	return 0;
 }
@@ -1352,8 +1364,17 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	/* should be timed out */
 	retval = amdkfd_fence_wait_timeout(dqm->fence_addr, KFD_FENCE_COMPLETED,
 				queue_preemption_timeout_ms);
-	if (retval)
+	if (retval) {
+		pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n");
+		dqm->is_hws_hang = true;
+		/* It's possible we're detecting a HWS hang in the
+		 * middle of a GPU reset. No need to schedule another
+		 * reset in this case.
+		 */
+		if (!dqm->is_resetting)
+			schedule_work(&dqm->hw_exception_work);
 		return retval;
+	}
 
 	pm_release_ib(&dqm->packets);
 	dqm->active_runlist = false;
@@ -1371,12 +1392,8 @@ static int execute_queues_cpsch(struct device_queue_manager *dqm,
 	if (dqm->is_hws_hang)
 		return -EIO;
 	retval = unmap_queues_cpsch(dqm, filter, filter_param);
-	if (retval) {
-		pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n");
-		dqm->is_hws_hang = true;
-		schedule_work(&dqm->hw_exception_work);
+	if (retval)
 		return retval;
-	}
 
 	return map_queues_cpsch(dqm);
 }
@@ -1595,7 +1612,7 @@ static int get_wave_state(struct device_queue_manager *dqm,
 		goto dqm_unlock;
 	}
 
-	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_COMPUTE];
+	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_CP];
 
 	if (!mqd_mgr->get_wave_state) {
 		r = -EINVAL;
@@ -1770,6 +1787,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.initialize = initialize_cpsch;
 		dqm->ops.start = start_cpsch;
 		dqm->ops.stop = stop_cpsch;
+		dqm->ops.pre_reset = pre_reset;
 		dqm->ops.destroy_queue = destroy_queue_cpsch;
 		dqm->ops.update_queue = update_queue;
 		dqm->ops.register_process = register_process;
@@ -1788,6 +1806,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		/* initialize dqm for no cp scheduling */
 		dqm->ops.start = start_nocpsch;
 		dqm->ops.stop = stop_nocpsch;
+		dqm->ops.pre_reset = pre_reset;
 		dqm->ops.create_queue = create_queue_nocpsch;
 		dqm->ops.destroy_queue = destroy_queue_nocpsch;
 		dqm->ops.update_queue = update_queue;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index a8c37e6da027..871d3b628d2d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -104,6 +104,7 @@ struct device_queue_manager_ops {
 	int	(*initialize)(struct device_queue_manager *dqm);
 	int	(*start)(struct device_queue_manager *dqm);
 	int	(*stop)(struct device_queue_manager *dqm);
+	void	(*pre_reset)(struct device_queue_manager *dqm);
 	void	(*uninitialize)(struct device_queue_manager *dqm);
 	int	(*create_kernel_queue)(struct device_queue_manager *dqm,
 					struct kernel_queue *kq,
@@ -190,7 +191,6 @@ struct device_queue_manager {
 	/* the pasid mapping for each kfd vmid */
 	uint16_t		vmid_pasid[VMID_NUM];
 	uint64_t		pipelines_addr;
-	struct kfd_mem_obj	*pipeline_mem;
 	uint64_t		fence_gpu_addr;
 	unsigned int		*fence_addr;
 	struct kfd_mem_obj	*fence_mem;
@@ -199,6 +199,7 @@ struct device_queue_manager {
 
 	/* hw exception  */
 	bool			is_hws_hang;
+	bool			is_resetting;
 	struct work_struct	hw_exception_work;
 	struct kfd_mem_obj	hiq_sdma_mqd;
 	bool			sched_running;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index ebe79bf00145..8e0c00b9555e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -91,7 +91,7 @@ int kfd_doorbell_init(struct kfd_dev *kfd)
 	kfd->doorbell_base = kfd->shared_resources.doorbell_physical_address +
 				doorbell_start_offset;
 
-	kfd->doorbell_id_offset = doorbell_start_offset / sizeof(u32);
+	kfd->doorbell_base_dw_offset = doorbell_start_offset / sizeof(u32);
 
 	kfd->doorbell_kernel_ptr = ioremap(kfd->doorbell_base,
 					   kfd_doorbell_process_slice(kfd));
@@ -103,8 +103,8 @@ int kfd_doorbell_init(struct kfd_dev *kfd)
 	pr_debug("doorbell base           == 0x%08lX\n",
 			(uintptr_t)kfd->doorbell_base);
 
-	pr_debug("doorbell_id_offset      == 0x%08lX\n",
-			kfd->doorbell_id_offset);
+	pr_debug("doorbell_base_dw_offset      == 0x%08lX\n",
+			kfd->doorbell_base_dw_offset);
 
 	pr_debug("doorbell_process_limit  == 0x%08lX\n",
 			doorbell_process_limit);
@@ -185,7 +185,7 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 	 * Calculating the kernel doorbell offset using the first
 	 * doorbell page.
 	 */
-	*doorbell_off = kfd->doorbell_id_offset + inx;
+	*doorbell_off = kfd->doorbell_base_dw_offset + inx;
 
 	pr_debug("Get kernel queue doorbell\n"
 			"     doorbell offset   == 0x%08X\n"
@@ -225,17 +225,17 @@ void write_kernel_doorbell64(void __iomem *db, u64 value)
 	}
 }
 
-unsigned int kfd_doorbell_id_to_offset(struct kfd_dev *kfd,
+unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd,
 					struct kfd_process *process,
 					unsigned int doorbell_id)
 {
 	/*
-	 * doorbell_id_offset accounts for doorbells taken by KGD.
+	 * doorbell_base_dw_offset accounts for doorbells taken by KGD.
 	 * index * kfd_doorbell_process_slice/sizeof(u32) adjusts to
 	 * the process's doorbells. The offset returned is in dword
 	 * units regardless of the ASIC-dependent doorbell size.
 	 */
-	return kfd->doorbell_id_offset +
+	return kfd->doorbell_base_dw_offset +
 		process->doorbell_index
 		* kfd_doorbell_process_slice(kfd) / sizeof(u32) +
 		doorbell_id * kfd->device_info->doorbell_size / sizeof(u32);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 908081c85de1..1f8365575b12 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -346,7 +346,6 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		ret = create_signal_event(devkfd, p, ev);
 		if (!ret) {
 			*event_page_offset = KFD_MMAP_TYPE_EVENTS;
-			*event_page_offset <<= PAGE_SHIFT;
 			*event_slot_index = ev->event_id;
 		}
 		break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 193e2835bd4d..8d871514671e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -62,9 +62,6 @@ int kfd_iommu_device_init(struct kfd_dev *kfd)
 	struct amd_iommu_device_info iommu_info;
 	unsigned int pasid_limit;
 	int err;
-	struct kfd_topology_device *top_dev;
-
-	top_dev = kfd_topology_device_by_id(kfd->id);
 
 	if (!kfd->device_info->needs_iommu_device)
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 11d244891393..bae706462f96 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -34,7 +34,10 @@
 
 #define PM4_COUNT_ZERO (((1 << 15) - 1) << 16)
 
-static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
+/* Initialize a kernel queue, including allocations of GART memory
+ * needed for the queue.
+ */
+static bool kq_initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		enum kfd_queue_type type, unsigned int queue_size)
 {
 	struct queue_properties prop;
@@ -87,9 +90,17 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	kq->pq_kernel_addr = kq->pq->cpu_ptr;
 	kq->pq_gpu_addr = kq->pq->gpu_addr;
 
-	retval = kq->ops_asic_specific.initialize(kq, dev, type, queue_size);
-	if (!retval)
-		goto err_eop_allocate_vidmem;
+	/* For CIK family asics, kq->eop_mem is not needed */
+	if (dev->device_info->asic_family > CHIP_MULLINS) {
+		retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
+		if (retval != 0)
+			goto err_eop_allocate_vidmem;
+
+		kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
+		kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
+
+		memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
+	}
 
 	retval = kfd_gtt_sa_allocate(dev, sizeof(*kq->rptr_kernel),
 					&kq->rptr_mem);
@@ -183,9 +194,10 @@ err_get_kernel_doorbell:
 
 }
 
-static void uninitialize(struct kernel_queue *kq)
+/* Uninitialize a kernel queue and free all its memory usages. */
+static void kq_uninitialize(struct kernel_queue *kq, bool hanging)
 {
-	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
+	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ && !hanging)
 		kq->mqd_mgr->destroy_mqd(kq->mqd_mgr,
 					kq->queue->mqd,
 					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
@@ -200,14 +212,19 @@ static void uninitialize(struct kernel_queue *kq)
 
 	kfd_gtt_sa_free(kq->dev, kq->rptr_mem);
 	kfd_gtt_sa_free(kq->dev, kq->wptr_mem);
-	kq->ops_asic_specific.uninitialize(kq);
+
+	/* For CIK family asics, kq->eop_mem is Null, kfd_gtt_sa_free()
+	 * is able to handle NULL properly.
+	 */
+	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
+
 	kfd_gtt_sa_free(kq->dev, kq->pq);
 	kfd_release_kernel_doorbell(kq->dev,
 					kq->queue->properties.doorbell_ptr);
 	uninit_queue(kq->queue);
 }
 
-static int acquire_packet_buffer(struct kernel_queue *kq,
+int kq_acquire_packet_buffer(struct kernel_queue *kq,
 		size_t packet_size_in_dwords, unsigned int **buffer_ptr)
 {
 	size_t available_size;
@@ -268,7 +285,7 @@ err_no_space:
 	return -ENOMEM;
 }
 
-static void submit_packet(struct kernel_queue *kq)
+void kq_submit_packet(struct kernel_queue *kq)
 {
 #ifdef DEBUG
 	int i;
@@ -280,11 +297,18 @@ static void submit_packet(struct kernel_queue *kq)
 	}
 	pr_debug("\n");
 #endif
-
-	kq->ops_asic_specific.submit_packet(kq);
+	if (kq->dev->device_info->doorbell_size == 8) {
+		*kq->wptr64_kernel = kq->pending_wptr64;
+		write_kernel_doorbell64(kq->queue->properties.doorbell_ptr,
+					kq->pending_wptr64);
+	} else {
+		*kq->wptr_kernel = kq->pending_wptr;
+		write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
+					kq->pending_wptr);
+	}
 }
 
-static void rollback_packet(struct kernel_queue *kq)
+void kq_rollback_packet(struct kernel_queue *kq)
 {
 	if (kq->dev->device_info->doorbell_size == 8) {
 		kq->pending_wptr64 = *kq->wptr64_kernel;
@@ -304,60 +328,18 @@ struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 	if (!kq)
 		return NULL;
 
-	kq->ops.initialize = initialize;
-	kq->ops.uninitialize = uninitialize;
-	kq->ops.acquire_packet_buffer = acquire_packet_buffer;
-	kq->ops.submit_packet = submit_packet;
-	kq->ops.rollback_packet = rollback_packet;
-
-	switch (dev->device_info->asic_family) {
-	case CHIP_CARRIZO:
-	case CHIP_TONGA:
-	case CHIP_FIJI:
-	case CHIP_POLARIS10:
-	case CHIP_POLARIS11:
-	case CHIP_POLARIS12:
-	case CHIP_VEGAM:
-		kernel_queue_init_vi(&kq->ops_asic_specific);
-		break;
-
-	case CHIP_KAVERI:
-	case CHIP_HAWAII:
-		kernel_queue_init_cik(&kq->ops_asic_specific);
-		break;
-
-	case CHIP_VEGA10:
-	case CHIP_VEGA12:
-	case CHIP_VEGA20:
-	case CHIP_RAVEN:
-	case CHIP_RENOIR:
-	case CHIP_ARCTURUS:
-		kernel_queue_init_v9(&kq->ops_asic_specific);
-		break;
-	case CHIP_NAVI10:
-	case CHIP_NAVI12:
-	case CHIP_NAVI14:
-		kernel_queue_init_v10(&kq->ops_asic_specific);
-		break;
-	default:
-		WARN(1, "Unexpected ASIC family %u",
-		     dev->device_info->asic_family);
-		goto out_free;
-	}
-
-	if (kq->ops.initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE))
+	if (kq_initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE))
 		return kq;
 
 	pr_err("Failed to init kernel queue\n");
 
-out_free:
 	kfree(kq);
 	return NULL;
 }
 
-void kernel_queue_uninit(struct kernel_queue *kq)
+void kernel_queue_uninit(struct kernel_queue *kq, bool hanging)
 {
-	kq->ops.uninitialize(kq);
+	kq_uninitialize(kq, hanging);
 	kfree(kq);
 }
 
@@ -377,7 +359,7 @@ static __attribute__((unused)) void test_kq(struct kfd_dev *dev)
 		return;
 	}
 
-	retval = kq->ops.acquire_packet_buffer(kq, 5, &buffer);
+	retval = kq_acquire_packet_buffer(kq, 5, &buffer);
 	if (unlikely(retval != 0)) {
 		pr_err("  Failed to acquire packet buffer\n");
 		pr_err("Kernel queue test failed\n");
@@ -385,7 +367,7 @@ static __attribute__((unused)) void test_kq(struct kfd_dev *dev)
 	}
 	for (i = 0; i < 5; i++)
 		buffer[i] = kq->nop_packet;
-	kq->ops.submit_packet(kq);
+	kq_submit_packet(kq);
 
 	pr_err("Ending kernel queue test\n");
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
index 365fc674fea4..f4cfe9f1871c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
@@ -29,45 +29,28 @@
 #include "kfd_priv.h"
 
 /**
- * struct kernel_queue_ops
- *
- * @initialize: Initialize a kernel queue, including allocations of GART memory
- * needed for the queue.
- *
- * @uninitialize: Uninitialize a kernel queue and free all its memory usages.
- *
- * @acquire_packet_buffer: Returns a pointer to the location in the kernel
+ * kq_acquire_packet_buffer: Returns a pointer to the location in the kernel
  * queue ring buffer where the calling function can write its packet. It is
  * Guaranteed that there is enough space for that packet. It also updates the
  * pending write pointer to that location so subsequent calls to
  * acquire_packet_buffer will get a correct write pointer
  *
- * @submit_packet: Update the write pointer and doorbell of a kernel queue.
- *
- * @sync_with_hw: Wait until the write pointer and the read pointer of a kernel
- * queue are equal, which means the CP has read all the submitted packets.
+ * kq_submit_packet: Update the write pointer and doorbell of a kernel queue.
  *
- * @rollback_packet: This routine is called if we failed to build an acquired
+ * kq_rollback_packet: This routine is called if we failed to build an acquired
  * packet for some reason. It just overwrites the pending wptr with the current
  * one
  *
  */
-struct kernel_queue_ops {
-	bool	(*initialize)(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-	void	(*uninitialize)(struct kernel_queue *kq);
-	int	(*acquire_packet_buffer)(struct kernel_queue *kq,
-					size_t packet_size_in_dwords,
-					unsigned int **buffer_ptr);
 
-	void	(*submit_packet)(struct kernel_queue *kq);
-	void	(*rollback_packet)(struct kernel_queue *kq);
-};
+int kq_acquire_packet_buffer(struct kernel_queue *kq,
+				size_t packet_size_in_dwords,
+				unsigned int **buffer_ptr);
+void kq_submit_packet(struct kernel_queue *kq);
+void kq_rollback_packet(struct kernel_queue *kq);
 
-struct kernel_queue {
-	struct kernel_queue_ops ops;
-	struct kernel_queue_ops ops_asic_specific;
 
+struct kernel_queue {
 	/* data */
 	struct kfd_dev		*dev;
 	struct mqd_manager	*mqd_mgr;
@@ -99,9 +82,4 @@ struct kernel_queue {
 	struct list_head	list;
 };
 
-void kernel_queue_init_cik(struct kernel_queue_ops *ops);
-void kernel_queue_init_vi(struct kernel_queue_ops *ops);
-void kernel_queue_init_v9(struct kernel_queue_ops *ops);
-void kernel_queue_init_v10(struct kernel_queue_ops *ops);
-
 #endif /* KFD_KERNEL_QUEUE_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v10.c
deleted file mode 100644
index aed32ab7102e..000000000000
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v10.c
+++ /dev/null
@@ -1,348 +0,0 @@
-/*
- * Copyright 2018 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#include "kfd_kernel_queue.h"
-#include "kfd_device_queue_manager.h"
-#include "kfd_pm4_headers_ai.h"
-#include "kfd_pm4_opcodes.h"
-#include "gc/gc_10_1_0_sh_mask.h"
-
-static bool initialize_v10(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-static void uninitialize_v10(struct kernel_queue *kq);
-static void submit_packet_v10(struct kernel_queue *kq);
-
-void kernel_queue_init_v10(struct kernel_queue_ops *ops)
-{
-	ops->initialize = initialize_v10;
-	ops->uninitialize = uninitialize_v10;
-	ops->submit_packet = submit_packet_v10;
-}
-
-static bool initialize_v10(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size)
-{
-	int retval;
-
-	retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
-	if (retval != 0)
-		return false;
-
-	kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
-	kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
-
-	memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
-
-	return true;
-}
-
-static void uninitialize_v10(struct kernel_queue *kq)
-{
-	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
-}
-
-static void submit_packet_v10(struct kernel_queue *kq)
-{
-	*kq->wptr64_kernel = kq->pending_wptr64;
-	write_kernel_doorbell64(kq->queue->properties.doorbell_ptr,
-				kq->pending_wptr64);
-}
-
-static int pm_map_process_v10(struct packet_manager *pm,
-		uint32_t *buffer, struct qcm_process_device *qpd)
-{
-	struct pm4_mes_map_process *packet;
-	uint64_t vm_page_table_base_addr = qpd->page_table_base;
-
-	packet = (struct pm4_mes_map_process *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_map_process));
-
-	packet->header.u32All = pm_build_pm4_header(IT_MAP_PROCESS,
-					sizeof(struct pm4_mes_map_process));
-	packet->bitfields2.diq_enable = (qpd->is_debug) ? 1 : 0;
-	packet->bitfields2.process_quantum = 1;
-	packet->bitfields2.pasid = qpd->pqm->process->pasid;
-	packet->bitfields14.gds_size = qpd->gds_size;
-	packet->bitfields14.num_gws = qpd->num_gws;
-	packet->bitfields14.num_oac = qpd->num_oac;
-	packet->bitfields14.sdma_enable = 1;
-
-	packet->bitfields14.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
-
-	packet->sh_mem_config = qpd->sh_mem_config;
-	packet->sh_mem_bases = qpd->sh_mem_bases;
-	if (qpd->tba_addr) {
-		packet->sq_shader_tba_lo = lower_32_bits(qpd->tba_addr >> 8);
-		packet->sq_shader_tba_hi = (1 << SQ_SHADER_TBA_HI__TRAP_EN__SHIFT) |
-			upper_32_bits(qpd->tba_addr >> 8);
-		packet->sq_shader_tma_lo = lower_32_bits(qpd->tma_addr >> 8);
-		packet->sq_shader_tma_hi = upper_32_bits(qpd->tma_addr >> 8);
-	}
-
-	packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
-	packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
-
-	packet->vm_context_page_table_base_addr_lo32 =
-			lower_32_bits(vm_page_table_base_addr);
-	packet->vm_context_page_table_base_addr_hi32 =
-			upper_32_bits(vm_page_table_base_addr);
-
-	return 0;
-}
-
-static int pm_runlist_v10(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t ib, size_t ib_size_in_dwords, bool chain)
-{
-	struct pm4_mes_runlist *packet;
-
-	int concurrent_proc_cnt = 0;
-	struct kfd_dev *kfd = pm->dqm->dev;
-
-	/* Determine the number of processes to map together to HW:
-	 * it can not exceed the number of VMIDs available to the
-	 * scheduler, and it is determined by the smaller of the number
-	 * of processes in the runlist and kfd module parameter
-	 * hws_max_conc_proc.
-	 * Note: the arbitration between the number of VMIDs and
-	 * hws_max_conc_proc has been done in
-	 * kgd2kfd_device_init().
-	 */
-	concurrent_proc_cnt = min(pm->dqm->processes_count,
-			kfd->max_proc_per_quantum);
-
-
-	packet = (struct pm4_mes_runlist *)buffer;
-
-	memset(buffer, 0, sizeof(struct pm4_mes_runlist));
-	packet->header.u32All = pm_build_pm4_header(IT_RUN_LIST,
-						sizeof(struct pm4_mes_runlist));
-
-	packet->bitfields4.ib_size = ib_size_in_dwords;
-	packet->bitfields4.chain = chain ? 1 : 0;
-	packet->bitfields4.offload_polling = 0;
-	packet->bitfields4.valid = 1;
-	packet->bitfields4.process_cnt = concurrent_proc_cnt;
-	packet->ordinal2 = lower_32_bits(ib);
-	packet->ib_base_hi = upper_32_bits(ib);
-
-	return 0;
-}
-
-static int pm_map_queues_v10(struct packet_manager *pm, uint32_t *buffer,
-		struct queue *q, bool is_static)
-{
-	struct pm4_mes_map_queues *packet;
-	bool use_static = is_static;
-
-	packet = (struct pm4_mes_map_queues *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_map_queues));
-
-	packet->header.u32All = pm_build_pm4_header(IT_MAP_QUEUES,
-					sizeof(struct pm4_mes_map_queues));
-	packet->bitfields2.num_queues = 1;
-	packet->bitfields2.queue_sel =
-		queue_sel__mes_map_queues__map_to_hws_determined_queue_slots_vi;
-
-	packet->bitfields2.engine_sel =
-		engine_sel__mes_map_queues__compute_vi;
-	packet->bitfields2.queue_type =
-		queue_type__mes_map_queues__normal_compute_vi;
-
-	switch (q->properties.type) {
-	case KFD_QUEUE_TYPE_COMPUTE:
-		if (use_static)
-			packet->bitfields2.queue_type =
-		queue_type__mes_map_queues__normal_latency_static_queue_vi;
-		break;
-	case KFD_QUEUE_TYPE_DIQ:
-		packet->bitfields2.queue_type =
-			queue_type__mes_map_queues__debug_interface_queue_vi;
-		break;
-	case KFD_QUEUE_TYPE_SDMA:
-	case KFD_QUEUE_TYPE_SDMA_XGMI:
-		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
-				engine_sel__mes_map_queues__sdma0_vi;
-		use_static = false; /* no static queues under SDMA */
-		break;
-	default:
-		WARN(1, "queue type %d\n", q->properties.type);
-		return -EINVAL;
-	}
-	packet->bitfields3.doorbell_offset =
-			q->properties.doorbell_off;
-
-	packet->mqd_addr_lo =
-			lower_32_bits(q->gart_mqd_addr);
-
-	packet->mqd_addr_hi =
-			upper_32_bits(q->gart_mqd_addr);
-
-	packet->wptr_addr_lo =
-			lower_32_bits((uint64_t)q->properties.write_ptr);
-
-	packet->wptr_addr_hi =
-			upper_32_bits((uint64_t)q->properties.write_ptr);
-
-	return 0;
-}
-
-static int pm_unmap_queues_v10(struct packet_manager *pm, uint32_t *buffer,
-			enum kfd_queue_type type,
-			enum kfd_unmap_queues_filter filter,
-			uint32_t filter_param, bool reset,
-			unsigned int sdma_engine)
-{
-	struct pm4_mes_unmap_queues *packet;
-
-	packet = (struct pm4_mes_unmap_queues *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues));
-
-	packet->header.u32All = pm_build_pm4_header(IT_UNMAP_QUEUES,
-					sizeof(struct pm4_mes_unmap_queues));
-	switch (type) {
-	case KFD_QUEUE_TYPE_COMPUTE:
-	case KFD_QUEUE_TYPE_DIQ:
-		packet->bitfields2.engine_sel =
-			engine_sel__mes_unmap_queues__compute;
-		break;
-	case KFD_QUEUE_TYPE_SDMA:
-	case KFD_QUEUE_TYPE_SDMA_XGMI:
-		packet->bitfields2.engine_sel =
-			engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
-		break;
-	default:
-		WARN(1, "queue type %d\n", type);
-		break;
-	}
-
-	if (reset)
-		packet->bitfields2.action =
-			action__mes_unmap_queues__reset_queues;
-	else
-		packet->bitfields2.action =
-			action__mes_unmap_queues__preempt_queues;
-
-	switch (filter) {
-	case KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE:
-		packet->bitfields2.queue_sel =
-			queue_sel__mes_unmap_queues__perform_request_on_specified_queues;
-		packet->bitfields2.num_queues = 1;
-		packet->bitfields3b.doorbell_offset0 = filter_param;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_BY_PASID:
-		packet->bitfields2.queue_sel =
-			queue_sel__mes_unmap_queues__perform_request_on_pasid_queues;
-		packet->bitfields3a.pasid = filter_param;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES:
-		packet->bitfields2.queue_sel =
-			queue_sel__mes_unmap_queues__unmap_all_queues;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES:
-		/* in this case, we do not preempt static queues */
-		packet->bitfields2.queue_sel =
-			queue_sel__mes_unmap_queues__unmap_all_non_static_queues;
-		break;
-	default:
-		WARN(1, "filter %d\n", filter);
-		break;
-	}
-
-	return 0;
-
-}
-
-static int pm_query_status_v10(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value)
-{
-	struct pm4_mes_query_status *packet;
-
-	packet = (struct pm4_mes_query_status *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_query_status));
-
-
-	packet->header.u32All = pm_build_pm4_header(IT_QUERY_STATUS,
-					sizeof(struct pm4_mes_query_status));
-
-	packet->bitfields2.context_id = 0;
-	packet->bitfields2.interrupt_sel =
-			interrupt_sel__mes_query_status__completion_status;
-	packet->bitfields2.command =
-			command__mes_query_status__fence_only_after_write_ack;
-
-	packet->addr_hi = upper_32_bits((uint64_t)fence_address);
-	packet->addr_lo = lower_32_bits((uint64_t)fence_address);
-	packet->data_hi = upper_32_bits((uint64_t)fence_value);
-	packet->data_lo = lower_32_bits((uint64_t)fence_value);
-
-	return 0;
-}
-
-
-static int pm_release_mem_v10(uint64_t gpu_addr, uint32_t *buffer)
-{
-	struct pm4_mec_release_mem *packet;
-
-	WARN_ON(!buffer);
-
-	packet = (struct pm4_mec_release_mem *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mec_release_mem));
-
-	packet->header.u32All = pm_build_pm4_header(IT_RELEASE_MEM,
-					sizeof(struct pm4_mec_release_mem));
-
-	packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
-	packet->bitfields2.event_index = event_index__mec_release_mem__end_of_pipe;
-	packet->bitfields2.tcl1_action_ena = 1;
-	packet->bitfields2.tc_action_ena = 1;
-	packet->bitfields2.cache_policy = cache_policy__mec_release_mem__lru;
-
-	packet->bitfields3.data_sel = data_sel__mec_release_mem__send_32_bit_low;
-	packet->bitfields3.int_sel =
-		int_sel__mec_release_mem__send_interrupt_after_write_confirm;
-
-	packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
-	packet->address_hi = upper_32_bits(gpu_addr);
-
-	packet->data_lo = 0;
-
-	return sizeof(struct pm4_mec_release_mem) / sizeof(unsigned int);
-}
-
-const struct packet_manager_funcs kfd_v10_pm_funcs = {
-	.map_process			= pm_map_process_v10,
-	.runlist			= pm_runlist_v10,
-	.set_resources			= pm_set_resources_vi,
-	.map_queues			= pm_map_queues_v10,
-	.unmap_queues			= pm_unmap_queues_v10,
-	.query_status			= pm_query_status_v10,
-	.release_mem			= pm_release_mem_v10,
-	.map_process_size		= sizeof(struct pm4_mes_map_process),
-	.runlist_size			= sizeof(struct pm4_mes_runlist),
-	.set_resources_size		= sizeof(struct pm4_mes_set_resources),
-	.map_queues_size		= sizeof(struct pm4_mes_map_queues),
-	.unmap_queues_size		= sizeof(struct pm4_mes_unmap_queues),
-	.query_status_size		= sizeof(struct pm4_mes_query_status),
-	.release_mem_size		= sizeof(struct pm4_mec_release_mem)
-};
-
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index 28876aceb14b..19f0fe547c57 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -374,7 +374,6 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 
 	switch (type) {
 	case KFD_MQD_TYPE_CP:
-	case KFD_MQD_TYPE_COMPUTE:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
 		mqd->free_mqd = free_mqd;
@@ -401,7 +400,7 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 #endif
 		break;
 	case KFD_MQD_TYPE_DIQ:
-		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd;
 		mqd->load_mqd = load_mqd;
@@ -442,7 +441,7 @@ struct mqd_manager *mqd_manager_init_cik_hawaii(enum KFD_MQD_TYPE type,
 	mqd = mqd_manager_init_cik(type, dev);
 	if (!mqd)
 		return NULL;
-	if ((type == KFD_MQD_TYPE_CP) || (type == KFD_MQD_TYPE_COMPUTE))
+	if (type == KFD_MQD_TYPE_CP)
 		mqd->update_mqd = update_mqd_hawaii;
 	return mqd;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 4a236b2c2354..d1d68a51bfb8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -66,6 +66,12 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		m->compute_static_thread_mgmt_se3);
 }
 
+static void set_priority(struct v10_compute_mqd *m, struct queue_properties *q)
+{
+	m->cp_hqd_pipe_priority = pipe_priority_map[q->priority];
+	m->cp_hqd_queue_priority = q->priority;
+}
+
 static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd,
 		struct queue_properties *q)
 {
@@ -109,9 +115,6 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 			1 << CP_HQD_QUANTUM__QUANTUM_SCALE__SHIFT |
 			10 << CP_HQD_QUANTUM__QUANTUM_DURATION__SHIFT;
 
-	m->cp_hqd_pipe_priority = 1;
-	m->cp_hqd_queue_priority = 15;
-
 	if (q->format == KFD_QUEUE_FORMAT_AQL) {
 		m->cp_hqd_aql_control =
 			1 << CP_HQD_AQL_CONTROL__CONTROL0__SHIFT;
@@ -150,6 +153,14 @@ static int load_mqd(struct mqd_manager *mm, void *mqd,
 	return r;
 }
 
+static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    struct queue_properties *p, struct mm_struct *mms)
+{
+	return mm->dev->kfd2kgd->hiq_mqd_load(mm->dev->kgd, mqd, pipe_id,
+					      queue_id, p->doorbell_off);
+}
+
 static void update_mqd(struct mqd_manager *mm, void *mqd,
 		      struct queue_properties *q)
 {
@@ -208,11 +219,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 		m->cp_hqd_ctx_save_control = 0;
 
 	update_cu_mask(mm, mqd, q);
+	set_priority(m, q);
 
-	q->is_active = (q->queue_size > 0 &&
-			q->queue_address != 0 &&
-			q->queue_percent > 0 &&
-			!q->is_evicted);
+	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
 static int destroy_mqd(struct mqd_manager *mm, void *mqd,
@@ -247,18 +256,22 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 {
 	struct v10_compute_mqd *m;
 
-	/* Control stack is located one page after MQD. */
-	void *mqd_ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
-
 	m = get_mqd(mqd);
 
+	/* Control stack is written backwards, while workgroup context data
+	 * is written forwards. Both starts from m->cp_hqd_cntl_stack_size.
+	 * Current position is at m->cp_hqd_cntl_stack_offset and
+	 * m->cp_hqd_wg_state_offset, respectively.
+	 */
 	*ctl_stack_used_size = m->cp_hqd_cntl_stack_size -
 		m->cp_hqd_cntl_stack_offset;
 	*save_area_used_size = m->cp_hqd_wg_state_offset -
 		m->cp_hqd_cntl_stack_size;
 
-	if (copy_to_user(ctl_stack, mqd_ctl_stack, m->cp_hqd_cntl_stack_size))
-		return -EFAULT;
+	/* Control stack is not copied to user mode for GFXv10 because
+	 * it's part of the context save area that is already
+	 * accessible to user mode
+	 */
 
 	return 0;
 }
@@ -277,18 +290,6 @@ static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			1 << CP_HQD_PQ_CONTROL__KMD_QUEUE__SHIFT;
 }
 
-static void update_mqd_hiq(struct mqd_manager *mm, void *mqd,
-			struct queue_properties *q)
-{
-	struct v10_compute_mqd *m;
-
-	update_mqd(mm, mqd, q);
-
-	/* TODO: what's the point? update_mqd already does this. */
-	m = get_mqd(mqd);
-	m->cp_hqd_vmid = q->vmid;
-}
-
 static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -340,11 +341,7 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	m->sdma_queue_id = q->sdma_queue_id;
 	m->sdmax_rlcx_dummy_reg = SDMA_RLC_DUMMY_DEFAULT;
 
-
-	q->is_active = (q->queue_size > 0 &&
-			q->queue_address != 0 &&
-			q->queue_percent > 0 &&
-			!q->is_evicted);
+	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
 /*
@@ -392,7 +389,7 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 
@@ -400,7 +397,6 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 
 	switch (type) {
 	case KFD_MQD_TYPE_CP:
-	case KFD_MQD_TYPE_COMPUTE:
 		pr_debug("%s@%i\n", __func__, __LINE__);
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
@@ -421,8 +417,8 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_hiq_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = load_mqd;
-		mqd->update_mqd = update_mqd_hiq;
+		mqd->load_mqd = hiq_load_mqd_kiq;
+		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
 		mqd->mqd_size = sizeof(struct v10_compute_mqd);
@@ -432,11 +428,11 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 		pr_debug("%s@%i\n", __func__, __LINE__);
 		break;
 	case KFD_MQD_TYPE_DIQ:
-		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd;
 		mqd->load_mqd = load_mqd;
-		mqd->update_mqd = update_mqd_hiq;
+		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
 		mqd->mqd_size = sizeof(struct v10_compute_mqd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index d3380c5bdbde..436b7f518979 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -92,7 +92,7 @@ static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd,
 	 * instead of sub-allocation function.
 	 */
 	if (kfd->cwsr_enabled && (q->type == KFD_QUEUE_TYPE_COMPUTE)) {
-		mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
+		mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
 		if (!mqd_mem_obj)
 			return NULL;
 		retval = amdgpu_amdkfd_alloc_gtt_mem(kfd->kgd,
@@ -191,6 +191,14 @@ static int load_mqd(struct mqd_manager *mm, void *mqd,
 					  wptr_shift, 0, mms);
 }
 
+static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    struct queue_properties *p, struct mm_struct *mms)
+{
+	return mm->dev->kfd2kgd->hiq_mqd_load(mm->dev->kgd, mqd, pipe_id,
+					      queue_id, p->doorbell_off);
+}
+
 static void update_mqd(struct mqd_manager *mm, void *mqd,
 		      struct queue_properties *q)
 {
@@ -302,7 +310,8 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 
 	*ctl_stack_used_size = m->cp_hqd_cntl_stack_size -
 		m->cp_hqd_cntl_stack_offset;
-	*save_area_used_size = m->cp_hqd_wg_state_offset;
+	*save_area_used_size = m->cp_hqd_wg_state_offset -
+		m->cp_hqd_cntl_stack_size;
 
 	if (copy_to_user(ctl_stack, mqd_ctl_stack, m->cp_hqd_cntl_stack_size))
 		return -EFAULT;
@@ -324,18 +333,6 @@ static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			1 << CP_HQD_PQ_CONTROL__KMD_QUEUE__SHIFT;
 }
 
-static void update_mqd_hiq(struct mqd_manager *mm, void *mqd,
-			struct queue_properties *q)
-{
-	struct v9_mqd *m;
-
-	update_mqd(mm, mqd, q);
-
-	/* TODO: what's the point? update_mqd already does this. */
-	m = get_mqd(mqd);
-	m->cp_hqd_vmid = q->vmid;
-}
-
 static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -443,7 +440,6 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 
 	switch (type) {
 	case KFD_MQD_TYPE_CP:
-	case KFD_MQD_TYPE_COMPUTE:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
 		mqd->free_mqd = free_mqd;
@@ -461,8 +457,8 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_hiq_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = load_mqd;
-		mqd->update_mqd = update_mqd_hiq;
+		mqd->load_mqd = hiq_load_mqd_kiq;
+		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
 		mqd->mqd_size = sizeof(struct v9_mqd);
@@ -471,11 +467,11 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 #endif
 		break;
 	case KFD_MQD_TYPE_DIQ:
-		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd;
 		mqd->load_mqd = load_mqd;
-		mqd->update_mqd = update_mqd_hiq;
+		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
 		mqd->mqd_size = sizeof(struct v9_mqd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index 7d144f56f421..a5e8ff1e5945 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -312,11 +312,7 @@ static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 static void update_mqd_hiq(struct mqd_manager *mm, void *mqd,
 			struct queue_properties *q)
 {
-	struct vi_mqd *m;
 	__update_mqd(mm, mqd, q, MTYPE_UC, 0);
-
-	m = get_mqd(mqd);
-	m->cp_hqd_vmid = q->vmid;
 }
 
 static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
@@ -425,7 +421,6 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 
 	switch (type) {
 	case KFD_MQD_TYPE_CP:
-	case KFD_MQD_TYPE_COMPUTE:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
 		mqd->free_mqd = free_mqd;
@@ -453,7 +448,7 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 #endif
 		break;
 	case KFD_MQD_TYPE_DIQ:
-		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd;
 		mqd->load_mqd = load_mqd;
@@ -494,7 +489,7 @@ struct mqd_manager *mqd_manager_init_vi_tonga(enum KFD_MQD_TYPE type,
 	mqd = mqd_manager_init_vi(type, dev);
 	if (!mqd)
 		return NULL;
-	if ((type == KFD_MQD_TYPE_CP) || (type == KFD_MQD_TYPE_COMPUTE))
+	if (type == KFD_MQD_TYPE_CP)
 		mqd->update_mqd = update_mqd_tonga;
 	return mqd;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 83ef4b3dd2fb..dc406e6dee23 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -241,12 +241,10 @@ int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
 	case CHIP_ARCTURUS:
-		pm->pmf = &kfd_v9_pm_funcs;
-		break;
 	case CHIP_NAVI10:
 	case CHIP_NAVI12:
 	case CHIP_NAVI14:
-		pm->pmf = &kfd_v10_pm_funcs;
+		pm->pmf = &kfd_v9_pm_funcs;
 		break;
 	default:
 		WARN(1, "Unexpected ASIC family %u",
@@ -266,10 +264,10 @@ int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
 	return 0;
 }
 
-void pm_uninit(struct packet_manager *pm)
+void pm_uninit(struct packet_manager *pm, bool hanging)
 {
 	mutex_destroy(&pm->lock);
-	kernel_queue_uninit(pm->priv_queue);
+	kernel_queue_uninit(pm->priv_queue, hanging);
 }
 
 int pm_send_set_resources(struct packet_manager *pm,
@@ -280,7 +278,7 @@ int pm_send_set_resources(struct packet_manager *pm,
 
 	size = pm->pmf->set_resources_size;
 	mutex_lock(&pm->lock);
-	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	kq_acquire_packet_buffer(pm->priv_queue,
 					size / sizeof(uint32_t),
 					(unsigned int **)&buffer);
 	if (!buffer) {
@@ -291,9 +289,9 @@ int pm_send_set_resources(struct packet_manager *pm,
 
 	retval = pm->pmf->set_resources(pm, buffer, res);
 	if (!retval)
-		pm->priv_queue->ops.submit_packet(pm->priv_queue);
+		kq_submit_packet(pm->priv_queue);
 	else
-		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+		kq_rollback_packet(pm->priv_queue);
 
 out:
 	mutex_unlock(&pm->lock);
@@ -318,7 +316,7 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
 	packet_size_dwords = pm->pmf->runlist_size / sizeof(uint32_t);
 	mutex_lock(&pm->lock);
 
-	retval = pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	retval = kq_acquire_packet_buffer(pm->priv_queue,
 					packet_size_dwords, &rl_buffer);
 	if (retval)
 		goto fail_acquire_packet_buffer;
@@ -328,14 +326,14 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
 	if (retval)
 		goto fail_create_runlist;
 
-	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+	kq_submit_packet(pm->priv_queue);
 
 	mutex_unlock(&pm->lock);
 
 	return retval;
 
 fail_create_runlist:
-	pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+	kq_rollback_packet(pm->priv_queue);
 fail_acquire_packet_buffer:
 	mutex_unlock(&pm->lock);
 fail_create_runlist_ib:
@@ -354,7 +352,7 @@ int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
 
 	size = pm->pmf->query_status_size;
 	mutex_lock(&pm->lock);
-	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	kq_acquire_packet_buffer(pm->priv_queue,
 			size / sizeof(uint32_t), (unsigned int **)&buffer);
 	if (!buffer) {
 		pr_err("Failed to allocate buffer on kernel queue\n");
@@ -364,9 +362,9 @@ int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
 
 	retval = pm->pmf->query_status(pm, buffer, fence_address, fence_value);
 	if (!retval)
-		pm->priv_queue->ops.submit_packet(pm->priv_queue);
+		kq_submit_packet(pm->priv_queue);
 	else
-		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+		kq_rollback_packet(pm->priv_queue);
 
 out:
 	mutex_unlock(&pm->lock);
@@ -383,7 +381,7 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 
 	size = pm->pmf->unmap_queues_size;
 	mutex_lock(&pm->lock);
-	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	kq_acquire_packet_buffer(pm->priv_queue,
 			size / sizeof(uint32_t), (unsigned int **)&buffer);
 	if (!buffer) {
 		pr_err("Failed to allocate buffer on kernel queue\n");
@@ -394,9 +392,9 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 	retval = pm->pmf->unmap_queues(pm, buffer, type, filter, filter_param,
 				       reset, sdma_engine);
 	if (!retval)
-		pm->priv_queue->ops.submit_packet(pm->priv_queue);
+		kq_submit_packet(pm->priv_queue);
 	else
-		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+		kq_rollback_packet(pm->priv_queue);
 
 out:
 	mutex_unlock(&pm->lock);
@@ -441,7 +439,7 @@ int pm_debugfs_hang_hws(struct packet_manager *pm)
 
 	size = pm->pmf->query_status_size;
 	mutex_lock(&pm->lock);
-	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	kq_acquire_packet_buffer(pm->priv_queue,
 			size / sizeof(uint32_t), (unsigned int **)&buffer);
 	if (!buffer) {
 		pr_err("Failed to allocate buffer on kernel queue\n");
@@ -449,7 +447,7 @@ int pm_debugfs_hang_hws(struct packet_manager *pm)
 		goto out;
 	}
 	memset(buffer, 0x55, size);
-	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+	kq_submit_packet(pm->priv_queue);
 
 	pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.",
 		buffer[0], buffer[1], buffer[2], buffer[3],
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
index 9a4bafb2e175..2de01009f1b6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
@@ -25,47 +25,7 @@
 #include "kfd_device_queue_manager.h"
 #include "kfd_pm4_headers_ai.h"
 #include "kfd_pm4_opcodes.h"
-
-static bool initialize_v9(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-static void uninitialize_v9(struct kernel_queue *kq);
-static void submit_packet_v9(struct kernel_queue *kq);
-
-void kernel_queue_init_v9(struct kernel_queue_ops *ops)
-{
-	ops->initialize = initialize_v9;
-	ops->uninitialize = uninitialize_v9;
-	ops->submit_packet = submit_packet_v9;
-}
-
-static bool initialize_v9(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size)
-{
-	int retval;
-
-	retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
-	if (retval)
-		return false;
-
-	kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
-	kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
-
-	memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
-
-	return true;
-}
-
-static void uninitialize_v9(struct kernel_queue *kq)
-{
-	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
-}
-
-static void submit_packet_v9(struct kernel_queue *kq)
-{
-	*kq->wptr64_kernel = kq->pending_wptr64;
-	write_kernel_doorbell64(kq->queue->properties.doorbell_ptr,
-				kq->pending_wptr64);
-}
+#include "gc/gc_10_1_0_sh_mask.h"
 
 static int pm_map_process_v9(struct packet_manager *pm,
 		uint32_t *buffer, struct qcm_process_device *qpd)
@@ -90,10 +50,17 @@ static int pm_map_process_v9(struct packet_manager *pm,
 
 	packet->sh_mem_config = qpd->sh_mem_config;
 	packet->sh_mem_bases = qpd->sh_mem_bases;
-	packet->sq_shader_tba_lo = lower_32_bits(qpd->tba_addr >> 8);
-	packet->sq_shader_tba_hi = upper_32_bits(qpd->tba_addr >> 8);
-	packet->sq_shader_tma_lo = lower_32_bits(qpd->tma_addr >> 8);
-	packet->sq_shader_tma_hi = upper_32_bits(qpd->tma_addr >> 8);
+	if (qpd->tba_addr) {
+		packet->sq_shader_tba_lo = lower_32_bits(qpd->tba_addr >> 8);
+		/* On GFX9, unlike GFX10, bit TRAP_EN of SQ_SHADER_TBA_HI is
+		 * not defined, so setting it won't do any harm.
+		 */
+		packet->sq_shader_tba_hi = upper_32_bits(qpd->tba_addr >> 8)
+				| 1 << SQ_SHADER_TBA_HI__TRAP_EN__SHIFT;
+
+		packet->sq_shader_tma_lo = lower_32_bits(qpd->tma_addr >> 8);
+		packet->sq_shader_tma_hi = upper_32_bits(qpd->tma_addr >> 8);
+	}
 
 	packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
 	packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
@@ -341,35 +308,6 @@ static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer,
 	return 0;
 }
 
-
-static int pm_release_mem_v9(uint64_t gpu_addr, uint32_t *buffer)
-{
-	struct pm4_mec_release_mem *packet;
-
-	packet = (struct pm4_mec_release_mem *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mec_release_mem));
-
-	packet->header.u32All = pm_build_pm4_header(IT_RELEASE_MEM,
-					sizeof(struct pm4_mec_release_mem));
-
-	packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
-	packet->bitfields2.event_index = event_index__mec_release_mem__end_of_pipe;
-	packet->bitfields2.tcl1_action_ena = 1;
-	packet->bitfields2.tc_action_ena = 1;
-	packet->bitfields2.cache_policy = cache_policy__mec_release_mem__lru;
-
-	packet->bitfields3.data_sel = data_sel__mec_release_mem__send_32_bit_low;
-	packet->bitfields3.int_sel =
-		int_sel__mec_release_mem__send_interrupt_after_write_confirm;
-
-	packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
-	packet->address_hi = upper_32_bits(gpu_addr);
-
-	packet->data_lo = 0;
-
-	return 0;
-}
-
 const struct packet_manager_funcs kfd_v9_pm_funcs = {
 	.map_process		= pm_map_process_v9,
 	.runlist		= pm_runlist_v9,
@@ -377,12 +315,12 @@ const struct packet_manager_funcs kfd_v9_pm_funcs = {
 	.map_queues		= pm_map_queues_v9,
 	.unmap_queues		= pm_unmap_queues_v9,
 	.query_status		= pm_query_status_v9,
-	.release_mem		= pm_release_mem_v9,
+	.release_mem		= NULL,
 	.map_process_size	= sizeof(struct pm4_mes_map_process),
 	.runlist_size		= sizeof(struct pm4_mes_runlist),
 	.set_resources_size	= sizeof(struct pm4_mes_set_resources),
 	.map_queues_size	= sizeof(struct pm4_mes_map_queues),
 	.unmap_queues_size	= sizeof(struct pm4_mes_unmap_queues),
 	.query_status_size	= sizeof(struct pm4_mes_query_status),
-	.release_mem_size	= sizeof(struct pm4_mec_release_mem)
+	.release_mem_size	= 0,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c
index 2adaf40027eb..bed4d0ccb6b1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c
@@ -26,47 +26,6 @@
 #include "kfd_pm4_headers_vi.h"
 #include "kfd_pm4_opcodes.h"
 
-static bool initialize_vi(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-static void uninitialize_vi(struct kernel_queue *kq);
-static void submit_packet_vi(struct kernel_queue *kq);
-
-void kernel_queue_init_vi(struct kernel_queue_ops *ops)
-{
-	ops->initialize = initialize_vi;
-	ops->uninitialize = uninitialize_vi;
-	ops->submit_packet = submit_packet_vi;
-}
-
-static bool initialize_vi(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size)
-{
-	int retval;
-
-	retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
-	if (retval != 0)
-		return false;
-
-	kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
-	kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
-
-	memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
-
-	return true;
-}
-
-static void uninitialize_vi(struct kernel_queue *kq)
-{
-	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
-}
-
-static void submit_packet_vi(struct kernel_queue *kq)
-{
-	*kq->wptr_kernel = kq->pending_wptr;
-	write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
-				kq->pending_wptr);
-}
-
 unsigned int pm_build_pm4_header(unsigned int opcode, size_t packet_size)
 {
 	union PM4_MES_TYPE_3_HEADER header;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 060a9e8b301e..6af1b5881f43 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -59,24 +59,21 @@
  * NOTE: struct vm_area_struct.vm_pgoff uses offset in pages. Hence, these
  *  defines are w.r.t to PAGE_SIZE
  */
-#define KFD_MMAP_TYPE_SHIFT	(62 - PAGE_SHIFT)
+#define KFD_MMAP_TYPE_SHIFT	62
 #define KFD_MMAP_TYPE_MASK	(0x3ULL << KFD_MMAP_TYPE_SHIFT)
 #define KFD_MMAP_TYPE_DOORBELL	(0x3ULL << KFD_MMAP_TYPE_SHIFT)
 #define KFD_MMAP_TYPE_EVENTS	(0x2ULL << KFD_MMAP_TYPE_SHIFT)
 #define KFD_MMAP_TYPE_RESERVED_MEM	(0x1ULL << KFD_MMAP_TYPE_SHIFT)
 #define KFD_MMAP_TYPE_MMIO	(0x0ULL << KFD_MMAP_TYPE_SHIFT)
 
-#define KFD_MMAP_GPU_ID_SHIFT (46 - PAGE_SHIFT)
+#define KFD_MMAP_GPU_ID_SHIFT 46
 #define KFD_MMAP_GPU_ID_MASK (((1ULL << KFD_GPU_ID_HASH_WIDTH) - 1) \
 				<< KFD_MMAP_GPU_ID_SHIFT)
 #define KFD_MMAP_GPU_ID(gpu_id) ((((uint64_t)gpu_id) << KFD_MMAP_GPU_ID_SHIFT)\
 				& KFD_MMAP_GPU_ID_MASK)
-#define KFD_MMAP_GPU_ID_GET(offset)    ((offset & KFD_MMAP_GPU_ID_MASK) \
+#define KFD_MMAP_GET_GPU_ID(offset)    ((offset & KFD_MMAP_GPU_ID_MASK) \
 				>> KFD_MMAP_GPU_ID_SHIFT)
 
-#define KFD_MMAP_OFFSET_VALUE_MASK	(0x3FFFFFFFFFFFULL >> PAGE_SHIFT)
-#define KFD_MMAP_OFFSET_VALUE_GET(offset) (offset & KFD_MMAP_OFFSET_VALUE_MASK)
-
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
  * the amdgpu driver to a fixed hqd slot, here are the fixed HIQ hqd slot
@@ -238,9 +235,10 @@ struct kfd_dev {
 					 * KFD. It is aligned for mapping
 					 * into user mode
 					 */
-	size_t doorbell_id_offset;	/* Doorbell offset (from KFD doorbell
-					 * to HW doorbell, GFX reserved some
-					 * at the start)
+	size_t doorbell_base_dw_offset;	/* Offset from the start of the PCI
+					 * doorbell BAR to the first KFD
+					 * doorbell in dwords. GFX reserves
+					 * the segment before this offset.
 					 */
 	u32 __iomem *doorbell_kernel_ptr; /* This is a pointer for a doorbells
 					   * page used by kernel queue
@@ -510,8 +508,7 @@ struct queue {
  * Please read the kfd_mqd_manager.h description.
  */
 enum KFD_MQD_TYPE {
-	KFD_MQD_TYPE_COMPUTE = 0,	/* for no cp scheduling */
-	KFD_MQD_TYPE_HIQ,		/* for hiq */
+	KFD_MQD_TYPE_HIQ = 0,		/* for hiq */
 	KFD_MQD_TYPE_CP,		/* for cp queues and diq */
 	KFD_MQD_TYPE_SDMA,		/* for sdma queues */
 	KFD_MQD_TYPE_DIQ,		/* for diq */
@@ -818,7 +815,7 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr);
 u32 read_kernel_doorbell(u32 __iomem *db);
 void write_kernel_doorbell(void __iomem *db, u32 value);
 void write_kernel_doorbell64(void __iomem *db, u64 value);
-unsigned int kfd_doorbell_id_to_offset(struct kfd_dev *kfd,
+unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd,
 					struct kfd_process *process,
 					unsigned int doorbell_id);
 phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev,
@@ -886,7 +883,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev);
 void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 					enum kfd_queue_type type);
-void kernel_queue_uninit(struct kernel_queue *kq);
+void kernel_queue_uninit(struct kernel_queue *kq, bool hanging);
 int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
 
 /* Process Queue Manager */
@@ -904,7 +901,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct kfd_dev *dev,
 			    struct file *f,
 			    struct queue_properties *properties,
-			    unsigned int *qid);
+			    unsigned int *qid,
+			    uint32_t *p_doorbell_offset_in_process);
 int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
 int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 			struct queue_properties *p);
@@ -972,10 +970,9 @@ struct packet_manager_funcs {
 
 extern const struct packet_manager_funcs kfd_vi_pm_funcs;
 extern const struct packet_manager_funcs kfd_v9_pm_funcs;
-extern const struct packet_manager_funcs kfd_v10_pm_funcs;
 
 int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm);
-void pm_uninit(struct packet_manager *pm);
+void pm_uninit(struct packet_manager *pm, bool hanging);
 int pm_send_set_resources(struct packet_manager *pm,
 				struct scheduling_resources *res);
 int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues);
@@ -991,9 +988,6 @@ void pm_release_ib(struct packet_manager *pm);
 
 /* Following PM funcs can be shared among VI and AI */
 unsigned int pm_build_pm4_header(unsigned int opcode, size_t packet_size);
-int pm_set_resources_vi(struct packet_manager *pm, uint32_t *buffer,
-			struct scheduling_resources *res);
-
 
 uint64_t kfd_get_number_elems(struct kfd_dev *kfd);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 10f9af5784f2..25b90f70aecd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -32,6 +32,7 @@
 #include <linux/mman.h>
 #include <linux/file.h>
 #include "amdgpu_amdkfd.h"
+#include "amdgpu.h"
 
 struct mm_struct;
 
@@ -324,6 +325,8 @@ struct kfd_process *kfd_create_process(struct file *filep)
 					(int)process->lead_thread->pid);
 	}
 out:
+	if (!IS_ERR(process))
+		kref_get(&process->ref);
 	mutex_unlock(&kfd_processes_mutex);
 
 	return process;
@@ -560,8 +563,7 @@ static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep)
 		if (!dev->cwsr_enabled || qpd->cwsr_kaddr || qpd->cwsr_base)
 			continue;
 
-		offset = (KFD_MMAP_TYPE_RESERVED_MEM | KFD_MMAP_GPU_ID(dev->id))
-			<< PAGE_SHIFT;
+		offset = KFD_MMAP_TYPE_RESERVED_MEM | KFD_MMAP_GPU_ID(dev->id);
 		qpd->tba_addr = (int64_t)vm_mmap(filep, 0,
 			KFD_CWSR_TBA_TMA_SIZE, PROT_READ | PROT_EXEC,
 			MAP_SHARED, offset);
@@ -1151,16 +1153,17 @@ int kfd_reserved_mem_mmap(struct kfd_dev *dev, struct kfd_process *process,
 void kfd_flush_tlb(struct kfd_process_device *pdd)
 {
 	struct kfd_dev *dev = pdd->dev;
-	const struct kfd2kgd_calls *f2g = dev->kfd2kgd;
 
 	if (dev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS) {
 		/* Nothing to flush until a VMID is assigned, which
 		 * only happens when the first queue is created.
 		 */
 		if (pdd->qpd.vmid)
-			f2g->invalidate_tlbs_vmid(dev->kgd, pdd->qpd.vmid);
+			amdgpu_amdkfd_flush_gpu_tlb_vmid(dev->kgd,
+							pdd->qpd.vmid);
 	} else {
-		f2g->invalidate_tlbs(dev->kgd, pdd->process->pasid);
+		amdgpu_amdkfd_flush_gpu_tlb_pasid(dev->kgd,
+						pdd->process->pasid);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 2659d226c056..31fcd1b51f00 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -162,7 +162,7 @@ void pqm_uninit(struct process_queue_manager *pqm)
 	pqm->queue_slot_bitmap = NULL;
 }
 
-static int create_cp_queue(struct process_queue_manager *pqm,
+static int init_user_queue(struct process_queue_manager *pqm,
 				struct kfd_dev *dev, struct queue **q,
 				struct queue_properties *q_properties,
 				struct file *f, unsigned int qid)
@@ -192,7 +192,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct kfd_dev *dev,
 			    struct file *f,
 			    struct queue_properties *properties,
-			    unsigned int *qid)
+			    unsigned int *qid,
+			    uint32_t *p_doorbell_offset_in_process)
 {
 	int retval;
 	struct kfd_process_device *pdd;
@@ -250,7 +251,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		}
 
-		retval = create_cp_queue(pqm, dev, &q, properties, f, *qid);
+		retval = init_user_queue(pqm, dev, &q, properties, f, *qid);
 		if (retval != 0)
 			goto err_create_queue;
 		pqn->q = q;
@@ -271,7 +272,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		}
 
-		retval = create_cp_queue(pqm, dev, &q, properties, f, *qid);
+		retval = init_user_queue(pqm, dev, &q, properties, f, *qid);
 		if (retval != 0)
 			goto err_create_queue;
 		pqn->q = q;
@@ -303,12 +304,15 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		goto err_create_queue;
 	}
 
-	if (q)
+	if (q && p_doorbell_offset_in_process)
 		/* Return the doorbell offset within the doorbell page
 		 * to the caller so it can be passed up to user mode
 		 * (in bytes).
+		 * There are always 1024 doorbells per process, so in case
+		 * of 8-byte doorbells, there are two doorbell pages per
+		 * process.
 		 */
-		properties->doorbell_off =
+		*p_doorbell_offset_in_process =
 			(q->properties.doorbell_off * sizeof(uint32_t)) &
 			(kfd_doorbell_process_slice(dev) - 1);
 
@@ -370,7 +374,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 		/* destroy kernel queue (DIQ) */
 		dqm = pqn->kq->dev->dqm;
 		dqm->ops.destroy_kernel_queue(dqm, pqn->kq, &pdd->qpd);
-		kernel_queue_uninit(pqn->kq);
+		kernel_queue_uninit(pqn->kq, false);
 	}
 
 	if (pqn->q) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 69bd0628fdc6..203c823d65f1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -486,6 +486,10 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.num_sdma_engines);
 	sysfs_show_32bit_prop(buffer, "num_sdma_xgmi_engines",
 			dev->node_props.num_sdma_xgmi_engines);
+	sysfs_show_32bit_prop(buffer, "num_sdma_queues_per_engine",
+			dev->node_props.num_sdma_queues_per_engine);
+	sysfs_show_32bit_prop(buffer, "num_cp_queues",
+			dev->node_props.num_cp_queues);
 
 	if (dev->gpu) {
 		log_max_watch_addr =
@@ -1309,9 +1313,12 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 	dev->node_props.num_sdma_engines = gpu->device_info->num_sdma_engines;
 	dev->node_props.num_sdma_xgmi_engines =
 				gpu->device_info->num_xgmi_sdma_engines;
+	dev->node_props.num_sdma_queues_per_engine =
+				gpu->device_info->num_sdma_queues_per_engine;
 	dev->node_props.num_gws = (hws_gws_support &&
 		dev->gpu->dqm->sched_policy != KFD_SCHED_POLICY_NO_HWS) ?
 		amdgpu_amdkfd_get_num_gws(dev->gpu->kgd) : 0;
+	dev->node_props.num_cp_queues = get_queues_num(dev->gpu->dqm);
 
 	kfd_fill_mem_clk_max_info(dev);
 	kfd_fill_iolink_non_crat_info(dev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index 15843e0fc756..74e9b1682af8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -81,6 +81,8 @@ struct kfd_node_properties {
 	int32_t  drm_render_minor;
 	uint32_t num_sdma_engines;
 	uint32_t num_sdma_xgmi_engines;
+	uint32_t num_sdma_queues_per_engine;
+	uint32_t num_cp_queues;
 	char name[KFD_TOPOLOGY_PUBLIC_NAME_SIZE];
 };
 
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index ae161fe86ebb..87858bc57e64 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -6,43 +6,16 @@ config DRM_AMD_DC
 	bool "AMD DC - Enable new display engine"
 	default y
 	select SND_HDA_COMPONENT if SND_HDA_CORE
-	select DRM_AMD_DC_DCN1_0 if X86 && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
+	select DRM_AMD_DC_DCN if (X86 || PPC64) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
-config DRM_AMD_DC_DCN1_0
+config DRM_AMD_DC_DCN
 	def_bool n
 	help
-	  RV family support for display engine
-
-config DRM_AMD_DC_DCN2_0
-	bool "DCN 2.0 family"
-	default y
-	depends on DRM_AMD_DC && X86
-	depends on DRM_AMD_DC_DCN1_0
-	help
-	  Choose this option if you want to have
-	  Navi support for display engine
-
-config DRM_AMD_DC_DCN2_1
-	bool "DCN 2.1 family"
-	depends on DRM_AMD_DC && X86
-	depends on DRM_AMD_DC_DCN2_0
-	help
-	  Choose this option if you want to have
-	  Renoir support for display engine
-
-config DRM_AMD_DC_DSC_SUPPORT
-	bool "DSC support"
-	default y
-	depends on DRM_AMD_DC && X86
-	depends on DRM_AMD_DC_DCN1_0
-	depends on DRM_AMD_DC_DCN2_0
-	help
-	  Choose this option if you want to have
-	  Dynamic Stream Compression support
+	  Raven, Navi and Renoir family support for display engine
 
 config DRM_AMD_DC_HDCP
 	bool "Enable HDCP support in DC"
diff --git a/drivers/gpu/drm/amd/display/Makefile b/drivers/gpu/drm/amd/display/Makefile
index 36b3d6a5d04d..2633de77de5e 100644
--- a/drivers/gpu/drm/amd/display/Makefile
+++ b/drivers/gpu/drm/amd/display/Makefile
@@ -34,6 +34,8 @@ subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/freesync
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/color
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/info_packet
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/power
+subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dmub/inc
+
 ifdef CONFIG_DRM_AMD_DC_HDCP
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/hdcp
 endif
@@ -41,7 +43,7 @@ endif
 #TODO: remove when Timing Sync feature is complete
 subdir-ccflags-y += -DBUILD_FEATURE_TIMING_SYNC=0
 
-DAL_LIBS = amdgpu_dm dc	modules/freesync modules/color modules/info_packet modules/power
+DAL_LIBS = amdgpu_dm dc	modules/freesync modules/color modules/info_packet modules/power dmub/src
 
 ifdef CONFIG_DRM_AMD_DC_HDCP
 DAL_LIBS += modules/hdcp
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 803e59d97411..9402374d2466 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -30,6 +30,10 @@
 #include "dc.h"
 #include "dc/inc/core_types.h"
 #include "dal_asic_id.h"
+#include "dmub/inc/dmub_srv.h"
+#include "dc/inc/hw/dmcu.h"
+#include "dc/inc/hw/abm.h"
+#include "dc/dc_dmub_srv.h"
 
 #include "vid.h"
 #include "amdgpu.h"
@@ -39,6 +43,7 @@
 #include "amdgpu_dm.h"
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 #include "amdgpu_dm_hdcp.h"
+#include <drm/drm_hdcp.h>
 #endif
 #include "amdgpu_pm.h"
 
@@ -72,7 +77,7 @@
 #include <drm/drm_audio_component.h>
 #include <drm/drm_hdcp.h>
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "ivsrcid/dcn/irqsrcs_dcn_1_0.h"
 
 #include "dcn/dcn_1_0_offset.h"
@@ -87,9 +92,18 @@
 #include "modules/power/power_helpers.h"
 #include "modules/inc/mod_info_packet.h"
 
+#define FIRMWARE_RENOIR_DMUB "amdgpu/renoir_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_RENOIR_DMUB);
+
 #define FIRMWARE_RAVEN_DMCU		"amdgpu/raven_dmcu.bin"
 MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU);
 
+/* Number of bytes in PSP header for firmware. */
+#define PSP_HEADER_BYTES 0x100
+
+/* Number of bytes in PSP footer for firmware. */
+#define PSP_FOOTER_BYTES 0x100
+
 /**
  * DOC: overview
  *
@@ -478,6 +492,70 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+/**
+ * dm_dcn_crtc_high_irq() - Handles VStartup interrupt for DCN generation ASICs
+ * @interrupt params - interrupt parameters
+ *
+ * Notify DRM's vblank event handler at VSTARTUP
+ *
+ * Unlike DCE hardware, we trigger the handler at VSTARTUP. at which:
+ * * We are close enough to VUPDATE - the point of no return for hw
+ * * We are in the fixed portion of variable front porch when vrr is enabled
+ * * We are before VUPDATE, where double-buffered vrr registers are swapped
+ *
+ * It is therefore the correct place to signal vblank, send user flip events,
+ * and update VRR.
+ */
+static void dm_dcn_crtc_high_irq(void *interrupt_params)
+{
+	struct common_irq_params *irq_params = interrupt_params;
+	struct amdgpu_device *adev = irq_params->adev;
+	struct amdgpu_crtc *acrtc;
+	struct dm_crtc_state *acrtc_state;
+	unsigned long flags;
+
+	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
+
+	if (!acrtc)
+		return;
+
+	acrtc_state = to_dm_crtc_state(acrtc->base.state);
+
+	DRM_DEBUG_DRIVER("crtc:%d, vupdate-vrr:%d\n", acrtc->crtc_id,
+				amdgpu_dm_vrr_active(acrtc_state));
+
+	amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
+	drm_crtc_handle_vblank(&acrtc->base);
+
+	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+
+	if (acrtc_state->vrr_params.supported &&
+	    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
+		mod_freesync_handle_v_update(
+		adev->dm.freesync_module,
+		acrtc_state->stream,
+		&acrtc_state->vrr_params);
+
+		dc_stream_adjust_vmin_vmax(
+			adev->dm.dc,
+			acrtc_state->stream,
+			&acrtc_state->vrr_params.adjust);
+	}
+
+	if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED) {
+		if (acrtc->event) {
+			drm_crtc_send_vblank_event(&acrtc->base, acrtc->event);
+			acrtc->event = NULL;
+			drm_crtc_vblank_put(&acrtc->base);
+		}
+		acrtc->pflip_status = AMDGPU_FLIP_NONE;
+	}
+
+	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+}
+#endif
+
 static int dm_set_clockgating_state(void *handle,
 		  enum amd_clockgating_state state)
 {
@@ -667,12 +745,126 @@ void amdgpu_dm_audio_eld_notify(struct amdgpu_device *adev, int pin)
 	}
 }
 
+static int dm_dmub_hw_init(struct amdgpu_device *adev)
+{
+	const struct dmcub_firmware_header_v1_0 *hdr;
+	struct dmub_srv *dmub_srv = adev->dm.dmub_srv;
+	struct dmub_srv_fb_info *fb_info = adev->dm.dmub_fb_info;
+	const struct firmware *dmub_fw = adev->dm.dmub_fw;
+	struct dmcu *dmcu = adev->dm.dc->res_pool->dmcu;
+	struct abm *abm = adev->dm.dc->res_pool->abm;
+	struct dmub_srv_hw_params hw_params;
+	enum dmub_status status;
+	const unsigned char *fw_inst_const, *fw_bss_data;
+	uint32_t i, fw_inst_const_size, fw_bss_data_size;
+	bool has_hw_support;
+
+	if (!dmub_srv)
+		/* DMUB isn't supported on the ASIC. */
+		return 0;
+
+	if (!fb_info) {
+		DRM_ERROR("No framebuffer info for DMUB service.\n");
+		return -EINVAL;
+	}
+
+	if (!dmub_fw) {
+		/* Firmware required for DMUB support. */
+		DRM_ERROR("No firmware provided for DMUB.\n");
+		return -EINVAL;
+	}
+
+	status = dmub_srv_has_hw_support(dmub_srv, &has_hw_support);
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error checking HW support for DMUB: %d\n", status);
+		return -EINVAL;
+	}
+
+	if (!has_hw_support) {
+		DRM_INFO("DMUB unsupported on ASIC\n");
+		return 0;
+	}
+
+	hdr = (const struct dmcub_firmware_header_v1_0 *)dmub_fw->data;
+
+	fw_inst_const = dmub_fw->data +
+			le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
+			PSP_HEADER_BYTES;
+
+	fw_bss_data = dmub_fw->data +
+		      le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
+		      le32_to_cpu(hdr->inst_const_bytes);
+
+	/* Copy firmware and bios info into FB memory. */
+	fw_inst_const_size = le32_to_cpu(hdr->inst_const_bytes) -
+			     PSP_HEADER_BYTES - PSP_FOOTER_BYTES;
+
+	fw_bss_data_size = le32_to_cpu(hdr->bss_data_bytes);
+
+	memcpy(fb_info->fb[DMUB_WINDOW_0_INST_CONST].cpu_addr, fw_inst_const,
+	       fw_inst_const_size);
+	memcpy(fb_info->fb[DMUB_WINDOW_2_BSS_DATA].cpu_addr, fw_bss_data,
+	       fw_bss_data_size);
+	memcpy(fb_info->fb[DMUB_WINDOW_3_VBIOS].cpu_addr, adev->bios,
+	       adev->bios_size);
+
+	/* Reset regions that need to be reset. */
+	memset(fb_info->fb[DMUB_WINDOW_4_MAILBOX].cpu_addr, 0,
+	fb_info->fb[DMUB_WINDOW_4_MAILBOX].size);
+
+	memset(fb_info->fb[DMUB_WINDOW_5_TRACEBUFF].cpu_addr, 0,
+	       fb_info->fb[DMUB_WINDOW_5_TRACEBUFF].size);
+
+	memset(fb_info->fb[DMUB_WINDOW_6_FW_STATE].cpu_addr, 0,
+	       fb_info->fb[DMUB_WINDOW_6_FW_STATE].size);
+
+	/* Initialize hardware. */
+	memset(&hw_params, 0, sizeof(hw_params));
+	hw_params.fb_base = adev->gmc.fb_start;
+	hw_params.fb_offset = adev->gmc.aper_base;
+
+	if (dmcu)
+		hw_params.psp_version = dmcu->psp_version;
+
+	for (i = 0; i < fb_info->num_fb; ++i)
+		hw_params.fb[i] = &fb_info->fb[i];
+
+	status = dmub_srv_hw_init(dmub_srv, &hw_params);
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error initializing DMUB HW: %d\n", status);
+		return -EINVAL;
+	}
+
+	/* Wait for firmware load to finish. */
+	status = dmub_srv_wait_for_auto_load(dmub_srv, 100000);
+	if (status != DMUB_STATUS_OK)
+		DRM_WARN("Wait for DMUB auto-load failed: %d\n", status);
+
+	/* Init DMCU and ABM if available. */
+	if (dmcu && abm) {
+		dmcu->funcs->dmcu_init(dmcu);
+		abm->dmcu_is_running = dmcu->funcs->is_dmcu_initialized(dmcu);
+	}
+
+	adev->dm.dc->ctx->dmub_srv = dc_dmub_srv_create(adev->dm.dc, dmub_srv);
+	if (!adev->dm.dc->ctx->dmub_srv) {
+		DRM_ERROR("Couldn't allocate DC DMUB server!\n");
+		return -ENOMEM;
+	}
+
+	DRM_INFO("DMUB hardware initialized: version=0x%08X\n",
+		 adev->dm.dmcub_fw_version);
+
+	return 0;
+}
+
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 	struct dc_callback_init init_params;
 #endif
+	int r;
 
 	adev->dm.ddev = adev->ddev;
 	adev->dm.adev = adev;
@@ -714,13 +906,16 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.dce_environment = DCE_ENV_PRODUCTION_DRV;
 
-	/*
-	 * TODO debug why this doesn't work on Raven
-	 */
-	if (adev->flags & AMD_IS_APU &&
-	    adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type < CHIP_RAVEN)
+	switch (adev->asic_type) {
+	case CHIP_CARRIZO:
+	case CHIP_STONEY:
+	case CHIP_RAVEN:
+	case CHIP_RENOIR:
 		init_data.flags.gpu_vm_support = true;
+		break;
+	default:
+		break;
+	}
 
 	if (amdgpu_dc_feature_mask & DC_FBC_MASK)
 		init_data.flags.fbc_support = true;
@@ -733,9 +928,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.flags.power_down_display_on_boot = true;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	init_data.soc_bounding_box = adev->dm.soc_bounding_box;
-#endif
 
 	/* Display Core create. */
 	adev->dm.dc = dc_create(&init_data);
@@ -749,6 +942,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	dc_hardware_init(adev->dm.dc);
 
+	r = dm_dmub_hw_init(adev);
+	if (r) {
+		DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r);
+		goto error;
+	}
+
 	adev->dm.freesync_module = mod_freesync_create(adev->dm.dc);
 	if (!adev->dm.freesync_module) {
 		DRM_ERROR(
@@ -821,6 +1020,15 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 	if (adev->dm.dc)
 		dc_deinit_callbacks(adev->dm.dc);
 #endif
+	if (adev->dm.dc->ctx->dmub_srv) {
+		dc_dmub_srv_destroy(&adev->dm.dc->ctx->dmub_srv);
+		adev->dm.dc->ctx->dmub_srv = NULL;
+	}
+
+	if (adev->dm.dmub_bo)
+		amdgpu_bo_free_kernel(&adev->dm.dmub_bo,
+				      &adev->dm.dmub_bo_gpu_addr,
+				      &adev->dm.dmub_bo_cpu_addr);
 
 	/* DC Destroy TODO: Replace destroy DAL */
 	if (adev->dm.dc)
@@ -932,9 +1140,160 @@ static int load_dmcu_fw(struct amdgpu_device *adev)
 	return 0;
 }
 
+static uint32_t amdgpu_dm_dmub_reg_read(void *ctx, uint32_t address)
+{
+	struct amdgpu_device *adev = ctx;
+
+	return dm_read_reg(adev->dm.dc->ctx, address);
+}
+
+static void amdgpu_dm_dmub_reg_write(void *ctx, uint32_t address,
+				     uint32_t value)
+{
+	struct amdgpu_device *adev = ctx;
+
+	return dm_write_reg(adev->dm.dc->ctx, address, value);
+}
+
+static int dm_dmub_sw_init(struct amdgpu_device *adev)
+{
+	struct dmub_srv_create_params create_params;
+	struct dmub_srv_region_params region_params;
+	struct dmub_srv_region_info region_info;
+	struct dmub_srv_fb_params fb_params;
+	struct dmub_srv_fb_info *fb_info;
+	struct dmub_srv *dmub_srv;
+	const struct dmcub_firmware_header_v1_0 *hdr;
+	const char *fw_name_dmub;
+	enum dmub_asic dmub_asic;
+	enum dmub_status status;
+	int r;
+
+	switch (adev->asic_type) {
+	case CHIP_RENOIR:
+		dmub_asic = DMUB_ASIC_DCN21;
+		fw_name_dmub = FIRMWARE_RENOIR_DMUB;
+		break;
+
+	default:
+		/* ASIC doesn't support DMUB. */
+		return 0;
+	}
+
+	r = request_firmware_direct(&adev->dm.dmub_fw, fw_name_dmub, adev->dev);
+	if (r) {
+		DRM_ERROR("DMUB firmware loading failed: %d\n", r);
+		return 0;
+	}
+
+	r = amdgpu_ucode_validate(adev->dm.dmub_fw);
+	if (r) {
+		DRM_ERROR("Couldn't validate DMUB firmware: %d\n", r);
+		return 0;
+	}
+
+	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
+		DRM_WARN("Only PSP firmware loading is supported for DMUB\n");
+		return 0;
+	}
+
+	hdr = (const struct dmcub_firmware_header_v1_0 *)adev->dm.dmub_fw->data;
+	adev->firmware.ucode[AMDGPU_UCODE_ID_DMCUB].ucode_id =
+		AMDGPU_UCODE_ID_DMCUB;
+	adev->firmware.ucode[AMDGPU_UCODE_ID_DMCUB].fw = adev->dm.dmub_fw;
+	adev->firmware.fw_size +=
+		ALIGN(le32_to_cpu(hdr->inst_const_bytes), PAGE_SIZE);
+
+	adev->dm.dmcub_fw_version = le32_to_cpu(hdr->header.ucode_version);
+
+	DRM_INFO("Loading DMUB firmware via PSP: version=0x%08X\n",
+		 adev->dm.dmcub_fw_version);
+
+	adev->dm.dmub_srv = kzalloc(sizeof(*adev->dm.dmub_srv), GFP_KERNEL);
+	dmub_srv = adev->dm.dmub_srv;
+
+	if (!dmub_srv) {
+		DRM_ERROR("Failed to allocate DMUB service!\n");
+		return -ENOMEM;
+	}
+
+	memset(&create_params, 0, sizeof(create_params));
+	create_params.user_ctx = adev;
+	create_params.funcs.reg_read = amdgpu_dm_dmub_reg_read;
+	create_params.funcs.reg_write = amdgpu_dm_dmub_reg_write;
+	create_params.asic = dmub_asic;
+
+	/* Create the DMUB service. */
+	status = dmub_srv_create(dmub_srv, &create_params);
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error creating DMUB service: %d\n", status);
+		return -EINVAL;
+	}
+
+	/* Calculate the size of all the regions for the DMUB service. */
+	memset(&region_params, 0, sizeof(region_params));
+
+	region_params.inst_const_size = le32_to_cpu(hdr->inst_const_bytes) -
+					PSP_HEADER_BYTES - PSP_FOOTER_BYTES;
+	region_params.bss_data_size = le32_to_cpu(hdr->bss_data_bytes);
+	region_params.vbios_size = adev->bios_size;
+	region_params.fw_bss_data =
+		adev->dm.dmub_fw->data +
+		le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
+		le32_to_cpu(hdr->inst_const_bytes);
+
+	status = dmub_srv_calc_region_info(dmub_srv, &region_params,
+					   &region_info);
+
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error calculating DMUB region info: %d\n", status);
+		return -EINVAL;
+	}
+
+	/*
+	 * Allocate a framebuffer based on the total size of all the regions.
+	 * TODO: Move this into GART.
+	 */
+	r = amdgpu_bo_create_kernel(adev, region_info.fb_size, PAGE_SIZE,
+				    AMDGPU_GEM_DOMAIN_VRAM, &adev->dm.dmub_bo,
+				    &adev->dm.dmub_bo_gpu_addr,
+				    &adev->dm.dmub_bo_cpu_addr);
+	if (r)
+		return r;
+
+	/* Rebase the regions on the framebuffer address. */
+	memset(&fb_params, 0, sizeof(fb_params));
+	fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr;
+	fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr;
+	fb_params.region_info = &region_info;
+
+	adev->dm.dmub_fb_info =
+		kzalloc(sizeof(*adev->dm.dmub_fb_info), GFP_KERNEL);
+	fb_info = adev->dm.dmub_fb_info;
+
+	if (!fb_info) {
+		DRM_ERROR(
+			"Failed to allocate framebuffer info for DMUB service!\n");
+		return -ENOMEM;
+	}
+
+	status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, fb_info);
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error calculating DMUB FB info: %d\n", status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int dm_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = dm_dmub_sw_init(adev);
+	if (r)
+		return r;
 
 	return load_dmcu_fw(adev);
 }
@@ -943,6 +1302,19 @@ static int dm_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	kfree(adev->dm.dmub_fb_info);
+	adev->dm.dmub_fb_info = NULL;
+
+	if (adev->dm.dmub_srv) {
+		dmub_srv_destroy(adev->dm.dmub_srv);
+		adev->dm.dmub_srv = NULL;
+	}
+
+	if (adev->dm.dmub_fw) {
+		release_firmware(adev->dm.dmub_fw);
+		adev->dm.dmub_fw = NULL;
+	}
+
 	if(adev->dm.fw_dmcu) {
 		release_firmware(adev->dm.fw_dmcu);
 		adev->dm.fw_dmcu = NULL;
@@ -1235,7 +1607,7 @@ static int dm_resume(void *handle)
 	struct dm_plane_state *dm_new_plane_state;
 	struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state);
 	enum dc_connection_type new_connection_type = dc_connection_none;
-	int i;
+	int i, r;
 
 	/* Recreate dc_state - DC invalidates it when setting power state to S3. */
 	dc_release_state(dm_state->context);
@@ -1243,6 +1615,11 @@ static int dm_resume(void *handle)
 	/* TODO: Remove dc_state->dccg, use dc->dccg directly. */
 	dc_resource_state_construct(dm->dc, dm_state->context);
 
+	/* Before powering on DC we need to re-initialize DMUB. */
+	r = dm_dmub_hw_init(adev);
+	if (r)
+		DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r);
+
 	/* power on hardware */
 	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0);
 
@@ -1868,7 +2245,7 @@ static int dce110_register_irq_handlers(struct amdgpu_device *adev)
 	return 0;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 /* Register IRQ sources and initialize IRQ callbacks */
 static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 {
@@ -1914,35 +2291,7 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 		c_irq_params->irq_src = int_params.irq_source;
 
 		amdgpu_dm_irq_register_interrupt(adev, &int_params,
-				dm_crtc_high_irq, c_irq_params);
-	}
-
-	/* Use VUPDATE_NO_LOCK interrupt on DCN, which seems to correspond to
-	 * the regular VUPDATE interrupt on DCE. We want DC_IRQ_SOURCE_VUPDATEx
-	 * to trigger at end of each vblank, regardless of state of the lock,
-	 * matching DCE behaviour.
-	 */
-	for (i = DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT;
-	     i <= DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT + adev->mode_info.num_crtc - 1;
-	     i++) {
-		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->vupdate_irq);
-
-		if (r) {
-			DRM_ERROR("Failed to add vupdate irq id!\n");
-			return r;
-		}
-
-		int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT;
-		int_params.irq_source =
-			dc_interrupt_to_irq_source(dc, i, 0);
-
-		c_irq_params = &adev->dm.vupdate_params[int_params.irq_source - DC_IRQ_SOURCE_VUPDATE1];
-
-		c_irq_params->adev = adev;
-		c_irq_params->irq_src = int_params.irq_source;
-
-		amdgpu_dm_irq_register_interrupt(adev, &int_params,
-				dm_vupdate_high_irq, c_irq_params);
+				dm_dcn_crtc_high_irq, c_irq_params);
 	}
 
 	/* Use GRPH_PFLIP interrupt */
@@ -2457,16 +2806,12 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			goto fail;
 		}
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case CHIP_RAVEN:
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case CHIP_NAVI12:
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case CHIP_RENOIR:
-#endif
 		if (dcn10_register_irq_handlers(dm->adev)) {
 			DRM_ERROR("DM: Failed to initialize IRQ\n");
 			goto fail;
@@ -2612,14 +2957,13 @@ static int dm_early_init(void *handle)
 		adev->mode_info.num_hpd = 6;
 		adev->mode_info.num_dig = 6;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case CHIP_RAVEN:
 		adev->mode_info.num_crtc = 4;
 		adev->mode_info.num_hpd = 4;
 		adev->mode_info.num_dig = 4;
 		break;
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case CHIP_NAVI10:
 	case CHIP_NAVI12:
 		adev->mode_info.num_crtc = 6;
@@ -2631,14 +2975,11 @@ static int dm_early_init(void *handle)
 		adev->mode_info.num_hpd = 5;
 		adev->mode_info.num_dig = 5;
 		break;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case CHIP_RENOIR:
 		adev->mode_info.num_crtc = 4;
 		adev->mode_info.num_hpd = 4;
 		adev->mode_info.num_dig = 4;
 		break;
-#endif
 	default:
 		DRM_ERROR("Unsupported ASIC type: 0x%X\n", adev->asic_type);
 		return -EINVAL;
@@ -2931,14 +3272,10 @@ fill_plane_buffer_attributes(struct amdgpu_device *adev,
 	if (adev->asic_type == CHIP_VEGA10 ||
 	    adev->asic_type == CHIP_VEGA12 ||
 	    adev->asic_type == CHIP_VEGA20 ||
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	    adev->asic_type == CHIP_NAVI10 ||
 	    adev->asic_type == CHIP_NAVI14 ||
 	    adev->asic_type == CHIP_NAVI12 ||
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	    adev->asic_type == CHIP_RENOIR ||
-#endif
 	    adev->asic_type == CHIP_RAVEN) {
 		/* Fill GFX9 params */
 		tiling_info->gfx9.num_pipes =
@@ -3256,12 +3593,26 @@ static void update_stream_scaling_settings(const struct drm_display_mode *mode,
 
 static enum dc_color_depth
 convert_color_depth_from_display_info(const struct drm_connector *connector,
-				      const struct drm_connector_state *state)
+				      const struct drm_connector_state *state,
+				      bool is_y420)
 {
-	uint8_t bpc = (uint8_t)connector->display_info.bpc;
+	uint8_t bpc;
 
-	/* Assume 8 bpc by default if no bpc is specified. */
-	bpc = bpc ? bpc : 8;
+	if (is_y420) {
+		bpc = 8;
+
+		/* Cap display bpc based on HDMI 2.0 HF-VSDB */
+		if (connector->display_info.hdmi.y420_dc_modes & DRM_EDID_YCBCR420_DC_48)
+			bpc = 16;
+		else if (connector->display_info.hdmi.y420_dc_modes & DRM_EDID_YCBCR420_DC_36)
+			bpc = 12;
+		else if (connector->display_info.hdmi.y420_dc_modes & DRM_EDID_YCBCR420_DC_30)
+			bpc = 10;
+	} else {
+		bpc = (uint8_t)connector->display_info.bpc;
+		/* Assume 8 bpc by default if no bpc is specified. */
+		bpc = bpc ? bpc : 8;
+	}
 
 	if (!state)
 		state = connector->state;
@@ -3427,7 +3778,8 @@ static void fill_stream_properties_from_drm_display_mode(
 
 	timing_out->timing_3d_format = TIMING_3D_FORMAT_NONE;
 	timing_out->display_color_depth = convert_color_depth_from_display_info(
-		connector, connector_state);
+		connector, connector_state,
+		(timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420));
 	timing_out->scan_type = SCANNING_TYPE_NODATA;
 	timing_out->hdmi_vic = 0;
 
@@ -3645,10 +3997,10 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 	bool scale = dm_state ? (dm_state->scaling != RMX_OFF) : false;
 	int mode_refresh;
 	int preferred_refresh = 0;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	struct dsc_dec_dpcd_caps dsc_caps;
-	uint32_t link_bandwidth_kbps;
 #endif
+	uint32_t link_bandwidth_kbps;
 
 	struct dc_sink *sink = NULL;
 	if (aconnector == NULL) {
@@ -3723,16 +4075,19 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 		fill_stream_properties_from_drm_display_mode(stream,
 			&mode, &aconnector->base, con_state, old_stream);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	stream->timing.flags.DSC = 0;
 
 	if (aconnector->dc_link && sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT) {
-		dc_dsc_parse_dsc_dpcd(aconnector->dc_link->dpcd_caps.dsc_caps.dsc_basic_caps.raw,
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		dc_dsc_parse_dsc_dpcd(aconnector->dc_link->ctx->dc,
+				      aconnector->dc_link->dpcd_caps.dsc_caps.dsc_basic_caps.raw,
 				      aconnector->dc_link->dpcd_caps.dsc_caps.dsc_ext_caps.raw,
 				      &dsc_caps);
+#endif
 		link_bandwidth_kbps = dc_link_bandwidth_kbps(aconnector->dc_link,
 							     dc_link_get_link_cap(aconnector->dc_link));
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 		if (dsc_caps.is_dsc_supported)
 			if (dc_dsc_compute_config(aconnector->dc_link->ctx->dc->res_pool->dscs[0],
 						  &dsc_caps,
@@ -3741,8 +4096,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 						  &stream->timing,
 						  &stream->timing.dsc_cfg))
 				stream->timing.flags.DSC = 1;
-	}
 #endif
+	}
 
 	update_stream_scaling_settings(&mode, dm_state, stream);
 
@@ -3762,7 +4117,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 			struct dmcu *dmcu = core_dc->res_pool->dmcu;
 
 			stream->psr_version = dmcu->dmcu_version.psr_version;
-			mod_build_vsc_infopacket(stream, &stream->vsc_infopacket);
+			mod_build_vsc_infopacket(stream,
+					&stream->vsc_infopacket,
+					&stream->use_vsc_sdp_for_colorimetry);
 		}
 	}
 finish:
@@ -3853,6 +4210,10 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
 	struct amdgpu_device *adev = crtc->dev->dev_private;
 	int rc;
 
+	/* Do not set vupdate for DCN hardware */
+	if (adev->family > AMDGPU_FAMILY_AI)
+		return 0;
+
 	irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst;
 
 	rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY;
@@ -4096,7 +4457,8 @@ void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector)
 		state->underscan_hborder = 0;
 		state->underscan_vborder = 0;
 		state->base.max_requested_bpc = 8;
-
+		state->vcpi_slots = 0;
+		state->pbn = 0;
 		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
 			state->abm_level = amdgpu_dm_abm_level;
 
@@ -4124,7 +4486,8 @@ amdgpu_dm_connector_atomic_duplicate_state(struct drm_connector *connector)
 	new_state->underscan_enable = state->underscan_enable;
 	new_state->underscan_hborder = state->underscan_hborder;
 	new_state->underscan_vborder = state->underscan_vborder;
-
+	new_state->vcpi_slots = state->vcpi_slots;
+	new_state->pbn = state->pbn;
 	return &new_state->base;
 }
 
@@ -4521,10 +4884,69 @@ static void dm_encoder_helper_disable(struct drm_encoder *encoder)
 
 }
 
+static int convert_dc_color_depth_into_bpc (enum dc_color_depth display_color_depth)
+{
+	switch (display_color_depth) {
+		case COLOR_DEPTH_666:
+			return 6;
+		case COLOR_DEPTH_888:
+			return 8;
+		case COLOR_DEPTH_101010:
+			return 10;
+		case COLOR_DEPTH_121212:
+			return 12;
+		case COLOR_DEPTH_141414:
+			return 14;
+		case COLOR_DEPTH_161616:
+			return 16;
+		default:
+			break;
+		}
+	return 0;
+}
+
 static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder,
 					  struct drm_crtc_state *crtc_state,
 					  struct drm_connector_state *conn_state)
 {
+	struct drm_atomic_state *state = crtc_state->state;
+	struct drm_connector *connector = conn_state->connector;
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	struct dm_connector_state *dm_new_connector_state = to_dm_connector_state(conn_state);
+	const struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode;
+	struct drm_dp_mst_topology_mgr *mst_mgr;
+	struct drm_dp_mst_port *mst_port;
+	enum dc_color_depth color_depth;
+	int clock, bpp = 0;
+	bool is_y420 = false;
+
+	if (!aconnector->port || !aconnector->dc_sink)
+		return 0;
+
+	mst_port = aconnector->port;
+	mst_mgr = &aconnector->mst_port->mst_mgr;
+
+	if (!crtc_state->connectors_changed && !crtc_state->mode_changed)
+		return 0;
+
+	if (!state->duplicated) {
+		is_y420 = drm_mode_is_420_also(&connector->display_info, adjusted_mode) &&
+				aconnector->force_yuv420_output;
+		color_depth = convert_color_depth_from_display_info(connector, conn_state,
+								    is_y420);
+		bpp = convert_dc_color_depth_into_bpc(color_depth) * 3;
+		clock = adjusted_mode->clock;
+		dm_new_connector_state->pbn = drm_dp_calc_pbn_mode(clock, bpp, false);
+	}
+	dm_new_connector_state->vcpi_slots = drm_dp_atomic_find_vcpi_slots(state,
+									   mst_mgr,
+									   mst_port,
+									   dm_new_connector_state->pbn,
+									   0);
+	if (dm_new_connector_state->vcpi_slots < 0) {
+		DRM_DEBUG_ATOMIC("failed finding vcpi slots: %d\n", (int)dm_new_connector_state->vcpi_slots);
+		return dm_new_connector_state->vcpi_slots;
+	}
 	return 0;
 }
 
@@ -4533,6 +4955,71 @@ const struct drm_encoder_helper_funcs amdgpu_dm_encoder_helper_funcs = {
 	.atomic_check = dm_encoder_helper_atomic_check
 };
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
+					    struct dc_state *dc_state)
+{
+	struct dc_stream_state *stream = NULL;
+	struct drm_connector *connector;
+	struct drm_connector_state *new_con_state, *old_con_state;
+	struct amdgpu_dm_connector *aconnector;
+	struct dm_connector_state *dm_conn_state;
+	int i, j, clock, bpp;
+	int vcpi, pbn_div, pbn = 0;
+
+	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
+
+		aconnector = to_amdgpu_dm_connector(connector);
+
+		if (!aconnector->port)
+			continue;
+
+		if (!new_con_state || !new_con_state->crtc)
+			continue;
+
+		dm_conn_state = to_dm_connector_state(new_con_state);
+
+		for (j = 0; j < dc_state->stream_count; j++) {
+			stream = dc_state->streams[j];
+			if (!stream)
+				continue;
+
+			if ((struct amdgpu_dm_connector*)stream->dm_stream_context == aconnector)
+				break;
+
+			stream = NULL;
+		}
+
+		if (!stream)
+			continue;
+
+		if (stream->timing.flags.DSC != 1) {
+			drm_dp_mst_atomic_enable_dsc(state,
+						     aconnector->port,
+						     dm_conn_state->pbn,
+						     0,
+						     false);
+			continue;
+		}
+
+		pbn_div = dm_mst_get_pbn_divider(stream->link);
+		bpp = stream->timing.dsc_cfg.bits_per_pixel;
+		clock = stream->timing.pix_clk_100hz / 10;
+		pbn = drm_dp_calc_pbn_mode(clock, bpp, true);
+		vcpi = drm_dp_mst_atomic_enable_dsc(state,
+						    aconnector->port,
+						    pbn, pbn_div,
+						    true);
+		if (vcpi < 0)
+			return vcpi;
+
+		dm_conn_state->pbn = pbn;
+		dm_conn_state->vcpi_slots = vcpi;
+	}
+	return 0;
+}
+#endif
+
 static void dm_drm_plane_reset(struct drm_plane *plane)
 {
 	struct dm_plane_state *amdgpu_state = NULL;
@@ -5195,9 +5682,9 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 
 	drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16);
 
-	/* This defaults to the max in the range, but we want 8bpc. */
-	aconnector->base.state->max_bpc = 8;
-	aconnector->base.state->max_requested_bpc = 8;
+	/* This defaults to the max in the range, but we want 8bpc for non-edp. */
+	aconnector->base.state->max_bpc = (connector_type == DRM_MODE_CONNECTOR_eDP) ? 16 : 8;
+	aconnector->base.state->max_requested_bpc = aconnector->base.state->max_bpc;
 
 	if (connector_type == DRM_MODE_CONNECTOR_eDP &&
 	    dc_is_dmcu_initialized(adev->dm.dc)) {
@@ -5216,7 +5703,7 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 			&aconnector->base);
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 		if (adev->asic_type >= CHIP_RAVEN)
-			drm_connector_attach_content_protection_property(&aconnector->base, false);
+			drm_connector_attach_content_protection_property(&aconnector->base, true);
 #endif
 	}
 }
@@ -5325,11 +5812,12 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm,
 
 	connector_type = to_drm_connector_type(link->connector_signal);
 
-	res = drm_connector_init(
+	res = drm_connector_init_with_ddc(
 			dm->ddev,
 			&aconnector->base,
 			&amdgpu_dm_connector_funcs,
-			connector_type);
+			connector_type,
+			&i2c->base);
 
 	if (res) {
 		DRM_ERROR("connector_init failed\n");
@@ -5467,6 +5955,12 @@ static bool is_content_protection_different(struct drm_connector_state *state,
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
+	if (old_state->hdcp_content_type != state->hdcp_content_type &&
+	    state->content_protection != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) {
+		state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+		return true;
+	}
+
 	/* CP is being re enabled, ignore this */
 	if (old_state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED &&
 	    state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) {
@@ -5495,17 +5989,6 @@ static bool is_content_protection_different(struct drm_connector_state *state,
 	return false;
 }
 
-static void update_content_protection(struct drm_connector_state *state, const struct drm_connector *connector,
-				      struct hdcp_workqueue *hdcp_w)
-{
-	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-
-	if (state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED)
-		hdcp_add_display(hdcp_w, aconnector->dc_link->link_index, aconnector);
-	else if (state->content_protection == DRM_MODE_CONTENT_PROTECTION_UNDESIRED)
-		hdcp_remove_display(hdcp_w, aconnector->dc_link->link_index, aconnector->base.index);
-
-}
 #endif
 static void remove_stream(struct amdgpu_device *adev,
 			  struct amdgpu_crtc *acrtc,
@@ -6475,7 +6958,11 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		}
 
 		if (is_content_protection_different(new_con_state, old_con_state, connector, adev->dm.hdcp_workqueue))
-			update_content_protection(new_con_state, connector, adev->dm.hdcp_workqueue);
+			hdcp_update_display(
+				adev->dm.hdcp_workqueue, aconnector->dc_link->link_index, aconnector,
+				new_con_state->hdcp_content_type,
+				new_con_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED ? true
+													 : false);
 	}
 #endif
 
@@ -7265,7 +7752,7 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
 	int i, j, num_plane, ret = 0;
 	struct drm_plane_state *old_plane_state, *new_plane_state;
 	struct dm_plane_state *new_dm_plane_state, *old_dm_plane_state;
-	struct drm_crtc *new_plane_crtc, *old_plane_crtc;
+	struct drm_crtc *new_plane_crtc;
 	struct drm_plane *plane;
 
 	struct drm_crtc *crtc;
@@ -7311,7 +7798,6 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
 			uint64_t tiling_flags;
 
 			new_plane_crtc = new_plane_state->crtc;
-			old_plane_crtc = old_plane_state->crtc;
 			new_dm_plane_state = to_dm_plane_state(new_plane_state);
 			old_dm_plane_state = to_dm_plane_state(old_plane_state);
 
@@ -7412,6 +7898,29 @@ cleanup:
 	return ret;
 }
 
+static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm_crtc *crtc)
+{
+	struct drm_connector *connector;
+	struct drm_connector_state *conn_state;
+	struct amdgpu_dm_connector *aconnector = NULL;
+	int i;
+	for_each_new_connector_in_state(state, connector, conn_state, i) {
+		if (conn_state->crtc != crtc)
+			continue;
+
+		aconnector = to_amdgpu_dm_connector(connector);
+		if (!aconnector->port || !aconnector->mst_port)
+			aconnector = NULL;
+		else
+			break;
+	}
+
+	if (!aconnector)
+		return 0;
+
+	return drm_dp_mst_add_affected_dsc_crtcs(state, &aconnector->mst_port->mst_mgr);
+}
+
 /**
  * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM.
  * @dev: The DRM device
@@ -7464,6 +7973,16 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	if (ret)
 		goto fail;
 
+	if (adev->asic_type >= CHIP_NAVI10) {
+		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+			if (drm_atomic_crtc_needs_modeset(new_crtc_state)) {
+				ret = add_affected_mst_dsc_crtcs(state, crtc);
+				if (ret)
+					goto fail;
+			}
+		}
+	}
+
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		if (!drm_atomic_crtc_needs_modeset(new_crtc_state) &&
 		    !new_crtc_state->color_mgmt_changed &&
@@ -7635,6 +8154,15 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		if (ret)
 			goto fail;
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		if (!compute_mst_dsc_configs_for_state(state, dm_state->context))
+			goto fail;
+
+		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context);
+		if (ret)
+			goto fail;
+#endif
+
 		if (dc_validate_global_state(dc, dm_state->context, false) != DC_OK) {
 			ret = -EINVAL;
 			goto fail;
@@ -7663,6 +8191,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 				dc_retain_state(old_dm_state->context);
 		}
 	}
+	/* Perform validation of MST topology in the state*/
+	ret = drm_dp_mst_atomic_check(state);
+	if (ret)
+		goto fail;
 
 	/* Store the overall update type for use later in atomic check. */
 	for_each_new_crtc_in_state (state, crtc, new_crtc_state, i) {
@@ -7861,17 +8393,37 @@ static bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream)
 bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
 {
 	struct dc_link *link = stream->link;
-	struct dc_static_screen_events triggers = {0};
+	unsigned int vsync_rate_hz = 0;
+	struct dc_static_screen_params params = {0};
+	/* Calculate number of static frames before generating interrupt to
+	 * enter PSR.
+	 */
+	unsigned int frame_time_microsec = 1000000 / vsync_rate_hz;
+	// Init fail safe of 2 frames static
+	unsigned int num_frames_static = 2;
 
 	DRM_DEBUG_DRIVER("Enabling psr...\n");
 
-	triggers.cursor_update = true;
-	triggers.overlay_update = true;
-	triggers.surface_update = true;
+	vsync_rate_hz = div64_u64(div64_u64((
+			stream->timing.pix_clk_100hz * 100),
+			stream->timing.v_total),
+			stream->timing.h_total);
+
+	/* Round up
+	 * Calculate number of frames such that at least 30 ms of time has
+	 * passed.
+	 */
+	if (vsync_rate_hz != 0)
+		num_frames_static = (30000 / frame_time_microsec) + 1;
+
+	params.triggers.cursor_update = true;
+	params.triggers.overlay_update = true;
+	params.triggers.surface_update = true;
+	params.num_frames = num_frames_static;
 
-	dc_stream_set_static_screen_events(link->ctx->dc,
+	dc_stream_set_static_screen_params(link->ctx->dc,
 					   &stream, 1,
-					   &triggers);
+					   &params);
 
 	return dc_link_set_psr_allow_active(link, true, false);
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 77c5166e6b08..7ea9acb0358d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -57,6 +57,8 @@ struct amdgpu_device;
 struct drm_device;
 struct amdgpu_dm_irq_handler_data;
 struct dc;
+struct amdgpu_bo;
+struct dmub_srv;
 
 struct common_irq_params {
 	struct amdgpu_device *adev;
@@ -122,6 +124,57 @@ struct amdgpu_display_manager {
 	struct dc *dc;
 
 	/**
+	 * @dmub_srv:
+	 *
+	 * DMUB service, used for controlling the DMUB on hardware
+	 * that supports it. The pointer to the dmub_srv will be
+	 * NULL on hardware that does not support it.
+	 */
+	struct dmub_srv *dmub_srv;
+
+	/**
+	 * @dmub_fb_info:
+	 *
+	 * Framebuffer regions for the DMUB.
+	 */
+	struct dmub_srv_fb_info *dmub_fb_info;
+
+	/**
+	 * @dmub_fw:
+	 *
+	 * DMUB firmware, required on hardware that has DMUB support.
+	 */
+	const struct firmware *dmub_fw;
+
+	/**
+	 * @dmub_bo:
+	 *
+	 * Buffer object for the DMUB.
+	 */
+	struct amdgpu_bo *dmub_bo;
+
+	/**
+	 * @dmub_bo_gpu_addr:
+	 *
+	 * GPU virtual address for the DMUB buffer object.
+	 */
+	u64 dmub_bo_gpu_addr;
+
+	/**
+	 * @dmub_bo_cpu_addr:
+	 *
+	 * CPU address for the DMUB buffer object.
+	 */
+	void *dmub_bo_cpu_addr;
+
+	/**
+	 * @dmcub_fw_version:
+	 *
+	 * DMCUB firmware version.
+	 */
+	uint32_t dmcub_fw_version;
+
+	/**
 	 * @cgs_device:
 	 *
 	 * The Common Graphics Services device. It provides an interface for
@@ -241,7 +294,6 @@ struct amdgpu_display_manager {
 
 	const struct firmware *fw_dmcu;
 	uint32_t dmcu_fw_version;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	/**
 	 * @soc_bounding_box:
 	 *
@@ -249,7 +301,6 @@ struct amdgpu_display_manager {
 	 * available in FW
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
-#endif
 };
 
 struct amdgpu_dm_connector {
@@ -279,6 +330,7 @@ struct amdgpu_dm_connector {
 	struct drm_dp_mst_port *port;
 	struct amdgpu_dm_connector *mst_port;
 	struct amdgpu_encoder *mst_encoder;
+	struct drm_dp_aux *dsc_aux;
 
 	/* TODO see if we can merge with ddc_bus or make a dm_connector */
 	struct amdgpu_i2c_adapter *i2c;
@@ -359,6 +411,8 @@ struct dm_connector_state {
 	bool underscan_enable;
 	bool freesync_capable;
 	uint8_t abm_level;
+	int vcpi_slots;
+	uint64_t pbn;
 };
 
 #define to_dm_connector_state(x)\
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index bdb37e611015..f81d3439ee8c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -657,6 +657,7 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
 	dc_link_set_test_pattern(
 		link,
 		test_pattern,
+		DP_TEST_PATTERN_COLOR_SPACE_RGB,
 		&link_training_settings,
 		custom_pattern,
 		10);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 77181ddf6c8e..ae329335dfcc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -85,42 +85,54 @@ static void process_output(struct hdcp_workqueue *hdcp_work)
 		schedule_delayed_work(&hdcp_work->watchdog_timer_dwork,
 				      msecs_to_jiffies(output.watchdog_timer_delay));
 
+	schedule_delayed_work(&hdcp_work->property_validate_dwork, msecs_to_jiffies(0));
 }
 
-void hdcp_add_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index, struct amdgpu_dm_connector *aconnector)
+void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
+			 unsigned int link_index,
+			 struct amdgpu_dm_connector *aconnector,
+			 uint8_t content_type,
+			 bool enable_encryption)
 {
 	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
 	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
 	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
+	struct mod_hdcp_display_query query;
 
 	mutex_lock(&hdcp_w->mutex);
 	hdcp_w->aconnector = aconnector;
 
-	mod_hdcp_add_display(&hdcp_w->hdcp, link, display, &hdcp_w->output);
-
-	schedule_delayed_work(&hdcp_w->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS));
-
-	process_output(hdcp_w);
+	query.display = NULL;
+	mod_hdcp_query_display(&hdcp_w->hdcp, aconnector->base.index, &query);
 
-	mutex_unlock(&hdcp_w->mutex);
+	if (query.display != NULL) {
+		memcpy(display, query.display, sizeof(struct mod_hdcp_display));
+		mod_hdcp_remove_display(&hdcp_w->hdcp, aconnector->base.index, &hdcp_w->output);
 
-}
+		hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0;
 
-void hdcp_remove_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index,  unsigned int display_index)
-{
-	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
+		if (enable_encryption) {
+			display->adjust.disable = 0;
+			if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0)
+				hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0;
+			else if (content_type == DRM_MODE_HDCP_CONTENT_TYPE1)
+				hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_1;
 
-	mutex_lock(&hdcp_w->mutex);
+			schedule_delayed_work(&hdcp_w->property_validate_dwork,
+					      msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS));
+		} else {
+			display->adjust.disable = 1;
+			hdcp_w->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+			cancel_delayed_work(&hdcp_w->property_validate_dwork);
+		}
 
-	mod_hdcp_remove_display(&hdcp_w->hdcp, display_index, &hdcp_w->output);
+		display->state = MOD_HDCP_DISPLAY_ACTIVE;
+	}
 
-	cancel_delayed_work(&hdcp_w->property_validate_dwork);
-	hdcp_w->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+	mod_hdcp_add_display(&hdcp_w->hdcp, link, display, &hdcp_w->output);
 
 	process_output(hdcp_w);
-
 	mutex_unlock(&hdcp_w->mutex);
-
 }
 
 void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index)
@@ -190,10 +202,16 @@ static void event_property_update(struct work_struct *work)
 		}
 	}
 
-	if (hdcp_work->encryption_status == MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON)
-		drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_ENABLED);
-	else
+	if (hdcp_work->encryption_status != MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF) {
+		if (aconnector->base.state->hdcp_content_type == DRM_MODE_HDCP_CONTENT_TYPE0 &&
+		    hdcp_work->encryption_status <= MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON)
+			drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_ENABLED);
+		else if (aconnector->base.state->hdcp_content_type == DRM_MODE_HDCP_CONTENT_TYPE1 &&
+			 hdcp_work->encryption_status == MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON)
+			drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_ENABLED);
+	} else {
 		drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_DESIRED);
+	}
 
 
 	mutex_unlock(&hdcp_work->mutex);
@@ -207,6 +225,9 @@ static void event_property_validate(struct work_struct *work)
 	struct mod_hdcp_display_query query;
 	struct amdgpu_dm_connector *aconnector = hdcp_work->aconnector;
 
+	if (!aconnector)
+		return;
+
 	mutex_lock(&hdcp_work->mutex);
 
 	query.encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
@@ -217,8 +238,6 @@ static void event_property_validate(struct work_struct *work)
 		schedule_work(&hdcp_work->property_update_work);
 	}
 
-	schedule_delayed_work(&hdcp_work->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS));
-
 	mutex_unlock(&hdcp_work->mutex);
 }
 
@@ -294,8 +313,10 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	link->dig_be = config->link_enc_inst;
 	link->ddc_line = aconnector->dc_link->ddc_hw_inst + 1;
 	link->dp.rev = aconnector->dc_link->dpcd_caps.dpcd_rev.raw;
-	link->adjust.hdcp2.disable = 1;
+	display->adjust.disable = 1;
+	link->adjust.auth_delay = 2;
 
+	hdcp_update_display(hdcp_work, link_index, aconnector, DRM_MODE_HDCP_CONTENT_TYPE0, false);
 }
 
 struct hdcp_workqueue *hdcp_create_workqueue(void *psp_context, struct cp_psp *cp_psp, struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
index d3ba505d0696..6abde86bce4a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
@@ -54,9 +54,12 @@ struct hdcp_workqueue {
 	uint8_t max_link;
 };
 
-void hdcp_add_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index,
-		      struct amdgpu_dm_connector *aconnector);
-void hdcp_remove_display(struct hdcp_workqueue *work, unsigned int link_index, unsigned int display_index);
+void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
+			 unsigned int link_index,
+			 struct amdgpu_dm_connector *aconnector,
+			 uint8_t content_type,
+			 bool enable_encryption);
+
 void hdcp_reset_display(struct hdcp_workqueue *work, unsigned int link_index);
 void hdcp_handle_cpirq(struct hdcp_workqueue *work, unsigned int link_index);
 void hdcp_destroy(struct hdcp_workqueue *work);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 11e5784aa62a..069b7a6f5597 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -37,6 +37,7 @@
 #include "dc.h"
 #include "amdgpu_dm.h"
 #include "amdgpu_dm_irq.h"
+#include "amdgpu_dm_mst_types.h"
 
 #include "dm_helpers.h"
 
@@ -97,8 +98,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 			(struct edid *) edid->raw_edid);
 
 	sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads);
-	if (sad_count < 0)
-		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
 	if (sad_count <= 0)
 		return result;
 
@@ -182,19 +181,22 @@ bool dm_helpers_dp_mst_write_payload_allocation_table(
 		bool enable)
 {
 	struct amdgpu_dm_connector *aconnector;
+	struct dm_connector_state *dm_conn_state;
 	struct drm_dp_mst_topology_mgr *mst_mgr;
 	struct drm_dp_mst_port *mst_port;
-	int slots = 0;
 	bool ret;
-	int clock;
-	int bpp = 0;
-	int pbn = 0;
 
 	aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+	/* Accessing the connector state is required for vcpi_slots allocation
+	 * and directly relies on behaviour in commit check
+	 * that blocks before commit guaranteeing that the state
+	 * is not gonna be swapped while still in use in commit tail */
 
 	if (!aconnector || !aconnector->mst_port)
 		return false;
 
+	dm_conn_state = to_dm_connector_state(aconnector->base.state);
+
 	mst_mgr = &aconnector->mst_port->mst_mgr;
 
 	if (!mst_mgr->mst_state)
@@ -203,42 +205,10 @@ bool dm_helpers_dp_mst_write_payload_allocation_table(
 	mst_port = aconnector->port;
 
 	if (enable) {
-		clock = stream->timing.pix_clk_100hz / 10;
-
-		switch (stream->timing.display_color_depth) {
-
-		case COLOR_DEPTH_666:
-			bpp = 6;
-			break;
-		case COLOR_DEPTH_888:
-			bpp = 8;
-			break;
-		case COLOR_DEPTH_101010:
-			bpp = 10;
-			break;
-		case COLOR_DEPTH_121212:
-			bpp = 12;
-			break;
-		case COLOR_DEPTH_141414:
-			bpp = 14;
-			break;
-		case COLOR_DEPTH_161616:
-			bpp = 16;
-			break;
-		default:
-			ASSERT(bpp != 0);
-			break;
-		}
-
-		bpp = bpp * 3;
-
-		/* TODO need to know link rate */
-
-		pbn = drm_dp_calc_pbn_mode(clock, bpp);
-
-		slots = drm_dp_find_vcpi_slots(mst_mgr, pbn);
-		ret = drm_dp_mst_allocate_vcpi(mst_mgr, mst_port, pbn, slots);
 
+		ret = drm_dp_mst_allocate_vcpi(mst_mgr, mst_port,
+					       dm_conn_state->pbn,
+					       dm_conn_state->vcpi_slots);
 		if (!ret)
 			return false;
 
@@ -540,7 +510,6 @@ bool dm_helpers_submit_i2c(
 
 	return result;
 }
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 bool dm_helpers_dp_write_dsc_enable(
 		struct dc_context *ctx,
 		const struct dc_stream_state *stream,
@@ -548,10 +517,25 @@ bool dm_helpers_dp_write_dsc_enable(
 )
 {
 	uint8_t enable_dsc = enable ? 1 : 0;
+	struct amdgpu_dm_connector *aconnector;
+
+	if (!stream)
+		return false;
+
+	if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+
+		if (!aconnector->dsc_aux)
+			return false;
+
+		return (drm_dp_dpcd_write(aconnector->dsc_aux, DP_DSC_ENABLE, &enable_dsc, 1) >= 0);
+	}
+
+	if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT)
+		return dm_helpers_dp_write_dpcd(ctx, stream->link, DP_DSC_ENABLE, &enable_dsc, 1);
 
-	return dm_helpers_dp_write_dpcd(ctx, stream->sink->link, DP_DSC_ENABLE, &enable_dsc, 1);
+	return false;
 }
-#endif
 
 bool dm_helpers_is_dp_sink_present(struct dc_link *link)
 {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 64445c4cc4c2..cbcf504f73a5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -111,17 +111,12 @@ static void init_handler_common_data(struct amdgpu_dm_irq_handler_data *hcd,
  */
 static void dm_irq_work_func(struct work_struct *work)
 {
-	struct list_head *entry;
 	struct irq_list_head *irq_list_head =
 		container_of(work, struct irq_list_head, work);
 	struct list_head *handler_list = &irq_list_head->head;
 	struct amdgpu_dm_irq_handler_data *handler_data;
 
-	list_for_each(entry, handler_list) {
-		handler_data = list_entry(entry,
-					  struct amdgpu_dm_irq_handler_data,
-					  list);
-
+	list_for_each_entry(handler_data, handler_list, list) {
 		DRM_DEBUG_KMS("DM_IRQ: work_func: for dal_src=%d\n",
 				handler_data->irq_source);
 
@@ -528,19 +523,13 @@ static void amdgpu_dm_irq_immediate_work(struct amdgpu_device *adev,
 					 enum dc_irq_source irq_source)
 {
 	struct amdgpu_dm_irq_handler_data *handler_data;
-	struct list_head *entry;
 	unsigned long irq_table_flags;
 
 	DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
 
-	list_for_each(
-		entry,
-		&adev->dm.irq_handler_list_high_tab[irq_source]) {
-
-		handler_data = list_entry(entry,
-					  struct amdgpu_dm_irq_handler_data,
-					  list);
-
+	list_for_each_entry(handler_data,
+			    &adev->dm.irq_handler_list_high_tab[irq_source],
+			    list) {
 		/* Call a subcomponent which registered for immediate
 		 * interrupt notification */
 		handler_data->handler(handler_data->handler_arg);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 2bf8534c18fb..96b391e4b3e7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -25,6 +25,7 @@
 
 #include <linux/version.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_dp_mst_helper.h>
 #include "dm_services.h"
 #include "amdgpu.h"
 #include "amdgpu_dm.h"
@@ -39,6 +40,12 @@
 #if defined(CONFIG_DEBUG_FS)
 #include "amdgpu_dm_debugfs.h"
 #endif
+
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+#include "dc/dcn20/dcn20_resource.h"
+#endif
+
 /* #define TRACE_DPCD */
 
 #ifdef TRACE_DPCD
@@ -180,6 +187,30 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
 	.early_unregister = amdgpu_dm_mst_connector_early_unregister,
 };
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector)
+{
+	struct dc_sink *dc_sink = aconnector->dc_sink;
+	struct drm_dp_mst_port *port = aconnector->port;
+	u8 dsc_caps[16] = { 0 };
+
+	aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port);
+
+	if (!aconnector->dsc_aux)
+		return false;
+
+	if (drm_dp_dpcd_read(aconnector->dsc_aux, DP_DSC_SUPPORT, dsc_caps, 16) < 0)
+		return false;
+
+	if (!dc_dsc_parse_dsc_dpcd(aconnector->dc_link->ctx->dc,
+				   dsc_caps, NULL,
+				   &dc_sink->sink_dsc_caps.dsc_dec_caps))
+		return false;
+
+	return true;
+}
+#endif
+
 static int dm_dp_mst_get_modes(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
@@ -222,10 +253,16 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 		/* dc_link_add_remote_sink returns a new reference */
 		aconnector->dc_sink = dc_sink;
 
-		if (aconnector->dc_sink)
+		if (aconnector->dc_sink) {
 			amdgpu_dm_update_freesync_caps(
 					connector, aconnector->edid);
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+			if (!validate_dsc_caps_on_connector(aconnector))
+				memset(&aconnector->dc_sink->sink_dsc_caps,
+				       0, sizeof(aconnector->dc_sink->sink_dsc_caps));
+#endif
+		}
 	}
 
 	drm_connector_update_edid_property(
@@ -254,11 +291,43 @@ dm_dp_mst_detect(struct drm_connector *connector,
 				      aconnector->port);
 }
 
+static int dm_dp_mst_atomic_check(struct drm_connector *connector,
+				struct drm_atomic_state *state)
+{
+	struct drm_connector_state *new_conn_state =
+			drm_atomic_get_new_connector_state(state, connector);
+	struct drm_connector_state *old_conn_state =
+			drm_atomic_get_old_connector_state(state, connector);
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_dp_mst_topology_mgr *mst_mgr;
+	struct drm_dp_mst_port *mst_port;
+
+	mst_port = aconnector->port;
+	mst_mgr = &aconnector->mst_port->mst_mgr;
+
+	if (!old_conn_state->crtc)
+		return 0;
+
+	if (new_conn_state->crtc) {
+		new_crtc_state = drm_atomic_get_new_crtc_state(state, new_conn_state->crtc);
+		if (!new_crtc_state ||
+		    !drm_atomic_crtc_needs_modeset(new_crtc_state) ||
+		    new_crtc_state->enable)
+			return 0;
+		}
+
+	return drm_dp_atomic_release_vcpi_slots(state,
+						mst_mgr,
+						mst_port);
+}
+
 static const struct drm_connector_helper_funcs dm_dp_mst_connector_helper_funcs = {
 	.get_modes = dm_dp_mst_get_modes,
 	.mode_valid = amdgpu_dm_connector_mode_valid,
 	.atomic_best_encoder = dm_mst_atomic_best_encoder,
 	.detect_ctx = dm_dp_mst_detect,
+	.atomic_check = dm_dp_mst_atomic_check,
 };
 
 static void amdgpu_dm_encoder_destroy(struct drm_encoder *encoder)
@@ -434,3 +503,384 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 		aconnector->connector_id);
 }
 
+int dm_mst_get_pbn_divider(struct dc_link *link)
+{
+	if (!link)
+		return 0;
+
+	return dc_link_bandwidth_kbps(link,
+			dc_link_get_link_cap(link)) / (8 * 1000 * 54);
+}
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+
+struct dsc_mst_fairness_params {
+	struct dc_crtc_timing *timing;
+	struct dc_sink *sink;
+	struct dc_dsc_bw_range bw_range;
+	bool compression_possible;
+	struct drm_dp_mst_port *port;
+};
+
+struct dsc_mst_fairness_vars {
+	int pbn;
+	bool dsc_enabled;
+	int bpp_x16;
+};
+
+static int kbps_to_peak_pbn(int kbps)
+{
+	u64 peak_kbps = kbps;
+
+	peak_kbps *= 1006;
+	peak_kbps = div_u64(peak_kbps, 1000);
+	return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000));
+}
+
+static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params,
+		struct dsc_mst_fairness_vars *vars,
+		int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		memset(&params[i].timing->dsc_cfg, 0, sizeof(params[i].timing->dsc_cfg));
+		if (vars[i].dsc_enabled && dc_dsc_compute_config(
+					params[i].sink->ctx->dc->res_pool->dscs[0],
+					&params[i].sink->sink_dsc_caps.dsc_dec_caps,
+					params[i].sink->ctx->dc->debug.dsc_min_slice_height_override,
+					0,
+					params[i].timing,
+					&params[i].timing->dsc_cfg)) {
+			params[i].timing->flags.DSC = 1;
+			params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16;
+		} else {
+			params[i].timing->flags.DSC = 0;
+		}
+	}
+}
+
+static int bpp_x16_from_pbn(struct dsc_mst_fairness_params param, int pbn)
+{
+	struct dc_dsc_config dsc_config;
+	u64 kbps;
+
+	kbps = div_u64((u64)pbn * 994 * 8 * 54, 64);
+	dc_dsc_compute_config(
+			param.sink->ctx->dc->res_pool->dscs[0],
+			&param.sink->sink_dsc_caps.dsc_dec_caps,
+			param.sink->ctx->dc->debug.dsc_min_slice_height_override,
+			(int) kbps, param.timing, &dsc_config);
+
+	return dsc_config.bits_per_pixel;
+}
+
+static void increase_dsc_bpp(struct drm_atomic_state *state,
+			     struct dc_link *dc_link,
+			     struct dsc_mst_fairness_params *params,
+			     struct dsc_mst_fairness_vars *vars,
+			     int count)
+{
+	int i;
+	bool bpp_increased[MAX_PIPES];
+	int initial_slack[MAX_PIPES];
+	int min_initial_slack;
+	int next_index;
+	int remaining_to_increase = 0;
+	int pbn_per_timeslot;
+	int link_timeslots_used;
+	int fair_pbn_alloc;
+
+	for (i = 0; i < count; i++) {
+		if (vars[i].dsc_enabled) {
+			initial_slack[i] = kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i].pbn;
+			bpp_increased[i] = false;
+			remaining_to_increase += 1;
+		} else {
+			initial_slack[i] = 0;
+			bpp_increased[i] = true;
+		}
+	}
+
+	pbn_per_timeslot = dc_link_bandwidth_kbps(dc_link,
+			dc_link_get_link_cap(dc_link)) / (8 * 1000 * 54);
+
+	while (remaining_to_increase) {
+		next_index = -1;
+		min_initial_slack = -1;
+		for (i = 0; i < count; i++) {
+			if (!bpp_increased[i]) {
+				if (min_initial_slack == -1 || min_initial_slack > initial_slack[i]) {
+					min_initial_slack = initial_slack[i];
+					next_index = i;
+				}
+			}
+		}
+
+		if (next_index == -1)
+			break;
+
+		link_timeslots_used = 0;
+
+		for (i = 0; i < count; i++)
+			link_timeslots_used += DIV_ROUND_UP(vars[i].pbn, pbn_per_timeslot);
+
+		fair_pbn_alloc = (63 - link_timeslots_used) / remaining_to_increase * pbn_per_timeslot;
+
+		if (initial_slack[next_index] > fair_pbn_alloc) {
+			vars[next_index].pbn += fair_pbn_alloc;
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[next_index].port->mgr,
+							  params[next_index].port,
+							  vars[next_index].pbn,\
+							  dm_mst_get_pbn_divider(dc_link)) < 0)
+				return;
+			if (!drm_dp_mst_atomic_check(state)) {
+				vars[next_index].bpp_x16 = bpp_x16_from_pbn(params[next_index], vars[next_index].pbn);
+			} else {
+				vars[next_index].pbn -= fair_pbn_alloc;
+				if (drm_dp_atomic_find_vcpi_slots(state,
+								  params[next_index].port->mgr,
+								  params[next_index].port,
+								  vars[next_index].pbn,
+								  dm_mst_get_pbn_divider(dc_link)) < 0)
+					return;
+			}
+		} else {
+			vars[next_index].pbn += initial_slack[next_index];
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[next_index].port->mgr,
+							  params[next_index].port,
+							  vars[next_index].pbn,
+							  dm_mst_get_pbn_divider(dc_link)) < 0)
+				return;
+			if (!drm_dp_mst_atomic_check(state)) {
+				vars[next_index].bpp_x16 = params[next_index].bw_range.max_target_bpp_x16;
+			} else {
+				vars[next_index].pbn -= initial_slack[next_index];
+				if (drm_dp_atomic_find_vcpi_slots(state,
+								  params[next_index].port->mgr,
+								  params[next_index].port,
+								  vars[next_index].pbn,
+								  dm_mst_get_pbn_divider(dc_link)) < 0)
+					return;
+			}
+		}
+
+		bpp_increased[next_index] = true;
+		remaining_to_increase--;
+	}
+}
+
+static void try_disable_dsc(struct drm_atomic_state *state,
+			    struct dc_link *dc_link,
+			    struct dsc_mst_fairness_params *params,
+			    struct dsc_mst_fairness_vars *vars,
+			    int count)
+{
+	int i;
+	bool tried[MAX_PIPES];
+	int kbps_increase[MAX_PIPES];
+	int max_kbps_increase;
+	int next_index;
+	int remaining_to_try = 0;
+
+	for (i = 0; i < count; i++) {
+		if (vars[i].dsc_enabled && vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16) {
+			kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps;
+			tried[i] = false;
+			remaining_to_try += 1;
+		} else {
+			kbps_increase[i] = 0;
+			tried[i] = true;
+		}
+	}
+
+	while (remaining_to_try) {
+		next_index = -1;
+		max_kbps_increase = -1;
+		for (i = 0; i < count; i++) {
+			if (!tried[i]) {
+				if (max_kbps_increase == -1 || max_kbps_increase < kbps_increase[i]) {
+					max_kbps_increase = kbps_increase[i];
+					next_index = i;
+				}
+			}
+		}
+
+		if (next_index == -1)
+			break;
+
+		vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps);
+		if (drm_dp_atomic_find_vcpi_slots(state,
+						  params[next_index].port->mgr,
+						  params[next_index].port,
+						  vars[next_index].pbn,
+						  0) < 0)
+			return;
+
+		if (!drm_dp_mst_atomic_check(state)) {
+			vars[next_index].dsc_enabled = false;
+			vars[next_index].bpp_x16 = 0;
+		} else {
+			vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps);
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[next_index].port->mgr,
+							  params[next_index].port,
+							  vars[next_index].pbn,
+							  dm_mst_get_pbn_divider(dc_link)) < 0)
+				return;
+		}
+
+		tried[next_index] = true;
+		remaining_to_try--;
+	}
+}
+
+static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
+					     struct dc_state *dc_state,
+					     struct dc_link *dc_link)
+{
+	int i;
+	struct dc_stream_state *stream;
+	struct dsc_mst_fairness_params params[MAX_PIPES];
+	struct dsc_mst_fairness_vars vars[MAX_PIPES];
+	struct amdgpu_dm_connector *aconnector;
+	int count = 0;
+
+	memset(params, 0, sizeof(params));
+
+	/* Set up params */
+	for (i = 0; i < dc_state->stream_count; i++) {
+		struct dc_dsc_policy dsc_policy = {0};
+
+		stream = dc_state->streams[i];
+
+		if (stream->link != dc_link)
+			continue;
+
+		stream->timing.flags.DSC = 0;
+
+		params[count].timing = &stream->timing;
+		params[count].sink = stream->sink;
+		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+		params[count].port = aconnector->port;
+		params[count].compression_possible = stream->sink->sink_dsc_caps.dsc_dec_caps.is_dsc_supported;
+		dc_dsc_get_policy_for_timing(params[count].timing, &dsc_policy);
+		if (!dc_dsc_compute_bandwidth_range(
+				stream->sink->ctx->dc->res_pool->dscs[0],
+				stream->sink->ctx->dc->debug.dsc_min_slice_height_override,
+				dsc_policy.min_target_bpp,
+				dsc_policy.max_target_bpp,
+				&stream->sink->sink_dsc_caps.dsc_dec_caps,
+				&stream->timing, &params[count].bw_range))
+			params[count].bw_range.stream_kbps = dc_bandwidth_in_kbps_from_timing(&stream->timing);
+
+		count++;
+	}
+	/* Try no compression */
+	for (i = 0; i < count; i++) {
+		vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+		vars[i].dsc_enabled = false;
+		vars[i].bpp_x16 = 0;
+		if (drm_dp_atomic_find_vcpi_slots(state,
+						 params[i].port->mgr,
+						 params[i].port,
+						 vars[i].pbn,
+						 0) < 0)
+			return false;
+	}
+	if (!drm_dp_mst_atomic_check(state)) {
+		set_dsc_configs_from_fairness_vars(params, vars, count);
+		return true;
+	}
+
+	/* Try max compression */
+	for (i = 0; i < count; i++) {
+		if (params[i].compression_possible) {
+			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
+			vars[i].dsc_enabled = true;
+			vars[i].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[i].port->mgr,
+							  params[i].port,
+							  vars[i].pbn,
+							  dm_mst_get_pbn_divider(dc_link)) < 0)
+				return false;
+		} else {
+			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+			vars[i].dsc_enabled = false;
+			vars[i].bpp_x16 = 0;
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[i].port->mgr,
+							  params[i].port,
+							  vars[i].pbn,
+							  0) < 0)
+				return false;
+		}
+	}
+	if (drm_dp_mst_atomic_check(state))
+		return false;
+
+	/* Optimize degree of compression */
+	increase_dsc_bpp(state, dc_link, params, vars, count);
+
+	try_disable_dsc(state, dc_link, params, vars, count);
+
+	set_dsc_configs_from_fairness_vars(params, vars, count);
+
+	return true;
+}
+
+bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
+				       struct dc_state *dc_state)
+{
+	int i, j;
+	struct dc_stream_state *stream;
+	bool computed_streams[MAX_PIPES];
+	struct amdgpu_dm_connector *aconnector;
+
+	for (i = 0; i < dc_state->stream_count; i++)
+		computed_streams[i] = false;
+
+	for (i = 0; i < dc_state->stream_count; i++) {
+		stream = dc_state->streams[i];
+
+		if (stream->signal != SIGNAL_TYPE_DISPLAY_PORT_MST)
+			continue;
+
+		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+
+		if (!aconnector || !aconnector->dc_sink)
+			continue;
+
+		if (!aconnector->dc_sink->sink_dsc_caps.dsc_dec_caps.is_dsc_supported)
+			continue;
+
+		if (computed_streams[i])
+			continue;
+
+		mutex_lock(&aconnector->mst_mgr.lock);
+		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link)) {
+			mutex_unlock(&aconnector->mst_mgr.lock);
+			return false;
+		}
+		mutex_unlock(&aconnector->mst_mgr.lock);
+
+		for (j = 0; j < dc_state->stream_count; j++) {
+			if (dc_state->streams[j]->link == stream->link)
+				computed_streams[j] = true;
+		}
+	}
+
+	for (i = 0; i < dc_state->stream_count; i++) {
+		stream = dc_state->streams[i];
+
+		if (stream->timing.flags.DSC == 1)
+			dcn20_add_dsc_to_stream_resource(stream->ctx->dc, dc_state, stream);
+	}
+
+	return true;
+}
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index 2da851b40042..d6813ce67bbd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -29,7 +29,14 @@
 struct amdgpu_display_manager;
 struct amdgpu_dm_connector;
 
+int dm_mst_get_pbn_divider(struct dc_link *link);
+
 void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 				       struct amdgpu_dm_connector *aconnector);
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
+				       struct dc_state *dc_state);
+#endif
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 778f186b3a05..a2e1a73f66b8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -892,7 +892,6 @@ enum pp_smu_status pp_nv_get_uclk_dpm_states(struct pp_smu *pp,
 	return PP_SMU_RESULT_FAIL;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 enum pp_smu_status pp_rn_get_dpm_clock_table(
 		struct pp_smu *pp, struct dpm_clocks *clock_table)
 {
@@ -974,7 +973,6 @@ enum pp_smu_status pp_rn_set_wm_ranges(struct pp_smu *pp,
 
 	return PP_SMU_RESULT_OK;
 }
-#endif
 
 void dm_pp_get_funcs(
 		struct dc_context *ctx,
@@ -996,7 +994,6 @@ void dm_pp_get_funcs(
 		funcs->rv_funcs.set_hard_min_fclk_by_freq =
 				pp_rv_set_hard_min_fclk_by_freq;
 		break;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	case DCN_VERSION_2_0:
 		funcs->ctx.ver = PP_SMU_VER_NV;
 		funcs->nv_funcs.pp_smu.dm = ctx;
@@ -1019,16 +1016,13 @@ void dm_pp_get_funcs(
 		funcs->nv_funcs.get_uclk_dpm_states = pp_nv_get_uclk_dpm_states;
 		funcs->nv_funcs.set_pstate_handshake_support = pp_nv_set_pstate_handshake_support;
 		break;
-#endif
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	case DCN_VERSION_2_1:
 		funcs->ctx.ver = PP_SMU_VER_RN;
 		funcs->rn_funcs.pp_smu.dm = ctx;
 		funcs->rn_funcs.set_wm_ranges = pp_rn_set_wm_ranges;
 		funcs->rn_funcs.get_dpm_clock_table = pp_rn_get_dpm_clock_table;
 		break;
-#endif
 	default:
 		DRM_ERROR("smu version is not supported !\n");
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index a160512a2f04..6e3dddc73246 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -25,19 +25,10 @@
 
 DC_LIBS = basics bios calcs clk_mgr dce gpio irq virtual
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 DC_LIBS += dcn20
-endif
-
-
-ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 DC_LIBS += dsc
-endif
-
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
 DC_LIBS += dcn10 dml
-endif
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 DC_LIBS += dcn21
 endif
 
@@ -59,7 +50,7 @@ include $(AMD_DC)
 DISPLAY_CORE = dc.o dc_link.o dc_resource.o dc_hw_sequencer.o dc_sink.o \
 dc_surface.o dc_link_hwss.o dc_link_dp.o dc_link_ddc.o dc_debug.o dc_stream.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 DISPLAY_CORE += dc_vm_helper.o
 endif
 
@@ -70,5 +61,6 @@ AMD_DM_REG_UPDATE = $(addprefix $(AMDDALPATH)/dc/,dc_helper.o)
 AMD_DISPLAY_FILES += $(AMD_DISPLAY_CORE)
 AMD_DISPLAY_FILES += $(AMD_DM_REG_UPDATE)
 
-
-
+DC_DMUB += dc_dmub_srv.o
+AMD_DISPLAY_DMUB = $(addprefix $(AMDDALPATH)/dc/,$(DC_DMUB))
+AMD_DISPLAY_FILES += $(AMD_DISPLAY_DMUB)
diff --git a/drivers/gpu/drm/amd/display/dc/basics/Makefile b/drivers/gpu/drm/amd/display/dc/basics/Makefile
index a50a76471107..7ad0cad0f4ef 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/basics/Makefile
@@ -25,7 +25,7 @@
 # subcomponents.
 
 BASICS = conversion.o fixpt31_32.o \
-	log_helpers.o vector.o
+	log_helpers.o vector.o dc_common.o
 
 AMD_DAL_BASICS = $(addprefix $(AMDDALPATH)/dc/basics/,$(BASICS))
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/dc_common.c b/drivers/gpu/drm/amd/display/dc/basics/dc_common.c
new file mode 100644
index 000000000000..b2fc4f8e6482
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/basics/dc_common.c
@@ -0,0 +1,101 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "core_types.h"
+#include "dc_common.h"
+#include "basics/conversion.h"
+
+bool is_rgb_cspace(enum dc_color_space output_color_space)
+{
+	switch (output_color_space) {
+	case COLOR_SPACE_SRGB:
+	case COLOR_SPACE_SRGB_LIMITED:
+	case COLOR_SPACE_2020_RGB_FULLRANGE:
+	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
+	case COLOR_SPACE_ADOBERGB:
+		return true;
+	case COLOR_SPACE_YCBCR601:
+	case COLOR_SPACE_YCBCR709:
+	case COLOR_SPACE_YCBCR601_LIMITED:
+	case COLOR_SPACE_YCBCR709_LIMITED:
+	case COLOR_SPACE_2020_YCBCR:
+		return false;
+	default:
+		/* Add a case to switch */
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+}
+
+bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
+{
+	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
+		return true;
+	if (pipe_ctx->bottom_pipe && is_lower_pipe_tree_visible(pipe_ctx->bottom_pipe))
+		return true;
+	return false;
+}
+
+bool is_upper_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
+{
+	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
+		return true;
+	if (pipe_ctx->top_pipe && is_upper_pipe_tree_visible(pipe_ctx->top_pipe))
+		return true;
+	return false;
+}
+
+bool is_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
+{
+	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
+		return true;
+	if (pipe_ctx->top_pipe && is_upper_pipe_tree_visible(pipe_ctx->top_pipe))
+		return true;
+	if (pipe_ctx->bottom_pipe && is_lower_pipe_tree_visible(pipe_ctx->bottom_pipe))
+		return true;
+	return false;
+}
+
+void build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
+		const struct dc_plane_state *plane_state)
+{
+	if (plane_state->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN
+			&& plane_state->format != SURFACE_PIXEL_FORMAT_INVALID
+			&& plane_state->input_csc_color_matrix.enable_adjustment
+			&& plane_state->coeff_reduction_factor.value != 0) {
+		bias_and_scale->scale_blue = fixed_point_to_int_frac(
+			dc_fixpt_mul(plane_state->coeff_reduction_factor,
+					dc_fixpt_from_fraction(256, 255)),
+				2,
+				13);
+		bias_and_scale->scale_red = bias_and_scale->scale_blue;
+		bias_and_scale->scale_green = bias_and_scale->scale_blue;
+	} else {
+		bias_and_scale->scale_blue = 0x2000;
+		bias_and_scale->scale_red = 0x2000;
+		bias_and_scale->scale_green = 0x2000;
+	}
+}
+
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.h b/drivers/gpu/drm/amd/display/dc/basics/dc_common.h
index 8bdfb3e5cd1c..7c0cbf47e8ce 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.h
+++ b/drivers/gpu/drm/amd/display/dc/basics/dc_common.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
+ * Copyright 2012-15 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"),
@@ -14,23 +14,29 @@
  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
  */
 
-#ifndef __NVKM_SECBOOT_ACR_R367_H__
-#define __NVKM_SECBOOT_ACR_R367_H__
+#ifndef __DAL_DC_COMMON_H__
+#define __DAL_DC_COMMON_H__
+
+#include "core_types.h"
+
+bool is_rgb_cspace(enum dc_color_space output_color_space);
+
+bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
+
+bool is_upper_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
 
-#include "acr_r352.h"
+bool is_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
 
-void acr_r367_fixup_hs_desc(struct acr_r352 *, struct nvkm_secboot *, void *);
+void build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
+		const struct dc_plane_state *plane_state);
 
-struct ls_ucode_img *acr_r367_ls_ucode_img_load(const struct acr_r352 *,
-						const struct nvkm_secboot *,
-						enum nvkm_secboot_falcon);
-int acr_r367_ls_fill_headers(struct acr_r352 *, struct list_head *);
-int acr_r367_ls_write_wpr(struct acr_r352 *, struct list_head *,
-			  struct nvkm_gpuobj *, u64);
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index 823843cd2613..008d4d11339d 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -111,7 +111,7 @@ struct dc_bios *bios_parser_create(
 	return NULL;
 }
 
-static void destruct(struct bios_parser *bp)
+static void bios_parser_destruct(struct bios_parser *bp)
 {
 	kfree(bp->base.bios_local_image);
 	kfree(bp->base.integrated_info);
@@ -126,7 +126,7 @@ static void bios_parser_destroy(struct dc_bios **dcb)
 		return;
 	}
 
-	destruct(bp);
+	bios_parser_destruct(bp);
 
 	kfree(bp);
 	*dcb = NULL;
@@ -2189,7 +2189,7 @@ static uint32_t get_support_mask_for_device_id(struct device_id device_id)
 		break;
 	default:
 		break;
-	};
+	}
 
 	/* Unidentified device ID, return empty support mask. */
 	return 0;
@@ -2739,7 +2739,6 @@ static enum bp_result bios_get_board_layout_info(
 	struct board_layout_info *board_layout_info)
 {
 	unsigned int i;
-	struct bios_parser *bp;
 	enum bp_result record_result;
 
 	const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = {
@@ -2748,7 +2747,6 @@ static enum bp_result bios_get_board_layout_info(
 		0, 0
 	};
 
-	bp = BP_FROM_DCB(dcb);
 	if (board_layout_info == NULL) {
 		DC_LOG_DETECTION_EDID_PARSER("Invalid board_layout_info\n");
 		return BP_RESULT_BADINPUT;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 5c3fcaa47410..2f1c9584ac32 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -111,7 +111,7 @@ static struct atom_encoder_caps_record *get_encoder_cap_record(
 
 #define DATA_TABLES(table) (bp->master_data_tbl->listOfdatatables.table)
 
-static void destruct(struct bios_parser *bp)
+static void bios_parser2_destruct(struct bios_parser *bp)
 {
 	kfree(bp->base.bios_local_image);
 	kfree(bp->base.integrated_info);
@@ -126,7 +126,7 @@ static void firmware_parser_destroy(struct dc_bios **dcb)
 		return;
 	}
 
-	destruct(bp);
+	bios_parser2_destruct(bp);
 
 	kfree(bp);
 	*dcb = NULL;
@@ -294,11 +294,21 @@ static enum bp_result bios_parser_get_i2c_info(struct dc_bios *dcb,
 	struct atom_display_object_path_v2 *object;
 	struct atom_common_record_header *header;
 	struct atom_i2c_record *record;
+	struct atom_i2c_record dummy_record = {0};
 	struct bios_parser *bp = BP_FROM_DCB(dcb);
 
 	if (!info)
 		return BP_RESULT_BADINPUT;
 
+	if (id.type == OBJECT_TYPE_GENERIC) {
+		dummy_record.i2c_id = id.id;
+
+		if (get_gpio_i2c_info(bp, &dummy_record, info) == BP_RESULT_OK)
+			return BP_RESULT_OK;
+		else
+			return BP_RESULT_NORECORD;
+	}
+
 	object = get_bios_object(bp, id);
 
 	if (!object)
@@ -341,6 +351,7 @@ static enum bp_result get_gpio_i2c_info(
 	struct atom_gpio_pin_lut_v2_1 *header;
 	uint32_t count = 0;
 	unsigned int table_index = 0;
+	bool find_valid = false;
 
 	if (!info)
 		return BP_RESULT_BADINPUT;
@@ -368,33 +379,28 @@ static enum bp_result get_gpio_i2c_info(
 			- sizeof(struct atom_common_table_header))
 				/ sizeof(struct atom_gpio_pin_assignment);
 
-	table_index = record->i2c_id  & I2C_HW_LANE_MUX;
-
-	if (count < table_index) {
-		bool find_valid = false;
-
-		for (table_index = 0; table_index < count; table_index++) {
-			if (((record->i2c_id & I2C_HW_CAP) == (
-			header->gpio_pin[table_index].gpio_id &
-							I2C_HW_CAP)) &&
-			((record->i2c_id & I2C_HW_ENGINE_ID_MASK)  ==
-			(header->gpio_pin[table_index].gpio_id &
-						I2C_HW_ENGINE_ID_MASK)) &&
-			((record->i2c_id & I2C_HW_LANE_MUX) ==
-			(header->gpio_pin[table_index].gpio_id &
-							I2C_HW_LANE_MUX))) {
-				/* still valid */
-				find_valid = true;
-				break;
-			}
+	for (table_index = 0; table_index < count; table_index++) {
+		if (((record->i2c_id & I2C_HW_CAP) == (
+		header->gpio_pin[table_index].gpio_id &
+						I2C_HW_CAP)) &&
+		((record->i2c_id & I2C_HW_ENGINE_ID_MASK)  ==
+		(header->gpio_pin[table_index].gpio_id &
+					I2C_HW_ENGINE_ID_MASK)) &&
+		((record->i2c_id & I2C_HW_LANE_MUX) ==
+		(header->gpio_pin[table_index].gpio_id &
+						I2C_HW_LANE_MUX))) {
+			/* still valid */
+			find_valid = true;
+			break;
 		}
-		/* If we don't find the entry that we are looking for then
-		 *  we will return BP_Result_BadBiosTable.
-		 */
-		if (find_valid == false)
-			return BP_RESULT_BADBIOSTABLE;
 	}
 
+	/* If we don't find the entry that we are looking for then
+	 *  we will return BP_Result_BadBiosTable.
+	 */
+	if (find_valid == false)
+		return BP_RESULT_BADBIOSTABLE;
+
 	/* get the GPIO_I2C_INFO */
 	info->i2c_hw_assist = (record->i2c_id & I2C_HW_CAP) ? true : false;
 	info->i2c_line = record->i2c_id & I2C_HW_LANE_MUX;
@@ -828,6 +834,7 @@ static enum bp_result bios_parser_get_spread_spectrum_info(
 		case 1:
 			return get_ss_info_v4_1(bp, signal, index, ss_info);
 		case 2:
+		case 3:
 			return get_ss_info_v4_2(bp, signal, index, ss_info);
 		default:
 			break;
@@ -986,7 +993,7 @@ static uint32_t get_support_mask_for_device_id(struct device_id device_id)
 		break;
 	default:
 		break;
-	};
+	}
 
 	/* Unidentified device ID, return empty support mask. */
 	return 0;
@@ -1205,6 +1212,8 @@ static enum bp_result get_firmware_info_v3_1(
 				bp->cmd_tbl.get_smu_clock_info(bp, SMU9_SYSPLL0_ID) * 10;
 	}
 
+	info->oem_i2c_present = false;
+
 	return BP_RESULT_OK;
 }
 
@@ -1283,6 +1292,13 @@ static enum bp_result get_firmware_info_v3_2(
 					bp->cmd_tbl.get_smu_clock_info(bp, SMU11_SYSPLL3_0_ID) * 10;
 	}
 
+	if (firmware_info->board_i2c_feature_id == 0x2) {
+		info->oem_i2c_present = true;
+		info->oem_i2c_obj_id = firmware_info->board_i2c_feature_gpio_id;
+	} else {
+		info->oem_i2c_present = false;
+	}
+
 	return BP_RESULT_OK;
 }
 
@@ -1402,10 +1418,8 @@ static enum bp_result get_integrated_info_v11(
 	info->ma_channel_number = info_v11->umachannelnumber;
 	info->lvds_ss_percentage =
 	le16_to_cpu(info_v11->lvds_ss_percentage);
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	info->dp_ss_control =
 	le16_to_cpu(info_v11->reserved1);
-#endif
 	info->lvds_sspread_rate_in_10hz =
 	le16_to_cpu(info_v11->lvds_ss_rate_10hz);
 	info->hdmi_ss_percentage =
@@ -1826,7 +1840,6 @@ static enum bp_result bios_get_board_layout_info(
 	struct board_layout_info *board_layout_info)
 {
 	unsigned int i;
-	struct bios_parser *bp;
 	enum bp_result record_result;
 
 	const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = {
@@ -1835,7 +1848,6 @@ static enum bp_result bios_get_board_layout_info(
 		0, 0
 	};
 
-	bp = BP_FROM_DCB(dcb);
 	if (board_layout_info == NULL) {
 		DC_LOG_DETECTION_EDID_PARSER("Invalid board_layout_info\n");
 		return BP_RESULT_BADINPUT;
@@ -1915,7 +1927,7 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.get_board_layout_info = bios_get_board_layout_info,
 };
 
-static bool bios_parser_construct(
+static bool bios_parser2_construct(
 	struct bios_parser *bp,
 	struct bp_init_data *init,
 	enum dce_version dce_version)
@@ -2008,7 +2020,7 @@ struct dc_bios *firmware_parser_create(
 	if (!bp)
 		return NULL;
 
-	if (bios_parser_construct(bp, init, dce_version))
+	if (bios_parser2_construct(bp, init, dce_version))
 		return &bp->base;
 
 	kfree(bp);
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index bb2e8105e6ab..2cb7a4288cb7 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -37,6 +37,8 @@
 #include "bios_parser_types_internal2.h"
 #include "amdgpu.h"
 
+#include "dc_dmub_srv.h"
+#include "dc.h"
 
 #define DC_LOGGER \
 	bp->base.ctx->logger
@@ -103,6 +105,21 @@ static void init_dig_encoder_control(struct bios_parser *bp)
 	}
 }
 
+static void encoder_control_dmcub(
+		struct dc_dmub_srv *dmcub,
+		struct dig_encoder_stream_setup_parameters_v1_5 *dig)
+{
+	struct dmub_rb_cmd_digx_encoder_control encoder_control = { 0 };
+
+	encoder_control.header.type = DMUB_CMD__VBIOS;
+	encoder_control.header.sub_type = DMUB_CMD__VBIOS_DIGX_ENCODER_CONTROL;
+	encoder_control.encoder_control.dig.stream_param = *dig;
+
+	dc_dmub_srv_cmd_queue(dmcub, &encoder_control.header);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+}
+
 static enum bp_result encoder_control_digx_v1_5(
 	struct bios_parser *bp,
 	struct bp_encoder_control *cntl)
@@ -155,6 +172,12 @@ static enum bp_result encoder_control_digx_v1_5(
 			break;
 		}
 
+	if (bp->base.ctx->dc->ctx->dmub_srv &&
+	    bp->base.ctx->dc->debug.dmub_command_table) {
+		encoder_control_dmcub(bp->base.ctx->dmub_srv, &params);
+		return BP_RESULT_OK;
+	}
+
 	if (EXEC_BIOS_CMD_TABLE(digxencodercontrol, params))
 		result = BP_RESULT_OK;
 
@@ -191,6 +214,22 @@ static void init_transmitter_control(struct bios_parser *bp)
 	}
 }
 
+static void transmitter_control_dmcub(
+		struct dc_dmub_srv *dmcub,
+		struct dig_transmitter_control_parameters_v1_6 *dig)
+{
+	struct dmub_rb_cmd_dig1_transmitter_control transmitter_control;
+
+	transmitter_control.header.type = DMUB_CMD__VBIOS;
+	transmitter_control.header.sub_type =
+		DMUB_CMD__VBIOS_DIG1_TRANSMITTER_CONTROL;
+	transmitter_control.transmitter_control.dig = *dig;
+
+	dc_dmub_srv_cmd_queue(dmcub, &transmitter_control.header);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+}
+
 static enum bp_result transmitter_control_v1_6(
 	struct bios_parser *bp,
 	struct bp_transmitter_control *cntl)
@@ -222,6 +261,11 @@ static enum bp_result transmitter_control_v1_6(
 		__func__, ps.param.symclk_10khz);
 	}
 
+	if (bp->base.ctx->dc->ctx->dmub_srv &&
+	    bp->base.ctx->dc->debug.dmub_command_table) {
+		transmitter_control_dmcub(bp->base.ctx->dmub_srv, &ps.param);
+		return BP_RESULT_OK;
+	}
 
 /*color_depth not used any more, driver has deep color factor in the Phyclk*/
 	if (EXEC_BIOS_CMD_TABLE(dig1transmittercontrol, ps))
@@ -255,7 +299,20 @@ static void init_set_pixel_clock(struct bios_parser *bp)
 	}
 }
 
+static void set_pixel_clock_dmcub(
+		struct dc_dmub_srv *dmcub,
+		struct set_pixel_clock_parameter_v1_7 *clk)
+{
+	struct dmub_rb_cmd_set_pixel_clock pixel_clock = { 0 };
+
+	pixel_clock.header.type = DMUB_CMD__VBIOS;
+	pixel_clock.header.sub_type = DMUB_CMD__VBIOS_SET_PIXEL_CLOCK;
+	pixel_clock.pixel_clock.clk = *clk;
 
+	dc_dmub_srv_cmd_queue(dmcub, &pixel_clock.header);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+}
 
 static enum bp_result set_pixel_clock_v7(
 	struct bios_parser *bp,
@@ -331,6 +388,12 @@ static enum bp_result set_pixel_clock_v7(
 		if (bp_params->signal_type == SIGNAL_TYPE_DVI_DUAL_LINK)
 			clk.miscinfo |= PIXEL_CLOCK_V7_MISC_DVI_DUALLINK_EN;
 
+		if (bp->base.ctx->dc->ctx->dmub_srv &&
+		    bp->base.ctx->dc->debug.dmub_command_table) {
+			set_pixel_clock_dmcub(bp->base.ctx->dmub_srv, &clk);
+			return BP_RESULT_OK;
+		}
+
 		if (EXEC_BIOS_CMD_TABLE(setpixelclock, clk))
 			result = BP_RESULT_OK;
 	}
@@ -585,6 +648,21 @@ static void init_enable_disp_power_gating(
 	}
 }
 
+static void enable_disp_power_gating_dmcub(
+	struct dc_dmub_srv *dmcub,
+	struct enable_disp_power_gating_parameters_v2_1 *pwr)
+{
+	struct dmub_rb_cmd_enable_disp_power_gating power_gating;
+
+	power_gating.header.type = DMUB_CMD__VBIOS;
+	power_gating.header.sub_type = DMUB_CMD__VBIOS_ENABLE_DISP_POWER_GATING;
+	power_gating.power_gating.pwr = *pwr;
+
+	dc_dmub_srv_cmd_queue(dmcub, &power_gating.header);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+}
+
 static enum bp_result enable_disp_power_gating_v2_1(
 	struct bios_parser *bp,
 	enum controller_id crtc_id,
@@ -604,6 +682,13 @@ static enum bp_result enable_disp_power_gating_v2_1(
 	ps.param.enable =
 		bp->cmd_helper->disp_power_gating_action_to_atom(action);
 
+	if (bp->base.ctx->dc->ctx->dmub_srv &&
+	    bp->base.ctx->dc->debug.dmub_command_table) {
+		enable_disp_power_gating_dmcub(bp->base.ctx->dmub_srv,
+					       &ps.param);
+		return BP_RESULT_OK;
+	}
+
 	if (EXEC_BIOS_CMD_TABLE(enabledisppowergating, ps.param))
 		result = BP_RESULT_OK;
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
index db153ddf0fee..7388c987c595 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
@@ -55,23 +55,19 @@ bool dal_bios_parser_init_cmd_tbl_helper2(
 	case DCE_VERSION_11_22:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case DCN_VERSION_1_0:
 	case DCN_VERSION_1_01:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
 #endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case DCN_VERSION_2_0:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case DCN_VERSION_2_1:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
-#endif
 	case DCE_VERSION_12_0:
 	case DCE_VERSION_12_1:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 26c6d735cdc7..4674aca8f206 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -1,5 +1,6 @@
 #
 # Copyright 2017 Advanced Micro Devices, Inc.
+# Copyright 2019 Raptor Engineering, LLC
 #
 # Permission is hereby granted, free of charge, to any person obtaining a
 # copy of this software and associated documentation files (the "Software"),
@@ -24,7 +25,13 @@
 # It calculates Bandwidth and Watermarks values for HW programming
 #
 
+ifdef CONFIG_X86
 calcs_ccflags := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+calcs_ccflags := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -32,6 +39,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -40,6 +48,7 @@ calcs_ccflags += -mpreferred-stack-boundary=4
 else
 calcs_ccflags += -msse2
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_auto.o := $(calcs_ccflags)
@@ -47,7 +56,7 @@ CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_math.o := $(calcs_ccflags) -Wno-tautologi
 
 BW_CALCS = dce_calcs.o bw_fixed.o custom_float.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 BW_CALCS += dcn_calcs.o dcn_calc_math.o dcn_calc_auto.o
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
index a1d49256fab7..5d081c42e81b 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
@@ -154,14 +154,14 @@ static void calculate_bandwidth(
 
 
 
-	if (data->d0_underlay_mode == bw_def_none) { d0_underlay_enable = 0; }
-	else {
-		d0_underlay_enable = 1;
-	}
-	if (data->d1_underlay_mode == bw_def_none) { d1_underlay_enable = 0; }
-	else {
-		d1_underlay_enable = 1;
-	}
+	if (data->d0_underlay_mode == bw_def_none)
+		d0_underlay_enable = false;
+	else
+		d0_underlay_enable = true;
+	if (data->d1_underlay_mode == bw_def_none)
+		d1_underlay_enable = false;
+	else
+		d1_underlay_enable = true;
 	data->number_of_underlay_surfaces = d0_underlay_enable + d1_underlay_enable;
 	switch (data->underlay_surface_type) {
 	case bw_def_420:
@@ -286,8 +286,8 @@ static void calculate_bandwidth(
 	data->cursor_width_pixels[2] = bw_int_to_fixed(0);
 	data->cursor_width_pixels[3] = bw_int_to_fixed(0);
 	/* graphics surface parameters from spreadsheet*/
-	fbc_enabled = 0;
-	lpt_enabled = 0;
+	fbc_enabled = false;
+	lpt_enabled = false;
 	for (i = 4; i <= maximum_number_of_surfaces - 3; i++) {
 		if (i < data->number_of_displays + 4) {
 			if (i == 4 && data->d0_underlay_mode == bw_def_underlay_only) {
@@ -338,9 +338,9 @@ static void calculate_bandwidth(
 			data->access_one_channel_only[i] = 0;
 		}
 		if (data->fbc_en[i] == 1) {
-			fbc_enabled = 1;
+			fbc_enabled = true;
 			if (data->lpt_en[i] == 1) {
-				lpt_enabled = 1;
+				lpt_enabled = true;
 			}
 		}
 		data->cursor_width_pixels[i] = bw_int_to_fixed(vbios->cursor_width);
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 9b2cb57bf2ba..a27d84ca15a5 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -1,5 +1,6 @@
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
+ * Copyright 2019 Raptor Engineering, LLC
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -53,13 +54,9 @@
  * remain as-is as it provides us with a guarantee from HW that it is correct.
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 /* Defaults from spreadsheet rev#247.
  * RV2 delta: dram_clock_change_latency, max_num_dpp
  */
-#else
-/* Defaults from spreadsheet rev#247 */
-#endif
 const struct dcn_soc_bounding_box dcn10_soc_defaults = {
 		/* latencies */
 		.sr_exit_time = 17, /*us*/
@@ -626,7 +623,7 @@ static bool dcn_bw_apply_registry_override(struct dc *dc)
 {
 	bool updated = false;
 
-	kernel_fpu_begin();
+	DC_FP_START();
 	if ((int)(dc->dcn_soc->sr_exit_time * 1000) != dc->debug.sr_exit_time_ns
 			&& dc->debug.sr_exit_time_ns) {
 		updated = true;
@@ -662,7 +659,7 @@ static bool dcn_bw_apply_registry_override(struct dc *dc)
 		dc->dcn_soc->dram_clock_change_latency =
 				dc->debug.dram_clock_change_latency_ns / 1000.0;
 	}
-	kernel_fpu_end();
+	DC_FP_END();
 
 	return updated;
 }
@@ -708,8 +705,8 @@ static void hack_bounding_box(struct dcn_bw_internal_vars *v,
 
 unsigned int get_highest_allowed_voltage_level(uint32_t hw_internal_rev)
 {
-	/* for dali, the highest voltage level we want is 0 */
-	if (ASICREV_IS_DALI(hw_internal_rev))
+	/* for dali & pollock, the highest voltage level we want is 0 */
+	if (ASICREV_IS_POLLOCK(hw_internal_rev) || ASICREV_IS_DALI(hw_internal_rev))
 		return 0;
 
 	/* we are ok with all levels */
@@ -742,7 +739,7 @@ bool dcn_validate_bandwidth(
 		dcn_bw_sync_calcs_and_dml(dc);
 
 	memset(v, 0, sizeof(*v));
-	kernel_fpu_begin();
+	DC_FP_START();
 
 	v->sr_exit_time = dc->dcn_soc->sr_exit_time;
 	v->sr_enter_plus_exit_time = dc->dcn_soc->sr_enter_plus_exit_time;
@@ -1275,7 +1272,7 @@ bool dcn_validate_bandwidth(
 	bw_limit = dc->dcn_soc->percent_disp_bw_limit * v->fabric_and_dram_bandwidth_vmax0p9;
 	bw_limit_pass = (v->total_data_read_bandwidth / 1000.0) < bw_limit;
 
-	kernel_fpu_end();
+	DC_FP_END();
 
 	PERFORMANCE_TRACE_END();
 	BW_VAL_TRACE_FINISH();
@@ -1443,7 +1440,7 @@ void dcn_bw_update_from_pplib(struct dc *dc)
 	res = dm_pp_get_clock_levels_by_type_with_voltage(
 			ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks);
 
-	kernel_fpu_begin();
+	DC_FP_START();
 
 	if (res)
 		res = verify_clock_values(&fclks);
@@ -1463,12 +1460,12 @@ void dcn_bw_update_from_pplib(struct dc *dc)
 	} else
 		BREAK_TO_DEBUGGER();
 
-	kernel_fpu_end();
+	DC_FP_END();
 
 	res = dm_pp_get_clock_levels_by_type_with_voltage(
 			ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks);
 
-	kernel_fpu_begin();
+	DC_FP_START();
 
 	if (res)
 		res = verify_clock_values(&dcfclks);
@@ -1481,7 +1478,7 @@ void dcn_bw_update_from_pplib(struct dc *dc)
 	} else
 		BREAK_TO_DEBUGGER();
 
-	kernel_fpu_end();
+	DC_FP_END();
 }
 
 void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
@@ -1496,11 +1493,11 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 	if (!pp || !pp->set_wm_ranges)
 		return;
 
-	kernel_fpu_begin();
+	DC_FP_START();
 	min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32;
 	min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000;
 	socclk_khz = dc->dcn_soc->socclk * 1000;
-	kernel_fpu_end();
+	DC_FP_END();
 
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
 	 * depending on DPM state they are in. And update BW MGR GFX Engine and
@@ -1551,7 +1548,7 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 
 void dcn_bw_sync_calcs_and_dml(struct dc *dc)
 {
-	kernel_fpu_begin();
+	DC_FP_START();
 	DC_LOG_BANDWIDTH_CALCS("sr_exit_time: %f ns\n"
 			"sr_enter_plus_exit_time: %f ns\n"
 			"urgent_latency: %f ns\n"
@@ -1740,5 +1737,5 @@ void dcn_bw_sync_calcs_and_dml(struct dc *dc)
 	dc->dml.ip.bug_forcing_LC_req_same_size_fixed =
 		dc->dcn_ip->bug_forcing_luma_and_chroma_request_to_same_size_fixed == dcn_bw_yes;
 	dc->dml.ip.dcfclk_cstate_latency = dc->dcn_ip->dcfclk_cstate_latency;
-	kernel_fpu_end();
+	DC_FP_END();
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
index b864869cc7e3..3cd283195091 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
@@ -63,7 +63,7 @@ CLK_MGR_DCE120 = dce120_clk_mgr.o
 AMD_DAL_CLK_MGR_DCE120 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dce120/,$(CLK_MGR_DCE120))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCE120)
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 ###############################################################################
 # DCN10
 ###############################################################################
@@ -72,9 +72,7 @@ CLK_MGR_DCN10 = rv1_clk_mgr.o rv1_clk_mgr_vbios_smu.o rv2_clk_mgr.o
 AMD_DAL_CLK_MGR_DCN10 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn10/,$(CLK_MGR_DCN10))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN10)
-endif
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
 ###############################################################################
 # DCN20
 ###############################################################################
@@ -83,9 +81,7 @@ CLK_MGR_DCN20 = dcn20_clk_mgr.o
 AMD_DAL_CLK_MGR_DCN20 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn20/,$(CLK_MGR_DCN20))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN20)
-endif
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 ###############################################################################
 # DCN21
 ###############################################################################
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index 8828dd9c3783..a78e5c74c79c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -37,9 +37,7 @@
 #include "dcn10/rv1_clk_mgr.h"
 #include "dcn10/rv2_clk_mgr.h"
 #include "dcn20/dcn20_clk_mgr.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #include "dcn21/rn_clk_mgr.h"
-#endif
 
 
 int clk_mgr_helper_get_active_display_cnt(
@@ -134,14 +132,19 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			dce120_clk_mgr_construct(ctx, clk_mgr);
 		break;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case FAMILY_RV:
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
+		if (ASICREV_IS_DALI(asic_id.hw_internal_rev) ||
+				ASICREV_IS_POLLOCK(asic_id.hw_internal_rev)) {
+			/* TEMP: this check has to come before ASICREV_IS_RENOIR */
+			/* which also incorrectly returns true for Dali/Pollock*/
+			rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu);
+			break;
+		}
 		if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev)) {
 			rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 			break;
 		}
-#endif	/* DCN2_1 */
 		if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) {
 			rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu);
 			break;
@@ -152,13 +155,11 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			break;
 		}
 		break;
-#endif	/* Family RV */
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case FAMILY_NV:
 		dcn20_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 		break;
-#endif /* Family NV */
+#endif	/* Family RV and NV*/
 
 	default:
 		ASSERT(0); /* Unknown Asic */
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
index a6c46e903ff9..d031bd3d3072 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
@@ -72,8 +72,8 @@ int dce112_set_clock(struct clk_mgr *clk_mgr_base, int requested_clk_khz)
 	struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	struct bp_set_dce_clock_parameters dce_clk_params;
 	struct dc_bios *bp = clk_mgr_base->ctx->dc_bios;
-	struct dc *core_dc = clk_mgr_base->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc *dc = clk_mgr_base->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 	int actual_clock = requested_clk_khz;
 	/* Prepare to program display clock*/
 	memset(&dce_clk_params, 0, sizeof(dce_clk_params));
@@ -110,7 +110,7 @@ int dce112_set_clock(struct clk_mgr *clk_mgr_base, int requested_clk_khz)
 
 	bp->funcs->set_dce_clock(bp, &dce_clk_params);
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 			if (clk_mgr_dce->dfs_bypass_disp_clk != actual_clock)
 				dmcu->funcs->set_psr_wait_loop(dmcu,
@@ -126,8 +126,8 @@ int dce112_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_clk_khz)
 {
 	struct bp_set_dce_clock_parameters dce_clk_params;
 	struct dc_bios *bp = clk_mgr->base.ctx->dc_bios;
-	struct dc *core_dc = clk_mgr->base.ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc *dc = clk_mgr->base.ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 	int actual_clock = requested_clk_khz;
 	/* Prepare to program display clock*/
 	memset(&dce_clk_params, 0, sizeof(dce_clk_params));
@@ -152,7 +152,7 @@ int dce112_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_clk_khz)
 		clk_mgr->cur_min_clks_state = DM_PP_CLOCKS_STATE_NOMINAL;
 
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 			if (clk_mgr->dfs_bypass_disp_clk != actual_clock)
 				dmcu->funcs->set_psr_wait_loop(dmcu,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
index 1897e91c8ccb..97b7f32294fd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
@@ -88,8 +88,8 @@ int rv1_vbios_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, unsigned
 int rv1_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dispclk_khz)
 {
 	int actual_dispclk_set_mhz = -1;
-	struct dc *core_dc = clk_mgr->base.ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc *dc = clk_mgr->base.ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 
 	/*  Unit of SMU msg parameter is Mhz */
 	actual_dispclk_set_mhz = rv1_vbios_smu_send_msg_with_param(
@@ -100,7 +100,7 @@ int rv1_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_di
 	/* Actual dispclk set is returned in the parameter register */
 	actual_dispclk_set_mhz = REG_READ(MP1_SMN_C2PMSG_83) * 1000;
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 			if (clk_mgr->dfs_bypass_disp_clk != actual_dispclk_set_mhz)
 				dmcu->funcs->set_psr_wait_loop(dmcu,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index 25d7b7c6681c..495f01e9f2ca 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -27,6 +27,7 @@
 #include "clk_mgr_internal.h"
 
 #include "dce100/dce_clk_mgr.h"
+#include "dcn20_clk_mgr.h"
 #include "reg_helper.h"
 #include "core_types.h"
 #include "dm_helpers.h"
@@ -100,13 +101,13 @@ uint32_t dentist_get_did_from_divider(int divider)
 }
 
 void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr,
-		struct dc_state *context)
+		struct dc_state *context, bool safe_to_lower)
 {
 	int i;
 
 	clk_mgr->dccg->ref_dppclk = clk_mgr->base.clks.dppclk_khz;
 	for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) {
-		int dpp_inst, dppclk_khz;
+		int dpp_inst, dppclk_khz, prev_dppclk_khz;
 
 		/* Loop index will match dpp->inst if resource exists,
 		 * and we want to avoid dependency on dpp object
@@ -114,8 +115,12 @@ void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr,
 		dpp_inst = i;
 		dppclk_khz = context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz;
 
-		clk_mgr->dccg->funcs->update_dpp_dto(
-				clk_mgr->dccg, dpp_inst, dppclk_khz);
+		prev_dppclk_khz = clk_mgr->base.ctx->dc->current_state->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz;
+
+		if (safe_to_lower || prev_dppclk_khz < dppclk_khz) {
+			clk_mgr->dccg->funcs->update_dpp_dto(
+							clk_mgr->dccg, dpp_inst, dppclk_khz);
+		}
 	}
 }
 
@@ -161,6 +166,9 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 		dc->debug.force_clock_mode & 0x1) {
 		//this is from resume or boot up, if forced_clock cfg option used, we bypass program dispclk and DPPCLK, but need set them for S3.
 		force_reset = true;
+
+		dcn2_read_clocks_from_hw_dentist(clk_mgr_base);
+
 		//force_clock_mode 0x1:  force reset the clock even it is the same clock as long as it is in Passive level.
 	}
 	display_count = clk_mgr_helper_get_active_display_cnt(dc, context);
@@ -240,7 +248,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (dc->config.forced_clocks == false || (force_reset && safe_to_lower)) {
 		if (dpp_clock_lowered) {
 			// if clock is being lowered, increase DTO before lowering refclk
-			dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+			dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 			dcn20_update_clocks_update_dentist(clk_mgr);
 		} else {
 			// if clock is being raised, increase refclk before lowering DTO
@@ -248,7 +256,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 				dcn20_update_clocks_update_dentist(clk_mgr);
 			// always update dtos unless clock is lowered and not safe to lower
 			if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz)
-				dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+				dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 		}
 	}
 
@@ -339,6 +347,32 @@ void dcn2_enable_pme_wa(struct clk_mgr *clk_mgr_base)
 	}
 }
 
+
+void dcn2_read_clocks_from_hw_dentist(struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+	uint32_t dispclk_wdivider;
+	uint32_t dppclk_wdivider;
+	int disp_divider;
+	int dpp_divider;
+
+	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, &dispclk_wdivider);
+	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, &dppclk_wdivider);
+
+	disp_divider = dentist_get_divider_from_did(dispclk_wdivider);
+	dpp_divider = dentist_get_divider_from_did(dispclk_wdivider);
+
+	if (disp_divider && dpp_divider) {
+		/* Calculate the current DFS clock, in kHz.*/
+		clk_mgr_base->clks.dispclk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
+			* clk_mgr->base.dentist_vco_freq_khz) / disp_divider;
+
+		clk_mgr_base->clks.dppclk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
+				* clk_mgr->base.dentist_vco_freq_khz) / dpp_divider;
+	}
+
+}
+
 void dcn2_get_clock(struct clk_mgr *clk_mgr,
 		struct dc_state *context,
 			enum dc_clock_type clock_type,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
index c9fd824f3c23..0b9c045b0c8e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
@@ -34,7 +34,7 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr,
 			struct dc_state *context,
 			bool safe_to_lower);
 void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr,
-		struct dc_state *context);
+		struct dc_state *context, bool safe_to_lower);
 
 void dcn2_init_clocks(struct clk_mgr *clk_mgr);
 
@@ -51,4 +51,8 @@ void dcn2_get_clock(struct clk_mgr *clk_mgr,
 			struct dc_clock_config *clock_cfg);
 
 void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr);
+
+void dcn2_read_clocks_from_hw_dentist(struct clk_mgr *clk_mgr_base);
+
+
 #endif //__DCN20_CLK_MGR_H__
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 35c55e54eac0..7ae4c06232dd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -59,14 +59,16 @@ int rn_get_active_display_cnt_wa(
 		struct dc_state *context)
 {
 	int i, display_count;
-	bool hdmi_present = false;
+	bool tmds_present = false;
 
 	display_count = 0;
 	for (i = 0; i < context->stream_count; i++) {
 		const struct dc_stream_state *stream = context->streams[i];
 
-		if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
-			hdmi_present = true;
+		if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A ||
+				stream->signal == SIGNAL_TYPE_DVI_SINGLE_LINK ||
+				stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK)
+			tmds_present = true;
 	}
 
 	for (i = 0; i < dc->link_count; i++) {
@@ -85,7 +87,7 @@ int rn_get_active_display_cnt_wa(
 	}
 
 	/* WA for hang on HDMI after display off back back on*/
-	if (display_count == 0 && hdmi_present)
+	if (display_count == 0 && tmds_present)
 		display_count = 1;
 
 	return display_count;
@@ -164,16 +166,16 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (dpp_clock_lowered) {
-		// if clock is being lowered, increase DTO before lowering refclk
-		dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+		// increase per DPP DTO before lowering global dppclk
+		dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 		rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz);
 	} else {
-		// if clock is being raised, increase refclk before lowering DTO
+		// increase global DPPCLK before lowering per DPP DTO
 		if (update_dppclk || update_dispclk)
 			rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz);
 		// always update dtos unless clock is lowered and not safe to lower
 		if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz)
-			dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+			dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 	}
 
 	if (update_dispclk &&
@@ -409,7 +411,7 @@ void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_smu_wm_ra
 			continue;
 
 		ranges->reader_wm_sets[num_valid_sets].wm_inst = bw_params->wm_table.entries[i].wm_inst;
-		ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type;;
+		ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type;
 		/* We will not select WM based on dcfclk, so leave it as unconstrained */
 		ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
 		ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
@@ -578,33 +580,33 @@ struct wm_table lpddr4_wm_table = {
 		{
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 23.84,
-			.sr_exit_time_us = 12.5,
-			.sr_enter_plus_exit_time_us = 17.0,
+			.pstate_latency_us = 11.65333,
+			.sr_exit_time_us = 5.32,
+			.sr_enter_plus_exit_time_us = 6.38,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 23.84,
-			.sr_exit_time_us = 12.5,
-			.sr_enter_plus_exit_time_us = 17.0,
+			.pstate_latency_us = 11.65333,
+			.sr_exit_time_us = 9.82,
+			.sr_enter_plus_exit_time_us = 11.196,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 23.84,
-			.sr_exit_time_us = 12.5,
-			.sr_enter_plus_exit_time_us = 17.0,
+			.pstate_latency_us = 11.65333,
+			.sr_exit_time_us = 9.89,
+			.sr_enter_plus_exit_time_us = 11.24,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 23.84,
-			.sr_exit_time_us = 12.5,
-			.sr_enter_plus_exit_time_us = 17.0,
+			.pstate_latency_us = 11.65333,
+			.sr_exit_time_us = 9.748,
+			.sr_enter_plus_exit_time_us = 11.102,
 			.valid = true,
 		},
 	}
@@ -691,7 +693,6 @@ void rn_clk_mgr_construct(
 {
 	struct dc_debug_options *debug = &ctx->dc->debug;
 	struct dpm_clocks clock_table = { 0 };
-	struct clk_state_registers_and_bypass s = { 0 };
 
 	clk_mgr->base.ctx = ctx;
 	clk_mgr->base.funcs = &dcn21_funcs;
@@ -711,7 +712,6 @@ void rn_clk_mgr_construct(
 	if (IS_FPGA_MAXIMUS_DC(ctx->dce_environment)) {
 		dcn21_funcs.update_clocks = dcn2_update_clocks_fpga;
 		clk_mgr->base.dentist_vco_freq_khz = 3600000;
-		clk_mgr->base.dprefclk_khz = 600000;
 	} else {
 		struct clk_log_info log_info = {0};
 
@@ -722,24 +722,16 @@ void rn_clk_mgr_construct(
 		if (clk_mgr->base.dentist_vco_freq_khz == 0)
 			clk_mgr->base.dentist_vco_freq_khz = 3600000;
 
-		rn_dump_clk_registers(&s, &clk_mgr->base, &log_info);
-		/* Convert dprefclk units from MHz to KHz */
-		/* Value already divided by 10, some resolution lost */
-		clk_mgr->base.dprefclk_khz = s.dprefclk * 1000;
-
-		/* in case we don't get a value from the register, use default */
-		if (clk_mgr->base.dprefclk_khz == 0) {
-			ASSERT(clk_mgr->base.dprefclk_khz == 600000);
-			clk_mgr->base.dprefclk_khz = 600000;
-		}
-
 		if (ctx->dc_bios->integrated_info->memory_type == LpDdr4MemType) {
 			rn_bw_params.wm_table = lpddr4_wm_table;
 		} else {
 			rn_bw_params.wm_table = ddr4_wm_table;
 		}
+		/* Saved clocks configured at boot for debug purposes */
+		rn_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info);
 	}
 
+	clk_mgr->base.dprefclk_khz = 600000;
 	dce_clock_read_ss_info(clk_mgr);
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
index cb7c0e8b7e1b..6878aedf1d3e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
@@ -82,8 +82,8 @@ int rn_vbios_smu_get_smu_version(struct clk_mgr_internal *clk_mgr)
 int rn_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dispclk_khz)
 {
 	int actual_dispclk_set_mhz = -1;
-	struct dc *core_dc = clk_mgr->base.ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc *dc = clk_mgr->base.ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 
 	/*  Unit of SMU msg parameter is Mhz */
 	actual_dispclk_set_mhz = rn_vbios_smu_send_msg_with_param(
@@ -91,7 +91,7 @@ int rn_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dis
 			VBIOSSMC_MSG_SetDispclkFreq,
 			requested_dispclk_khz / 1000);
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 			if (clk_mgr->dfs_bypass_disp_clk != actual_dispclk_set_mhz)
 				dmcu->funcs->set_psr_wait_loop(dmcu,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 32f31bf91915..6c797fac189d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -58,21 +58,21 @@
 #include "hubp.h"
 
 #include "dc_link_dp.h"
+#include "dc_dmub_srv.h"
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dsc.h"
-#endif
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #include "vm_helper.h"
-#endif
 
 #include "dce/dce_i2c.h"
 
+#define CTX \
+	dc->ctx
+
 #define DC_LOGGER \
 	dc->ctx->logger
 
-const static char DC_BUILD_ID[] = "production-build";
+static const char DC_BUILD_ID[] = "production-build";
 
 /**
  * DOC: Overview
@@ -287,7 +287,6 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe->stream == stream && pipe->stream_res.tg) {
-			pipe->stream->adjust = *adjust;
 			dc->hwss.set_drr(&pipe,
 					1,
 					adjust->v_total_min,
@@ -511,10 +510,10 @@ bool dc_stream_program_csc_matrix(struct dc *dc, struct dc_stream_state *stream)
 	return ret;
 }
 
-void dc_stream_set_static_screen_events(struct dc *dc,
+void dc_stream_set_static_screen_params(struct dc *dc,
 		struct dc_stream_state **streams,
 		int num_streams,
-		const struct dc_static_screen_events *events)
+		const struct dc_static_screen_params *params)
 {
 	int i = 0;
 	int j = 0;
@@ -533,10 +532,10 @@ void dc_stream_set_static_screen_events(struct dc *dc,
 		}
 	}
 
-	dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, events);
+	dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, params);
 }
 
-static void destruct(struct dc *dc)
+static void dc_destruct(struct dc *dc)
 {
 	if (dc->current_state) {
 		dc_release_state(dc->current_state);
@@ -569,7 +568,7 @@ static void destruct(struct dc *dc)
 	kfree(dc->bw_dceip);
 	dc->bw_dceip = NULL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	kfree(dc->dcn_soc);
 	dc->dcn_soc = NULL;
 
@@ -577,28 +576,58 @@ static void destruct(struct dc *dc)
 	dc->dcn_ip = NULL;
 
 #endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	kfree(dc->vm_helper);
 	dc->vm_helper = NULL;
 
-#endif
 }
 
-static bool construct(struct dc *dc,
+static bool dc_construct_ctx(struct dc *dc,
+		const struct dc_init_data *init_params)
+{
+	struct dc_context *dc_ctx;
+	enum dce_version dc_version = DCE_VERSION_UNKNOWN;
+
+	dc_ctx = kzalloc(sizeof(*dc_ctx), GFP_KERNEL);
+	if (!dc_ctx)
+		return false;
+
+	dc_ctx->cgs_device = init_params->cgs_device;
+	dc_ctx->driver_context = init_params->driver;
+	dc_ctx->dc = dc;
+	dc_ctx->asic_id = init_params->asic_id;
+	dc_ctx->dc_sink_id_count = 0;
+	dc_ctx->dc_stream_id_count = 0;
+	dc_ctx->dce_environment = init_params->dce_environment;
+
+	/* Create logger */
+
+	dc_version = resource_parse_asic_id(init_params->asic_id);
+	dc_ctx->dce_version = dc_version;
+
+	dc_ctx->perf_trace = dc_perf_trace_create();
+	if (!dc_ctx->perf_trace) {
+		ASSERT_CRITICAL(false);
+		return false;
+	}
+
+	dc->ctx = dc_ctx;
+
+	return true;
+}
+
+static bool dc_construct(struct dc *dc,
 		const struct dc_init_data *init_params)
 {
 	struct dc_context *dc_ctx;
 	struct bw_calcs_dceip *dc_dceip;
 	struct bw_calcs_vbios *dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 #endif
 
-	enum dce_version dc_version = DCE_VERSION_UNKNOWN;
 	dc->config = init_params->flags;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	// Allocate memory for the vm_helper
 	dc->vm_helper = kzalloc(sizeof(struct vm_helper), GFP_KERNEL);
 	if (!dc->vm_helper) {
@@ -606,7 +635,6 @@ static bool construct(struct dc *dc,
 		goto fail;
 	}
 
-#endif
 	memcpy(&dc->bb_overrides, &init_params->bb_overrides, sizeof(dc->bb_overrides));
 
 	dc_dceip = kzalloc(sizeof(*dc_dceip), GFP_KERNEL);
@@ -624,7 +652,7 @@ static bool construct(struct dc *dc,
 	}
 
 	dc->bw_vbios = dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	dcn_soc = kzalloc(sizeof(*dcn_soc), GFP_KERNEL);
 	if (!dcn_soc) {
 		dm_error("%s: failed to create dcn_soc\n", __func__);
@@ -640,31 +668,15 @@ static bool construct(struct dc *dc,
 	}
 
 	dc->dcn_ip = dcn_ip;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	dc->soc_bounding_box = init_params->soc_bounding_box;
 #endif
-#endif
 
-	dc_ctx = kzalloc(sizeof(*dc_ctx), GFP_KERNEL);
-	if (!dc_ctx) {
+	if (!dc_construct_ctx(dc, init_params)) {
 		dm_error("%s: failed to create ctx\n", __func__);
 		goto fail;
 	}
 
-	dc_ctx->cgs_device = init_params->cgs_device;
-	dc_ctx->driver_context = init_params->driver;
-	dc_ctx->dc = dc;
-	dc_ctx->asic_id = init_params->asic_id;
-	dc_ctx->dc_sink_id_count = 0;
-	dc_ctx->dc_stream_id_count = 0;
-	dc->ctx = dc_ctx;
-
-	/* Create logger */
-
-	dc_ctx->dce_environment = init_params->dce_environment;
-
-	dc_version = resource_parse_asic_id(init_params->asic_id);
-	dc_ctx->dce_version = dc_version;
+        dc_ctx = dc->ctx;
 
 	/* Resource should construct all asic specific resources.
 	 * This should be the only place where we need to parse the asic id
@@ -679,7 +691,7 @@ static bool construct(struct dc *dc,
 		bp_init_data.bios = init_params->asic_id.atombios_base_address;
 
 		dc_ctx->dc_bios = dal_bios_parser_create(
-				&bp_init_data, dc_version);
+				&bp_init_data, dc_ctx->dce_version);
 
 		if (!dc_ctx->dc_bios) {
 			ASSERT_CRITICAL(false);
@@ -687,17 +699,13 @@ static bool construct(struct dc *dc,
 		}
 
 		dc_ctx->created_bios = true;
-		}
-
-	dc_ctx->perf_trace = dc_perf_trace_create();
-	if (!dc_ctx->perf_trace) {
-		ASSERT_CRITICAL(false);
-		goto fail;
 	}
 
+
+
 	/* Create GPIO service */
 	dc_ctx->gpio_service = dal_gpio_service_create(
-			dc_version,
+			dc_ctx->dce_version,
 			dc_ctx->dce_environment,
 			dc_ctx);
 
@@ -706,7 +714,7 @@ static bool construct(struct dc *dc,
 		goto fail;
 	}
 
-	dc->res_pool = dc_create_resource_pool(dc, init_params, dc_version);
+	dc->res_pool = dc_create_resource_pool(dc, init_params, dc_ctx->dce_version);
 	if (!dc->res_pool)
 		goto fail;
 
@@ -714,10 +722,8 @@ static bool construct(struct dc *dc,
 	if (!dc->clk_mgr)
 		goto fail;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	if (dc->res_pool->funcs->update_bw_bounding_box)
 		dc->res_pool->funcs->update_bw_bounding_box(dc, dc->clk_mgr->bw_params);
-#endif
 
 	/* Creation of current_state must occur after dc->dml
 	 * is initialized in dc_create_resource_pool because
@@ -739,12 +745,9 @@ static bool construct(struct dc *dc,
 	return true;
 
 fail:
-
-	destruct(dc);
 	return false;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 static bool disable_all_writeback_pipes_for_stream(
 		const struct dc *dc,
 		struct dc_stream_state *stream,
@@ -757,7 +760,6 @@ static bool disable_all_writeback_pipes_for_stream(
 
 	return true;
 }
-#endif
 
 static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 {
@@ -783,16 +785,12 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 		}
 		if (should_disable && old_stream) {
 			dc_rem_all_planes_for_stream(dc, old_stream, dangling_context);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 			disable_all_writeback_pipes_for_stream(dc, old_stream, dangling_context);
-#endif
 			if (dc->hwss.apply_ctx_for_surface)
 				dc->hwss.apply_ctx_for_surface(dc, old_stream, 0, dangling_context);
 		}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (dc->hwss.program_front_end_for_ctx)
 			dc->hwss.program_front_end_for_ctx(dc, dangling_context);
-#endif
 	}
 
 	current_ctx = dc->current_state;
@@ -800,6 +798,33 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 	dc_release_state(current_ctx);
 }
 
+static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context)
+{
+	int i;
+	int count = 0;
+	struct pipe_ctx *pipe;
+	PERF_TRACE();
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe->plane_state)
+			continue;
+
+		/* Timeout 100 ms */
+		while (count < 100000) {
+			/* Must set to false to start with, due to OR in update function */
+			pipe->plane_state->status.is_flip_pending = false;
+			dc->hwss.update_pending_status(pipe);
+			if (!pipe->plane_state->status.is_flip_pending)
+				break;
+			udelay(1);
+			count++;
+		}
+		ASSERT(!pipe->plane_state->status.is_flip_pending);
+	}
+	PERF_TRACE();
+}
+
 /*******************************************************************************
  * Public functions
  ******************************************************************************/
@@ -812,26 +837,38 @@ struct dc *dc_create(const struct dc_init_data *init_params)
 	if (NULL == dc)
 		goto alloc_fail;
 
-	if (false == construct(dc, init_params))
-		goto construct_fail;
+	if (init_params->dce_environment == DCE_ENV_VIRTUAL_HW) {
+		if (false == dc_construct_ctx(dc, init_params)) {
+			dc_destruct(dc);
+			goto construct_fail;
+		}
+	} else {
+		if (false == dc_construct(dc, init_params)) {
+			dc_destruct(dc);
+			goto construct_fail;
+		}
+
+		full_pipe_count = dc->res_pool->pipe_count;
+		if (dc->res_pool->underlay_pipe_index != NO_UNDERLAY_PIPE)
+			full_pipe_count--;
+		dc->caps.max_streams = min(
+				full_pipe_count,
+				dc->res_pool->stream_enc_count);
 
-	full_pipe_count = dc->res_pool->pipe_count;
-	if (dc->res_pool->underlay_pipe_index != NO_UNDERLAY_PIPE)
-		full_pipe_count--;
-	dc->caps.max_streams = min(
-			full_pipe_count,
-			dc->res_pool->stream_enc_count);
+		dc->optimize_seamless_boot_streams = 0;
+		dc->caps.max_links = dc->link_count;
+		dc->caps.max_audios = dc->res_pool->audio_count;
+		dc->caps.linear_pitch_alignment = 64;
 
-	dc->caps.max_links = dc->link_count;
-	dc->caps.max_audios = dc->res_pool->audio_count;
-	dc->caps.linear_pitch_alignment = 64;
+		dc->caps.max_dp_protocol_version = DP_VERSION_1_4;
+
+		if (dc->res_pool->dmcu != NULL)
+			dc->versions.dmcu_version = dc->res_pool->dmcu->dmcu_version;
+	}
 
 	/* Populate versioning information */
 	dc->versions.dc_ver = DC_VER;
 
-	if (dc->res_pool->dmcu != NULL)
-		dc->versions.dmcu_version = dc->res_pool->dmcu->dmcu_version;
-
 	dc->build_id = DC_BUILD_ID;
 
 	DC_LOG_DC("Display Core initialized\n");
@@ -849,7 +886,8 @@ alloc_fail:
 
 void dc_hardware_init(struct dc *dc)
 {
-	dc->hwss.init_hw(dc);
+	if (dc->ctx->dce_environment != DCE_ENV_VIRTUAL_HW)
+		dc->hwss.init_hw(dc);
 }
 
 void dc_init_callbacks(struct dc *dc,
@@ -869,7 +907,7 @@ void dc_deinit_callbacks(struct dc *dc)
 
 void dc_destroy(struct dc **dc)
 {
-	destruct(*dc);
+	dc_destruct(*dc);
 	kfree(*dc);
 	*dc = NULL;
 }
@@ -1163,10 +1201,10 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 
 	for (i = 0; i < context->stream_count; i++) {
 		if (context->streams[i]->apply_seamless_boot_optimization)
-			dc->optimize_seamless_boot = true;
+			dc->optimize_seamless_boot_streams++;
 	}
 
-	if (!dc->optimize_seamless_boot)
+	if (dc->optimize_seamless_boot_streams == 0)
 		dc->hwss.prepare_bandwidth(dc, context);
 
 	/* re-program planes for existing stream, in case we need to
@@ -1182,10 +1220,6 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 				context->stream_status[i].plane_count,
 				context); /* use new pipe config in new context */
 		}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	if (dc->hwss.program_front_end_for_ctx)
-		dc->hwss.program_front_end_for_ctx(dc, context);
-#endif
 
 	/* Program hardware */
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -1204,10 +1238,8 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	}
 
 	/* Program all planes within new context*/
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	if (dc->hwss.program_front_end_for_ctx)
 		dc->hwss.program_front_end_for_ctx(dc, context);
-#endif
 	for (i = 0; i < context->stream_count; i++) {
 		const struct dc_link *link = context->streams[i]->link;
 
@@ -1245,6 +1277,13 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 
 	dc_enable_stereo(dc, context, dc_streams, context->stream_count);
 
+	if (dc->optimize_seamless_boot_streams == 0) {
+		/* Must wait for no flips to be pending before doing optimize bw */
+		wait_for_no_pipes_pending(dc, context);
+		/* pplib is notified if disp_num changed */
+		dc->hwss.optimize_bandwidth(dc, context);
+	}
+
 	for (i = 0; i < context->stream_count; i++)
 		context->streams[i]->mode_changed = false;
 
@@ -1279,12 +1318,18 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context)
 	return (result == DC_OK);
 }
 
+bool dc_is_hw_initialized(struct dc *dc)
+{
+	struct dc_bios *dcb = dc->ctx->dc_bios;
+	return dcb->funcs->is_accelerated_mode(dcb);
+}
+
 bool dc_post_update_surfaces_to_stream(struct dc *dc)
 {
 	int i;
 	struct dc_state *context = dc->current_state;
 
-	if (!dc->optimized_required || dc->optimize_seamless_boot)
+	if (!dc->optimized_required || dc->optimize_seamless_boot_streams > 0)
 		return true;
 
 	post_surface_trace(dc);
@@ -1313,7 +1358,7 @@ struct dc_state *dc_create_state(struct dc *dc)
 	 * initialize and obtain IP and SOC the base DML instance from DC is
 	 * initially copied into every context
 	 */
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	memcpy(&context->bw_ctx.dml, &dc->dml, sizeof(struct display_mode_lib));
 #endif
 
@@ -1486,11 +1531,6 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa
 		elevate_update_type(&update_type, UPDATE_TYPE_MED);
 	}
 
-	if (u->plane_info->sdr_white_level != u->surface->sdr_white_level) {
-		update_flags->bits.sdr_white_level = 1;
-		elevate_update_type(&update_type, UPDATE_TYPE_MED);
-	}
-
 	if (u->plane_info->dcc.enable != u->surface->dcc.enable
 			|| u->plane_info->dcc.independent_64b_blks != u->surface->dcc.independent_64b_blks
 			|| u->plane_info->dcc.meta_pitch != u->surface->dcc.meta_pitch) {
@@ -1508,7 +1548,6 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa
 	}
 
 	if (u->plane_info->plane_size.surface_pitch != u->surface->plane_size.surface_pitch
-			|| u->plane_info->plane_size.surface_pitch != u->surface->plane_size.surface_pitch
 			|| u->plane_info->plane_size.chroma_pitch != u->surface->plane_size.chroma_pitch) {
 		update_flags->bits.plane_size_change = 1;
 		elevate_update_type(&update_type, UPDATE_TYPE_MED);
@@ -1547,7 +1586,10 @@ static enum surface_update_type get_scaling_info_update_type(
 	if (u->scaling_info->clip_rect.width != u->surface->clip_rect.width
 			|| u->scaling_info->clip_rect.height != u->surface->clip_rect.height
 			|| u->scaling_info->dst_rect.width != u->surface->dst_rect.width
-			|| u->scaling_info->dst_rect.height != u->surface->dst_rect.height) {
+			|| u->scaling_info->dst_rect.height != u->surface->dst_rect.height
+			|| u->scaling_info->scaling_quality.integer_scaling !=
+				u->surface->scaling_quality.integer_scaling
+			) {
 		update_flags->bits.scaling_change = 1;
 
 		if ((u->scaling_info->dst_rect.width < u->surface->dst_rect.width
@@ -1563,7 +1605,7 @@ static enum surface_update_type get_scaling_info_update_type(
 
 		update_flags->bits.scaling_change = 1;
 		if (u->scaling_info->src_rect.width > u->surface->src_rect.width
-				&& u->scaling_info->src_rect.height > u->surface->src_rect.height)
+				|| u->scaling_info->src_rect.height > u->surface->src_rect.height)
 			/* Making src rect bigger requires a bandwidth change */
 			update_flags->bits.clock_change = 1;
 	}
@@ -1577,11 +1619,11 @@ static enum surface_update_type get_scaling_info_update_type(
 		update_flags->bits.position_change = 1;
 
 	if (update_flags->bits.clock_change
-			|| update_flags->bits.bandwidth_change)
+			|| update_flags->bits.bandwidth_change
+			|| update_flags->bits.scaling_change)
 		return UPDATE_TYPE_FULL;
 
-	if (update_flags->bits.scaling_change
-			|| update_flags->bits.position_change)
+	if (update_flags->bits.position_change)
 		return UPDATE_TYPE_MED;
 
 	return UPDATE_TYPE_FAST;
@@ -1635,6 +1677,12 @@ static enum surface_update_type det_surface_update(const struct dc *dc,
 			update_flags->bits.gamma_change = 1;
 	}
 
+	if (u->hdr_mult.value)
+		if (u->hdr_mult.value != u->surface->hdr_mult.value) {
+			update_flags->bits.hdr_mult = 1;
+			elevate_update_type(&overall_type, UPDATE_TYPE_MED);
+		}
+
 	if (update_flags->bits.in_transfer_func_change) {
 		type = UPDATE_TYPE_MED;
 		elevate_update_type(&overall_type, type);
@@ -1668,7 +1716,8 @@ static enum surface_update_type check_update_surfaces_for_stream(
 		union stream_update_flags *su_flags = &stream_update->stream->update_flags;
 
 		if ((stream_update->src.height != 0 && stream_update->src.width != 0) ||
-				(stream_update->dst.height != 0 && stream_update->dst.width != 0))
+			(stream_update->dst.height != 0 && stream_update->dst.width != 0) ||
+			stream_update->integer_scaling_update)
 			su_flags->bits.scaling = 1;
 
 		if (stream_update->out_transfer_func)
@@ -1683,15 +1732,16 @@ static enum surface_update_type check_update_surfaces_for_stream(
 		if (stream_update->gamut_remap)
 			su_flags->bits.gamut_remap = 1;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (stream_update->wb_update)
 			su_flags->bits.wb_update = 1;
-#endif
 		if (su_flags->raw != 0)
 			overall_type = UPDATE_TYPE_FULL;
 
 		if (stream_update->output_csc_transform || stream_update->output_color_space)
 			su_flags->bits.out_csc = 1;
+
+		if (stream_update->dsc_config)
+			overall_type = UPDATE_TYPE_FULL;
 	}
 
 	for (i = 0 ; i < surface_count; i++) {
@@ -1817,8 +1867,6 @@ static void copy_surface_update_to_plane(
 				srf_update->plane_info->global_alpha_value;
 		surface->dcc =
 				srf_update->plane_info->dcc;
-		surface->sdr_white_level =
-				srf_update->plane_info->sdr_white_level;
 		surface->layer_index =
 				srf_update->plane_info->layer_index;
 	}
@@ -1851,7 +1899,6 @@ static void copy_surface_update_to_plane(
 			sizeof(struct dc_transfer_func_distributed_points));
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	if (srf_update->func_shaper &&
 			(surface->in_shaper_func !=
 			srf_update->func_shaper))
@@ -1864,13 +1911,16 @@ static void copy_surface_update_to_plane(
 		memcpy(surface->lut3d_func, srf_update->lut3d_func,
 		sizeof(*surface->lut3d_func));
 
+	if (srf_update->hdr_mult.value)
+		surface->hdr_mult =
+				srf_update->hdr_mult;
+
 	if (srf_update->blend_tf &&
 			(surface->blend_tf !=
 			srf_update->blend_tf))
 		memcpy(surface->blend_tf, srf_update->blend_tf,
 		sizeof(*surface->blend_tf));
 
-#endif
 	if (srf_update->input_csc_color_matrix)
 		surface->input_csc_color_matrix =
 			*srf_update->input_csc_color_matrix;
@@ -1883,8 +1933,10 @@ static void copy_surface_update_to_plane(
 static void copy_stream_update_to_stream(struct dc *dc,
 					 struct dc_state *context,
 					 struct dc_stream_state *stream,
-					 const struct dc_stream_update *update)
+					 struct dc_stream_update *update)
 {
+	struct dc_context *dc_ctx = dc->ctx;
+
 	if (update == NULL || stream == NULL)
 		return;
 
@@ -1945,7 +1997,6 @@ static void copy_stream_update_to_stream(struct dc *dc,
 
 	if (update->dither_option)
 		stream->dither_option = *update->dither_option;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* update current stream with writeback info */
 	if (update->wb_update) {
 		int i;
@@ -1956,23 +2007,32 @@ static void copy_stream_update_to_stream(struct dc *dc,
 			stream->writeback_info[i] =
 				update->wb_update->writeback_info[i];
 	}
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 	if (update->dsc_config) {
 		struct dc_dsc_config old_dsc_cfg = stream->timing.dsc_cfg;
 		uint32_t old_dsc_enabled = stream->timing.flags.DSC;
 		uint32_t enable_dsc = (update->dsc_config->num_slices_h != 0 &&
 				       update->dsc_config->num_slices_v != 0);
 
-		stream->timing.dsc_cfg = *update->dsc_config;
-		stream->timing.flags.DSC = enable_dsc;
-		if (!dc->res_pool->funcs->validate_bandwidth(dc, context,
-							     true)) {
-			stream->timing.dsc_cfg = old_dsc_cfg;
-			stream->timing.flags.DSC = old_dsc_enabled;
+		/* Use temporarry context for validating new DSC config */
+		struct dc_state *dsc_validate_context = dc_create_state(dc);
+
+		if (dsc_validate_context) {
+			dc_resource_state_copy_construct(dc->current_state, dsc_validate_context);
+
+			stream->timing.dsc_cfg = *update->dsc_config;
+			stream->timing.flags.DSC = enable_dsc;
+			if (!dc->res_pool->funcs->validate_bandwidth(dc, dsc_validate_context, true)) {
+				stream->timing.dsc_cfg = old_dsc_cfg;
+				stream->timing.flags.DSC = old_dsc_enabled;
+				update->dsc_config = NULL;
+			}
+
+			dc_release_state(dsc_validate_context);
+		} else {
+			DC_ERROR("Failed to allocate new validate context for DSC change\n");
+			update->dsc_config = NULL;
 		}
 	}
-#endif
 }
 
 static void commit_planes_do_stream_update(struct dc *dc,
@@ -1992,11 +2052,11 @@ static void commit_planes_do_stream_update(struct dc *dc,
 
 			if (stream_update->periodic_interrupt0 &&
 					dc->hwss.setup_periodic_interrupt)
-				dc->hwss.setup_periodic_interrupt(pipe_ctx, VLINE0);
+				dc->hwss.setup_periodic_interrupt(dc, pipe_ctx, VLINE0);
 
 			if (stream_update->periodic_interrupt1 &&
 					dc->hwss.setup_periodic_interrupt)
-				dc->hwss.setup_periodic_interrupt(pipe_ctx, VLINE1);
+				dc->hwss.setup_periodic_interrupt(dc, pipe_ctx, VLINE1);
 
 			if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) ||
 					stream_update->vrr_infopacket ||
@@ -2006,6 +2066,12 @@ static void commit_planes_do_stream_update(struct dc *dc,
 				dc->hwss.update_info_frame(pipe_ctx);
 			}
 
+			if (stream_update->hdr_static_metadata &&
+					stream->use_dynamic_meta &&
+					dc->hwss.set_dmdata_attributes &&
+					pipe_ctx->stream->dmdata_address.quad_part != 0)
+				dc->hwss.set_dmdata_attributes(pipe_ctx);
+
 			if (stream_update->gamut_remap)
 				dc_stream_set_gamut_remap(dc, stream);
 
@@ -2013,31 +2079,25 @@ static void commit_planes_do_stream_update(struct dc *dc,
 				dc_stream_program_csc_matrix(dc, stream);
 
 			if (stream_update->dither_option) {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 				struct pipe_ctx *odm_pipe = pipe_ctx->next_odm_pipe;
-#endif
 				resource_build_bit_depth_reduction_params(pipe_ctx->stream,
 									&pipe_ctx->stream->bit_depth_params);
 				pipe_ctx->stream_res.opp->funcs->opp_program_fmt(pipe_ctx->stream_res.opp,
 						&stream->bit_depth_params,
 						&stream->clamping);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 				while (odm_pipe) {
 					odm_pipe->stream_res.opp->funcs->opp_program_fmt(odm_pipe->stream_res.opp,
 							&stream->bit_depth_params,
 							&stream->clamping);
 					odm_pipe = odm_pipe->next_odm_pipe;
 				}
-#endif
 			}
 
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 			if (stream_update->dsc_config && dc->hwss.pipe_control_lock_global) {
 				dc->hwss.pipe_control_lock_global(dc, pipe_ctx, true);
 				dp_update_dsc_config(pipe_ctx);
 				dc->hwss.pipe_control_lock_global(dc, pipe_ctx, false);
 			}
-#endif
 			/* Full fe update*/
 			if (update_type == UPDATE_TYPE_FAST)
 				continue;
@@ -2053,7 +2113,7 @@ static void commit_planes_do_stream_update(struct dc *dc,
 
 					dc->hwss.optimize_bandwidth(dc, dc->current_state);
 				} else {
-					if (!dc->optimize_seamless_boot)
+					if (dc->optimize_seamless_boot_streams == 0)
 						dc->hwss.prepare_bandwidth(dc, dc->current_state);
 
 					core_link_enable_stream(dc->current_state, pipe_ctx);
@@ -2094,7 +2154,7 @@ static void commit_planes_for_stream(struct dc *dc,
 	int i, j;
 	struct pipe_ctx *top_pipe_to_program = NULL;
 
-	if (dc->optimize_seamless_boot && surface_count > 0) {
+	if (dc->optimize_seamless_boot_streams > 0 && surface_count > 0) {
 		/* Optimize seamless boot flag keeps clocks and watermarks high until
 		 * first flip. After first flip, optimization is required to lower
 		 * bandwidth. Important to note that it is expected UEFI will
@@ -2103,12 +2163,14 @@ static void commit_planes_for_stream(struct dc *dc,
 		 */
 		if (stream->apply_seamless_boot_optimization) {
 			stream->apply_seamless_boot_optimization = false;
-			dc->optimize_seamless_boot = false;
-			dc->optimized_required = true;
+			dc->optimize_seamless_boot_streams--;
+
+			if (dc->optimize_seamless_boot_streams == 0)
+				dc->optimized_required = true;
 		}
 	}
 
-	if (update_type == UPDATE_TYPE_FULL && !dc->optimize_seamless_boot) {
+	if (update_type == UPDATE_TYPE_FULL && dc->optimize_seamless_boot_streams == 0) {
 		dc->hwss.prepare_bandwidth(dc, context);
 		context_clock_trace(dc, context);
 	}
@@ -2124,15 +2186,12 @@ static void commit_planes_for_stream(struct dc *dc,
 		 */
 		if (dc->hwss.apply_ctx_for_surface)
 			dc->hwss.apply_ctx_for_surface(dc, stream, 0, context);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (dc->hwss.program_front_end_for_ctx)
 			dc->hwss.program_front_end_for_ctx(dc, context);
-#endif
 
 		return;
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
 		for (i = 0; i < surface_count; i++) {
 			struct dc_plane_state *plane_state = srf_updates[i].surface;
@@ -2154,7 +2213,6 @@ static void commit_planes_for_stream(struct dc *dc,
 			}
 		}
 	}
-#endif
 
 	// Update Type FULL, Surface updates
 	for (j = 0; j < dc->res_pool->pipe_count; j++) {
@@ -2175,7 +2233,6 @@ static void commit_planes_for_stream(struct dc *dc,
 			if (update_type == UPDATE_TYPE_FAST)
 				continue;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 			ASSERT(!pipe_ctx->plane_state->triplebuffer_flips);
 
 			if (dc->hwss.program_triplebuffer != NULL &&
@@ -2184,7 +2241,6 @@ static void commit_planes_for_stream(struct dc *dc,
 				dc->hwss.program_triplebuffer(
 					dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips);
 			}
-#endif
 			stream_status =
 				stream_get_status(context, pipe_ctx->stream);
 
@@ -2193,10 +2249,24 @@ static void commit_planes_for_stream(struct dc *dc,
 					dc, pipe_ctx->stream, stream_status->plane_count, context);
 		}
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	if (dc->hwss.program_front_end_for_ctx && update_type != UPDATE_TYPE_FAST)
+	if (dc->hwss.program_front_end_for_ctx && update_type != UPDATE_TYPE_FAST) {
 		dc->hwss.program_front_end_for_ctx(dc, context);
+#ifdef CONFIG_DRM_AMD_DC_DCN
+		if (dc->debug.validate_dml_output) {
+			for (i = 0; i < dc->res_pool->pipe_count; i++) {
+				struct pipe_ctx cur_pipe = context->res_ctx.pipe_ctx[i];
+				if (cur_pipe.stream == NULL)
+					continue;
+
+				cur_pipe.plane_res.hubp->funcs->validate_dml_output(
+						cur_pipe.plane_res.hubp, dc->ctx,
+						&context->res_ctx.pipe_ctx[i].rq_regs,
+						&context->res_ctx.pipe_ctx[i].dlg_regs,
+						&context->res_ctx.pipe_ctx[i].ttu_regs);
+			}
+		}
 #endif
+	}
 
 	// Update Type FAST, Surface updates
 	if (update_type == UPDATE_TYPE_FAST) {
@@ -2206,7 +2276,6 @@ static void commit_planes_for_stream(struct dc *dc,
 		 */
 		dc->hwss.pipe_control_lock(dc, top_pipe_to_program, true);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (dc->hwss.set_flip_control_gsl)
 			for (i = 0; i < surface_count; i++) {
 				struct dc_plane_state *plane_state = srf_updates[i].surface;
@@ -2225,7 +2294,6 @@ static void commit_planes_for_stream(struct dc *dc,
 							plane_state->flip_immediate);
 				}
 			}
-#endif
 		/* Perform requested Updates */
 		for (i = 0; i < surface_count; i++) {
 			struct dc_plane_state *plane_state = srf_updates[i].surface;
@@ -2238,7 +2306,6 @@ static void commit_planes_for_stream(struct dc *dc,
 
 				if (pipe_ctx->plane_state != plane_state)
 					continue;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 				/*program triple buffer after lock based on flip type*/
 				if (dc->hwss.program_triplebuffer != NULL &&
 					!dc->debug.disable_tri_buf) {
@@ -2246,7 +2313,6 @@ static void commit_planes_for_stream(struct dc *dc,
 					dc->hwss.program_triplebuffer(
 						dc, pipe_ctx, plane_state->triplebuffer_flips);
 				}
-#endif
 				if (srf_updates[i].flip_addr)
 					dc->hwss.update_plane_addr(dc, pipe_ctx);
 			}
@@ -2407,14 +2473,15 @@ void dc_set_power_state(
 	case DC_ACPI_CM_POWER_STATE_D0:
 		dc_resource_state_construct(dc, dc->current_state);
 
+		if (dc->ctx->dmub_srv)
+			dc_dmub_srv_wait_phy_init(dc->ctx->dmub_srv);
+
 		dc->hwss.init_hw(dc);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		if (dc->hwss.init_sys_ctx != NULL &&
 			dc->vm_pa_config.valid) {
 			dc->hwss.init_sys_ctx(dc->hwseq, dc, &dc->vm_pa_config);
 		}
-#endif
 
 		break;
 	default:
@@ -2494,6 +2561,17 @@ bool dc_submit_i2c(
 		cmd);
 }
 
+bool dc_submit_i2c_oem(
+		struct dc *dc,
+		struct i2c_command *cmd)
+{
+	struct ddc_service *ddc = dc->res_pool->oem_device;
+	return dce_i2c_submit_command(
+		dc->res_pool,
+		ddc->ddc_pin,
+		cmd);
+}
+
 static bool link_add_remote_sink_helper(struct dc_link *dc_link, struct dc_sink *sink)
 {
 	if (dc_link->sink_count >= MAX_SINKS_PER_LINK) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
index b9227d5de3a3..502ed3c7959d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
@@ -33,7 +33,6 @@
 
 #include "core_status.h"
 #include "core_types.h"
-#include "hw_sequencer.h"
 
 #include "resource.h"
 
@@ -310,14 +309,13 @@ void context_timing_trace(
 		struct resource_context *res_ctx)
 {
 	int i;
-	struct dc  *core_dc = dc;
 	int h_pos[MAX_PIPES] = {0}, v_pos[MAX_PIPES] = {0};
 	struct crtc_position position;
-	unsigned int underlay_idx = core_dc->res_pool->underlay_pipe_index;
+	unsigned int underlay_idx = dc->res_pool->underlay_pipe_index;
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 
-	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
 		/* get_position() returns CRTC vertical/horizontal counter
 		 * hence not applicable for underlay pipe
@@ -329,7 +327,7 @@ void context_timing_trace(
 		h_pos[i] = position.horizontal_count;
 		v_pos[i] = position.vertical_count;
 	}
-	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
 
 		if (pipe_ctx->stream == NULL || pipe_ctx->pipe_idx == underlay_idx)
@@ -347,7 +345,7 @@ void context_clock_trace(
 		struct dc *dc,
 		struct dc_state *context)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	DC_LOGGER_INIT(dc->ctx->logger);
 	CLOCK_TRACE("Current: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 4619f94f0ac7..260c0b62d37d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -45,6 +45,7 @@
 #include "dpcd_defs.h"
 #include "dmcu.h"
 #include "hw/clk_mgr.h"
+#include "../dce/dmub_psr.h"
 
 #define DC_LOGGER_INIT(logger)
 
@@ -74,7 +75,7 @@ enum {
 /*******************************************************************************
  * Private functions
  ******************************************************************************/
-static void destruct(struct dc_link *link)
+static void dc_link_destruct(struct dc_link *link)
 {
 	int i;
 
@@ -1244,7 +1245,7 @@ static enum transmitter translate_encoder_to_transmitter(
 	}
 }
 
-static bool construct(
+static bool dc_link_construct(
 	struct dc_link *link,
 	const struct link_init_data *init_params)
 {
@@ -1446,7 +1447,7 @@ struct dc_link *link_create(const struct link_init_data *init_params)
 	if (NULL == link)
 		goto alloc_fail;
 
-	if (false == construct(link, init_params))
+	if (false == dc_link_construct(link, init_params))
 		goto construct_fail;
 
 	return link;
@@ -1460,7 +1461,7 @@ alloc_fail:
 
 void link_destroy(struct dc_link **link)
 {
-	destruct(*link);
+	dc_link_destruct(*link);
 	kfree(*link);
 	*link = NULL;
 }
@@ -1495,10 +1496,7 @@ static enum dc_status enable_link_dp(
 	bool skip_video_pattern;
 	struct dc_link *link = stream->link;
 	struct dc_link_settings link_settings = {0};
-	enum dp_panel_mode panel_mode;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool fec_enable;
-#endif
 	int i;
 	bool apply_seamless_boot_optimization = false;
 
@@ -1514,15 +1512,6 @@ static enum dc_status enable_link_dp(
 	decide_link_settings(stream, &link_settings);
 
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_EDP) {
-		/* If link settings are different than current and link already enabled
-		 * then need to disable before programming to new rate.
-		 */
-		if (link->link_status.link_active &&
-			(link->cur_link_settings.lane_count != link_settings.lane_count ||
-			 link->cur_link_settings.link_rate != link_settings.link_rate)) {
-			dp_disable_link_phy(link, pipe_ctx->stream->signal);
-		}
-
 		/*in case it is not on*/
 		link->dc->hwss.edp_power_control(link, true);
 		link->dc->hwss.edp_wait_for_hpd_ready(link, true);
@@ -1533,50 +1522,29 @@ static enum dc_status enable_link_dp(
 	if (state->clk_mgr && !apply_seamless_boot_optimization)
 		state->clk_mgr->funcs->update_clocks(state->clk_mgr, state, false);
 
-	dp_enable_link_phy(
-		link,
-		pipe_ctx->stream->signal,
-		pipe_ctx->clock_source->id,
-		&link_settings);
-
-	if (stream->sink_patches.dppowerup_delay > 0) {
-		int delay_dp_power_up_in_ms = stream->sink_patches.dppowerup_delay;
-
-		msleep(delay_dp_power_up_in_ms);
-	}
-
-	panel_mode = dp_get_panel_mode(link);
-	dp_set_panel_mode(link, panel_mode);
-
 	skip_video_pattern = true;
 
 	if (link_settings.link_rate == LINK_RATE_LOW)
 			skip_video_pattern = false;
 
-	if (link->aux_access_disabled) {
-		dc_link_dp_perform_link_training_skip_aux(link, &link_settings);
-
-		link->cur_link_settings = link_settings;
-		status = DC_OK;
-	} else if (perform_link_training_with_retries(
-			link,
+	if (perform_link_training_with_retries(
 			&link_settings,
 			skip_video_pattern,
-			LINK_TRAINING_ATTEMPTS)) {
+			LINK_TRAINING_ATTEMPTS,
+			pipe_ctx,
+			pipe_ctx->stream->signal)) {
 		link->cur_link_settings = link_settings;
 		status = DC_OK;
 	}
 	else
 		status = DC_FAIL_DP_LINK_TRAINING;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (link->preferred_training_settings.fec_enable != NULL)
 		fec_enable = *link->preferred_training_settings.fec_enable;
 	else
 		fec_enable = true;
 
 	dp_set_fec_enable(link, fec_enable);
-#endif
 	return status;
 }
 
@@ -2063,6 +2031,45 @@ static void write_i2c_redriver_setting(
 		ASSERT(i2c_success);
 }
 
+static void disable_link(struct dc_link *link, enum signal_type signal)
+{
+	/*
+	 * TODO: implement call for dp_set_hw_test_pattern
+	 * it is needed for compliance testing
+	 */
+
+	/* Here we need to specify that encoder output settings
+	 * need to be calculated as for the set mode,
+	 * it will lead to querying dynamic link capabilities
+	 * which should be done before enable output
+	 */
+
+	if (dc_is_dp_signal(signal)) {
+		/* SST DP, eDP */
+		if (dc_is_dp_sst_signal(signal))
+			dp_disable_link_phy(link, signal);
+		else
+			dp_disable_link_phy_mst(link, signal);
+
+		if (dc_is_dp_sst_signal(signal) ||
+				link->mst_stream_alloc_table.stream_count == 0) {
+			dp_set_fec_enable(link, false);
+			dp_set_fec_ready(link, false);
+		}
+	} else {
+		if (signal != SIGNAL_TYPE_VIRTUAL)
+			link->link_enc->funcs->disable_output(link->link_enc, signal);
+	}
+
+	if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+		/* MST disable link only when no stream use the link */
+		if (link->mst_stream_alloc_table.stream_count <= 0)
+			link->link_status.link_active = false;
+	} else {
+		link->link_status.link_active = false;
+	}
+}
+
 static void enable_link_hdmi(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
@@ -2147,6 +2154,19 @@ static enum dc_status enable_link(
 		struct pipe_ctx *pipe_ctx)
 {
 	enum dc_status status = DC_ERROR_UNEXPECTED;
+	struct dc_stream_state *stream = pipe_ctx->stream;
+	struct dc_link *link = stream->link;
+
+	/* There's some scenarios where driver is unloaded with display
+	 * still enabled. When driver is reloaded, it may cause a display
+	 * to not light up if there is a mismatch between old and new
+	 * link settings. Need to call disable first before enabling at
+	 * new link settings.
+	 */
+	if (link->link_status.link_active) {
+		disable_link(link, pipe_ctx->stream->signal);
+	}
+
 	switch (pipe_ctx->stream->signal) {
 	case SIGNAL_TYPE_DISPLAY_PORT:
 		status = enable_link_dp(state, pipe_ctx);
@@ -2181,46 +2201,6 @@ static enum dc_status enable_link(
 	return status;
 }
 
-static void disable_link(struct dc_link *link, enum signal_type signal)
-{
-	/*
-	 * TODO: implement call for dp_set_hw_test_pattern
-	 * it is needed for compliance testing
-	 */
-
-	/* here we need to specify that encoder output settings
-	 * need to be calculated as for the set mode,
-	 * it will lead to querying dynamic link capabilities
-	 * which should be done before enable output */
-
-	if (dc_is_dp_signal(signal)) {
-		/* SST DP, eDP */
-		if (dc_is_dp_sst_signal(signal))
-			dp_disable_link_phy(link, signal);
-		else
-			dp_disable_link_phy_mst(link, signal);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-
-		if (dc_is_dp_sst_signal(signal) ||
-				link->mst_stream_alloc_table.stream_count == 0) {
-			dp_set_fec_enable(link, false);
-			dp_set_fec_ready(link, false);
-		}
-#endif
-	} else {
-		if (signal != SIGNAL_TYPE_VIRTUAL)
-			link->link_enc->funcs->disable_output(link->link_enc, signal);
-	}
-
-	if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
-		/* MST disable link only when no stream use the link */
-		if (link->mst_stream_alloc_table.stream_count <= 0)
-			link->link_status.link_active = false;
-	} else {
-		link->link_status.link_active = false;
-	}
-}
-
 static uint32_t get_timing_pixel_clock_100hz(const struct dc_crtc_timing *timing)
 {
 
@@ -2357,9 +2337,9 @@ bool dc_link_set_backlight_level(const struct dc_link *link,
 		uint32_t backlight_pwm_u16_16,
 		uint32_t frame_ramp)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct abm *abm = core_dc->res_pool->abm;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct abm *abm = dc->res_pool->abm;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 	unsigned int controller_id = 0;
 	bool use_smooth_brightness = true;
 	int i;
@@ -2377,22 +2357,22 @@ bool dc_link_set_backlight_level(const struct dc_link *link,
 
 	if (dc_is_embedded_signal(link->connector_signal)) {
 		for (i = 0; i < MAX_PIPES; i++) {
-			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream) {
-				if (core_dc->current_state->res_ctx.
+			if (dc->current_state->res_ctx.pipe_ctx[i].stream) {
+				if (dc->current_state->res_ctx.
 						pipe_ctx[i].stream->link
 						== link) {
 					/* DMCU -1 for all controller id values,
 					 * therefore +1 here
 					 */
 					controller_id =
-						core_dc->current_state->
+						dc->current_state->
 						res_ctx.pipe_ctx[i].stream_res.tg->inst +
 						1;
 
 					/* Disable brightness ramping when the display is blanked
 					 * as it can hang the DMCU
 					 */
-					if (core_dc->current_state->res_ctx.pipe_ctx[i].plane_state == NULL)
+					if (dc->current_state->res_ctx.pipe_ctx[i].plane_state == NULL)
 						frame_ramp = 0;
 				}
 			}
@@ -2410,8 +2390,8 @@ bool dc_link_set_backlight_level(const struct dc_link *link,
 
 bool dc_link_set_abm_disable(const struct dc_link *link)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct abm *abm = core_dc->res_pool->abm;
+	struct dc  *dc = link->ctx->dc;
+	struct abm *abm = dc->res_pool->abm;
 
 	if ((abm == NULL) || (abm->funcs->set_backlight_level_pwm == NULL))
 		return false;
@@ -2423,12 +2403,13 @@ bool dc_link_set_abm_disable(const struct dc_link *link)
 
 bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, bool wait)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
+	struct dmub_psr *psr = dc->res_pool->psr;
 
-
-
-	if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_feature_enabled)
+	if ((psr != NULL) && link->psr_feature_enabled)
+		psr->funcs->set_psr_enable(psr, allow_active);
+	else if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_feature_enabled)
 		dmcu->funcs->set_psr_enable(dmcu, allow_active, wait);
 
 	link->psr_allow_active = allow_active;
@@ -2438,10 +2419,13 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, bool
 
 bool dc_link_get_psr_state(const struct dc_link *link, uint32_t *psr_state)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
+	struct dmub_psr *psr = dc->res_pool->psr;
 
-	if (dmcu != NULL && link->psr_feature_enabled)
+	if (psr != NULL && link->psr_feature_enabled)
+		psr->funcs->get_psr_state(psr_state);
+	else if (dmcu != NULL && link->psr_feature_enabled)
 		dmcu->funcs->get_psr_state(dmcu, psr_state);
 
 	return true;
@@ -2486,8 +2470,9 @@ bool dc_link_setup_psr(struct dc_link *link,
 		const struct dc_stream_state *stream, struct psr_config *psr_config,
 		struct psr_context *psr_context)
 {
-	struct dc *core_dc;
+	struct dc *dc;
 	struct dmcu *dmcu;
+	struct dmub_psr *psr;
 	int i;
 	/* updateSinkPsrDpcdConfig*/
 	union dpcd_psr_configuration psr_configuration;
@@ -2497,10 +2482,11 @@ bool dc_link_setup_psr(struct dc_link *link,
 	if (!link)
 		return false;
 
-	core_dc = link->ctx->dc;
-	dmcu = core_dc->res_pool->dmcu;
+	dc = link->ctx->dc;
+	dmcu = dc->res_pool->dmcu;
+	psr = dc->res_pool->psr;
 
-	if (!dmcu)
+	if (!dmcu && !psr)
 		return false;
 
 
@@ -2537,13 +2523,13 @@ bool dc_link_setup_psr(struct dc_link *link,
 	psr_context->engineId = link->link_enc->preferred_engine;
 
 	for (i = 0; i < MAX_PIPES; i++) {
-		if (core_dc->current_state->res_ctx.pipe_ctx[i].stream
+		if (dc->current_state->res_ctx.pipe_ctx[i].stream
 				== stream) {
 			/* dmcu -1 for all controller id values,
 			 * therefore +1 here
 			 */
 			psr_context->controllerId =
-				core_dc->current_state->res_ctx.
+				dc->current_state->res_ctx.
 				pipe_ctx[i].stream_res.tg->inst + 1;
 			break;
 		}
@@ -2556,7 +2542,7 @@ bool dc_link_setup_psr(struct dc_link *link,
 		transmitter_to_phy_id(link->link_enc->transmitter);
 
 	psr_context->crtcTimingVerticalTotal = stream->timing.v_total;
-	psr_context->vsyncRateHz = div64_u64(div64_u64((stream->
+	psr_context->vsync_rate_hz = div64_u64(div64_u64((stream->
 					timing.pix_clk_100hz * 100),
 					stream->timing.v_total),
 					stream->timing.h_total);
@@ -2586,7 +2572,7 @@ bool dc_link_setup_psr(struct dc_link *link,
 
 	psr_context->psr_level.u32all = 0;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	/*skip power down the single pipe since it blocks the cstate*/
 	if (ASICREV_IS_RAVEN(link->ctx->asic_id.hw_internal_rev))
 		psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true;
@@ -2609,7 +2595,10 @@ bool dc_link_setup_psr(struct dc_link *link,
 	 */
 	psr_context->frame_delay = 0;
 
-	link->psr_feature_enabled = dmcu->funcs->setup_psr(dmcu, link, psr_context);
+	if (psr)
+		link->psr_feature_enabled = psr->funcs->setup_psr(psr, link, psr_context);
+	else
+		link->psr_feature_enabled = dmcu->funcs->setup_psr(dmcu, link, psr_context);
 
 	/* psr_enabled == 0 indicates setup_psr did not succeed, but this
 	 * should not happen since firmware should be running at this point
@@ -2644,28 +2633,13 @@ static struct fixed31_32 get_pbn_per_slot(struct dc_stream_state *stream)
 	return dc_fixpt_div_int(mbytes_per_sec, 54);
 }
 
-static int get_color_depth(enum dc_color_depth color_depth)
-{
-	switch (color_depth) {
-	case COLOR_DEPTH_666: return 6;
-	case COLOR_DEPTH_888: return 8;
-	case COLOR_DEPTH_101010: return 10;
-	case COLOR_DEPTH_121212: return 12;
-	case COLOR_DEPTH_141414: return 14;
-	case COLOR_DEPTH_161616: return 16;
-	default: return 0;
-	}
-}
-
 static struct fixed31_32 get_pbn_from_timing(struct pipe_ctx *pipe_ctx)
 {
-	uint32_t bpc;
 	uint64_t kbps;
 	struct fixed31_32 peak_kbps;
 	uint32_t numerator;
 	uint32_t denominator;
 
-	bpc = get_color_depth(pipe_ctx->stream_res.pix_clk_params.color_depth);
 	kbps = dc_bandwidth_in_kbps_from_timing(&pipe_ctx->stream->timing);
 
 	/*
@@ -2899,6 +2873,39 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
 
 	return DC_OK;
 }
+
+enum dc_status dc_link_reallocate_mst_payload(struct dc_link *link)
+{
+	int i;
+	struct pipe_ctx *pipe_ctx;
+
+	// Clear all of MST payload then reallocate
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link &&
+				pipe_ctx->stream->dpms_off == false &&
+				pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+			deallocate_mst_payload(pipe_ctx);
+		}
+	}
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link &&
+				pipe_ctx->stream->dpms_off == false &&
+				pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+			/* enable/disable PHY will clear connection between BE and FE
+			 * need to restore it.
+			 */
+			link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc,
+									pipe_ctx->stream_res.stream_enc->id, true);
+			dc_link_allocate_mst_payload(pipe_ctx);
+		}
+	}
+
+	return DC_OK;
+}
+
 #if defined(CONFIG_DRM_AMD_DC_HDCP)
 static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off)
 {
@@ -2922,12 +2929,12 @@ void core_link_enable_stream(
 		struct dc_state *state,
 		struct pipe_ctx *pipe_ctx)
 {
-	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	enum dc_status status;
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment) &&
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) &&
 			dc_is_virtual_signal(pipe_ctx->stream->signal))
 		return;
 
@@ -2946,6 +2953,7 @@ void core_link_enable_stream(
 			pipe_ctx->stream_res.stream_enc,
 			&stream->timing,
 			stream->output_color_space,
+			stream->use_vsc_sdp_for_colorimetry,
 			stream->link->dpcd_caps.dprx_feature.bits.SST_SPLIT_SDP_CAP);
 
 	if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal))
@@ -2969,14 +2977,14 @@ void core_link_enable_stream(
 			pipe_ctx->stream_res.stream_enc,
 			&stream->timing);
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		bool apply_edp_fast_boot_optimization =
 			pipe_ctx->stream->apply_edp_fast_boot_optimization;
 
 		pipe_ctx->stream->apply_edp_fast_boot_optimization = false;
 
 		resource_build_info_frame(pipe_ctx);
-		core_dc->hwss.update_info_frame(pipe_ctx);
+		dc->hwss.update_info_frame(pipe_ctx);
 
 		/* Do not touch link on seamless boot optimization. */
 		if (pipe_ctx->stream->apply_seamless_boot_optimization) {
@@ -3019,7 +3027,7 @@ void core_link_enable_stream(
 			}
 		}
 
-		core_dc->hwss.enable_audio_stream(pipe_ctx);
+		dc->hwss.enable_audio_stream(pipe_ctx);
 
 		/* turn off otg test pattern if enable */
 		if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
@@ -3027,28 +3035,24 @@ void core_link_enable_stream(
 					CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
 					COLOR_DEPTH_UNDEFINED);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		if (pipe_ctx->stream->timing.flags.DSC) {
 			if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
 					dc_is_virtual_signal(pipe_ctx->stream->signal))
 				dp_set_dsc_enable(pipe_ctx, true);
 		}
-#endif
-		core_dc->hwss.enable_stream(pipe_ctx);
+		dc->hwss.enable_stream(pipe_ctx);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		/* Set DPS PPS SDP (AKA "info frames") */
 		if (pipe_ctx->stream->timing.flags.DSC) {
 			if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
 					dc_is_virtual_signal(pipe_ctx->stream->signal))
 				dp_set_dsc_pps_sdp(pipe_ctx, true);
 		}
-#endif
 
 		if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 			dc_link_allocate_mst_payload(pipe_ctx);
 
-		core_dc->hwss.unblank_stream(pipe_ctx,
+		dc->hwss.unblank_stream(pipe_ctx,
 			&pipe_ctx->stream->link->cur_link_settings);
 
 		if (dc_is_dp_signal(pipe_ctx->stream->signal))
@@ -3056,24 +3060,21 @@ void core_link_enable_stream(
 #if defined(CONFIG_DRM_AMD_DC_HDCP)
 		update_psp_stream_config(pipe_ctx, false);
 #endif
-	}
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-	else { // if (IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment))
+	} else { // if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
 		if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
 				dc_is_virtual_signal(pipe_ctx->stream->signal))
 			dp_set_dsc_enable(pipe_ctx, true);
 
 	}
-#endif
 }
 
 void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 {
-	struct dc  *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc  *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->sink->link;
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment) &&
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) &&
 			dc_is_virtual_signal(pipe_ctx->stream->signal))
 		return;
 
@@ -3081,7 +3082,7 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 	update_psp_stream_config(pipe_ctx, true);
 #endif
 
-	core_dc->hwss.blank_stream(pipe_ctx);
+	dc->hwss.blank_stream(pipe_ctx);
 
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		deallocate_mst_payload(pipe_ctx);
@@ -3110,25 +3111,23 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 			write_i2c_redriver_setting(pipe_ctx, false);
 		}
 	}
-	core_dc->hwss.disable_stream(pipe_ctx);
+	dc->hwss.disable_stream(pipe_ctx);
 
 	disable_link(pipe_ctx->stream->link, pipe_ctx->stream->signal);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (pipe_ctx->stream->timing.flags.DSC) {
 		if (dc_is_dp_signal(pipe_ctx->stream->signal))
 			dp_set_dsc_enable(pipe_ctx, false);
 	}
-#endif
 }
 
 void core_link_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
 {
-	struct dc  *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc  *dc = pipe_ctx->stream->ctx->dc;
 
 	if (!dc_is_hdmi_signal(pipe_ctx->stream->signal))
 		return;
 
-	core_dc->hwss.set_avmute(pipe_ctx, enable);
+	dc->hwss.set_avmute(pipe_ctx, enable);
 }
 
 /**
@@ -3186,13 +3185,11 @@ uint32_t dc_bandwidth_in_kbps_from_timing(
 	uint32_t bits_per_channel = 0;
 	uint32_t kbps;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (timing->flags.DSC) {
 		kbps = (timing->pix_clk_100hz * timing->dsc_cfg.bits_per_pixel);
 		kbps = kbps / 160 + ((kbps % 160) ? 1 : 0);
 		return kbps;
 	}
-#endif
 
 	switch (timing->display_color_depth) {
 	case COLOR_DEPTH_666:
@@ -3345,6 +3342,7 @@ void dc_link_disable_hpd(const struct dc_link *link)
 
 void dc_link_set_test_pattern(struct dc_link *link,
 			      enum dp_test_pattern test_pattern,
+			      enum dp_test_pattern_color_space test_pattern_color_space,
 			      const struct link_training_settings *p_link_settings,
 			      const unsigned char *p_custom_pattern,
 			      unsigned int cust_pattern_size)
@@ -3353,6 +3351,7 @@ void dc_link_set_test_pattern(struct dc_link *link,
 		dc_link_dp_set_test_pattern(
 			link,
 			test_pattern,
+			test_pattern_color_space,
 			p_link_settings,
 			p_custom_pattern,
 			cust_pattern_size);
@@ -3368,7 +3367,6 @@ uint32_t dc_link_bandwidth_kbps(
 	link_bw_kbps *= 8;   /* 8 bits per byte*/
 	link_bw_kbps *= link_setting->lane_count;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) {
 		/* Account for FEC overhead.
 		 * We have to do it based on caps,
@@ -3393,7 +3391,6 @@ uint32_t dc_link_bandwidth_kbps(
 		link_bw_kbps = mul_u64_u32_shr(BIT_ULL(32) * 970LL / 1000,
 					       link_bw_kbps, 32);
 	}
-#endif
 
 	return link_bw_kbps;
 
@@ -3407,3 +3404,10 @@ const struct dc_link_settings *dc_link_get_link_cap(
 		return &link->preferred_link_setting;
 	return &link->verified_link_cap;
 }
+
+void dc_link_overwrite_extended_receiver_cap(
+		struct dc_link *link)
+{
+	dp_overwrite_extended_receiver_cap(link);
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 81789191d4ec..a49c10d5df26 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -187,7 +187,7 @@ void dal_ddc_i2c_payloads_add(
 
 }
 
-static void construct(
+static void ddc_service_construct(
 	struct ddc_service *ddc_service,
 	struct ddc_service_init_data *init_data)
 {
@@ -206,7 +206,10 @@ static void construct(
 		ddc_service->ddc_pin = NULL;
 	} else {
 		hw_info.ddc_channel = i2c_info.i2c_line;
-		hw_info.hw_supported = i2c_info.i2c_hw_assist;
+		if (ddc_service->link != NULL)
+			hw_info.hw_supported = i2c_info.i2c_hw_assist;
+		else
+			hw_info.hw_supported = false;
 
 		ddc_service->ddc_pin = dal_gpio_create_ddc(
 			gpio_service,
@@ -236,11 +239,11 @@ struct ddc_service *dal_ddc_service_create(
 	if (!ddc_service)
 		return NULL;
 
-	construct(ddc_service, init_data);
+	ddc_service_construct(ddc_service, init_data);
 	return ddc_service;
 }
 
-static void destruct(struct ddc_service *ddc)
+static void ddc_service_destruct(struct ddc_service *ddc)
 {
 	if (ddc->ddc_pin)
 		dal_gpio_destroy_ddc(&ddc->ddc_pin);
@@ -252,7 +255,7 @@ void dal_ddc_service_destroy(struct ddc_service **ddc)
 		BREAK_TO_DEBUGGER();
 		return;
 	}
-	destruct(*ddc);
+	ddc_service_destruct(*ddc);
 	kfree(*ddc);
 	*ddc = NULL;
 }
@@ -587,7 +590,7 @@ bool dal_ddc_submit_aux_command(struct ddc_service *ddc,
 		struct aux_payload *payload)
 {
 	uint32_t retrieved = 0;
-	bool ret = 0;
+	bool ret = false;
 
 	if (!ddc)
 		return false;
@@ -647,17 +650,16 @@ bool dc_link_aux_transfer_with_retries(struct ddc_service *ddc,
 }
 
 
-enum dc_status dc_link_aux_configure_timeout(struct ddc_service *ddc,
+uint32_t dc_link_aux_configure_timeout(struct ddc_service *ddc,
 		uint32_t timeout)
 {
-	enum dc_status status = DC_OK;
+	uint32_t prev_timeout = 0;
 	struct ddc *ddc_pin = ddc->ddc_pin;
 
-	if (ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout == NULL)
-		return DC_ERROR_UNEXPECTED;
-	if (!ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout(ddc, timeout))
-		status = DC_ERROR_UNEXPECTED;
-	return status;
+	if (ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout)
+		prev_timeout =
+				ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout(ddc, timeout);
+	return prev_timeout;
 }
 
 /*test only function*/
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 504055fc70e8..6ab298c65247 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -4,12 +4,8 @@
 #include "dc_link_dp.h"
 #include "dm_helpers.h"
 #include "opp.h"
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dsc.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "resource.h"
-#endif
 
 #include "inc/core_types.h"
 #include "link_hwss.h"
@@ -21,6 +17,9 @@
 #define DC_LOGGER \
 	link->ctx->logger
 
+
+#define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE   0x50
+
 /* maximum pre emphasis level allowed for each voltage swing level*/
 static const enum dc_pre_emphasis voltage_swing_to_pre_emphasis[] = {
 		PRE_EMPHASIS_LEVEL3,
@@ -221,19 +220,31 @@ static enum dpcd_training_patterns
 	return dpcd_tr_pattern;
 }
 
+static inline bool is_repeater(struct dc_link *link, uint32_t offset)
+{
+	return (!link->is_lttpr_mode_transparent && offset != 0);
+}
+
 static void dpcd_set_lt_pattern_and_lane_settings(
 	struct dc_link *link,
 	const struct link_training_settings *lt_settings,
-	enum dc_dp_training_pattern pattern)
+	enum dc_dp_training_pattern pattern,
+	uint32_t offset)
 {
 	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = { { {0} } };
-	const uint32_t dpcd_base_lt_offset =
-	DP_TRAINING_PATTERN_SET;
+
+	uint32_t dpcd_base_lt_offset;
+
 	uint8_t dpcd_lt_buffer[5] = {0};
 	union dpcd_training_pattern dpcd_pattern = { {0} };
 	uint32_t lane;
 	uint32_t size_in_bytes;
 	bool edp_workaround = false; /* TODO link_prop.INTERNAL */
+	dpcd_base_lt_offset = DP_TRAINING_PATTERN_SET;
+
+	if (is_repeater(link, offset))
+		dpcd_base_lt_offset = DP_TRAINING_PATTERN_SET_PHY_REPEATER1 +
+			((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
 
 	/*****************************************************************
 	* DpcdAddress_TrainingPatternSet
@@ -241,14 +252,21 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 	dpcd_pattern.v1_4.TRAINING_PATTERN_SET =
 		dc_dp_training_pattern_to_dpcd_training_pattern(link, pattern);
 
-	dpcd_lt_buffer[DP_TRAINING_PATTERN_SET - dpcd_base_lt_offset]
+	dpcd_lt_buffer[DP_TRAINING_PATTERN_SET - DP_TRAINING_PATTERN_SET]
 		= dpcd_pattern.raw;
 
-	DC_LOG_HW_LINK_TRAINING("%s\n %x pattern = %x\n",
-		__func__,
-		DP_TRAINING_PATTERN_SET,
-		dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
-
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n 0x%X pattern = %x\n",
+			__func__,
+			offset,
+			dpcd_base_lt_offset,
+			dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s\n 0x%X pattern = %x\n",
+			__func__,
+			dpcd_base_lt_offset,
+			dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
+	}
 	/*****************************************************************
 	* DpcdAddress_Lane0Set -> DpcdAddress_Lane3Set
 	*****************************************************************/
@@ -268,24 +286,35 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 		PRE_EMPHASIS_MAX_LEVEL ? 1 : 0);
 	}
 
-	/* concatinate everything into one buffer*/
+	/* concatenate everything into one buffer*/
 
 	size_in_bytes = lt_settings->link_settings.lane_count * sizeof(dpcd_lane[0]);
 
 	 // 0x00103 - 0x00102
 	memmove(
-		&dpcd_lt_buffer[DP_TRAINING_LANE0_SET - dpcd_base_lt_offset],
+		&dpcd_lt_buffer[DP_TRAINING_LANE0_SET - DP_TRAINING_PATTERN_SET],
 		dpcd_lane,
 		size_in_bytes);
 
-	DC_LOG_HW_LINK_TRAINING("%s:\n %x VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
-		__func__,
-		DP_TRAINING_LANE0_SET,
-		dpcd_lane[0].bits.VOLTAGE_SWING_SET,
-		dpcd_lane[0].bits.PRE_EMPHASIS_SET,
-		dpcd_lane[0].bits.MAX_SWING_REACHED,
-		dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
-
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n"
+				" 0x%X VS set = %x PE set = %x max VS Reached = %x  max PE Reached = %x\n",
+			__func__,
+			offset,
+			dpcd_base_lt_offset,
+			dpcd_lane[0].bits.VOLTAGE_SWING_SET,
+			dpcd_lane[0].bits.PRE_EMPHASIS_SET,
+			dpcd_lane[0].bits.MAX_SWING_REACHED,
+			dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
+			__func__,
+			dpcd_base_lt_offset,
+			dpcd_lane[0].bits.VOLTAGE_SWING_SET,
+			dpcd_lane[0].bits.PRE_EMPHASIS_SET,
+			dpcd_lane[0].bits.MAX_SWING_REACHED,
+			dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
+	}
 	if (edp_workaround) {
 		/* for eDP write in 2 parts because the 5-byte burst is
 		* causing issues on some eDP panels (EPR#366724)
@@ -495,8 +524,12 @@ static void get_lane_status_and_drive_settings(
 	const struct link_training_settings *link_training_setting,
 	union lane_status *ln_status,
 	union lane_align_status_updated *ln_status_updated,
-	struct link_training_settings *req_settings)
+	struct link_training_settings *req_settings,
+	uint32_t offset)
 {
+	unsigned int lane01_status_address = DP_LANE0_1_STATUS;
+	uint8_t lane_adjust_offset = 4;
+	unsigned int lane01_adjust_address;
 	uint8_t dpcd_buf[6] = {0};
 	union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } };
 	struct link_training_settings request_settings = { {0} };
@@ -504,9 +537,16 @@ static void get_lane_status_and_drive_settings(
 
 	memset(req_settings, '\0', sizeof(struct link_training_settings));
 
+	if (is_repeater(link, offset)) {
+		lane01_status_address =
+				DP_LANE0_1_STATUS_PHY_REPEATER1 +
+				((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
+		lane_adjust_offset = 3;
+	}
+
 	core_link_read_dpcd(
 		link,
-		DP_LANE0_1_STATUS,
+		lane01_status_address,
 		(uint8_t *)(dpcd_buf),
 		sizeof(dpcd_buf));
 
@@ -517,22 +557,47 @@ static void get_lane_status_and_drive_settings(
 		ln_status[lane].raw =
 			get_nibble_at_index(&dpcd_buf[0], lane);
 		dpcd_lane_adjust[lane].raw =
-			get_nibble_at_index(&dpcd_buf[4], lane);
+			get_nibble_at_index(&dpcd_buf[lane_adjust_offset], lane);
 	}
 
 	ln_status_updated->raw = dpcd_buf[2];
 
-	DC_LOG_HW_LINK_TRAINING("%s:\n%x Lane01Status = %x\n %x Lane23Status = %x\n ",
-		__func__,
-		DP_LANE0_1_STATUS, dpcd_buf[0],
-		DP_LANE2_3_STATUS, dpcd_buf[1]);
-
-	DC_LOG_HW_LINK_TRAINING("%s:\n %x Lane01AdjustRequest = %x\n %x Lane23AdjustRequest = %x\n",
-		__func__,
-		DP_ADJUST_REQUEST_LANE0_1,
-		dpcd_buf[4],
-		DP_ADJUST_REQUEST_LANE2_3,
-		dpcd_buf[5]);
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n"
+				" 0x%X Lane01Status = %x\n 0x%X Lane23Status = %x\n ",
+			__func__,
+			offset,
+			lane01_status_address, dpcd_buf[0],
+			lane01_status_address + 1, dpcd_buf[1]);
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X Lane01Status = %x\n 0x%X Lane23Status = %x\n ",
+			__func__,
+			lane01_status_address, dpcd_buf[0],
+			lane01_status_address + 1, dpcd_buf[1]);
+	}
+	lane01_adjust_address = DP_ADJUST_REQUEST_LANE0_1;
+
+	if (is_repeater(link, offset))
+		lane01_adjust_address = DP_ADJUST_REQUEST_LANE0_1_PHY_REPEATER1 +
+				((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
+
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n"
+				" 0x%X Lane01AdjustRequest = %x\n 0x%X Lane23AdjustRequest = %x\n",
+					__func__,
+					offset,
+					lane01_adjust_address,
+					dpcd_buf[lane_adjust_offset],
+					lane01_adjust_address + 1,
+					dpcd_buf[lane_adjust_offset + 1]);
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X Lane01AdjustRequest = %x\n 0x%X Lane23AdjustRequest = %x\n",
+			__func__,
+			lane01_adjust_address,
+			dpcd_buf[lane_adjust_offset],
+			lane01_adjust_address + 1,
+			dpcd_buf[lane_adjust_offset + 1]);
+	}
 
 	/*copy to req_settings*/
 	request_settings.link_settings.lane_count =
@@ -571,10 +636,18 @@ static void get_lane_status_and_drive_settings(
 
 static void dpcd_set_lane_settings(
 	struct dc_link *link,
-	const struct link_training_settings *link_training_setting)
+	const struct link_training_settings *link_training_setting,
+	uint32_t offset)
 {
 	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = {{{0}}};
 	uint32_t lane;
+	unsigned int lane0_set_address;
+
+	lane0_set_address = DP_TRAINING_LANE0_SET;
+
+	if (is_repeater(link, offset))
+		lane0_set_address = DP_TRAINING_LANE0_SET_PHY_REPEATER1 +
+		((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
 
 	for (lane = 0; lane <
 		(uint32_t)(link_training_setting->
@@ -597,7 +670,7 @@ static void dpcd_set_lane_settings(
 	}
 
 	core_link_write_dpcd(link,
-		DP_TRAINING_LANE0_SET,
+		lane0_set_address,
 		(uint8_t *)(dpcd_lane),
 		link_training_setting->link_settings.lane_count);
 
@@ -620,14 +693,26 @@ static void dpcd_set_lane_settings(
 	}
 	*/
 
-	DC_LOG_HW_LINK_TRAINING("%s\n %x VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
-		__func__,
-		DP_TRAINING_LANE0_SET,
-		dpcd_lane[0].bits.VOLTAGE_SWING_SET,
-		dpcd_lane[0].bits.PRE_EMPHASIS_SET,
-		dpcd_lane[0].bits.MAX_SWING_REACHED,
-		dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n"
+				" 0x%X VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
+			__func__,
+			offset,
+			lane0_set_address,
+			dpcd_lane[0].bits.VOLTAGE_SWING_SET,
+			dpcd_lane[0].bits.PRE_EMPHASIS_SET,
+			dpcd_lane[0].bits.MAX_SWING_REACHED,
+			dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
 
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s\n 0x%X VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
+			__func__,
+			lane0_set_address,
+			dpcd_lane[0].bits.VOLTAGE_SWING_SET,
+			dpcd_lane[0].bits.PRE_EMPHASIS_SET,
+			dpcd_lane[0].bits.MAX_SWING_REACHED,
+			dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
+	}
 	link->cur_lane_setting = link_training_setting->lane_settings[0];
 
 }
@@ -647,17 +732,6 @@ static bool is_max_vs_reached(
 
 }
 
-void dc_link_dp_set_drive_settings(
-	struct dc_link *link,
-	struct link_training_settings *lt_settings)
-{
-	/* program ASIC PHY settings*/
-	dp_set_hw_lane_settings(link, lt_settings);
-
-	/* Notify DP sink the PHY settings from source */
-	dpcd_set_lane_settings(link, lt_settings);
-}
-
 static bool perform_post_lt_adj_req_sequence(
 	struct dc_link *link,
 	struct link_training_settings *lt_settings)
@@ -690,7 +764,8 @@ static bool perform_post_lt_adj_req_sequence(
 			lt_settings,
 			dpcd_lane_status,
 			&dpcd_lane_status_updated,
-			&req_settings);
+			&req_settings,
+			DPRX);
 
 			if (dpcd_lane_status_updated.bits.
 					POST_LT_ADJ_REQ_IN_PROGRESS == 0)
@@ -747,6 +822,31 @@ static bool perform_post_lt_adj_req_sequence(
 
 }
 
+/* Only used for channel equalization */
+static uint32_t translate_training_aux_read_interval(uint32_t dpcd_aux_read_interval)
+{
+	unsigned int aux_rd_interval_us = 400;
+
+	switch (dpcd_aux_read_interval) {
+	case 0x01:
+		aux_rd_interval_us = 400;
+		break;
+	case 0x02:
+		aux_rd_interval_us = 4000;
+		break;
+	case 0x03:
+		aux_rd_interval_us = 8000;
+		break;
+	case 0x04:
+		aux_rd_interval_us = 16000;
+		break;
+	default:
+		break;
+	}
+
+	return aux_rd_interval_us;
+}
+
 static enum link_training_result get_cr_failure(enum dc_lane_count ln_count,
 					union lane_status *dpcd_lane_status)
 {
@@ -765,37 +865,55 @@ static enum link_training_result get_cr_failure(enum dc_lane_count ln_count,
 
 static enum link_training_result perform_channel_equalization_sequence(
 	struct dc_link *link,
-	struct link_training_settings *lt_settings)
+	struct link_training_settings *lt_settings,
+	uint32_t offset)
 {
 	struct link_training_settings req_settings;
 	enum dc_dp_training_pattern tr_pattern;
 	uint32_t retries_ch_eq;
+	uint32_t wait_time_microsec;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
 	union lane_align_status_updated dpcd_lane_status_updated = { {0} };
 	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } };
 
+	/* Note: also check that TPS4 is a supported feature*/
+
 	tr_pattern = lt_settings->pattern_for_eq;
 
-	dp_set_hw_training_pattern(link, tr_pattern);
+	if (is_repeater(link, offset))
+		tr_pattern = DP_TRAINING_PATTERN_SEQUENCE_4;
+
+	dp_set_hw_training_pattern(link, tr_pattern, offset);
 
 	for (retries_ch_eq = 0; retries_ch_eq <= LINK_TRAINING_MAX_RETRY_COUNT;
 		retries_ch_eq++) {
 
-		dp_set_hw_lane_settings(link, lt_settings);
+		dp_set_hw_lane_settings(link, lt_settings, offset);
 
 		/* 2. update DPCD*/
 		if (!retries_ch_eq)
 			/* EPR #361076 - write as a 5-byte burst,
-			 * but only for the 1-st iteration*/
+			 * but only for the 1-st iteration
+			 */
+
 			dpcd_set_lt_pattern_and_lane_settings(
 				link,
 				lt_settings,
-				tr_pattern);
+				tr_pattern, offset);
 		else
-			dpcd_set_lane_settings(link, lt_settings);
+			dpcd_set_lane_settings(link, lt_settings, offset);
 
 		/* 3. wait for receiver to lock-on*/
-		wait_for_training_aux_rd_interval(link, lt_settings->eq_pattern_time);
+		wait_time_microsec = lt_settings->eq_pattern_time;
+
+		if (is_repeater(link, offset))
+			wait_time_microsec =
+					translate_training_aux_read_interval(
+						link->dpcd_caps.lttpr_caps.aux_rd_interval[offset - 1]);
+
+		wait_for_training_aux_rd_interval(
+				link,
+				wait_time_microsec);
 
 		/* 4. Read lane status and requested
 		 * drive settings as set by the sink*/
@@ -805,7 +923,8 @@ static enum link_training_result perform_channel_equalization_sequence(
 			lt_settings,
 			dpcd_lane_status,
 			&dpcd_lane_status_updated,
-			&req_settings);
+			&req_settings,
+			offset);
 
 		/* 5. check CR done*/
 		if (!is_cr_done(lane_count, dpcd_lane_status))
@@ -824,13 +943,16 @@ static enum link_training_result perform_channel_equalization_sequence(
 	return LINK_TRAINING_EQ_FAIL_EQ;
 
 }
+#define TRAINING_AUX_RD_INTERVAL 100 //us
 
 static enum link_training_result perform_clock_recovery_sequence(
 	struct dc_link *link,
-	struct link_training_settings *lt_settings)
+	struct link_training_settings *lt_settings,
+	uint32_t offset)
 {
 	uint32_t retries_cr;
 	uint32_t retry_count;
+	uint32_t wait_time_microsec;
 	struct link_training_settings req_settings;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
 	enum dc_dp_training_pattern tr_pattern = DP_TRAINING_PATTERN_SEQUENCE_1;
@@ -840,7 +962,7 @@ static enum link_training_result perform_clock_recovery_sequence(
 	retries_cr = 0;
 	retry_count = 0;
 
-	dp_set_hw_training_pattern(link, tr_pattern);
+	dp_set_hw_training_pattern(link, tr_pattern, offset);
 
 	/* najeeb - The synaptics MST hub can put the LT in
 	* infinite loop by switching the VS
@@ -857,7 +979,8 @@ static enum link_training_result perform_clock_recovery_sequence(
 		/* 1. call HWSS to set lane settings*/
 		dp_set_hw_lane_settings(
 				link,
-				lt_settings);
+				lt_settings,
+				offset);
 
 		/* 2. update DPCD of the receiver*/
 		if (!retries_cr)
@@ -866,16 +989,23 @@ static enum link_training_result perform_clock_recovery_sequence(
 			dpcd_set_lt_pattern_and_lane_settings(
 					link,
 					lt_settings,
-					tr_pattern);
+					tr_pattern,
+					offset);
 		else
 			dpcd_set_lane_settings(
 					link,
-					lt_settings);
+					lt_settings,
+					offset);
 
 		/* 3. wait receiver to lock-on*/
+		wait_time_microsec = lt_settings->cr_pattern_time;
+
+		if (!link->is_lttpr_mode_transparent)
+			wait_time_microsec = TRAINING_AUX_RD_INTERVAL;
+
 		wait_for_training_aux_rd_interval(
 				link,
-				lt_settings->cr_pattern_time);
+				wait_time_microsec);
 
 		/* 4. Read lane status and requested drive
 		* settings as set by the sink
@@ -885,7 +1015,8 @@ static enum link_training_result perform_clock_recovery_sequence(
 				lt_settings,
 				dpcd_lane_status,
 				&dpcd_lane_status_updated,
-				&req_settings);
+				&req_settings,
+				offset);
 
 		/* 5. check CR done*/
 		if (is_cr_done(lane_count, dpcd_lane_status))
@@ -1054,6 +1185,102 @@ static void initialize_training_settings(
 		lt_settings->enhanced_framing = 1;
 }
 
+static uint8_t convert_to_count(uint8_t lttpr_repeater_count)
+{
+	switch (lttpr_repeater_count) {
+	case 0x80: // 1 lttpr repeater
+		return 1;
+	case 0x40: // 2 lttpr repeaters
+		return 2;
+	case 0x20: // 3 lttpr repeaters
+		return 3;
+	case 0x10: // 4 lttpr repeaters
+		return 4;
+	case 0x08: // 5 lttpr repeaters
+		return 5;
+	case 0x04: // 6 lttpr repeaters
+		return 6;
+	case 0x02: // 7 lttpr repeaters
+		return 7;
+	case 0x01: // 8 lttpr repeaters
+		return 8;
+	default:
+		break;
+	}
+	return 0; // invalid value
+}
+
+static void configure_lttpr_mode(struct dc_link *link)
+{
+	/* aux timeout is already set to extended */
+	/* RESET/SET lttpr mode to enable non transparent mode */
+	uint8_t repeater_cnt;
+	uint32_t aux_interval_address;
+	uint8_t repeater_id;
+	enum dc_status result = DC_ERROR_UNEXPECTED;
+	uint8_t repeater_mode = DP_PHY_REPEATER_MODE_TRANSPARENT;
+
+	DC_LOG_HW_LINK_TRAINING("%s\n Set LTTPR to Transparent Mode\n", __func__);
+	result = core_link_write_dpcd(link,
+			DP_PHY_REPEATER_MODE,
+			(uint8_t *)&repeater_mode,
+			sizeof(repeater_mode));
+
+	if (result == DC_OK) {
+		link->dpcd_caps.lttpr_caps.mode = repeater_mode;
+	}
+
+	if (!link->is_lttpr_mode_transparent) {
+
+		DC_LOG_HW_LINK_TRAINING("%s\n Set LTTPR to Non Transparent Mode\n", __func__);
+
+		repeater_mode = DP_PHY_REPEATER_MODE_NON_TRANSPARENT;
+		result = core_link_write_dpcd(link,
+				DP_PHY_REPEATER_MODE,
+				(uint8_t *)&repeater_mode,
+				sizeof(repeater_mode));
+
+		if (result == DC_OK) {
+			link->dpcd_caps.lttpr_caps.mode = repeater_mode;
+		}
+
+		repeater_cnt = convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+		for (repeater_id = repeater_cnt; repeater_id > 0; repeater_id--) {
+			aux_interval_address = DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 +
+						((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (repeater_id - 1));
+			core_link_read_dpcd(
+				link,
+				aux_interval_address,
+				(uint8_t *)&link->dpcd_caps.lttpr_caps.aux_rd_interval[repeater_id - 1],
+				sizeof(link->dpcd_caps.lttpr_caps.aux_rd_interval[repeater_id - 1]));
+			link->dpcd_caps.lttpr_caps.aux_rd_interval[repeater_id - 1] &= 0x7F;
+		}
+	}
+}
+
+static void repeater_training_done(struct dc_link *link, uint32_t offset)
+{
+	union dpcd_training_pattern dpcd_pattern = { {0} };
+
+	const uint32_t dpcd_base_lt_offset =
+			DP_TRAINING_PATTERN_SET_PHY_REPEATER1 +
+				((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
+	/* Set training not in progress*/
+	dpcd_pattern.v1_4.TRAINING_PATTERN_SET = DPCD_TRAINING_PATTERN_VIDEOIDLE;
+
+	core_link_write_dpcd(
+		link,
+		dpcd_base_lt_offset,
+		&dpcd_pattern.raw,
+		1);
+
+	DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Id: %d 0x%X pattern = %x\n",
+		__func__,
+		offset,
+		dpcd_base_lt_offset,
+		dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
+}
+
 static void print_status_message(
 	struct dc_link *link,
 	const struct link_training_settings *lt_settings,
@@ -1133,6 +1360,17 @@ static void print_status_message(
 				lt_spread);
 }
 
+void dc_link_dp_set_drive_settings(
+	struct dc_link *link,
+	struct link_training_settings *lt_settings)
+{
+	/* program ASIC PHY settings*/
+	dp_set_hw_lane_settings(link, lt_settings, DPRX);
+
+	/* Notify DP sink the PHY settings from source */
+	dpcd_set_lane_settings(link, lt_settings, DPRX);
+}
+
 bool dc_link_dp_perform_link_training_skip_aux(
 	struct dc_link *link,
 	const struct dc_link_settings *link_setting)
@@ -1149,10 +1387,10 @@ bool dc_link_dp_perform_link_training_skip_aux(
 	/* 1. Perform_clock_recovery_sequence. */
 
 	/* transmit training pattern for clock recovery */
-	dp_set_hw_training_pattern(link, pattern_for_cr);
+	dp_set_hw_training_pattern(link, pattern_for_cr, DPRX);
 
 	/* call HWSS to set lane settings*/
-	dp_set_hw_lane_settings(link, &lt_settings);
+	dp_set_hw_lane_settings(link, &lt_settings, DPRX);
 
 	/* wait receiver to lock-on*/
 	wait_for_training_aux_rd_interval(link, lt_settings.cr_pattern_time);
@@ -1160,10 +1398,10 @@ bool dc_link_dp_perform_link_training_skip_aux(
 	/* 2. Perform_channel_equalization_sequence. */
 
 	/* transmit training pattern for channel equalization. */
-	dp_set_hw_training_pattern(link, lt_settings.pattern_for_eq);
+	dp_set_hw_training_pattern(link, lt_settings.pattern_for_eq, DPRX);
 
 	/* call HWSS to set lane settings*/
-	dp_set_hw_lane_settings(link, &lt_settings);
+	dp_set_hw_lane_settings(link, &lt_settings, DPRX);
 
 	/* wait receiver to lock-on. */
 	wait_for_training_aux_rd_interval(link, lt_settings.eq_pattern_time);
@@ -1185,9 +1423,10 @@ enum link_training_result dc_link_dp_perform_link_training(
 {
 	enum link_training_result status = LINK_TRAINING_SUCCESS;
 	struct link_training_settings lt_settings;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+
 	bool fec_enable;
-#endif
+	uint8_t repeater_cnt;
+	uint8_t repeater_id;
 
 	initialize_training_settings(
 			link,
@@ -1198,23 +1437,47 @@ enum link_training_result dc_link_dp_perform_link_training(
 	/* 1. set link rate, lane count and spread. */
 	dpcd_set_link_settings(link, &lt_settings);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (link->preferred_training_settings.fec_enable != NULL)
 		fec_enable = *link->preferred_training_settings.fec_enable;
 	else
 		fec_enable = true;
 
 	dp_set_fec_ready(link, fec_enable);
-#endif
 
+	if (!link->is_lttpr_mode_transparent) {
+		/* Configure lttpr mode */
+		configure_lttpr_mode(link);
+
+		/* 2. perform link training (set link training done
+		 *  to false is done as well)
+		 */
+		repeater_cnt = convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+
+		for (repeater_id = repeater_cnt; (repeater_id > 0 && status == LINK_TRAINING_SUCCESS);
+				repeater_id--) {
+			status = perform_clock_recovery_sequence(link, &lt_settings, repeater_id);
+
+			if (status != LINK_TRAINING_SUCCESS)
+				break;
+
+			status = perform_channel_equalization_sequence(link,
+					&lt_settings,
+					repeater_id);
+
+			if (status != LINK_TRAINING_SUCCESS)
+				break;
+
+			repeater_training_done(link, repeater_id);
+		}
+	}
 
-	/* 2. perform link training (set link training done
-	 *  to false is done as well)
-	 */
-	status = perform_clock_recovery_sequence(link, &lt_settings);
+	if (status == LINK_TRAINING_SUCCESS) {
+		status = perform_clock_recovery_sequence(link, &lt_settings, DPRX);
 	if (status == LINK_TRAINING_SUCCESS) {
 		status = perform_channel_equalization_sequence(link,
-				&lt_settings);
+					&lt_settings,
+					DPRX);
+		}
 	}
 
 	if ((status == LINK_TRAINING_SUCCESS) || !skip_video_pattern) {
@@ -1233,23 +1496,58 @@ enum link_training_result dc_link_dp_perform_link_training(
 }
 
 bool perform_link_training_with_retries(
-	struct dc_link *link,
 	const struct dc_link_settings *link_setting,
 	bool skip_video_pattern,
-	int attempts)
+	int attempts,
+	struct pipe_ctx *pipe_ctx,
+	enum signal_type signal)
 {
 	uint8_t j;
 	uint8_t delay_between_attempts = LINK_TRAINING_RETRY_DELAY;
+	struct dc_stream_state *stream = pipe_ctx->stream;
+	struct dc_link *link = stream->link;
+	enum dp_panel_mode panel_mode = dp_get_panel_mode(link);
 
 	for (j = 0; j < attempts; ++j) {
 
-		if (dc_link_dp_perform_link_training(
+		dp_enable_link_phy(
+			link,
+			signal,
+			pipe_ctx->clock_source->id,
+			link_setting);
+
+		if (stream->sink_patches.dppowerup_delay > 0) {
+			int delay_dp_power_up_in_ms = stream->sink_patches.dppowerup_delay;
+
+			msleep(delay_dp_power_up_in_ms);
+		}
+
+		dp_set_panel_mode(link, panel_mode);
+
+		/* We need to do this before the link training to ensure the idle pattern in SST
+		 * mode will be sent right after the link training
+		 */
+		link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc,
+								pipe_ctx->stream_res.stream_enc->id, true);
+
+		if (link->aux_access_disabled) {
+			dc_link_dp_perform_link_training_skip_aux(link, link_setting);
+			return true;
+		} else if (dc_link_dp_perform_link_training(
 				link,
 				link_setting,
 				skip_video_pattern) == LINK_TRAINING_SUCCESS)
 			return true;
 
+		/* latest link training still fail, skip delay and keep PHY on
+		 */
+		if (j == (attempts - 1))
+			break;
+
+		dp_disable_link_phy(link, signal);
+
 		msleep(delay_between_attempts);
+
 		delay_between_attempts += LINK_TRAINING_RETRY_DELAY;
 	}
 
@@ -1321,9 +1619,7 @@ enum link_training_result dc_link_dp_sync_lt_attempt(
 	enum link_training_result lt_status = LINK_TRAINING_SUCCESS;
 	enum dp_panel_mode panel_mode = DP_PANEL_MODE_DEFAULT;
 	enum clock_source_id dp_cs_id = CLOCK_SOURCE_ID_EXTERNAL;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool fec_enable = false;
-#endif
 
 	initialize_training_settings(
 		link,
@@ -1343,11 +1639,9 @@ enum link_training_result dc_link_dp_sync_lt_attempt(
 	dp_enable_link_phy(link, link->connector_signal,
 		dp_cs_id, link_settings);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	/* Set FEC enable */
 	fec_enable = lt_overrides->fec_enable && *lt_overrides->fec_enable;
 	dp_set_fec_ready(link, fec_enable);
-#endif
 
 	if (lt_overrides->alternate_scrambler_reset) {
 		if (*lt_overrides->alternate_scrambler_reset)
@@ -1367,10 +1661,11 @@ enum link_training_result dc_link_dp_sync_lt_attempt(
 	/* 2. perform link training (set link training done
 	 *  to false is done as well)
 	 */
-	lt_status = perform_clock_recovery_sequence(link, &lt_settings);
+	lt_status = perform_clock_recovery_sequence(link, &lt_settings, DPRX);
 	if (lt_status == LINK_TRAINING_SUCCESS) {
 		lt_status = perform_channel_equalization_sequence(link,
-						&lt_settings);
+						&lt_settings,
+						DPRX);
 	}
 
 	/* 3. Sync LT must skip TRAINING_PATTERN_SET:0 (video pattern)*/
@@ -1387,9 +1682,7 @@ bool dc_link_dp_sync_lt_end(struct dc_link *link, bool link_down)
 	 */
 	if (link_down == true) {
 		dp_disable_link_phy(link, link->connector_signal);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		dp_set_fec_ready(link, false);
-#endif
 	}
 
 	link->sync_lt_in_progress = false;
@@ -1423,6 +1716,22 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 			max_link_cap.link_spread)
 		max_link_cap.link_spread =
 				link->reported_link_cap.link_spread;
+	/*
+	 * account for lttpr repeaters cap
+	 * notes: repeaters do not snoop in the DPRX Capabilities addresses (3.6.3).
+	 */
+	if (!link->is_lttpr_mode_transparent) {
+		if (link->dpcd_caps.lttpr_caps.max_lane_count < max_link_cap.lane_count)
+			max_link_cap.lane_count = link->dpcd_caps.lttpr_caps.max_lane_count;
+
+		if (link->dpcd_caps.lttpr_caps.max_link_rate < max_link_cap.link_rate)
+			max_link_cap.link_rate = link->dpcd_caps.lttpr_caps.max_link_rate;
+
+		DC_LOG_HW_LINK_TRAINING("%s\n Training with LTTPR,  max_lane count %d max_link rate %d \n",
+						__func__,
+						max_link_cap.lane_count,
+						max_link_cap.link_rate);
+	}
 	return max_link_cap;
 }
 
@@ -1568,6 +1877,13 @@ bool dp_verify_link_cap(
 
 	max_link_cap = get_max_link_cap(link);
 
+	/* Grant extended timeout request */
+	if (!link->is_lttpr_mode_transparent && link->dpcd_caps.lttpr_caps.max_ext_timeout > 0) {
+		uint8_t grant = link->dpcd_caps.lttpr_caps.max_ext_timeout & 0x80;
+
+		core_link_write_dpcd(link, DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT, &grant, sizeof(grant));
+	}
+
 	/* TODO implement override and monitor patch later */
 
 	/* try to train the link from high to low to
@@ -1576,6 +1892,16 @@ bool dp_verify_link_cap(
 	/* disable PHY done possible by BIOS, will be done by driver itself */
 	dp_disable_link_phy(link, link->connector_signal);
 
+	/* Temporary Renoir-specific workaround for SWDEV-215184;
+	 * PHY will sometimes be in bad state on hotplugging display from certain USB-C dongle,
+	 * so add extra cycle of enabling and disabling the PHY before first link training.
+	 */
+	if (link->link_enc->features.flags.bits.DP_IS_USB_C &&
+			link->dc->debug.usbc_combo_phy_reset_wa) {
+		dp_enable_link_phy(link, link->connector_signal, dp_cs_id, cur);
+		dp_disable_link_phy(link, link->connector_signal);
+	}
+
 	dp_cs_id = get_clock_source_id(link);
 
 	/* link training starts with the maximum common settings
@@ -2280,6 +2606,7 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link)
 	dc_link_dp_set_test_pattern(
 		link,
 		test_pattern,
+		DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED,
 		&link_training_settings,
 		test_80_bit_pattern,
 		(DP_TEST_80BIT_CUSTOM_PATTERN_79_72 -
@@ -2291,6 +2618,8 @@ static void dp_test_send_link_test_pattern(struct dc_link *link)
 	union link_test_pattern dpcd_test_pattern;
 	union test_misc dpcd_test_params;
 	enum dp_test_pattern test_pattern;
+	enum dp_test_pattern_color_space test_pattern_color_space =
+			DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED;
 
 	memset(&dpcd_test_pattern, 0, sizeof(dpcd_test_pattern));
 	memset(&dpcd_test_params, 0, sizeof(dpcd_test_params));
@@ -2325,14 +2654,105 @@ static void dp_test_send_link_test_pattern(struct dc_link *link)
 	break;
 	}
 
+	test_pattern_color_space = dpcd_test_params.bits.YCBCR_COEFS ?
+			DP_TEST_PATTERN_COLOR_SPACE_YCBCR709 :
+			DP_TEST_PATTERN_COLOR_SPACE_YCBCR601;
+
 	dc_link_dp_set_test_pattern(
 			link,
 			test_pattern,
+			test_pattern_color_space,
 			NULL,
 			NULL,
 			0);
 }
 
+static void dp_test_get_audio_test_data(struct dc_link *link, bool disable_video)
+{
+	union audio_test_mode            dpcd_test_mode = {0};
+	struct audio_test_pattern_type   dpcd_pattern_type = {0};
+	union audio_test_pattern_period  dpcd_pattern_period[AUDIO_CHANNELS_COUNT] = {0};
+	enum dp_test_pattern test_pattern = DP_TEST_PATTERN_AUDIO_OPERATOR_DEFINED;
+
+	struct pipe_ctx *pipes = link->dc->current_state->res_ctx.pipe_ctx;
+	struct pipe_ctx *pipe_ctx = &pipes[0];
+	unsigned int channel_count;
+	unsigned int channel = 0;
+	unsigned int modes = 0;
+	unsigned int sampling_rate_in_hz = 0;
+
+	// get audio test mode and test pattern parameters
+	core_link_read_dpcd(
+		link,
+		DP_TEST_AUDIO_MODE,
+		&dpcd_test_mode.raw,
+		sizeof(dpcd_test_mode));
+
+	core_link_read_dpcd(
+		link,
+		DP_TEST_AUDIO_PATTERN_TYPE,
+		&dpcd_pattern_type.value,
+		sizeof(dpcd_pattern_type));
+
+	channel_count = dpcd_test_mode.bits.channel_count + 1;
+
+	// read pattern periods for requested channels when sawTooth pattern is requested
+	if (dpcd_pattern_type.value == AUDIO_TEST_PATTERN_SAWTOOTH ||
+			dpcd_pattern_type.value == AUDIO_TEST_PATTERN_OPERATOR_DEFINED) {
+
+		test_pattern = (dpcd_pattern_type.value == AUDIO_TEST_PATTERN_SAWTOOTH) ?
+				DP_TEST_PATTERN_AUDIO_SAWTOOTH : DP_TEST_PATTERN_AUDIO_OPERATOR_DEFINED;
+		// read period for each channel
+		for (channel = 0; channel < channel_count; channel++) {
+			core_link_read_dpcd(
+							link,
+							DP_TEST_AUDIO_PERIOD_CH1 + channel,
+							&dpcd_pattern_period[channel].raw,
+							sizeof(dpcd_pattern_period[channel]));
+		}
+	}
+
+	// translate sampling rate
+	switch (dpcd_test_mode.bits.sampling_rate) {
+	case AUDIO_SAMPLING_RATE_32KHZ:
+		sampling_rate_in_hz = 32000;
+		break;
+	case AUDIO_SAMPLING_RATE_44_1KHZ:
+		sampling_rate_in_hz = 44100;
+		break;
+	case AUDIO_SAMPLING_RATE_48KHZ:
+		sampling_rate_in_hz = 48000;
+		break;
+	case AUDIO_SAMPLING_RATE_88_2KHZ:
+		sampling_rate_in_hz = 88200;
+		break;
+	case AUDIO_SAMPLING_RATE_96KHZ:
+		sampling_rate_in_hz = 96000;
+		break;
+	case AUDIO_SAMPLING_RATE_176_4KHZ:
+		sampling_rate_in_hz = 176400;
+		break;
+	case AUDIO_SAMPLING_RATE_192KHZ:
+		sampling_rate_in_hz = 192000;
+		break;
+	default:
+		sampling_rate_in_hz = 0;
+		break;
+	}
+
+	link->audio_test_data.flags.test_requested = 1;
+	link->audio_test_data.flags.disable_video = disable_video;
+	link->audio_test_data.sampling_rate = sampling_rate_in_hz;
+	link->audio_test_data.channel_count = channel_count;
+	link->audio_test_data.pattern_type = test_pattern;
+
+	if (test_pattern == DP_TEST_PATTERN_AUDIO_SAWTOOTH) {
+		for (modes = 0; modes < pipe_ctx->stream->audio_info.mode_count; modes++) {
+			link->audio_test_data.pattern_period[modes] = dpcd_pattern_period[modes].bits.pattern_period;
+		}
+	}
+}
+
 static void handle_automated_test(struct dc_link *link)
 {
 	union test_request test_request;
@@ -2362,6 +2782,12 @@ static void handle_automated_test(struct dc_link *link)
 		dp_test_send_link_test_pattern(link);
 		test_response.bits.ACK = 1;
 	}
+
+	if (test_request.bits.AUDIO_TEST_PATTERN) {
+		dp_test_get_audio_test_data(link, test_request.bits.TEST_AUDIO_DISABLED_VIDEO);
+		test_response.bits.ACK = 1;
+	}
+
 	if (test_request.bits.PHY_TEST_PATTERN) {
 		dp_test_send_phy_test_pattern(link);
 		test_response.bits.ACK = 1;
@@ -2381,9 +2807,9 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 	union hpd_irq_data hpd_irq_dpcd_data = { { { {0} } } };
 	union device_service_irq device_service_clear = { { 0 } };
 	enum dc_status result;
-
 	bool status = false;
 	struct pipe_ctx *pipe_ctx;
+	struct dc_link_settings previous_link_settings;
 	int i;
 
 	if (out_link_loss)
@@ -2447,29 +2873,37 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 	/* For now we only handle 'Downstream port status' case.
 	 * If we got sink count changed it means
 	 * Downstream port status changed,
-	 * then DM should call DC to do the detection. */
-	if (hpd_rx_irq_check_link_loss_status(
-		link,
-		&hpd_irq_dpcd_data)) {
+	 * then DM should call DC to do the detection.
+	 * NOTE: Do not handle link loss on eDP since it is internal link*/
+	if ((link->connector_signal != SIGNAL_TYPE_EDP) &&
+		hpd_rx_irq_check_link_loss_status(
+			link,
+			&hpd_irq_dpcd_data)) {
 		/* Connectivity log: link loss */
 		CONN_DATA_LINK_LOSS(link,
 					hpd_irq_dpcd_data.raw,
 					sizeof(hpd_irq_dpcd_data),
 					"Status: ");
 
-		perform_link_training_with_retries(link,
-			&link->cur_link_settings,
-			true, LINK_TRAINING_ATTEMPTS);
-
 		for (i = 0; i < MAX_PIPES; i++) {
 			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
-			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link &&
-					pipe_ctx->stream->dpms_off == false &&
-					pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
-				dc_link_allocate_mst_payload(pipe_ctx);
-			}
+			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link)
+				break;
 		}
 
+		if (pipe_ctx == NULL || pipe_ctx->stream == NULL)
+			return false;
+
+		previous_link_settings = link->cur_link_settings;
+
+		perform_link_training_with_retries(&previous_link_settings,
+			true, LINK_TRAINING_ATTEMPTS,
+			pipe_ctx,
+			pipe_ctx->stream->signal);
+
+		if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
+			dc_link_reallocate_mst_payload(link);
+
 		status = false;
 		if (out_link_loss)
 			*out_link_loss = true;
@@ -2697,7 +3131,6 @@ static void dp_wa_power_up_0010FA(struct dc_link *link, uint8_t *dpcd_data,
 		int length)
 {
 	int retry = 0;
-	union dp_downstream_port_present ds_port = { 0 };
 
 	if (!link->dpcd_caps.dpcd_rev.raw) {
 		do {
@@ -2710,9 +3143,6 @@ static void dp_wa_power_up_0010FA(struct dc_link *link, uint8_t *dpcd_data,
 		} while (retry++ < 4 && !link->dpcd_caps.dpcd_rev.raw);
 	}
 
-	ds_port.byte = dpcd_data[DP_DOWNSTREAMPORT_PRESENT -
-				 DP_DPCD_REV];
-
 	if (link->dpcd_caps.dongle_type == DISPLAY_DONGLE_DP_VGA_CONVERTER) {
 		switch (link->dpcd_caps.branch_dev_id) {
 		/* 0010FA active dongles (DP-VGA, DP-DLDVI converters) power down
@@ -2737,7 +3167,11 @@ static void dp_wa_power_up_0010FA(struct dc_link *link, uint8_t *dpcd_data,
 
 static bool retrieve_link_cap(struct dc_link *link)
 {
-	uint8_t dpcd_data[DP_ADAPTER_CAP - DP_DPCD_REV + 1];
+	/* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16,
+	 * which means size 16 will be good for both of those DPCD register block reads
+	 */
+	uint8_t dpcd_data[16];
+	uint8_t lttpr_dpcd_data[6];
 
 	/*Only need to read 1 byte starting from DP_DPRX_FEATURE_ENUMERATION_LIST.
 	 */
@@ -2753,7 +3187,19 @@ static bool retrieve_link_cap(struct dc_link *link)
 	int i;
 	struct dp_sink_hw_fw_revision dp_hw_fw_revision;
 
+	/* Set default timeout to 3.2ms and read LTTPR capabilities */
+	bool ext_timeout_support = link->dc->caps.extended_aux_timeout_support &&
+			!link->dc->config.disable_extended_timeout_support;
+
+	link->is_lttpr_mode_transparent = true;
+
+	if (ext_timeout_support) {
+		dc_link_aux_configure_timeout(link->ddc,
+					LINK_AUX_DEFAULT_EXTENDED_TIMEOUT_PERIOD);
+	}
+
 	memset(dpcd_data, '\0', sizeof(dpcd_data));
+	memset(lttpr_dpcd_data, '\0', sizeof(lttpr_dpcd_data));
 	memset(&down_strm_port_count,
 		'\0', sizeof(union down_stream_port_count));
 	memset(&edp_config_cap, '\0',
@@ -2785,6 +3231,52 @@ static bool retrieve_link_cap(struct dc_link *link)
 		return false;
 	}
 
+	if (ext_timeout_support) {
+
+		status = core_link_read_dpcd(
+				link,
+				DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV,
+				lttpr_dpcd_data,
+				sizeof(lttpr_dpcd_data));
+
+		link->dpcd_caps.lttpr_caps.revision.raw =
+				lttpr_dpcd_data[DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.max_link_rate =
+				lttpr_dpcd_data[DP_MAX_LINK_RATE_PHY_REPEATER -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.phy_repeater_cnt =
+				lttpr_dpcd_data[DP_PHY_REPEATER_CNT -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.max_lane_count =
+				lttpr_dpcd_data[DP_MAX_LANE_COUNT_PHY_REPEATER -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.mode =
+				lttpr_dpcd_data[DP_PHY_REPEATER_MODE -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.max_ext_timeout =
+				lttpr_dpcd_data[DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		if (link->dpcd_caps.lttpr_caps.phy_repeater_cnt > 0 &&
+				link->dpcd_caps.lttpr_caps.max_lane_count > 0 &&
+				link->dpcd_caps.lttpr_caps.max_lane_count <= 4 &&
+				link->dpcd_caps.lttpr_caps.revision.raw >= 0x14) {
+			link->is_lttpr_mode_transparent = false;
+		} else {
+			/*No lttpr reset timeout to its default value*/
+			link->is_lttpr_mode_transparent = true;
+			dc_link_aux_configure_timeout(link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD);
+		}
+
+		CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: ");
+	}
+
 	{
 		union training_aux_rd_interval aux_rd_interval;
 
@@ -2792,7 +3284,7 @@ static bool retrieve_link_cap(struct dc_link *link)
 			dpcd_data[DP_TRAINING_AUX_RD_INTERVAL];
 
 		link->dpcd_caps.ext_receiver_cap_field_present =
-				aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1 ? true:false;
+				aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1;
 
 		if (aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1) {
 			uint8_t ext_cap_data[16];
@@ -2923,7 +3415,6 @@ static bool retrieve_link_cap(struct dc_link *link)
 		dp_hw_fw_revision.ieee_fw_rev,
 		sizeof(dp_hw_fw_revision.ieee_fw_rev));
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	memset(&link->dpcd_caps.dsc_caps, '\0',
 			sizeof(link->dpcd_caps.dsc_caps));
 	memset(&link->dpcd_caps.fec_cap, '\0', sizeof(link->dpcd_caps.fec_cap));
@@ -2945,7 +3436,6 @@ static bool retrieve_link_cap(struct dc_link *link)
 				link->dpcd_caps.dsc_caps.dsc_ext_caps.raw,
 				sizeof(link->dpcd_caps.dsc_caps.dsc_ext_caps.raw));
 	}
-#endif
 
 	/* Connectivity log: detection */
 	CONN_DATA_DETECT(link, dpcd_data, sizeof(dpcd_data), "Rx Caps: ");
@@ -2953,6 +3443,68 @@ static bool retrieve_link_cap(struct dc_link *link)
 	return true;
 }
 
+bool dp_overwrite_extended_receiver_cap(struct dc_link *link)
+{
+	uint8_t dpcd_data[16];
+	uint32_t read_dpcd_retry_cnt = 3;
+	enum dc_status status = DC_ERROR_UNEXPECTED;
+	union dp_downstream_port_present ds_port = { 0 };
+	union down_stream_port_count down_strm_port_count;
+	union edp_configuration_cap edp_config_cap;
+
+	int i;
+
+	for (i = 0; i < read_dpcd_retry_cnt; i++) {
+		status = core_link_read_dpcd(
+				link,
+				DP_DPCD_REV,
+				dpcd_data,
+				sizeof(dpcd_data));
+		if (status == DC_OK)
+			break;
+	}
+
+	link->dpcd_caps.dpcd_rev.raw =
+		dpcd_data[DP_DPCD_REV - DP_DPCD_REV];
+
+	if (dpcd_data[DP_MAX_LANE_COUNT - DP_DPCD_REV] == 0)
+		return false;
+
+	ds_port.byte = dpcd_data[DP_DOWNSTREAMPORT_PRESENT -
+			DP_DPCD_REV];
+
+	get_active_converter_info(ds_port.byte, link);
+
+	down_strm_port_count.raw = dpcd_data[DP_DOWN_STREAM_PORT_COUNT -
+			DP_DPCD_REV];
+
+	link->dpcd_caps.allow_invalid_MSA_timing_param =
+		down_strm_port_count.bits.IGNORE_MSA_TIMING_PARAM;
+
+	link->dpcd_caps.max_ln_count.raw = dpcd_data[
+		DP_MAX_LANE_COUNT - DP_DPCD_REV];
+
+	link->dpcd_caps.max_down_spread.raw = dpcd_data[
+		DP_MAX_DOWNSPREAD - DP_DPCD_REV];
+
+	link->reported_link_cap.lane_count =
+		link->dpcd_caps.max_ln_count.bits.MAX_LANE_COUNT;
+	link->reported_link_cap.link_rate = dpcd_data[
+		DP_MAX_LINK_RATE - DP_DPCD_REV];
+	link->reported_link_cap.link_spread =
+		link->dpcd_caps.max_down_spread.bits.MAX_DOWN_SPREAD ?
+		LINK_SPREAD_05_DOWNSPREAD_30KHZ : LINK_SPREAD_DISABLED;
+
+	edp_config_cap.raw = dpcd_data[
+		DP_EDP_CONFIGURATION_CAP - DP_DPCD_REV];
+	link->dpcd_caps.panel_mode_edp =
+		edp_config_cap.bits.ALT_SCRAMBLER_RESET;
+	link->dpcd_caps.dpcd_display_control_capable =
+		edp_config_cap.bits.DPCD_DISPLAY_CONTROL_CAPABLE;
+
+	return true;
+}
+
 bool detect_dp_sink_caps(struct dc_link *link)
 {
 	return retrieve_link_cap(link);
@@ -3067,21 +3619,20 @@ static bool is_dp_phy_pattern(enum dp_test_pattern test_pattern)
 
 static void set_crtc_test_pattern(struct dc_link *link,
 				struct pipe_ctx *pipe_ctx,
-				enum dp_test_pattern test_pattern)
+				enum dp_test_pattern test_pattern,
+				enum dp_test_pattern_color_space test_pattern_color_space)
 {
 	enum controller_dp_test_pattern controller_test_pattern;
 	enum dc_color_depth color_depth = pipe_ctx->
 		stream->timing.display_color_depth;
 	struct bit_depth_reduction_params params;
 	struct output_pixel_processor *opp = pipe_ctx->stream_res.opp;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	int width = pipe_ctx->stream->timing.h_addressable +
 		pipe_ctx->stream->timing.h_border_left +
 		pipe_ctx->stream->timing.h_border_right;
 	int height = pipe_ctx->stream->timing.v_addressable +
 		pipe_ctx->stream->timing.v_border_bottom +
 		pipe_ctx->stream->timing.v_border_top;
-#endif
 
 	memset(&params, 0, sizeof(params));
 
@@ -3125,10 +3676,29 @@ static void set_crtc_test_pattern(struct dc_link *link,
 		if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
 			pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 				controller_test_pattern, color_depth);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		else if (opp->funcs->opp_set_disp_pattern_generator) {
 			struct pipe_ctx *odm_pipe;
+			enum controller_dp_color_space controller_color_space;
 			int opp_cnt = 1;
+			uint8_t count = 0;
+
+			switch (test_pattern_color_space) {
+			case DP_TEST_PATTERN_COLOR_SPACE_RGB:
+				controller_color_space = CONTROLLER_DP_COLOR_SPACE_RGB;
+				break;
+			case DP_TEST_PATTERN_COLOR_SPACE_YCBCR601:
+				controller_color_space = CONTROLLER_DP_COLOR_SPACE_YCBCR601;
+				break;
+			case DP_TEST_PATTERN_COLOR_SPACE_YCBCR709:
+				controller_color_space = CONTROLLER_DP_COLOR_SPACE_YCBCR709;
+				break;
+			case DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED:
+			default:
+				controller_color_space = CONTROLLER_DP_COLOR_SPACE_UDEFINED;
+				DC_LOG_ERROR("%s: Color space must be defined for test pattern", __func__);
+				ASSERT(0);
+				break;
+			}
 
 			for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe)
 				opp_cnt++;
@@ -3141,6 +3711,7 @@ static void set_crtc_test_pattern(struct dc_link *link,
 				odm_opp->funcs->opp_program_bit_depth_reduction(odm_opp, &params);
 				odm_opp->funcs->opp_set_disp_pattern_generator(odm_opp,
 					controller_test_pattern,
+					controller_color_space,
 					color_depth,
 					NULL,
 					width,
@@ -3148,12 +3719,18 @@ static void set_crtc_test_pattern(struct dc_link *link,
 			}
 			opp->funcs->opp_set_disp_pattern_generator(opp,
 				controller_test_pattern,
+				controller_color_space,
 				color_depth,
 				NULL,
 				width,
 				height);
+			/* wait for dpg to blank pixel data with test pattern */
+			for (count = 0; count < 1000; count++)
+				if (opp->funcs->dpg_is_blanked(opp))
+					break;
+				else
+					udelay(100);
 		}
-#endif
 	}
 	break;
 	case DP_TEST_PATTERN_VIDEO_MODE:
@@ -3166,7 +3743,6 @@ static void set_crtc_test_pattern(struct dc_link *link,
 			pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 				CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
 				color_depth);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		else if (opp->funcs->opp_set_disp_pattern_generator) {
 			struct pipe_ctx *odm_pipe;
 			int opp_cnt = 1;
@@ -3181,6 +3757,7 @@ static void set_crtc_test_pattern(struct dc_link *link,
 				odm_opp->funcs->opp_program_bit_depth_reduction(odm_opp, &params);
 				odm_opp->funcs->opp_set_disp_pattern_generator(odm_opp,
 					CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
+					CONTROLLER_DP_COLOR_SPACE_UDEFINED,
 					color_depth,
 					NULL,
 					width,
@@ -3188,12 +3765,12 @@ static void set_crtc_test_pattern(struct dc_link *link,
 			}
 			opp->funcs->opp_set_disp_pattern_generator(opp,
 				CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
+				CONTROLLER_DP_COLOR_SPACE_UDEFINED,
 				color_depth,
 				NULL,
 				width,
 				height);
 		}
-#endif
 	}
 	break;
 
@@ -3205,6 +3782,7 @@ static void set_crtc_test_pattern(struct dc_link *link,
 bool dc_link_dp_set_test_pattern(
 	struct dc_link *link,
 	enum dp_test_pattern test_pattern,
+	enum dp_test_pattern_color_space test_pattern_color_space,
 	const struct link_training_settings *p_link_settings,
 	const unsigned char *p_custom_pattern,
 	unsigned int cust_pattern_size)
@@ -3233,7 +3811,7 @@ bool dc_link_dp_set_test_pattern(
 	if (link->test_pattern_enabled && test_pattern ==
 			DP_TEST_PATTERN_VIDEO_MODE) {
 		/* Set CRTC Test Pattern */
-		set_crtc_test_pattern(link, pipe_ctx, test_pattern);
+		set_crtc_test_pattern(link, pipe_ctx, test_pattern, test_pattern_color_space);
 		dp_set_hw_test_pattern(link, test_pattern,
 				(uint8_t *)p_custom_pattern,
 				(uint32_t)cust_pattern_size);
@@ -3256,8 +3834,8 @@ bool dc_link_dp_set_test_pattern(
 	if (is_dp_phy_pattern(test_pattern)) {
 		/* Set DPCD Lane Settings before running test pattern */
 		if (p_link_settings != NULL) {
-			dp_set_hw_lane_settings(link, p_link_settings);
-			dpcd_set_lane_settings(link, p_link_settings);
+			dp_set_hw_lane_settings(link, p_link_settings, DPRX);
+			dpcd_set_lane_settings(link, p_link_settings, DPRX);
 		}
 
 		/* Blank stream if running test pattern */
@@ -3348,7 +3926,7 @@ bool dc_link_dp_set_test_pattern(
 		}
 	} else {
 	/* CRTC Patterns */
-		set_crtc_test_pattern(link, pipe_ctx, test_pattern);
+		set_crtc_test_pattern(link, pipe_ctx, test_pattern, test_pattern_color_space);
 		/* Set Test Pattern state */
 		link->test_pattern_enabled = true;
 	}
@@ -3468,7 +4046,6 @@ enum dp_panel_mode dp_get_panel_mode(struct dc_link *link)
 	return DP_PANEL_MODE_DEFAULT;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 void dp_set_fec_ready(struct dc_link *link, bool ready)
 {
 	/* FEC has to be "set ready" before the link training.
@@ -3538,5 +4115,4 @@ void dp_set_fec_enable(struct dc_link *link, bool enable)
 		}
 	}
 }
-#endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
index a519dbc5ecb6..ddb855045767 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
@@ -12,12 +12,38 @@
 #include "dc_link_ddc.h"
 #include "dm_helpers.h"
 #include "dpcd_defs.h"
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dsc.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "resource.h"
-#endif
+
+static uint8_t convert_to_count(uint8_t lttpr_repeater_count)
+{
+	switch (lttpr_repeater_count) {
+	case 0x80: // 1 lttpr repeater
+		return 1;
+	case 0x40: // 2 lttpr repeaters
+		return 2;
+	case 0x20: // 3 lttpr repeaters
+		return 3;
+	case 0x10: // 4 lttpr repeaters
+		return 4;
+	case 0x08: // 5 lttpr repeaters
+		return 5;
+	case 0x04: // 6 lttpr repeaters
+		return 6;
+	case 0x02: // 7 lttpr repeaters
+		return 7;
+	case 0x01: // 8 lttpr repeaters
+		return 8;
+	default:
+		break;
+	}
+	return 0; // invalid value
+}
+
+static inline bool is_immediate_downstream(struct dc_link *link, uint32_t offset)
+{
+	return (convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == offset);
+}
 
 enum dc_status core_link_read_dpcd(
 	struct dc_link *link,
@@ -69,8 +95,8 @@ void dp_enable_link_phy(
 	const struct dc_link_settings *link_settings)
 {
 	struct link_encoder *link_enc = link->link_enc;
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 
 	struct pipe_ctx *pipes =
 			link->dc->current_state->res_ctx.pipe_ctx;
@@ -147,15 +173,20 @@ bool edp_receiver_ready_T9(struct dc_link *link)
 }
 bool edp_receiver_ready_T7(struct dc_link *link)
 {
-	unsigned int tries = 0;
 	unsigned char sinkstatus = 0;
 	unsigned char edpRev = 0;
 	enum dc_status result = DC_OK;
 
+	/* use absolute time stamp to constrain max T7*/
+	unsigned long long enter_timestamp = 0;
+	unsigned long long finish_timestamp = 0;
+	unsigned long long time_taken_in_ns = 0;
+
 	result = core_link_read_dpcd(link, DP_EDP_DPCD_REV, &edpRev, sizeof(edpRev));
 	if (result == DC_OK && edpRev < DP_EDP_12)
 		return true;
 	/* start from eDP version 1.2, SINK_STAUS indicate the sink is ready.*/
+	enter_timestamp = dm_get_timestamp(link->ctx);
 	do {
 		sinkstatus = 0;
 		result = core_link_read_dpcd(link, DP_SINK_STATUS, &sinkstatus, sizeof(sinkstatus));
@@ -163,8 +194,10 @@ bool edp_receiver_ready_T7(struct dc_link *link)
 			break;
 		if (result != DC_OK)
 			break;
-		udelay(25); //MAx T7 is 50ms
-	} while (++tries < 300);
+		udelay(25);
+		finish_timestamp = dm_get_timestamp(link->ctx);
+		time_taken_in_ns = dm_get_elapse_time_in_ns(link->ctx, finish_timestamp, enter_timestamp);
+	} while (time_taken_in_ns < 50 * 1000000); //MAx T7 is 50ms
 
 	if (link->local_sink->edid_caps.panel_patch.extra_t7_ms > 0)
 		udelay(link->local_sink->edid_caps.panel_patch.extra_t7_ms * 1000);
@@ -174,8 +207,8 @@ bool edp_receiver_ready_T7(struct dc_link *link)
 
 void dp_disable_link_phy(struct dc_link *link, enum signal_type signal)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 
 	if (!link->wa_flags.dp_keep_receiver_powered)
 		dp_receiver_power_ctrl(link, false);
@@ -212,7 +245,8 @@ void dp_disable_link_phy_mst(struct dc_link *link, enum signal_type signal)
 
 bool dp_set_hw_training_pattern(
 	struct dc_link *link,
-	enum dc_dp_training_pattern pattern)
+	enum dc_dp_training_pattern pattern,
+	uint32_t offset)
 {
 	enum dp_test_pattern test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
 
@@ -240,10 +274,14 @@ bool dp_set_hw_training_pattern(
 
 void dp_set_hw_lane_settings(
 	struct dc_link *link,
-	const struct link_training_settings *link_settings)
+	const struct link_training_settings *link_settings,
+	uint32_t offset)
 {
 	struct link_encoder *encoder = link->link_enc;
 
+	if (!link->is_lttpr_mode_transparent && !is_immediate_downstream(link, offset))
+		return;
+
 	/* call Encoder to set lane settings */
 	encoder->funcs->dp_set_lane_settings(encoder, link_settings);
 }
@@ -302,20 +340,12 @@ void dp_retrain_link_dp_test(struct dc_link *link,
 			memset(&link->cur_link_settings, 0,
 				sizeof(link->cur_link_settings));
 
-			link->link_enc->funcs->enable_dp_output(
-						link->link_enc,
-						link_setting,
-						pipes[i].clock_source->id);
-			link->cur_link_settings = *link_setting;
-
-			dp_receiver_power_ctrl(link, true);
-
 			perform_link_training_with_retries(
-					link,
 					link_setting,
 					skip_video_pattern,
-					LINK_TRAINING_ATTEMPTS);
-
+					LINK_TRAINING_ATTEMPTS,
+					&pipes[i],
+					SIGNAL_TYPE_DISPLAY_PORT);
 
 			link->dc->hwss.enable_stream(&pipes[i]);
 
@@ -339,7 +369,6 @@ void dp_retrain_link_dp_test(struct dc_link *link,
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define DC_LOGGER \
 	dsc->ctx->logger
 static void dsc_optc_config_log(struct display_stream_compressor *dsc,
@@ -365,14 +394,14 @@ static void dsc_optc_config_log(struct display_stream_compressor *dsc,
 
 static bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable)
 {
-	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	bool result = false;
 
-	if (IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment))
+	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
 		result = true;
 	else
-		result = dm_helpers_dp_write_dsc_enable(core_dc->ctx, stream, enable);
+		result = dm_helpers_dp_write_dsc_enable(dc->ctx, stream, enable);
 	return result;
 }
 
@@ -382,7 +411,7 @@ static bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable)
 void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
-	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 1;
@@ -418,7 +447,7 @@ void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 		optc_dsc_mode = dsc_optc_cfg.is_pixel_format_444 ? OPTC_DSC_ENABLED_444 : OPTC_DSC_ENABLED_NATIVE_SUBSAMPLED;
 
 		/* Enable DSC in encoder */
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 			DC_LOG_DSC("Setting stream encoder DSC config for engine %d:", (int)pipe_ctx->stream_res.stream_enc->id);
 			dsc_optc_config_log(dsc, &dsc_optc_cfg);
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_config(pipe_ctx->stream_res.stream_enc,
@@ -443,7 +472,7 @@ void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 				OPTC_DSC_DISABLED, 0, 0);
 
 		/* disable DSC in stream encoder */
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_config(
 					pipe_ctx->stream_res.stream_enc,
 					OPTC_DSC_DISABLED, 0, 0);
@@ -486,7 +515,7 @@ out:
 bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
-	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 
 	if (!pipe_ctx->stream->timing.flags.DSC || !dsc)
@@ -496,6 +525,9 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 		struct dsc_config dsc_cfg;
 		uint8_t dsc_packed_pps[128];
 
+		memset(&dsc_cfg, 0, sizeof(dsc_cfg));
+		memset(dsc_packed_pps, 0, 128);
+
 		/* Enable DSC hw block */
 		dsc_cfg.pic_width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right;
 		dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom;
@@ -505,7 +537,7 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 
 		DC_LOG_DSC(" ");
 		dsc->funcs->dsc_get_packed_pps(dsc, &dsc_cfg, &dsc_packed_pps[0]);
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 			DC_LOG_DSC("Setting stream encoder DSC PPS SDP for engine %d\n", (int)pipe_ctx->stream_res.stream_enc->id);
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet(
 									pipe_ctx->stream_res.stream_enc,
@@ -514,7 +546,7 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 		}
 	} else {
 		/* disable DSC PPS in stream encoder */
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet(
 						pipe_ctx->stream_res.stream_enc, false, NULL);
 		}
@@ -537,5 +569,4 @@ bool dp_update_dsc_config(struct pipe_ctx *pipe_ctx)
 	dp_set_dsc_pps_sdp(pipe_ctx, true);
 	return true;
 }
-#endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 37698305a2dc..a0eb9e533a61 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -46,15 +46,11 @@
 #include "dce100/dce100_resource.h"
 #include "dce110/dce110_resource.h"
 #include "dce112/dce112_resource.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "dcn10/dcn10_resource.h"
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dcn20/dcn20_resource.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #include "dcn21/dcn21_resource.h"
-#endif
 #include "dce120/dce120_resource.h"
 
 #define DC_LOGGER_INIT(logger)
@@ -99,23 +95,19 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 		else
 			dc_version = DCE_VERSION_12_0;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case FAMILY_RV:
 		dc_version = DCN_VERSION_1_0;
 		if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev))
 			dc_version = DCN_VERSION_1_01;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 		if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev))
 			dc_version = DCN_VERSION_2_1;
-#endif
 		break;
 #endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case FAMILY_NV:
 		dc_version = DCN_VERSION_2_0;
 		break;
-#endif
 	default:
 		dc_version = DCE_VERSION_UNKNOWN;
 		break;
@@ -162,20 +154,16 @@ struct resource_pool *dc_create_resource_pool(struct dc  *dc,
 				init_data->num_virtual_links, dc);
 		break;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case DCN_VERSION_1_0:
 	case DCN_VERSION_1_01:
 		res_pool = dcn10_create_resource_pool(init_data, dc);
 		break;
-#endif
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case DCN_VERSION_2_0:
 		res_pool = dcn20_create_resource_pool(init_data, dc);
 		break;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case DCN_VERSION_2_1:
 		res_pool = dcn21_create_resource_pool(init_data, dc);
 		break;
@@ -951,44 +939,44 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx)
 	data->inits.v_c_bot = dc_fixpt_add(data->inits.v_c, data->ratios.vert_c);
 
 }
-static bool are_rects_integer_multiples(struct rect src, struct rect dest)
-{
-	if (dest.width  >= src.width  && dest.width  % src.width  == 0 &&
-		dest.height >= src.height && dest.height % src.height == 0)
-		return true;
-
-	return false;
-}
 
-static void calculate_integer_scaling(struct pipe_ctx *pipe_ctx)
+/*
+ * When handling 270 rotation in mixed SLS mode, we have
+ * stream->timing.h_border_left that is non zero.  If we are doing
+ * pipe-splitting, this h_border_left value gets added to recout.x and when it
+ * calls calculate_inits_and_adj_vp() and
+ * adjust_vp_and_init_for_seamless_clip(), it can cause viewport.height for a
+ * pipe to be incorrect.
+ *
+ * To fix this, instead of using stream->timing.h_border_left, we can use
+ * stream->dst.x to represent the border instead.  So we will set h_border_left
+ * to 0 and shift the appropriate amount in stream->dst.x.  We will then
+ * perform all calculations in resource_build_scaling_params() based on this
+ * and then restore the h_border_left and stream->dst.x to their original
+ * values.
+ *
+ * shift_border_left_to_dst() will shift the amount of h_border_left to
+ * stream->dst.x and set h_border_left to 0.  restore_border_left_from_dst()
+ * will restore h_border_left and stream->dst.x back to their original values
+ * We also need to make sure pipe_ctx->plane_res.scl_data.h_active uses the
+ * original h_border_left value in its calculation.
+ */
+int shift_border_left_to_dst(struct pipe_ctx *pipe_ctx)
 {
-	if (!pipe_ctx->plane_state->scaling_quality.integer_scaling)
-		return;
-
-	//for Centered Mode
-	if (pipe_ctx->stream->dst.width  == pipe_ctx->stream->src.width &&
-		pipe_ctx->stream->dst.height == pipe_ctx->stream->src.height) {
-		// calculate maximum # of replication of src onto addressable
-		unsigned int integer_multiple = min(
-				pipe_ctx->stream->timing.h_addressable / pipe_ctx->stream->src.width,
-				pipe_ctx->stream->timing.v_addressable  / pipe_ctx->stream->src.height);
-
-		//scale dst
-		pipe_ctx->stream->dst.width  = integer_multiple * pipe_ctx->stream->src.width;
-		pipe_ctx->stream->dst.height = integer_multiple * pipe_ctx->stream->src.height;
+	int store_h_border_left = pipe_ctx->stream->timing.h_border_left;
 
-		//center dst onto addressable
-		pipe_ctx->stream->dst.x = (pipe_ctx->stream->timing.h_addressable - pipe_ctx->stream->dst.width)/2;
-		pipe_ctx->stream->dst.y = (pipe_ctx->stream->timing.v_addressable - pipe_ctx->stream->dst.height)/2;
+	if (store_h_border_left) {
+		pipe_ctx->stream->timing.h_border_left = 0;
+		pipe_ctx->stream->dst.x += store_h_border_left;
 	}
+	return store_h_border_left;
+}
 
-	//disable taps if src & dst are integer ratio
-	if (are_rects_integer_multiples(pipe_ctx->stream->src, pipe_ctx->stream->dst)) {
-		pipe_ctx->plane_state->scaling_quality.v_taps = 1;
-		pipe_ctx->plane_state->scaling_quality.h_taps = 1;
-		pipe_ctx->plane_state->scaling_quality.v_taps_c = 1;
-		pipe_ctx->plane_state->scaling_quality.h_taps_c = 1;
-	}
+void restore_border_left_from_dst(struct pipe_ctx *pipe_ctx,
+                                  int store_h_border_left)
+{
+	pipe_ctx->stream->dst.x -= store_h_border_left;
+	pipe_ctx->stream->timing.h_border_left = store_h_border_left;
 }
 
 bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
@@ -996,6 +984,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	const struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct dc_crtc_timing *timing = &pipe_ctx->stream->timing;
 	bool res = false;
+	int store_h_border_left = shift_border_left_to_dst(pipe_ctx);
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 	/* Important: scaling ratio calculation requires pixel format,
 	 * lb depth calculation requires recout and taps require scaling ratios.
@@ -1004,14 +993,18 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_res.scl_data.format = convert_pixel_format_to_dalsurface(
 			pipe_ctx->plane_state->format);
 
-	calculate_integer_scaling(pipe_ctx);
-
 	calculate_scaling_ratios(pipe_ctx);
 
 	calculate_viewport(pipe_ctx);
 
-	if (pipe_ctx->plane_res.scl_data.viewport.height < 16 || pipe_ctx->plane_res.scl_data.viewport.width < 16)
+	if (pipe_ctx->plane_res.scl_data.viewport.height < 16 ||
+		pipe_ctx->plane_res.scl_data.viewport.width < 16) {
+		if (store_h_border_left) {
+			restore_border_left_from_dst(pipe_ctx,
+				store_h_border_left);
+		}
 		return false;
+	}
 
 	calculate_recout(pipe_ctx);
 
@@ -1024,8 +1017,10 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_res.scl_data.recout.x += timing->h_border_left;
 	pipe_ctx->plane_res.scl_data.recout.y += timing->v_border_top;
 
-	pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable + timing->h_border_left + timing->h_border_right;
-	pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
+	pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable +
+		store_h_border_left + timing->h_border_right;
+	pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable +
+		timing->v_border_top + timing->v_border_bottom;
 
 	/* Taps calculations */
 	if (pipe_ctx->plane_res.xfm != NULL)
@@ -1072,6 +1067,9 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 				plane_state->dst_rect.x,
 				plane_state->dst_rect.y);
 
+	if (store_h_border_left)
+		restore_border_left_from_dst(pipe_ctx, store_h_border_left);
+
 	return res;
 }
 
@@ -1217,7 +1215,7 @@ static struct pipe_ctx *acquire_free_pipe_for_head(
 	return pool->funcs->acquire_idle_pipe_for_layer(context, pool, head_pipe->stream);
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 static int acquire_first_split_pipe(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
@@ -1298,7 +1296,7 @@ bool dc_add_plane_to_context(
 
 		free_pipe = acquire_free_pipe_for_head(context, pool, head_pipe);
 
-	#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+	#if defined(CONFIG_DRM_AMD_DC_DCN)
 		if (!free_pipe) {
 			int pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 			if (pipe_idx >= 0)
@@ -1891,7 +1889,7 @@ static int acquire_resource_from_hw_enabled_state(
 	inst = link->link_enc->funcs->get_dig_frontend(link->link_enc);
 
 	if (inst == ENGINE_ID_UNKNOWN)
-		return false;
+		return -1;
 
 	for (i = 0; i < pool->stream_enc_count; i++) {
 		if (pool->stream_enc[i]->id == inst) {
@@ -1903,10 +1901,10 @@ static int acquire_resource_from_hw_enabled_state(
 
 	// tg_inst not found
 	if (i == pool->stream_enc_count)
-		return false;
+		return -1;
 
 	if (tg_inst >= pool->timing_generator_count)
-		return false;
+		return -1;
 
 	if (!res_ctx->pipe_ctx[tg_inst].stream) {
 		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[tg_inst];
@@ -1919,8 +1917,26 @@ static int acquire_resource_from_hw_enabled_state(
 		pipe_ctx->plane_res.dpp = pool->dpps[tg_inst];
 		pipe_ctx->stream_res.opp = pool->opps[tg_inst];
 
-		if (pool->dpps[tg_inst])
+		if (pool->dpps[tg_inst]) {
 			pipe_ctx->plane_res.mpcc_inst = pool->dpps[tg_inst]->inst;
+
+			// Read DPP->MPCC->OPP Pipe from HW State
+			if (pool->mpc->funcs->read_mpcc_state) {
+				struct mpcc_state s = {0};
+
+				pool->mpc->funcs->read_mpcc_state(pool->mpc, pipe_ctx->plane_res.mpcc_inst, &s);
+
+				if (s.dpp_id < MAX_MPCC)
+					pool->mpc->mpcc_array[pipe_ctx->plane_res.mpcc_inst].dpp_id = s.dpp_id;
+
+				if (s.bot_mpcc_id < MAX_MPCC)
+					pool->mpc->mpcc_array[pipe_ctx->plane_res.mpcc_inst].mpcc_bot =
+							&pool->mpc->mpcc_array[s.bot_mpcc_id];
+
+				if (s.opp_id < MAX_OPP)
+					pipe_ctx->stream_res.opp->mpc_tree_params.opp_id = s.opp_id;
+			}
+		}
 		pipe_ctx->pipe_idx = tg_inst;
 
 		pipe_ctx->stream = stream;
@@ -1972,7 +1988,7 @@ enum dc_status resource_map_pool_resources(
 		/* acquire new resources */
 		pipe_idx = acquire_first_free_pipe(&context->res_ctx, pool, stream);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	if (pipe_idx < 0)
 		pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 #endif
@@ -2050,6 +2066,13 @@ void dc_resource_state_construct(
 	dst_ctx->clk_mgr = dc->clk_mgr;
 }
 
+
+bool dc_resource_is_dsc_encoding_supported(const struct dc *dc)
+{
+	return dc->res_pool->res_cap->num_dsc > 0;
+}
+
+
 /**
  * dc_validate_global_state() - Determine if HW can support a given state
  * Checks HW resource availability and bandwidth requirement.
@@ -2306,7 +2329,7 @@ static void set_avi_info_frame(
 		if (color_space == COLOR_SPACE_SRGB ||
 			color_space == COLOR_SPACE_2020_RGB_FULLRANGE) {
 			hdmi_info.bits.Q0_Q1   = RGB_QUANTIZATION_FULL_RANGE;
-			hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_FULL_RANGE;
+			hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE;
 		} else if (color_space == COLOR_SPACE_SRGB_LIMITED ||
 					color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE) {
 			hdmi_info.bits.Q0_Q1   = RGB_QUANTIZATION_LIMITED_RANGE;
@@ -2772,9 +2795,8 @@ void resource_build_bit_depth_reduction_params(struct dc_stream_state *stream,
 
 enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream)
 {
-	struct dc  *core_dc = dc;
 	struct dc_link *link = stream->link;
-	struct timing_generator *tg = core_dc->res_pool->timing_generators[0];
+	struct timing_generator *tg = dc->res_pool->timing_generators[0];
 	enum dc_status res = DC_OK;
 
 	calculate_phy_pix_clks(stream);
@@ -2837,3 +2859,48 @@ unsigned int resource_pixel_format_to_bpp(enum surface_pixel_format format)
 		return -1;
 	}
 }
+static unsigned int get_max_audio_sample_rate(struct audio_mode *modes)
+{
+	if (modes) {
+		if (modes->sample_rates.rate.RATE_192)
+			return 192000;
+		if (modes->sample_rates.rate.RATE_176_4)
+			return 176400;
+		if (modes->sample_rates.rate.RATE_96)
+			return 96000;
+		if (modes->sample_rates.rate.RATE_88_2)
+			return 88200;
+		if (modes->sample_rates.rate.RATE_48)
+			return 48000;
+		if (modes->sample_rates.rate.RATE_44_1)
+			return 44100;
+		if (modes->sample_rates.rate.RATE_32)
+			return 32000;
+	}
+	/*original logic when no audio info*/
+	return 441000;
+}
+
+void get_audio_check(struct audio_info *aud_modes,
+	struct audio_check *audio_chk)
+{
+	unsigned int i;
+	unsigned int max_sample_rate = 0;
+
+	if (aud_modes) {
+		audio_chk->audio_packet_type = 0x2;/*audio sample packet AP = .25 for layout0, 1 for layout1*/
+
+		audio_chk->max_audiosample_rate = 0;
+		for (i = 0; i < aud_modes->mode_count; i++) {
+			max_sample_rate = get_max_audio_sample_rate(&aud_modes->modes[i]);
+			if (audio_chk->max_audiosample_rate < max_sample_rate)
+				audio_chk->max_audiosample_rate = max_sample_rate;
+			/*dts takes the same as type 2: AP = 0.25*/
+		}
+		/*check which one take more bandwidth*/
+		if (audio_chk->max_audiosample_rate > 192000)
+			audio_chk->audio_packet_type = 0x9;/*AP =1*/
+		audio_chk->acat = 0;/*not support*/
+	}
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_sink.c b/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
index 5cbfdf1c4b11..a249a0e5edd0 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
@@ -33,7 +33,7 @@
  * Private functions
  ******************************************************************************/
 
-static void destruct(struct dc_sink *sink)
+static void dc_sink_destruct(struct dc_sink *sink)
 {
 	if (sink->dc_container_id) {
 		kfree(sink->dc_container_id);
@@ -41,7 +41,7 @@ static void destruct(struct dc_sink *sink)
 	}
 }
 
-static bool construct(struct dc_sink *sink, const struct dc_sink_init_data *init_params)
+static bool dc_sink_construct(struct dc_sink *sink, const struct dc_sink_init_data *init_params)
 {
 
 	struct dc_link *link = init_params->link;
@@ -75,7 +75,7 @@ void dc_sink_retain(struct dc_sink *sink)
 static void dc_sink_free(struct kref *kref)
 {
 	struct dc_sink *sink = container_of(kref, struct dc_sink, refcount);
-	destruct(sink);
+	dc_sink_destruct(sink);
 	kfree(sink);
 }
 
@@ -91,7 +91,7 @@ struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params)
 	if (NULL == sink)
 		goto alloc_fail;
 
-	if (false == construct(sink, init_params))
+	if (false == dc_sink_construct(sink, init_params))
 		goto construct_fail;
 
 	kref_init(&sink->refcount);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index bb09243758fe..6ddbb00ed37a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -27,14 +27,12 @@
 #include <linux/slab.h>
 
 #include "dm_services.h"
+#include "basics/dc_common.h"
 #include "dc.h"
 #include "core_types.h"
 #include "resource.h"
 #include "ipp.h"
 #include "timing_generator.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-#include "dcn10/dcn10_hw_sequencer.h"
-#endif
 
 #define DC_LOGGER dc->ctx->logger
 
@@ -58,7 +56,7 @@ void update_stream_signal(struct dc_stream_state *stream, struct dc_sink *sink)
 	}
 }
 
-static void construct(struct dc_stream_state *stream,
+static void dc_stream_construct(struct dc_stream_state *stream,
 	struct dc_sink *dc_sink_data)
 {
 	uint32_t i = 0;
@@ -108,7 +106,6 @@ static void construct(struct dc_stream_state *stream,
 	/* EDID CAP translation for HDMI 2.0 */
 	stream->timing.flags.LTE_340MCSC_SCRAMBLE = dc_sink_data->edid_caps.lte_340mcsc_scramble;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	memset(&stream->timing.dsc_cfg, 0, sizeof(stream->timing.dsc_cfg));
 	stream->timing.dsc_cfg.num_slices_h = 0;
 	stream->timing.dsc_cfg.num_slices_v = 0;
@@ -117,7 +114,6 @@ static void construct(struct dc_stream_state *stream,
 	stream->timing.dsc_cfg.linebuf_depth = 9;
 	stream->timing.dsc_cfg.version_minor = 2;
 	stream->timing.dsc_cfg.ycbcr422_simple = 0;
-#endif
 
 	update_stream_signal(stream, dc_sink_data);
 
@@ -129,7 +125,7 @@ static void construct(struct dc_stream_state *stream,
 	stream->ctx->dc_stream_id_count++;
 }
 
-static void destruct(struct dc_stream_state *stream)
+static void dc_stream_destruct(struct dc_stream_state *stream)
 {
 	dc_sink_release(stream->sink);
 	if (stream->out_transfer_func != NULL) {
@@ -147,7 +143,7 @@ static void dc_stream_free(struct kref *kref)
 {
 	struct dc_stream_state *stream = container_of(kref, struct dc_stream_state, refcount);
 
-	destruct(stream);
+	dc_stream_destruct(stream);
 	kfree(stream);
 }
 
@@ -170,7 +166,7 @@ struct dc_stream_state *dc_create_stream_for_sink(
 	if (stream == NULL)
 		return NULL;
 
-	construct(stream, sink);
+	dc_stream_construct(stream, sink);
 
 	kref_init(&stream->refcount);
 
@@ -237,7 +233,7 @@ struct dc_stream_status *dc_stream_get_status(
 
 static void delay_cursor_until_vupdate(struct pipe_ctx *pipe_ctx, struct dc *dc)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	unsigned int vupdate_line;
 	unsigned int lines_to_vupdate, us_to_vupdate, vpos, nvpos;
 	struct dc_stream_state *stream = pipe_ctx->stream;
@@ -246,7 +242,7 @@ static void delay_cursor_until_vupdate(struct pipe_ctx *pipe_ctx, struct dc *dc)
 	if (stream->ctx->asic_id.chip_family == FAMILY_RV &&
 			ASICREV_IS_RAVEN(stream->ctx->asic_id.hw_internal_rev)) {
 
-		vupdate_line = get_vupdate_offset_from_vsync(pipe_ctx);
+		vupdate_line = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
 		if (!dc_stream_get_crtc_position(dc, &stream, 1, &vpos, &nvpos))
 			return;
 
@@ -272,7 +268,7 @@ bool dc_stream_set_cursor_attributes(
 	const struct dc_cursor_attributes *attributes)
 {
 	int i;
-	struct dc  *core_dc;
+	struct dc  *dc;
 	struct resource_context *res_ctx;
 	struct pipe_ctx *pipe_to_program = NULL;
 
@@ -290,8 +286,8 @@ bool dc_stream_set_cursor_attributes(
 		return false;
 	}
 
-	core_dc = stream->ctx->dc;
-	res_ctx = &core_dc->current_state->res_ctx;
+	dc = stream->ctx->dc;
+	res_ctx = &dc->current_state->res_ctx;
 	stream->cursor_attributes = *attributes;
 
 	for (i = 0; i < MAX_PIPES; i++) {
@@ -303,17 +299,17 @@ bool dc_stream_set_cursor_attributes(
 		if (!pipe_to_program) {
 			pipe_to_program = pipe_ctx;
 
-			delay_cursor_until_vupdate(pipe_ctx, core_dc);
-			core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, true);
+			delay_cursor_until_vupdate(pipe_ctx, dc);
+			dc->hwss.pipe_control_lock(dc, pipe_to_program, true);
 		}
 
-		core_dc->hwss.set_cursor_attribute(pipe_ctx);
-		if (core_dc->hwss.set_cursor_sdr_white_level)
-			core_dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
+		dc->hwss.set_cursor_attribute(pipe_ctx);
+		if (dc->hwss.set_cursor_sdr_white_level)
+			dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
 	}
 
 	if (pipe_to_program)
-		core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, false);
+		dc->hwss.pipe_control_lock(dc, pipe_to_program, false);
 
 	return true;
 }
@@ -323,7 +319,7 @@ bool dc_stream_set_cursor_position(
 	const struct dc_cursor_position *position)
 {
 	int i;
-	struct dc  *core_dc;
+	struct dc  *dc;
 	struct resource_context *res_ctx;
 	struct pipe_ctx *pipe_to_program = NULL;
 
@@ -337,8 +333,8 @@ bool dc_stream_set_cursor_position(
 		return false;
 	}
 
-	core_dc = stream->ctx->dc;
-	res_ctx = &core_dc->current_state->res_ctx;
+	dc = stream->ctx->dc;
+	res_ctx = &dc->current_state->res_ctx;
 	stream->cursor_position = *position;
 
 	for (i = 0; i < MAX_PIPES; i++) {
@@ -354,20 +350,19 @@ bool dc_stream_set_cursor_position(
 		if (!pipe_to_program) {
 			pipe_to_program = pipe_ctx;
 
-			delay_cursor_until_vupdate(pipe_ctx, core_dc);
-			core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, true);
+			delay_cursor_until_vupdate(pipe_ctx, dc);
+			dc->hwss.pipe_control_lock(dc, pipe_to_program, true);
 		}
 
-		core_dc->hwss.set_cursor_position(pipe_ctx);
+		dc->hwss.set_cursor_position(pipe_ctx);
 	}
 
 	if (pipe_to_program)
-		core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, false);
+		dc->hwss.pipe_control_lock(dc, pipe_to_program, false);
 
 	return true;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dc_stream_add_writeback(struct dc *dc,
 		struct dc_stream_state *stream,
 		struct dc_writeback_info *wb_info)
@@ -411,25 +406,30 @@ bool dc_stream_add_writeback(struct dc *dc,
 		stream->writeback_info[stream->num_wb_info++] = *wb_info;
 	}
 
-	if (!dc->hwss.update_bandwidth(dc, dc->current_state)) {
-		dm_error("DC: update_bandwidth failed!\n");
-		return false;
-	}
-
-	/* enable writeback */
 	if (dc->hwss.enable_writeback) {
 		struct dc_stream_status *stream_status = dc_stream_get_status(stream);
 		struct dwbc *dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst];
+		dwb->otg_inst = stream_status->primary_otg_inst;
+	}
+	if (IS_DIAG_DC(dc->ctx->dce_environment)) {
+		if (!dc->hwss.update_bandwidth(dc, dc->current_state)) {
+			dm_error("DC: update_bandwidth failed!\n");
+			return false;
+		}
 
-		if (dwb->funcs->is_enabled(dwb)) {
-			/* writeback pipe already enabled, only need to update */
-			dc->hwss.update_writeback(dc, stream_status, wb_info, dc->current_state);
-		} else {
-			/* Enable writeback pipe from scratch*/
-			dc->hwss.enable_writeback(dc, stream_status, wb_info, dc->current_state);
+		/* enable writeback */
+		if (dc->hwss.enable_writeback) {
+			struct dwbc *dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst];
+
+			if (dwb->funcs->is_enabled(dwb)) {
+				/* writeback pipe already enabled, only need to update */
+				dc->hwss.update_writeback(dc, wb_info, dc->current_state);
+			} else {
+				/* Enable writeback pipe from scratch*/
+				dc->hwss.enable_writeback(dc, wb_info, dc->current_state);
+			}
 		}
 	}
-
 	return true;
 }
 
@@ -468,26 +468,35 @@ bool dc_stream_remove_writeback(struct dc *dc,
 	}
 	stream->num_wb_info = j;
 
-	/* recalculate and apply DML parameters */
-	if (!dc->hwss.update_bandwidth(dc, dc->current_state)) {
-		dm_error("DC: update_bandwidth failed!\n");
-		return false;
-	}
-
-	/* disable writeback */
-	if (dc->hwss.disable_writeback)
-		dc->hwss.disable_writeback(dc, dwb_pipe_inst);
+	if (IS_DIAG_DC(dc->ctx->dce_environment)) {
+		/* recalculate and apply DML parameters */
+		if (!dc->hwss.update_bandwidth(dc, dc->current_state)) {
+			dm_error("DC: update_bandwidth failed!\n");
+			return false;
+		}
 
+		/* disable writeback */
+		if (dc->hwss.disable_writeback)
+			dc->hwss.disable_writeback(dc, dwb_pipe_inst);
+	}
 	return true;
 }
-#endif
 
+bool dc_stream_warmup_writeback(struct dc *dc,
+		int num_dwb,
+		struct dc_writeback_info *wb_info)
+{
+	if (dc->hwss.mmhubbub_warmup)
+		return dc->hwss.mmhubbub_warmup(dc, num_dwb, wb_info);
+	else
+		return false;
+}
 uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream)
 {
 	uint8_t i;
-	struct dc  *core_dc = stream->ctx->dc;
+	struct dc  *dc = stream->ctx->dc;
 	struct resource_context *res_ctx =
-		&core_dc->current_state->res_ctx;
+		&dc->current_state->res_ctx;
 
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg;
@@ -544,9 +553,9 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
 {
 	uint8_t i;
 	bool ret = false;
-	struct dc  *core_dc = stream->ctx->dc;
+	struct dc  *dc = stream->ctx->dc;
 	struct resource_context *res_ctx =
-		&core_dc->current_state->res_ctx;
+		&dc->current_state->res_ctx;
 
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg;
@@ -567,10 +576,8 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
 	return ret;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dc_stream_dmdata_status_done(struct dc *dc, struct dc_stream_state *stream)
 {
-	bool status = true;
 	struct pipe_ctx *pipe = NULL;
 	int i;
 
@@ -586,8 +593,7 @@ bool dc_stream_dmdata_status_done(struct dc *dc, struct dc_stream_state *stream)
 	if (i == MAX_PIPES)
 		return true;
 
-	status = dc->hwss.dmdata_status_done(pipe);
-	return status;
+	return dc->hwss.dmdata_status_done(pipe);
 }
 
 bool dc_stream_set_dynamic_metadata(struct dc *dc,
@@ -630,7 +636,6 @@ bool dc_stream_set_dynamic_metadata(struct dc *dc,
 
 	return true;
 }
-#endif
 
 void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index b9d6a5bd8522..ea1229a3e2b2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -37,7 +37,7 @@
 /*******************************************************************************
  * Private functions
  ******************************************************************************/
-static void construct(struct dc_context *ctx, struct dc_plane_state *plane_state)
+static void dc_plane_construct(struct dc_context *ctx, struct dc_plane_state *plane_state)
 {
 	plane_state->ctx = ctx;
 
@@ -50,7 +50,6 @@ static void construct(struct dc_context *ctx, struct dc_plane_state *plane_state
 		plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
 		plane_state->in_transfer_func->ctx = ctx;
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	plane_state->in_shaper_func = dc_create_transfer_func();
 	if (plane_state->in_shaper_func != NULL) {
 		plane_state->in_shaper_func->type = TF_TYPE_BYPASS;
@@ -67,10 +66,9 @@ static void construct(struct dc_context *ctx, struct dc_plane_state *plane_state
 		plane_state->blend_tf->ctx = ctx;
 	}
 
-#endif
 }
 
-static void destruct(struct dc_plane_state *plane_state)
+static void dc_plane_destruct(struct dc_plane_state *plane_state)
 {
 	if (plane_state->gamma_correction != NULL) {
 		dc_gamma_release(&plane_state->gamma_correction);
@@ -80,7 +78,6 @@ static void destruct(struct dc_plane_state *plane_state)
 				plane_state->in_transfer_func);
 		plane_state->in_transfer_func = NULL;
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	if (plane_state->in_shaper_func != NULL) {
 		dc_transfer_func_release(
 				plane_state->in_shaper_func);
@@ -97,7 +94,6 @@ static void destruct(struct dc_plane_state *plane_state)
 		plane_state->blend_tf = NULL;
 	}
 
-#endif
 }
 
 /*******************************************************************************
@@ -112,16 +108,14 @@ void enable_surface_flip_reporting(struct dc_plane_state *plane_state,
 
 struct dc_plane_state *dc_create_plane_state(struct dc *dc)
 {
-	struct dc *core_dc = dc;
-
 	struct dc_plane_state *plane_state = kvzalloc(sizeof(*plane_state),
-						      GFP_KERNEL);
+							GFP_KERNEL);
 
 	if (NULL == plane_state)
 		return NULL;
 
 	kref_init(&plane_state->refcount);
-	construct(core_dc->ctx, plane_state);
+	dc_plane_construct(dc->ctx, plane_state);
 
 	return plane_state;
 }
@@ -141,7 +135,7 @@ const struct dc_plane_status *dc_plane_get_status(
 		const struct dc_plane_state *plane_state)
 {
 	const struct dc_plane_status *plane_status;
-	struct dc  *core_dc;
+	struct dc  *dc;
 	int i;
 
 	if (!plane_state ||
@@ -152,15 +146,15 @@ const struct dc_plane_status *dc_plane_get_status(
 	}
 
 	plane_status = &plane_state->status;
-	core_dc = plane_state->ctx->dc;
+	dc = plane_state->ctx->dc;
 
-	if (core_dc->current_state == NULL)
+	if (dc->current_state == NULL)
 		return NULL;
 
 	/* Find the current plane state and set its pending bit to false */
-	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx =
-				&core_dc->current_state->res_ctx.pipe_ctx[i];
+				&dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe_ctx->plane_state != plane_state)
 			continue;
@@ -170,14 +164,14 @@ const struct dc_plane_status *dc_plane_get_status(
 		break;
 	}
 
-	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx =
-				&core_dc->current_state->res_ctx.pipe_ctx[i];
+				&dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe_ctx->plane_state != plane_state)
 			continue;
 
-		core_dc->hwss.update_pending_status(pipe_ctx);
+		dc->hwss.update_pending_status(pipe_ctx);
 	}
 
 	return plane_status;
@@ -191,7 +185,7 @@ void dc_plane_state_retain(struct dc_plane_state *plane_state)
 static void dc_plane_state_free(struct kref *kref)
 {
 	struct dc_plane_state *plane_state = container_of(kref, struct dc_plane_state, refcount);
-	destruct(plane_state);
+	dc_plane_destruct(plane_state);
 	kvfree(plane_state);
 }
 
@@ -262,7 +256,6 @@ alloc_fail:
 	return NULL;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 static void dc_3dlut_func_free(struct kref *kref)
 {
 	struct dc_3dlut *lut = container_of(kref, struct dc_3dlut, refcount);
@@ -296,6 +289,5 @@ void dc_3dlut_func_retain(struct dc_3dlut *lut)
 {
 	kref_get(&lut->refcount);
 }
-#endif
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 0416a17b0897..3fa85a54360f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -39,7 +39,7 @@
 #include "inc/hw/dmcu.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.2.56"
+#define DC_VER "3.2.68"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -54,6 +54,10 @@ struct dc_versions {
 	struct dmcu_version dmcu_version;
 };
 
+enum dp_protocol_version {
+	DP_VERSION_1_4,
+};
+
 enum dc_plane_type {
 	DC_PLANE_TYPE_INVALID,
 	DC_PLANE_TYPE_DCE_RGB,
@@ -112,17 +116,15 @@ struct dc_caps {
 	bool disable_dp_clk_share;
 	bool psp_setup_panel_mode;
 	bool extended_aux_timeout_support;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
+	bool dmcub_support;
 	bool hw_3d_lut;
-#endif
+	enum dp_protocol_version max_dp_protocol_version;
 	struct dc_plane_cap planes[MAX_PLANES];
 };
 
 struct dc_bug_wa {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool no_connect_phy_config;
 	bool dedcn20_305_wa;
-#endif
 	bool skip_clock_update;
 };
 
@@ -155,11 +157,14 @@ struct dc_surface_dcc_cap {
 	bool const_color_support;
 };
 
-struct dc_static_screen_events {
-	bool force_trigger;
-	bool cursor_update;
-	bool surface_update;
-	bool overlay_update;
+struct dc_static_screen_params {
+	struct {
+		bool force_trigger;
+		bool cursor_update;
+		bool surface_update;
+		bool overlay_update;
+	} triggers;
+	unsigned int num_frames;
 };
 
 
@@ -363,10 +368,10 @@ struct dc_debug_options {
 	bool disable_dfs_bypass;
 	bool disable_dpp_power_gate;
 	bool disable_hubp_power_gate;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool disable_dsc_power_gate;
 	int dsc_min_slice_height_override;
-#endif
+	int dsc_bpp_increment_div;
+	bool native422_support;
 	bool disable_pplib_wm_range;
 	enum wm_report_mode pplib_wm_report_mode;
 	unsigned int min_disp_clk_khz;
@@ -401,22 +406,25 @@ struct dc_debug_options {
 	unsigned int force_odm_combine; //bit vector based on otg inst
 	unsigned int force_fclk_khz;
 	bool disable_tri_buf;
+	bool dmub_offload_enabled;
+	bool dmcub_emulation;
+	bool dmub_command_table; /* for testing only */
 	struct dc_bw_validation_profile bw_val_profile;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool disable_fec;
-#endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	bool disable_48mhz_pwrdwn;
-#endif
 	/* This forces a hard min on the DCFCLK requested to SMU/PP
 	 * watermarks are not affected.
 	 */
 	unsigned int force_min_dcfclk_mhz;
 	bool disable_timing_sync;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool cm_in_bypass;
-#endif
 	int force_clock_mode;/*every mode change.*/
+
+	bool nv12_iflip_vm_wa;
+	bool disable_dram_clock_change_vactive_support;
+	bool validate_dml_output;
+	bool enable_dmcub_surface_flip;
+	bool usbc_combo_phy_reset_wa;
 };
 
 struct dc_debug_data {
@@ -425,7 +433,6 @@ struct dc_debug_data {
 	uint32_t auxErrorCount;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 struct dc_phy_addr_space_config {
 	struct {
 		uint64_t start_addr;
@@ -455,7 +462,6 @@ struct dc_virtual_addr_space_config {
 	uint32_t	page_table_block_size_in_bytes;
 	uint8_t		page_table_depth; // 1 = 1 level, 2 = 2 level, etc.  0 = invalid
 };
-#endif
 
 struct dc_bounding_box_overrides {
 	int sr_exit_time_ns;
@@ -483,9 +489,7 @@ struct dc {
 	struct dc_bounding_box_overrides bb_overrides;
 	struct dc_bug_wa work_arounds;
 	struct dc_context *ctx;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct dc_phy_addr_space_config vm_pa_config;
-#endif
 
 	uint8_t link_count;
 	struct dc_link *links[MAX_PIPES * 2];
@@ -501,7 +505,7 @@ struct dc {
 	/* Inputs into BW and WM calculations. */
 	struct bw_calcs_dceip *bw_dceip;
 	struct bw_calcs_vbios *bw_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 	struct display_mode_lib dml;
@@ -515,7 +519,7 @@ struct dc {
 	bool optimized_required;
 
 	/* Require to maintain clocks and bandwidth for UEFI enabled HW */
-	bool optimize_seamless_boot;
+	int optimize_seamless_boot_streams;
 
 	/* FBC compressor */
 	struct compressor *fbc_compressor;
@@ -523,10 +527,8 @@ struct dc {
 	struct dc_debug_data debug_data;
 
 	const char *build_id;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct vm_helper *vm_helper;
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
-#endif
 };
 
 enum frame_buffer_mode {
@@ -558,15 +560,16 @@ struct dc_init_data {
 	struct dc_bios *vbios_override;
 	enum dce_environment dce_environment;
 
+	struct dmub_offload_funcs *dmub_if;
+	struct dc_reg_helper_state *dmub_offload;
+
 	struct dc_config flags;
 	uint32_t log_mask;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	/**
 	 * gpu_info FW provided soc bounding box struct or 0 if not
 	 * available in FW
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
-#endif
 };
 
 struct dc_callback_init {
@@ -581,11 +584,9 @@ struct dc *dc_create(const struct dc_init_data *init_params);
 void dc_hardware_init(struct dc *dc);
 
 int dc_get_vmid_use_vector(struct dc *dc);
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 void dc_setup_vm_context(struct dc *dc, struct dc_virtual_addr_space_config *va_config, int vmid);
 /* Returns the number of vmids supported */
 int dc_setup_system_context(struct dc *dc, struct dc_phy_addr_space_config *pa_config);
-#endif
 void dc_init_callbacks(struct dc *dc,
 		const struct dc_callback_init *init_params);
 void dc_deinit_callbacks(struct dc *dc);
@@ -661,7 +662,6 @@ struct dc_transfer_func {
 	};
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 union dc_3dlut_state {
 	struct {
@@ -680,12 +680,11 @@ union dc_3dlut_state {
 struct dc_3dlut {
 	struct kref refcount;
 	struct tetrahedral_params lut_3d;
-	uint32_t hdr_multiplier;
+	struct fixed31_32 hdr_multiplier;
 	bool initialized; /*remove after diag fix*/
 	union dc_3dlut_state state;
 	struct dc_context *ctx;
 };
-#endif
 /*
  * This structure is filled in by dc_surface_get_status and contains
  * the last requested address and the currently active address so the called
@@ -708,7 +707,7 @@ union surface_update_flags {
 		uint32_t horizontal_mirror_change:1;
 		uint32_t per_pixel_alpha_change:1;
 		uint32_t global_alpha_change:1;
-		uint32_t sdr_white_level:1;
+		uint32_t hdr_mult:1;
 		uint32_t rotation_change:1;
 		uint32_t swizzle_change:1;
 		uint32_t scaling_change:1;
@@ -736,9 +735,7 @@ union surface_update_flags {
 struct dc_plane_state {
 	struct dc_plane_address address;
 	struct dc_plane_flip_time time;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool triplebuffer_flips;
-#endif
 	struct scaling_taps scaling_quality;
 	struct rect src_rect;
 	struct rect dst_rect;
@@ -754,18 +751,16 @@ struct dc_plane_state {
 	struct dc_bias_and_scale *bias_and_scale;
 	struct dc_csc_transform input_csc_color_matrix;
 	struct fixed31_32 coeff_reduction_factor;
-	uint32_t sdr_white_level;
+	struct fixed31_32 hdr_mult;
 
 	// TODO: No longer used, remove
 	struct dc_hdr_static_metadata hdr_static_ctx;
 
 	enum dc_color_space color_space;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dc_3dlut *lut3d_func;
 	struct dc_transfer_func *in_shaper_func;
 	struct dc_transfer_func *blend_tf;
-#endif
 
 	enum surface_pixel_format format;
 	enum dc_rotation_angle rotation;
@@ -801,7 +796,6 @@ struct dc_plane_info {
 	enum dc_rotation_angle rotation;
 	enum plane_stereo_format stereo_format;
 	enum dc_color_space color_space;
-	unsigned int sdr_white_level;
 	bool horizontal_mirror;
 	bool visible;
 	bool per_pixel_alpha;
@@ -825,7 +819,7 @@ struct dc_surface_update {
 	const struct dc_flip_addrs *flip_addr;
 	const struct dc_plane_info *plane_info;
 	const struct dc_scaling_info *scaling_info;
-
+	struct fixed31_32 hdr_mult;
 	/* following updates require alloc/sleep/spin that is not isr safe,
 	 * null means no updates
 	 */
@@ -834,11 +828,9 @@ struct dc_surface_update {
 
 	const struct dc_csc_transform *input_csc_color_matrix;
 	const struct fixed31_32 *coeff_reduction_factor;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	const struct dc_transfer_func *func_shaper;
 	const struct dc_3dlut *lut3d_func;
 	const struct dc_transfer_func *blend_tf;
-#endif
 };
 
 /*
@@ -859,11 +851,9 @@ void dc_transfer_func_retain(struct dc_transfer_func *dc_tf);
 void dc_transfer_func_release(struct dc_transfer_func *dc_tf);
 struct dc_transfer_func *dc_create_transfer_func(void);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_3dlut *dc_create_3dlut_func(void);
 void dc_3dlut_func_release(struct dc_3dlut *lut);
 void dc_3dlut_func_retain(struct dc_3dlut *lut);
-#endif
 /*
  * This structure holds a surface address.  There could be multiple addresses
  * in cases such as Stereo 3D, Planar YUV, etc.  Other per-flip attributes such
@@ -925,6 +915,8 @@ void dc_resource_state_copy_construct_current(
 
 void dc_resource_state_destruct(struct dc_state *context);
 
+bool dc_resource_is_dsc_encoding_supported(const struct dc *dc);
+
 /*
  * TODO update to make it about validation sets
  * Set up streams and links associated to drive sinks
@@ -980,10 +972,10 @@ struct dpcd_caps {
 	bool panel_mode_edp;
 	bool dpcd_display_control_capable;
 	bool ext_receiver_cap_field_present;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	union dpcd_fec_capability fec_cap;
 	struct dpcd_dsc_capabilities dsc_caps;
-#endif
+	struct dc_lttpr_caps lttpr_caps;
+
 };
 
 #include "dc_link.h"
@@ -1004,14 +996,12 @@ struct dc_container_id {
 };
 
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct dc_sink_dsc_caps {
 	// 'true' if these are virtual DPCD's DSC caps (immediately upstream of sink in MST topology),
 	// 'false' if they are sink's DSC caps
 	bool is_virtual_dpcd_dsc;
 	struct dsc_dec_dpcd_caps dsc_dec_caps;
 };
-#endif
 
 /*
  * The sink structure contains EDID and other display device properties
@@ -1026,9 +1016,7 @@ struct dc_sink {
 	struct stereo_3d_features features_3d[TIMING_3D_FORMAT_MAX];
 	bool converter_disable_audio;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct dc_sink_dsc_caps sink_dsc_caps;
-#endif
 
 	/* private to DC core */
 	struct dc_link *link;
@@ -1086,13 +1074,12 @@ unsigned int dc_get_current_backlight_pwm(struct dc *dc);
 unsigned int dc_get_target_backlight_pwm(struct dc *dc);
 
 bool dc_is_dmcu_initialized(struct dc *dc);
+bool dc_is_hw_initialized(struct dc *dc);
 
 enum dc_status dc_set_clock(struct dc *dc, enum dc_clock_type clock_type, uint32_t clk_khz, uint32_t stepping);
 void dc_get_clock(struct dc *dc, enum dc_clock_type clock_type, struct dc_clock_config *clock_cfg);
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 /*******************************************************************************
  * DSC Interfaces
  ******************************************************************************/
 #include "dc_dsc.h"
-#endif
 #endif /* DC_INTERFACE_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
new file mode 100644
index 000000000000..59c298a6484f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -0,0 +1,134 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dc.h"
+#include "dc_dmub_srv.h"
+#include "../dmub/inc/dmub_srv.h"
+
+static void dc_dmub_srv_construct(struct dc_dmub_srv *dc_srv, struct dc *dc,
+				  struct dmub_srv *dmub)
+{
+	dc_srv->dmub = dmub;
+	dc_srv->ctx = dc->ctx;
+}
+
+struct dc_dmub_srv *dc_dmub_srv_create(struct dc *dc, struct dmub_srv *dmub)
+{
+	struct dc_dmub_srv *dc_srv =
+		kzalloc(sizeof(struct dc_dmub_srv), GFP_KERNEL);
+
+	if (dc_srv == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dc_dmub_srv_construct(dc_srv, dc, dmub);
+
+	return dc_srv;
+}
+
+void dc_dmub_srv_destroy(struct dc_dmub_srv **dmub_srv)
+{
+	if (*dmub_srv) {
+		kfree(*dmub_srv);
+		*dmub_srv = NULL;
+	}
+}
+
+void dc_dmub_srv_cmd_queue(struct dc_dmub_srv *dc_dmub_srv,
+			   struct dmub_cmd_header *cmd)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_cmd_queue(dmub, cmd);
+	if (status == DMUB_STATUS_OK)
+		return;
+
+	if (status != DMUB_STATUS_QUEUE_FULL)
+		goto error;
+
+	/* Execute and wait for queue to become empty again. */
+	dc_dmub_srv_cmd_execute(dc_dmub_srv);
+	dc_dmub_srv_wait_idle(dc_dmub_srv);
+
+	/* Requeue the command. */
+	status = dmub_srv_cmd_queue(dmub, cmd);
+	if (status == DMUB_STATUS_OK)
+		return;
+
+error:
+	DC_ERROR("Error queuing DMUB command: status=%d\n", status);
+}
+
+void dc_dmub_srv_cmd_execute(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_cmd_execute(dmub);
+	if (status != DMUB_STATUS_OK)
+		DC_ERROR("Error starting DMUB execution: status=%d\n", status);
+}
+
+void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_wait_for_idle(dmub, 100000);
+	if (status != DMUB_STATUS_OK)
+		DC_ERROR("Error waiting for DMUB idle: status=%d\n", status);
+}
+
+void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	for (;;) {
+		/* Wait up to a second for PHY init. */
+		status = dmub_srv_wait_for_phy_init(dmub, 1000000);
+		if (status == DMUB_STATUS_OK)
+			/* Initialization OK */
+			break;
+
+		DC_ERROR("DMCUB PHY init failed: status=%d\n", status);
+		ASSERT(0);
+
+		if (status != DMUB_STATUS_TIMEOUT)
+			/*
+			 * Server likely initialized or we don't have
+			 * DMCUB HW support - this won't end.
+			 */
+			break;
+
+		/* Continue spinning so we don't hang the ASIC. */
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
new file mode 100644
index 000000000000..754b6077539c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_DC_SRV_H_
+#define _DMUB_DC_SRV_H_
+
+#include "os_types.h"
+#include "../dmub/inc/dmub_cmd.h"
+
+struct dmub_srv;
+struct dmub_cmd_header;
+
+struct dc_reg_helper_state {
+	bool gather_in_progress;
+	uint32_t same_addr_count;
+	bool should_burst_write;
+	union dmub_rb_cmd cmd_data;
+	unsigned int reg_seq_count;
+};
+
+struct dc_dmub_srv {
+	struct dmub_srv *dmub;
+	struct dc_reg_helper_state reg_helper_offload;
+
+	struct dc_context *ctx;
+	void *dm;
+};
+
+void dc_dmub_srv_cmd_queue(struct dc_dmub_srv *dc_dmub_srv,
+			   struct dmub_cmd_header *cmd);
+
+void dc_dmub_srv_cmd_execute(struct dc_dmub_srv *dc_dmub_srv);
+
+void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv);
+
+void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv);
+
+#endif /* _DMUB_DC_SRV_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index ef79a686e4c2..dfe4472c9e40 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -129,9 +129,7 @@ struct dc_link_training_overrides {
 	bool *alternate_scrambler_reset;
 	bool *enhanced_framing;
 	bool *mst_enable;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool *fec_enable;
-#endif
 };
 
 union dpcd_rev {
@@ -471,13 +469,13 @@ union training_aux_rd_interval {
 /* Automated test structures */
 union test_request {
 	struct {
-	uint8_t LINK_TRAINING         :1;
-	uint8_t LINK_TEST_PATTRN      :1;
-	uint8_t EDID_READ             :1;
-	uint8_t PHY_TEST_PATTERN      :1;
-	uint8_t AUDIO_TEST_PATTERN    :1;
-	uint8_t RESERVED              :1;
-	uint8_t TEST_STEREO_3D        :1;
+	uint8_t LINK_TRAINING                :1;
+	uint8_t LINK_TEST_PATTRN             :1;
+	uint8_t EDID_READ                    :1;
+	uint8_t PHY_TEST_PATTERN             :1;
+	uint8_t RESERVED                     :1;
+	uint8_t AUDIO_TEST_PATTERN           :1;
+	uint8_t TEST_AUDIO_DISABLED_VIDEO    :1;
 	} bits;
 	uint8_t raw;
 };
@@ -524,19 +522,52 @@ union link_test_pattern {
 
 union test_misc {
 	struct dpcd_test_misc_bits {
-		unsigned char SYNC_CLOCK :1;
+		unsigned char SYNC_CLOCK  :1;
 		/* dpcd_test_color_format */
-		unsigned char CLR_FORMAT :2;
+		unsigned char CLR_FORMAT  :2;
 		/* dpcd_test_dyn_range */
-		unsigned char DYN_RANGE  :1;
-		unsigned char YCBCR      :1;
+		unsigned char DYN_RANGE   :1;
+		unsigned char YCBCR_COEFS :1;
 		/* dpcd_test_bit_depth */
-		unsigned char BPC        :3;
+		unsigned char BPC         :3;
 	} bits;
 	unsigned char raw;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+union audio_test_mode {
+	struct {
+		unsigned char sampling_rate   :4;
+		unsigned char channel_count   :4;
+	} bits;
+	unsigned char raw;
+};
+
+union audio_test_pattern_period {
+	struct {
+		unsigned char pattern_period   :4;
+		unsigned char reserved         :4;
+	} bits;
+	unsigned char raw;
+};
+
+struct audio_test_pattern_type {
+	unsigned char value;
+};
+
+struct dp_audio_test_data_flags {
+	uint8_t test_requested  :1;
+	uint8_t disable_video   :1;
+};
+
+struct dp_audio_test_data {
+
+	struct dp_audio_test_data_flags flags;
+	uint8_t sampling_rate;
+	uint8_t channel_count;
+	uint8_t pattern_type;
+	uint8_t pattern_period[8];
+};
+
 /* FEC capability DPCD register field bits-*/
 union dpcd_fec_capability {
 	struct {
@@ -661,6 +692,5 @@ struct dpcd_dsc_capabilities {
 	union dpcd_dsc_ext_capabilities dsc_ext_caps;
 };
 
-#endif /* CONFIG_DRM_AMD_DC_DSC_SUPPORT */
 
 #endif /* DC_DP_TYPES_H */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
index 0ed2962add5a..3800340a5b4f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
@@ -1,4 +1,3 @@
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #ifndef DC_DSC_H_
 #define DC_DSC_H_
 /*
@@ -42,21 +41,28 @@ struct dc_dsc_bw_range {
 
 struct display_stream_compressor {
 	const struct dsc_funcs *funcs;
-#ifndef AMD_EDID_UTILITY
 	struct dc_context *ctx;
 	int inst;
-#endif
 };
 
-bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data,
+struct dc_dsc_policy {
+	bool use_min_slices_h;
+	int max_slices_h; // Maximum available if 0
+	int min_slice_height; // Must not be less than 8
+	uint32_t max_target_bpp;
+	uint32_t min_target_bpp;
+};
+
+bool dc_dsc_parse_dsc_dpcd(const struct dc *dc,
+		const uint8_t *dpcd_dsc_basic_data,
 		const uint8_t *dpcd_dsc_ext_data,
 		struct dsc_dec_dpcd_caps *dsc_sink_caps);
 
 bool dc_dsc_compute_bandwidth_range(
 		const struct display_stream_compressor *dsc,
 		const uint32_t dsc_min_slice_height_override,
-		const uint32_t min_kbps,
-		const uint32_t max_kbps,
+		const uint32_t min_bpp,
+		const uint32_t max_bpp,
 		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
 		const struct dc_crtc_timing *timing,
 		struct dc_dsc_bw_range *range);
@@ -68,5 +74,10 @@ bool dc_dsc_compute_config(
 		uint32_t target_bandwidth_kbps,
 		const struct dc_crtc_timing *timing,
 		struct dc_dsc_config *dsc_cfg);
-#endif
+
+void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing,
+		struct dc_dsc_policy *policy);
+
+void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index 30b2f9edd42f..737048d8a96c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -32,6 +32,74 @@
 #include "dm_services.h"
 #include <stdarg.h>
 
+#include "dc.h"
+#include "dc_dmub_srv.h"
+
+static inline void submit_dmub_read_modify_write(
+	struct dc_reg_helper_state *offload,
+	const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_read_modify_write *cmd_buf = &offload->cmd_data.read_modify_write;
+	bool gather = false;
+
+	offload->should_burst_write =
+			(offload->same_addr_count == (DMUB_READ_MODIFY_WRITE_SEQ__MAX - 1));
+	cmd_buf->header.payload_bytes =
+			sizeof(struct dmub_cmd_read_modify_write_sequence) * offload->reg_seq_count;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+
+	offload->reg_seq_count = 0;
+	offload->same_addr_count = 0;
+}
+
+static inline void submit_dmub_burst_write(
+	struct dc_reg_helper_state *offload,
+	const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_burst_write *cmd_buf = &offload->cmd_data.burst_write;
+	bool gather = false;
+
+	cmd_buf->header.payload_bytes =
+			sizeof(uint32_t) * offload->reg_seq_count;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+
+	offload->reg_seq_count = 0;
+}
+
+static inline void submit_dmub_reg_wait(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait;
+	bool gather = false;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+	offload->reg_seq_count = 0;
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+}
+
 struct dc_reg_value_masks {
 	uint32_t value;
 	uint32_t mask;
@@ -77,6 +145,100 @@ static void set_reg_field_values(struct dc_reg_value_masks *field_value_mask,
 	}
 }
 
+static void dmub_flush_buffer_execute(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	submit_dmub_read_modify_write(offload, ctx);
+	dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+}
+
+static void dmub_flush_burst_write_buffer_execute(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	submit_dmub_burst_write(offload, ctx);
+	dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+}
+
+static bool dmub_reg_value_burst_set_pack(const struct dc_context *ctx, uint32_t addr,
+		uint32_t reg_val)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_burst_write *cmd_buf = &offload->cmd_data.burst_write;
+
+	/* flush command if buffer is full */
+	if (offload->reg_seq_count == DMUB_BURST_WRITE_VALUES__MAX)
+		dmub_flush_burst_write_buffer_execute(offload, ctx);
+
+	if (offload->cmd_data.cmd_common.header.type == DMUB_CMD__REG_SEQ_BURST_WRITE &&
+			addr != cmd_buf->addr) {
+		dmub_flush_burst_write_buffer_execute(offload, ctx);
+		return false;
+	}
+
+	cmd_buf->header.type = DMUB_CMD__REG_SEQ_BURST_WRITE;
+	cmd_buf->header.sub_type = 0;
+	cmd_buf->addr = addr;
+	cmd_buf->write_values[offload->reg_seq_count] = reg_val;
+	offload->reg_seq_count++;
+
+	return true;
+}
+
+static uint32_t dmub_reg_value_pack(const struct dc_context *ctx, uint32_t addr,
+		struct dc_reg_value_masks *field_value_mask)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_read_modify_write *cmd_buf = &offload->cmd_data.read_modify_write;
+	struct dmub_cmd_read_modify_write_sequence *seq;
+
+	/* flush command if buffer is full */
+	if (offload->cmd_data.cmd_common.header.type != DMUB_CMD__REG_SEQ_BURST_WRITE &&
+			offload->reg_seq_count == DMUB_READ_MODIFY_WRITE_SEQ__MAX)
+		dmub_flush_buffer_execute(offload, ctx);
+
+	if (offload->should_burst_write) {
+		if (dmub_reg_value_burst_set_pack(ctx, addr, field_value_mask->value))
+			return field_value_mask->value;
+		else
+			offload->should_burst_write = false;
+	}
+
+	/* pack commands */
+	cmd_buf->header.type = DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE;
+	cmd_buf->header.sub_type = 0;
+	seq = &cmd_buf->seq[offload->reg_seq_count];
+
+	if (offload->reg_seq_count) {
+		if (cmd_buf->seq[offload->reg_seq_count - 1].addr == addr)
+			offload->same_addr_count++;
+		else
+			offload->same_addr_count = 0;
+	}
+
+	seq->addr = addr;
+	seq->modify_mask = field_value_mask->mask;
+	seq->modify_value = field_value_mask->value;
+	offload->reg_seq_count++;
+
+	return field_value_mask->value;
+}
+
+static void dmub_reg_wait_done_pack(const struct dc_context *ctx, uint32_t addr,
+		uint32_t mask, uint32_t shift, uint32_t condition_value, uint32_t time_out_us)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait;
+
+	cmd_buf->header.type = DMUB_CMD__REG_REG_WAIT;
+	cmd_buf->header.sub_type = 0;
+	cmd_buf->reg_wait.addr = addr;
+	cmd_buf->reg_wait.condition_field_value = mask & (condition_value << shift);
+	cmd_buf->reg_wait.mask = mask;
+	cmd_buf->reg_wait.time_out_us = time_out_us;
+}
+
 uint32_t generic_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr, int n,
 		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
@@ -93,6 +255,11 @@ uint32_t generic_reg_update_ex(const struct dc_context *ctx,
 
 	va_end(ap);
 
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress)
+		return dmub_reg_value_pack(ctx, addr, &field_value_mask);
+		/* todo: return void so we can decouple code running in driver from register states */
+
 	/* mmio write directly */
 	reg_val = dm_read_reg(ctx, addr);
 	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
@@ -118,6 +285,13 @@ uint32_t generic_reg_set_ex(const struct dc_context *ctx,
 
 	/* mmio write directly */
 	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		return dmub_reg_value_burst_set_pack(ctx, addr, reg_val);
+		/* todo: return void so we can decouple code running in driver from register states */
+	}
+
 	dm_write_reg(ctx, addr, reg_val);
 	return reg_val;
 }
@@ -134,6 +308,14 @@ uint32_t dm_read_reg_func(
 		return 0;
 	}
 #endif
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress &&
+	    !ctx->dmub_srv->reg_helper_offload.should_burst_write) {
+		ASSERT(false);
+		return 0;
+	}
+
 	value = cgs_read_register(ctx->cgs_device, address);
 	trace_amdgpu_dc_rreg(&ctx->perf_trace->read_count, address, value);
 
@@ -299,7 +481,19 @@ void generic_reg_wait(const struct dc_context *ctx,
 	uint32_t reg_val;
 	int i;
 
-	/* something is terribly wrong if time out is > 200ms. (5Hz) */
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		dmub_reg_wait_done_pack(ctx, addr, mask, shift, condition_value,
+				delay_between_poll_us * time_out_num_tries);
+		return;
+	}
+
+	/*
+	 * Something is terribly wrong if time out is > 3000ms.
+	 * 3000ms is the maximum time needed for SMU to pass values back.
+	 * This value comes from experiments.
+	 *
+	 */
 	ASSERT(delay_between_poll_us * time_out_num_tries <= 3000000);
 
 	for (i = 0; i <= time_out_num_tries; i++) {
@@ -346,12 +540,48 @@ uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
 {
 	uint32_t value = 0;
 
+	// when reg read, there should not be any offload.
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		ASSERT(false);
+	}
+
 	dm_write_reg(ctx, addr_index, index);
 	value = dm_read_reg(ctx, addr_data);
 
 	return value;
 }
 
+uint32_t generic_indirect_reg_get(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		...)
+{
+	uint32_t shift, mask, *field_value;
+	uint32_t value = 0;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	value = generic_read_indirect_reg(ctx, addr_index, addr_data, index);
+	*field_value1 = get_reg_field_value_ex(value, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t *);
+
+		*field_value = get_reg_field_value_ex(value, mask, shift);
+		i++;
+	}
+
+	va_end(ap);
+
+	return value;
+}
 
 uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr_index, uint32_t addr_data,
@@ -382,3 +612,68 @@ uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
 
 	return reg_val;
 }
+
+void reg_sequence_start_gather(const struct dc_context *ctx)
+{
+	/* if reg sequence is supported and enabled, set flag to
+	 * indicate we want to have REG_SET, REG_UPDATE macro build
+	 * reg sequence command buffer rather than MMIO directly.
+	 */
+
+	if (ctx->dmub_srv && ctx->dc->debug.dmub_offload_enabled) {
+		struct dc_reg_helper_state *offload =
+			&ctx->dmub_srv->reg_helper_offload;
+
+		/* caller sequence mismatch.  need to debug caller.  offload will not work!!! */
+		ASSERT(!offload->gather_in_progress);
+
+		offload->gather_in_progress = true;
+	}
+}
+
+void reg_sequence_start_execute(const struct dc_context *ctx)
+{
+	struct dc_reg_helper_state *offload;
+
+	if (!ctx->dmub_srv)
+		return;
+
+	offload = &ctx->dmub_srv->reg_helper_offload;
+
+	if (offload && offload->gather_in_progress) {
+		offload->gather_in_progress = false;
+		offload->should_burst_write = false;
+		switch (offload->cmd_data.cmd_common.header.type) {
+		case DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE:
+			submit_dmub_read_modify_write(offload, ctx);
+			break;
+		case DMUB_CMD__REG_REG_WAIT:
+			submit_dmub_reg_wait(offload, ctx);
+			break;
+		case DMUB_CMD__REG_SEQ_BURST_WRITE:
+			submit_dmub_burst_write(offload, ctx);
+			break;
+		default:
+			return;
+		}
+
+		dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+	}
+}
+
+void reg_sequence_wait_done(const struct dc_context *ctx)
+{
+	/* callback to DM to poll for last submission done*/
+	struct dc_reg_helper_state *offload;
+
+	if (!ctx->dmub_srv)
+		return;
+
+	offload = &ctx->dmub_srv->reg_helper_offload;
+
+	if (offload &&
+	    ctx->dc->debug.dmub_offload_enabled &&
+	    !ctx->dc->debug.dmcub_emulation) {
+		dc_dmub_srv_wait_idle(ctx->dmub_srv);
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index e0856bb8511f..25c50bcab9e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -26,8 +26,6 @@
 #ifndef DC_HW_TYPES_H
 #define DC_HW_TYPES_H
 
-#ifndef AMD_EDID_UTILITY
-
 #include "os_types.h"
 #include "fixed31_32.h"
 #include "signal_types.h"
@@ -167,12 +165,10 @@ enum surface_pixel_format {
 	/*swaped & float*/
 	SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F,
 	/*grow graphics here if necessary */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX,
 	SURFACE_PIXEL_FORMAT_GRPH_BGR101111_FIX,
 	SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FLOAT,
 	SURFACE_PIXEL_FORMAT_GRPH_BGR101111_FLOAT,
-#endif
 	SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr =
 		SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
@@ -180,10 +176,8 @@ enum surface_pixel_format {
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb,
 		SURFACE_PIXEL_FORMAT_SUBSAMPLE_END,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	SURFACE_PIXEL_FORMAT_VIDEO_ACrYCb2101010,
 	SURFACE_PIXEL_FORMAT_VIDEO_CrYCbA1010102,
-#endif
 	SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888,
 	SURFACE_PIXEL_FORMAT_INVALID
 
@@ -222,12 +216,10 @@ enum tile_split_values {
 	DC_ROTATED_MICRO_TILING = 0x3,
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 enum tripleBuffer_enable {
 	DC_TRIPLEBUFFER_DISABLE = 0x0,
 	DC_TRIPLEBUFFER_ENABLE = 0x1,
 };
-#endif
 
 /* TODO: These values come from hardware spec. We need to readdress this
  * if they ever change.
@@ -427,13 +419,11 @@ struct dc_csc_transform {
 	bool enable_adjustment;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 struct dc_rgb_fixed {
 	struct fixed31_32 red;
 	struct fixed31_32 green;
 	struct fixed31_32 blue;
 };
-#endif
 
 struct dc_gamma {
 	struct kref refcount;
@@ -468,10 +458,8 @@ enum dc_cursor_color_format {
 	CURSOR_MODE_COLOR_1BIT_AND,
 	CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA,
 	CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED,
 	CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED
-#endif
 };
 
 /*
@@ -594,8 +582,6 @@ struct scaling_taps {
 	bool integer_scaling;
 };
 
-#endif /* AMD_EDID_UTILITY */
-
 enum dc_timing_standard {
 	DC_TIMING_STANDARD_UNDEFINED,
 	DC_TIMING_STANDARD_DMT,
@@ -626,10 +612,8 @@ enum dc_color_depth {
 	COLOR_DEPTH_121212,
 	COLOR_DEPTH_141414,
 	COLOR_DEPTH_161616,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	COLOR_DEPTH_999,
 	COLOR_DEPTH_111111,
-#endif
 	COLOR_DEPTH_COUNT
 };
 
@@ -690,9 +674,7 @@ struct dc_crtc_timing_flags {
 	 * rates less than or equal to 340Mcsc */
 	uint32_t LTE_340MCSC_SCRAMBLE:1;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	uint32_t DSC : 1; /* Use DSC with this timing */
-#endif
 };
 
 enum dc_timing_3d_format {
@@ -717,7 +699,6 @@ enum dc_timing_3d_format {
 	TIMING_3D_FORMAT_MAX,
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct dc_dsc_config {
 	uint32_t num_slices_h; /* Number of DSC slices - horizontal */
 	uint32_t num_slices_v; /* Number of DSC slices - vertical */
@@ -728,7 +709,6 @@ struct dc_dsc_config {
 	bool ycbcr422_simple; /* Tell DSC engine to convert YCbCr 4:2:2 to 'YCbCr 4:2:2 simple'. */
 	int32_t rc_buffer_size; /* DSC RC buffer block size in bytes */
 };
-#endif
 struct dc_crtc_timing {
 	uint32_t h_total;
 	uint32_t h_border_left;
@@ -755,13 +735,9 @@ struct dc_crtc_timing {
 	enum scanning_type scan_type;
 
 	struct dc_crtc_timing_flags flags;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct dc_dsc_config dsc_cfg;
-#endif
 };
 
-#ifndef AMD_EDID_UTILITY
-
 enum trigger_delay {
 	TRIGGER_DELAY_NEXT_PIXEL = 0,
 	TRIGGER_DELAY_NEXT_LINE,
@@ -796,7 +772,6 @@ enum vram_type {
 	VIDEO_MEMORY_TYPE_GDDR6  = 6,
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 enum dwb_cnv_out_bpc {
 	DWB_CNV_OUT_BPC_8BPC  = 0,
 	DWB_CNV_OUT_BPC_10BPC = 1,
@@ -847,7 +822,6 @@ struct mcif_buf_params {
 	unsigned int		swlock;
 };
 
-#endif
 
 #define MAX_TG_COLOR_VALUE 0x3FF
 struct tg_color {
@@ -857,7 +831,5 @@ struct tg_color {
 	uint16_t color_b_cb;
 };
 
-#endif /* AMD_EDID_UTILITY */
-
 #endif /* DC_HW_TYPES_H */
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index f24fd19ed93d..d25603128394 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -29,13 +29,11 @@
 #include "dc_types.h"
 #include "grph_object_defs.h"
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 enum dc_link_fec_state {
 	dc_link_fec_not_ready,
 	dc_link_fec_ready,
 	dc_link_fec_enabled
 };
-#endif
 struct dc_link_status {
 	bool link_active;
 	struct dpcd_caps *dpcd_caps;
@@ -85,6 +83,7 @@ struct dc_link {
 	bool link_state_valid;
 	bool aux_access_disabled;
 	bool sync_lt_in_progress;
+	bool is_lttpr_mode_transparent;
 
 	/* caps is the same as reported_link_cap. link_traing use
 	 * reported_link_cap. Will clean up.  TODO
@@ -95,6 +94,7 @@ struct dc_link {
 	struct dc_lane_settings cur_lane_setting;
 	struct dc_link_settings preferred_link_setting;
 	struct dc_link_training_overrides preferred_training_settings;
+	struct dp_audio_test_data audio_test_data;
 
 	uint8_t ddc_hw_inst;
 
@@ -133,6 +133,7 @@ struct dc_link {
 	struct link_flags {
 		bool dp_keep_receiver_powered;
 		bool dp_skip_DID2;
+		bool dp_skip_reset_segment;
 	} wa_flags;
 	struct link_mst_stream_allocation_table mst_stream_alloc_table;
 
@@ -140,9 +141,7 @@ struct dc_link {
 
 	struct link_trace link_trace;
 	struct gpio *hpd_gpio;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	enum dc_link_fec_state fec_state;
-#endif
 };
 
 const struct dc_link_status *dc_link_get_status(const struct dc_link *dc_link);
@@ -206,6 +205,7 @@ enum dc_detect_reason {
 bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
 bool dc_link_get_hpd_state(struct dc_link *dc_link);
 enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx);
+enum dc_status dc_link_reallocate_mst_payload(struct dc_link *link);
 
 /* Notify DC about DP RX Interrupt (aka Short Pulse Interrupt).
  * Return:
@@ -259,6 +259,7 @@ void dc_link_dp_disable_hpd(const struct dc_link *link);
 bool dc_link_dp_set_test_pattern(
 	struct dc_link *link,
 	enum dp_test_pattern test_pattern,
+	enum dp_test_pattern_color_space test_pattern_color_space,
 	const struct link_training_settings *p_link_settings,
 	const unsigned char *p_custom_pattern,
 	unsigned int cust_pattern_size);
@@ -290,6 +291,7 @@ void dc_link_enable_hpd(const struct dc_link *link);
 void dc_link_disable_hpd(const struct dc_link *link);
 void dc_link_set_test_pattern(struct dc_link *link,
 			enum dp_test_pattern test_pattern,
+			enum dp_test_pattern_color_space test_pattern_color_space,
 			const struct link_training_settings *p_link_settings,
 			const unsigned char *p_custom_pattern,
 			unsigned int cust_pattern_size);
@@ -300,11 +302,18 @@ uint32_t dc_link_bandwidth_kbps(
 const struct dc_link_settings *dc_link_get_link_cap(
 		const struct dc_link *link);
 
+void dc_link_overwrite_extended_receiver_cap(
+		struct dc_link *link);
+
 bool dc_submit_i2c(
 		struct dc *dc,
 		uint32_t link_index,
 		struct i2c_command *cmd);
 
+bool dc_submit_i2c_oem(
+		struct dc *dc,
+		struct i2c_command *cmd);
+
 uint32_t dc_bandwidth_in_kbps_from_timing(
 	const struct dc_crtc_timing *timing);
 #endif /* DC_LINK_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index fdb6adc37857..92096de79dec 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -52,7 +52,6 @@ struct freesync_context {
 	bool dummy;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 enum hubp_dmdata_mode {
 	DMDATA_SW_MODE,
 	DMDATA_HW_MODE
@@ -82,9 +81,7 @@ struct dc_dmdata_attributes {
 	/* An unbounded array of uint32s, represents software dmdata to be loaded */
 	uint32_t *dmdata_sw_data;
 };
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_writeback_info {
 	bool wb_enabled;
 	int dwb_pipe_inst;
@@ -96,7 +93,6 @@ struct dc_writeback_update {
 	unsigned int num_wb_info;
 	struct dc_writeback_info writeback_info[MAX_DWB_PIPES];
 };
-#endif
 
 enum vertical_interrupt_ref_point {
 	START_V_UPDATE = 0,
@@ -121,9 +117,7 @@ union stream_update_flags {
 		uint32_t abm_level:1;
 		uint32_t dpms_off:1;
 		uint32_t gamut_remap:1;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		uint32_t wb_update:1;
-#endif
 	} bits;
 
 	uint32_t raw;
@@ -164,6 +158,7 @@ struct dc_stream_state {
 
 	enum view_3d_format view_format;
 
+	bool use_vsc_sdp_for_colorimetry;
 	bool ignore_msa_timing_param;
 	bool converter_disable_audio;
 	uint8_t qs_bit;
@@ -203,11 +198,9 @@ struct dc_stream_state {
 
 	struct crtc_trigger_info triggered_crtc_reset;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* writeback */
 	unsigned int num_wb_info;
 	struct dc_writeback_info writeback_info[MAX_DWB_PIPES];
-#endif
 	/* Computed state bits */
 	bool mode_changed : 1;
 
@@ -226,9 +219,7 @@ struct dc_stream_state {
 	bool apply_seamless_boot_optimization;
 
 	uint32_t stream_id;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool is_dsc_enabled;
-#endif
 	union stream_update_flags update_flags;
 };
 
@@ -251,6 +242,7 @@ struct dc_stream_update {
 	struct dc_info_packet *vsp_infopacket;
 
 	bool *dpms_off;
+	bool integer_scaling_update;
 
 	struct colorspace_transform *gamut_remap;
 	enum dc_color_space *output_color_space;
@@ -258,12 +250,8 @@ struct dc_stream_update {
 
 	struct dc_csc_transform *output_csc_transform;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dc_writeback_update *wb_update;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 	struct dc_dsc_config *dsc_config;
-#endif
 };
 
 bool dc_is_stream_unchanged(
@@ -353,18 +341,23 @@ bool dc_add_all_planes_for_stream(
 		int plane_count,
 		struct dc_state *context);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dc_stream_add_writeback(struct dc *dc,
 		struct dc_stream_state *stream,
 		struct dc_writeback_info *wb_info);
+
 bool dc_stream_remove_writeback(struct dc *dc,
 		struct dc_stream_state *stream,
 		uint32_t dwb_pipe_inst);
+
+bool dc_stream_warmup_writeback(struct dc *dc,
+		int num_dwb,
+		struct dc_writeback_info *wb_info);
+
 bool dc_stream_dmdata_status_done(struct dc *dc, struct dc_stream_state *stream);
+
 bool dc_stream_set_dynamic_metadata(struct dc *dc,
 		struct dc_stream_state *stream,
 		struct dc_dmdata_attributes *dmdata_attr);
-#endif
 
 enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream);
 
@@ -446,10 +439,10 @@ bool dc_stream_get_crc(struct dc *dc,
 		       uint32_t *g_y,
 		       uint32_t *b_cb);
 
-void dc_stream_set_static_screen_events(struct dc *dc,
+void dc_stream_set_static_screen_params(struct dc *dc,
 					struct dc_stream_state **stream,
 					int num_streams,
-					const struct dc_static_screen_events *events);
+					const struct dc_static_screen_params *params);
 
 void dc_stream_set_dyn_expansion(struct dc *dc, struct dc_stream_state *stream,
 		enum dc_dynamic_expansion option);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index d9be8fc3889f..e59532d98cb4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -25,7 +25,6 @@
 #ifndef DC_TYPES_H_
 #define DC_TYPES_H_
 
-#ifndef AMD_EDID_UTILITY
 /* AND EdidUtility only needs a portion
  * of this file, including the rest only
  * causes additional issues.
@@ -48,6 +47,7 @@ struct dc_stream_state;
 struct dc_link;
 struct dc_sink;
 struct dal;
+struct dc_dmub_srv;
 
 /********************************
  * Environment definitions
@@ -60,7 +60,12 @@ enum dce_environment {
 	DCE_ENV_FPGA_MAXIMUS,
 	/* Emulation on real HW or on FPGA. Used by Diagnostics, enforces
 	 * requirements of Diagnostics team. */
-	DCE_ENV_DIAG
+	DCE_ENV_DIAG,
+	/*
+	 * Guest VM system, DC HW may exist but is not virtualized and
+	 * should not be used.  SW support for VDI only.
+	 */
+	DCE_ENV_VIRTUAL_HW
 };
 
 /* Note: use these macro definitions instead of direct comparison! */
@@ -109,6 +114,8 @@ struct dc_context {
 	uint32_t dc_sink_id_count;
 	uint32_t dc_stream_id_count;
 	uint64_t fbc_gpu_addr;
+	struct dc_dmub_srv *dmub_srv;
+
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 	struct cp_psp cp_psp;
 #endif
@@ -119,6 +126,7 @@ struct dc_context {
 #define DC_EDID_BLOCK_SIZE 128
 #define MAX_SURFACE_NUM 4
 #define NUM_PIXEL_FORMATS 10
+#define MAX_REPEATER_CNT 8
 
 #include "dc_ddc_types.h"
 
@@ -221,6 +229,7 @@ struct dc_panel_patch {
 	unsigned int extra_t12_ms;
 	unsigned int extra_delay_backlight_off;
 	unsigned int extra_t7_ms;
+	unsigned int manage_secondary_link;
 };
 
 struct dc_edid_caps {
@@ -402,6 +411,30 @@ enum dpcd_downstream_port_max_bpc {
 	DOWN_STREAM_MAX_12BPC,
 	DOWN_STREAM_MAX_16BPC
 };
+
+
+enum link_training_offset {
+	DPRX                = 0,
+	LTTPR_PHY_REPEATER1 = 1,
+	LTTPR_PHY_REPEATER2 = 2,
+	LTTPR_PHY_REPEATER3 = 3,
+	LTTPR_PHY_REPEATER4 = 4,
+	LTTPR_PHY_REPEATER5 = 5,
+	LTTPR_PHY_REPEATER6 = 6,
+	LTTPR_PHY_REPEATER7 = 7,
+	LTTPR_PHY_REPEATER8 = 8
+};
+
+struct dc_lttpr_caps {
+	union dpcd_rev revision;
+	uint8_t mode;
+	uint8_t max_lane_count;
+	uint8_t max_link_rate;
+	uint8_t phy_repeater_cnt;
+	uint8_t max_ext_timeout;
+	uint8_t aux_rd_interval[MAX_REPEATER_CNT - 1];
+};
+
 struct dc_dongle_caps {
 	/* dongle type (DP converter, CV smart dongle) */
 	enum display_dongle_type dongle_type;
@@ -440,7 +473,6 @@ enum display_content_type {
 	DISPLAY_CONTENT_TYPE_GAME = 8
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 /* writeback */
 struct dwb_stereo_params {
 	bool				stereo_enabled;		/* false: normal mode, true: 3D stereo */
@@ -471,7 +503,6 @@ struct dc_dwb_params {
 	enum dwb_subsample_position	subsample_position;
 	struct dc_transfer_func *out_transfer_func;
 };
-#endif
 
 /* audio*/
 
@@ -573,15 +604,17 @@ struct audio_info {
 	/* this field must be last in this struct */
 	struct audio_mode modes[DC_MAX_AUDIO_DESC_COUNT];
 };
-
+struct audio_check {
+	unsigned int audio_packet_type;
+	unsigned int max_audiosample_rate;
+	unsigned int acat;
+};
 enum dc_infoframe_type {
 	DC_HDMI_INFOFRAME_TYPE_VENDOR = 0x81,
 	DC_HDMI_INFOFRAME_TYPE_AVI = 0x82,
 	DC_HDMI_INFOFRAME_TYPE_SPD = 0x83,
 	DC_HDMI_INFOFRAME_TYPE_AUDIO = 0x84,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	DC_DP_INFOFRAME_TYPE_PPS = 0x10,
-#endif
 };
 
 struct dc_info_packet {
@@ -696,7 +729,7 @@ struct psr_context {
 	/* The VSync rate in Hz used to calculate the
 	 * step size for smooth brightness feature
 	 */
-	unsigned int vsyncRateHz;
+	unsigned int vsync_rate_hz;
 	unsigned int skipPsrWaitForPllLock;
 	unsigned int numberOfControllers;
 	/* Unused, for future use. To indicate that first changed frame from
@@ -757,10 +790,6 @@ struct dc_clock_config {
 	uint32_t current_clock_khz;/*current clock in use*/
 };
 
-#endif /*AMD_EDID_UTILITY*/
-//AMD EDID UTILITY does not need any of the above structures
-
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* DSC DPCD capabilities */
 union dsc_slice_caps1 {
 	struct {
@@ -830,6 +859,5 @@ struct dsc_dec_dpcd_caps {
 	uint32_t branch_overall_throughput_1_mps; /* In MPs */
 	uint32_t branch_max_line_width;
 };
-#endif
 
 #endif /* DC_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
index 7ba7e6f722f6..ba0caaffa24b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
@@ -67,7 +67,6 @@
 	SRI(DC_ABM1_HGLS_REG_READ_PROGRESS, ABM, id), \
 	NBIO_SR(BIOS_SCRATCH_2)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define ABM_DCN20_REG_LIST() \
 	ABM_COMMON_REG_LIST_DCE_BASE(), \
 	SR(DC_ABM1_HG_SAMPLE_RATE), \
@@ -81,7 +80,6 @@
 	SR(DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES), \
 	SR(DC_ABM1_HGLS_REG_READ_PROGRESS), \
 	NBIO_SR(BIOS_SCRATCH_2)
-#endif
 
 #define ABM_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
@@ -163,9 +161,7 @@
 	ABM_SF(ABM0_DC_ABM1_HGLS_REG_READ_PROGRESS, \
 			ABM1_BL_REG_READ_MISSED_FRAME_CLEAR, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define ABM_MASK_SH_LIST_DCN20(mask_sh) ABM_MASK_SH_LIST_DCE110(mask_sh)
-#endif
 
 #define ABM_REG_FIELD_LIST(type) \
 	type ABM1_HG_NUM_OF_BINS_SEL; \
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index 793c0cec407f..f1a5d2c6aa37 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -60,12 +60,14 @@ enum {
 	AUX_DEFER_RETRY_COUNTER = 6
 };
 
-#define TIME_OUT_INCREMENT      1016
-#define TIME_OUT_MULTIPLIER_8 	8
-#define TIME_OUT_MULTIPLIER_16  16
-#define TIME_OUT_MULTIPLIER_32  32
-#define TIME_OUT_MULTIPLIER_64  64
-#define MAX_TIMEOUT_LENGTH      127
+#define TIME_OUT_INCREMENT        1016
+#define TIME_OUT_MULTIPLIER_8     8
+#define TIME_OUT_MULTIPLIER_16    16
+#define TIME_OUT_MULTIPLIER_32    32
+#define TIME_OUT_MULTIPLIER_64    64
+#define MAX_TIMEOUT_LENGTH        127
+#define DEFAULT_AUX_ENGINE_MULT   0
+#define DEFAULT_AUX_ENGINE_LENGTH 69
 
 static void release_engine(
 	struct dce_aux *engine)
@@ -427,11 +429,14 @@ void dce110_engine_destroy(struct dce_aux **engine)
 
 }
 
-static bool dce_aux_configure_timeout(struct ddc_service *ddc,
+static uint32_t dce_aux_configure_timeout(struct ddc_service *ddc,
 		uint32_t timeout_in_us)
 {
 	uint32_t multiplier = 0;
 	uint32_t length = 0;
+	uint32_t prev_length = 0;
+	uint32_t prev_mult = 0;
+	uint32_t prev_timeout_val = 0;
 	struct ddc *ddc_pin = ddc->ddc_pin;
 	struct dce_aux *aux_engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
 	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(aux_engine);
@@ -440,7 +445,10 @@ static bool dce_aux_configure_timeout(struct ddc_service *ddc,
 	aux110->polling_timeout_period = timeout_in_us * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER;
 
 	/* 2-Update aux timeout period length and multiplier */
-	if (timeout_in_us <= TIME_OUT_INCREMENT) {
+	if (timeout_in_us == 0) {
+		multiplier = DEFAULT_AUX_ENGINE_MULT;
+		length = DEFAULT_AUX_ENGINE_LENGTH;
+	} else if (timeout_in_us <= TIME_OUT_INCREMENT) {
 		multiplier = 0;
 		length = timeout_in_us/TIME_OUT_MULTIPLIER_8;
 		if (timeout_in_us % TIME_OUT_MULTIPLIER_8 != 0)
@@ -464,9 +472,29 @@ static bool dce_aux_configure_timeout(struct ddc_service *ddc,
 
 	length = (length < MAX_TIMEOUT_LENGTH) ? length : MAX_TIMEOUT_LENGTH;
 
+	REG_GET_2(AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN, &prev_length, AUX_RX_TIMEOUT_LEN_MUL, &prev_mult);
+
+	switch (prev_mult) {
+	case 0:
+		prev_timeout_val = prev_length * TIME_OUT_MULTIPLIER_8;
+		break;
+	case 1:
+		prev_timeout_val = prev_length * TIME_OUT_MULTIPLIER_16;
+		break;
+	case 2:
+		prev_timeout_val = prev_length * TIME_OUT_MULTIPLIER_32;
+		break;
+	case 3:
+		prev_timeout_val = prev_length * TIME_OUT_MULTIPLIER_64;
+		break;
+	default:
+		prev_timeout_val = DEFAULT_AUX_ENGINE_LENGTH * TIME_OUT_MULTIPLIER_8;
+		break;
+	}
+
 	REG_UPDATE_SEQ_2(AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN, length, AUX_RX_TIMEOUT_LEN_MUL, multiplier);
 
-	return true;
+	return prev_timeout_val;
 }
 
 static struct dce_aux_funcs aux_functions = {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
index b4b2c79a8073..382465862f29 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -30,7 +30,6 @@
 #include "inc/hw/aux_engine.h"
 
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define AUX_COMMON_REG_LIST0(id)\
 	SRI(AUX_CONTROL, DP_AUX, id), \
 	SRI(AUX_ARB_CONTROL, DP_AUX, id), \
@@ -39,7 +38,6 @@
 	SRI(AUX_INTERRUPT_CONTROL, DP_AUX, id), \
 	SRI(AUX_DPHY_RX_CONTROL1, DP_AUX, id), \
 	SRI(AUX_SW_STATUS, DP_AUX, id)
-#endif
 
 #define AUX_COMMON_REG_LIST(id)\
 	SRI(AUX_CONTROL, DP_AUX, id), \
@@ -311,7 +309,7 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 		struct aux_payload *cmd);
 
 struct dce_aux_funcs {
-	bool (*configure_timeout)
+	uint32_t (*configure_timeout)
 		(struct ddc_service *ddc,
 		 uint32_t timeout);
 	void (*destroy)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index f787a6b94781..2e992fbc0d71 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -905,7 +905,7 @@ static bool dce112_program_pix_clk(
 	struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source);
 	struct bp_pixel_clock_parameters bp_pc_params = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (IS_FPGA_MAXIMUS_DC(clock_source->ctx->dce_environment)) {
 		unsigned int inst = pix_clk_params->controller_id - CONTROLLER_ID_D0;
 		unsigned dp_dto_ref_100hz = 7000000;
@@ -1004,7 +1004,6 @@ static bool get_pixel_clk_frequency_100hz(
 	return false;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 /* this table is use to find *1.001 and /1.001 pixel rates from non-precise pixel rate */
 struct pixel_rate_range_table_entry {
@@ -1064,7 +1063,6 @@ static const struct clock_source_funcs dcn20_clk_src_funcs = {
 	.get_pix_clk_dividers = dce112_get_pix_clk_dividers,
 	.get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz
 };
-#endif
 
 /*****************************************/
 /* Constructor                           */
@@ -1435,7 +1433,6 @@ bool dce112_clk_src_construct(
 	return true;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dcn20_clk_src_construct(
 	struct dce110_clk_src *clk_src,
 	struct dc_context *ctx,
@@ -1451,4 +1448,3 @@ bool dcn20_clk_src_construct(
 
 	return ret;
 }
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
index 43c1bf60b83c..51bd25079606 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
@@ -55,7 +55,6 @@
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_DCCG_DEEP_COLOR_CNTL, mask_sh),\
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_PIXCLK_DOUBLE_RATE_ENABLE, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define CS_COMMON_REG_LIST_DCN2_0(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
 		SRII(PHASE, DP_DTO, 0),\
@@ -76,9 +75,7 @@
 		SRII(PIXEL_RATE_CNTL, OTG, 3),\
 		SRII(PIXEL_RATE_CNTL, OTG, 4),\
 		SRII(PIXEL_RATE_CNTL, OTG, 5)
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define CS_COMMON_REG_LIST_DCN2_1(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
 		SRII(PHASE, DP_DTO, 0),\
@@ -93,17 +90,14 @@
 		SRII(PIXEL_RATE_CNTL, OTG, 1),\
 		SRII(PIXEL_RATE_CNTL, OTG, 2),\
 		SRII(PIXEL_RATE_CNTL, OTG, 3)
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define CS_COMMON_MASK_SH_LIST_DCN2_0(mask_sh)\
 	CS_SF(DP_DTO0_PHASE, DP_DTO0_PHASE, mask_sh),\
 	CS_SF(DP_DTO0_MODULO, DP_DTO0_MODULO, mask_sh),\
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_DCCG_DEEP_COLOR_CNTL, mask_sh),\
 	CS_SF(OTG0_PIXEL_RATE_CNTL, DP_DTO0_ENABLE, mask_sh)
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 
 #define CS_COMMON_REG_LIST_DCN1_0(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
@@ -201,7 +195,6 @@ bool dce112_clk_src_construct(
 	const struct dce110_clk_src_shift *cs_shift,
 	const struct dce110_clk_src_mask *cs_mask);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dcn20_clk_src_construct(
 	struct dce110_clk_src *clk_src,
 	struct dc_context *ctx,
@@ -210,6 +203,5 @@ bool dcn20_clk_src_construct(
 	const struct dce110_clk_src_regs *regs,
 	const struct dce110_clk_src_shift *cs_shift,
 	const struct dce110_clk_src_mask *cs_mask);
-#endif
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
index ba995d3f2318..30d953acd016 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -59,6 +59,12 @@
 #define MCP_BL_SET_PWM_FRAC 0x6A  /* Enable or disable Fractional PWM */
 #define MASTER_COMM_CNTL_REG__MASTER_COMM_INTERRUPT_MASK   0x00000001L
 
+// PSP FW version
+#define mmMP0_SMN_C2PMSG_58				0x1607A
+
+//Register access policy version
+#define mmMP0_SMN_C2PMSG_91				0x1609B
+
 static bool dce_dmcu_init(struct dmcu *dmcu)
 {
 	// Do nothing
@@ -318,7 +324,7 @@ static void dce_get_psr_wait_loop(
 	return;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 static void dcn10_get_dmcu_version(struct dmcu *dmcu)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
@@ -373,6 +379,7 @@ static bool dcn10_dmcu_init(struct dmcu *dmcu)
 	const struct dc_config *config = &dmcu->ctx->dc->config;
 	bool status = false;
 
+	PERF_TRACE();
 	/*  Definition of DC_DMCU_SCRATCH
 	 *  0 : firmare not loaded
 	 *  1 : PSP load DMCU FW but not initialized
@@ -429,9 +436,21 @@ static bool dcn10_dmcu_init(struct dmcu *dmcu)
 		break;
 	}
 
+	PERF_TRACE();
 	return status;
 }
 
+static bool dcn21_dmcu_init(struct dmcu *dmcu)
+{
+	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
+	uint32_t dmcub_psp_version = REG_READ(DMCUB_SCRATCH15);
+
+	if (dmcu->auto_load_dmcu && dmcub_psp_version == 0) {
+		return false;
+	}
+
+	return dcn10_dmcu_init(dmcu);
+}
 
 static bool dcn10_dmcu_load_iram(struct dmcu *dmcu,
 		unsigned int start_offset,
@@ -518,9 +537,6 @@ static void dcn10_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait)
 	if (dmcu->dmcu_state != DMCU_RUNNING)
 		return;
 
-	dcn10_get_dmcu_psr_state(dmcu, &psr_state);
-	if (psr_state == 0 && !enable)
-		return;
 	/* waitDMCUReadyForCmd */
 	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0,
 				dmcu_wait_reg_ready_interval,
@@ -727,9 +743,7 @@ static bool dcn10_is_dmcu_initialized(struct dmcu *dmcu)
 	return true;
 }
 
-#endif //(CONFIG_DRM_AMD_DC_DCN1_0)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 static bool dcn20_lock_phy(struct dmcu *dmcu)
 {
@@ -777,7 +791,7 @@ static bool dcn20_unlock_phy(struct dmcu *dmcu)
 	return true;
 }
 
-#endif //(CONFIG_DRM_AMD_DC_DCN2_0)
+#endif //(CONFIG_DRM_AMD_DC_DCN)
 
 static const struct dmcu_funcs dce_funcs = {
 	.dmcu_init = dce_dmcu_init,
@@ -790,7 +804,7 @@ static const struct dmcu_funcs dce_funcs = {
 	.is_dmcu_initialized = dce_is_dmcu_initialized
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 static const struct dmcu_funcs dcn10_funcs = {
 	.dmcu_init = dcn10_dmcu_init,
 	.load_iram = dcn10_dmcu_load_iram,
@@ -801,9 +815,7 @@ static const struct dmcu_funcs dcn10_funcs = {
 	.get_psr_wait_loop = dcn10_get_psr_wait_loop,
 	.is_dmcu_initialized = dcn10_is_dmcu_initialized
 };
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 static const struct dmcu_funcs dcn20_funcs = {
 	.dmcu_init = dcn10_dmcu_init,
 	.load_iram = dcn10_dmcu_load_iram,
@@ -816,6 +828,19 @@ static const struct dmcu_funcs dcn20_funcs = {
 	.lock_phy = dcn20_lock_phy,
 	.unlock_phy = dcn20_unlock_phy
 };
+
+static const struct dmcu_funcs dcn21_funcs = {
+	.dmcu_init = dcn21_dmcu_init,
+	.load_iram = dcn10_dmcu_load_iram,
+	.set_psr_enable = dcn10_dmcu_set_psr_enable,
+	.setup_psr = dcn10_dmcu_setup_psr,
+	.get_psr_state = dcn10_get_dmcu_psr_state,
+	.set_psr_wait_loop = dcn10_psr_wait_loop,
+	.get_psr_wait_loop = dcn10_get_psr_wait_loop,
+	.is_dmcu_initialized = dcn10_is_dmcu_initialized,
+	.lock_phy = dcn20_lock_phy,
+	.unlock_phy = dcn20_unlock_phy
+};
 #endif
 
 static void dce_dmcu_construct(
@@ -836,6 +861,26 @@ static void dce_dmcu_construct(
 	dmcu_dce->dmcu_mask = dmcu_mask;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static void dcn21_dmcu_construct(
+		struct dce_dmcu *dmcu_dce,
+		struct dc_context *ctx,
+		const struct dce_dmcu_registers *regs,
+		const struct dce_dmcu_shift *dmcu_shift,
+		const struct dce_dmcu_mask *dmcu_mask)
+{
+	uint32_t psp_version = 0;
+
+	dce_dmcu_construct(dmcu_dce, ctx, regs, dmcu_shift, dmcu_mask);
+
+	if (!IS_FPGA_MAXIMUS_DC(ctx->dce_environment)) {
+		psp_version = dm_read_reg(ctx, mmMP0_SMN_C2PMSG_58);
+		dmcu_dce->base.auto_load_dmcu = ((psp_version & 0x00FF00FF) > 0x00110029);
+		dmcu_dce->base.psp_version = psp_version;
+	}
+}
+#endif
+
 struct dmcu *dce_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
@@ -857,7 +902,7 @@ struct dmcu *dce_dmcu_create(
 	return &dmcu_dce->base;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 struct dmcu *dcn10_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
@@ -878,9 +923,7 @@ struct dmcu *dcn10_dmcu_create(
 
 	return &dmcu_dce->base;
 }
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dmcu *dcn20_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
@@ -901,6 +944,27 @@ struct dmcu *dcn20_dmcu_create(
 
 	return &dmcu_dce->base;
 }
+
+struct dmcu *dcn21_dmcu_create(
+	struct dc_context *ctx,
+	const struct dce_dmcu_registers *regs,
+	const struct dce_dmcu_shift *dmcu_shift,
+	const struct dce_dmcu_mask *dmcu_mask)
+{
+	struct dce_dmcu *dmcu_dce = kzalloc(sizeof(*dmcu_dce), GFP_KERNEL);
+
+	if (dmcu_dce == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dcn21_dmcu_construct(
+		dmcu_dce, ctx, regs, dmcu_shift, dmcu_mask);
+
+	dmcu_dce->base.funcs = &dcn21_funcs;
+
+	return &dmcu_dce->base;
+}
 #endif
 
 void dce_dmcu_destroy(struct dmcu **dmcu)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
index cc8587683b4b..5e044c2d3d6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
@@ -71,6 +71,10 @@
 	DMCU_COMMON_REG_LIST_DCE_BASE(), \
 	SR(DMU_MEM_PWR_CNTL)
 
+#define DMCU_DCN20_REG_LIST()\
+	DMCU_DCN10_REG_LIST(), \
+	SR(DMCUB_SCRATCH15)
+
 #define DMCU_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
@@ -175,6 +179,7 @@ struct dce_dmcu_registers {
 	uint32_t DMCU_INTERRUPT_TO_UC_EN_MASK;
 	uint32_t SMU_INTERRUPT_CONTROL;
 	uint32_t DC_DMCU_SCRATCH;
+	uint32_t DMCUB_SCRATCH15;
 };
 
 struct dce_dmcu {
@@ -261,13 +266,17 @@ struct dmcu *dcn10_dmcu_create(
 	const struct dce_dmcu_shift *dmcu_shift,
 	const struct dce_dmcu_mask *dmcu_mask);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dmcu *dcn20_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
 	const struct dce_dmcu_shift *dmcu_shift,
 	const struct dce_dmcu_mask *dmcu_mask);
-#endif
+
+struct dmcu *dcn21_dmcu_create(
+	struct dc_context *ctx,
+	const struct dce_dmcu_registers *regs,
+	const struct dce_dmcu_shift *dmcu_shift,
+	const struct dce_dmcu_mask *dmcu_mask);
 
 void dce_dmcu_destroy(struct dmcu **dmcu);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
index 0275d6d60da4..e1c5839a80dc 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
@@ -25,7 +25,7 @@
 
 #include "dce_hwseq.h"
 #include "reg_helper.h"
-#include "hw_sequencer.h"
+#include "hw_sequencer_private.h"
 #include "core_types.h"
 
 #define CTX \
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index 32d145a0d6fc..c5aa1f48593a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -25,7 +25,7 @@
 #ifndef __DCE_HWSEQ_H__
 #define __DCE_HWSEQ_H__
 
-#include "hw_sequencer.h"
+#include "dc_types.h"
 
 #define BL_REG_LIST()\
 	SR(LVTMA_PWRSEQ_CNTL), \
@@ -210,7 +210,6 @@
 	SR(DC_IP_REQUEST_CNTL), \
 	BL_REG_LIST()
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define HWSEQ_DCN2_REG_LIST()\
 	HWSEQ_DCN_REG_LIST(), \
 	HSWEQ_DCN_PIXEL_RATE_REG_LIST(OTG, 0), \
@@ -276,9 +275,7 @@
 	SR(D6VGA_CONTROL), \
 	SR(DC_IP_REQUEST_CNTL), \
 	BL_REG_LIST()
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define HWSEQ_DCN21_REG_LIST()\
 	HWSEQ_DCN_REG_LIST(), \
 	HSWEQ_DCN_PIXEL_RATE_REG_LIST(OTG, 0), \
@@ -329,7 +326,6 @@
 	SR(D6VGA_CONTROL), \
 	SR(DC_IP_REQUEST_CNTL), \
 	BL_REG_LIST()
-#endif
 
 struct dce_hwseq_registers {
 
@@ -577,7 +573,6 @@ struct dce_hwseq_registers {
 	HWS_SF(, VGA_TEST_CONTROL, VGA_TEST_RENDER_START, mask_sh),\
 	HWSEQ_LVTMA_MASK_SH_LIST(mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define HWSEQ_DCN2_MASK_SH_LIST(mask_sh)\
 	HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
 	HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \
@@ -637,9 +632,7 @@ struct dce_hwseq_registers {
 	HWS_SF(, DOMAIN21_PG_STATUS, DOMAIN21_PGFSM_PWR_STATUS, mask_sh), \
 	HWS_SF(, DC_IP_REQUEST_CNTL, IP_REQUEST_EN, mask_sh), \
 	HWSEQ_LVTMA_MASK_SH_LIST(mask_sh)
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define HWSEQ_DCN21_MASK_SH_LIST(mask_sh)\
 	HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
 	HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \
@@ -682,7 +675,6 @@ struct dce_hwseq_registers {
 	HWSEQ_LVTMA_MASK_SH_LIST(mask_sh), \
 	HWS_SF(, LVTMA_PWRSEQ_CNTL, LVTMA_BLON, mask_sh), \
 	HWS_SF(, LVTMA_PWRSEQ_STATE, LVTMA_PWRSEQ_TARGET_STATE_R, mask_sh)
-#endif
 
 #define HWSEQ_REG_FIELD_LIST(type) \
 	type DCFE_CLOCK_ENABLE; \
@@ -800,8 +792,7 @@ struct dce_hwseq_registers {
 	type D2VGA_MODE_ENABLE; \
 	type D3VGA_MODE_ENABLE; \
 	type D4VGA_MODE_ENABLE; \
-	type AZALIA_AUDIO_DTO_MODULE;\
-	type HPO_HDMISTREAMCLK_GATE_DIS;
+	type AZALIA_AUDIO_DTO_MODULE;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
@@ -820,6 +811,10 @@ enum blnd_mode {
 	BLND_MODE_BLENDING,/* Alpha blending - blend 'current' and 'other' */
 };
 
+struct dce_hwseq;
+struct pipe_ctx;
+struct clock_source;
+
 void dce_enable_fe_clock(struct dce_hwseq *hwss,
 		unsigned int inst, bool enable);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c
index 35a75398fcb4..dd41736bb5c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c
@@ -31,7 +31,7 @@ bool dce_i2c_submit_command(
 	struct i2c_command *cmd)
 {
 	struct dce_i2c_hw *dce_i2c_hw;
-	struct dce_i2c_sw *dce_i2c_sw;
+	struct dce_i2c_sw dce_i2c_sw = {0};
 
 	if (!ddc) {
 		BREAK_TO_DEBUGGER();
@@ -43,18 +43,15 @@ bool dce_i2c_submit_command(
 		return false;
 	}
 
-	/* The software engine is only available on dce8 */
-	dce_i2c_sw = dce_i2c_acquire_i2c_sw_engine(pool, ddc);
-
-	if (!dce_i2c_sw) {
-		dce_i2c_hw = acquire_i2c_hw_engine(pool, ddc);
-
-		if (!dce_i2c_hw)
-			return false;
+	dce_i2c_hw = acquire_i2c_hw_engine(pool, ddc);
 
+	if (dce_i2c_hw)
 		return dce_i2c_submit_command_hw(pool, ddc, cmd, dce_i2c_hw);
-	}
 
-	return dce_i2c_submit_command_sw(pool, ddc, cmd, dce_i2c_sw);
+	dce_i2c_sw.ctx = ddc->ctx;
+	if (dce_i2c_engine_acquire_sw(&dce_i2c_sw, ddc)) {
+		return dce_i2c_submit_command_sw(pool, ddc, cmd, &dce_i2c_sw);
+	}
 
+	return false;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
index aad7b52165be..1cd4d8fc361f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
@@ -296,9 +296,7 @@ static bool setup_engine(
 	struct dce_i2c_hw *dce_i2c_hw)
 {
 	uint32_t i2c_setup_limit = I2C_SETUP_TIME_LIMIT_DCE;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t  reset_length = 0;
-#endif
 	/* we have checked I2c not used by DMCU, set SW use I2C REQ to 1 to indicate SW using it*/
 	REG_UPDATE(DC_I2C_ARBITRATION, DC_I2C_SW_USE_I2C_REG_REQ, 1);
 
@@ -322,14 +320,12 @@ static bool setup_engine(
 		REG_UPDATE_N(SETUP, 2,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), i2c_setup_limit,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	} else {
 		reset_length = dce_i2c_hw->send_reset_length;
 		REG_UPDATE_N(SETUP, 3,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), i2c_setup_limit,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_SEND_RESET_LENGTH), reset_length,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
-#endif
 	}
 	/* Program HW priority
 	 * set to High - interrupt software I2C at any time
@@ -705,7 +701,6 @@ void dcn1_i2c_hw_construct(
 	dce_i2c_hw->setup_limit = I2C_SETUP_TIME_LIMIT_DCN;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 void dcn2_i2c_hw_construct(
 	struct dce_i2c_hw *dce_i2c_hw,
 	struct dc_context *ctx,
@@ -724,4 +719,3 @@ void dcn2_i2c_hw_construct(
 	if (ctx->dc->debug.scl_reset_length10)
 		dce_i2c_hw->send_reset_length = I2C_SEND_RESET_LENGTH_10;
 }
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h
index cb0234e5d597..d4b2037f7d74 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h
@@ -177,9 +177,7 @@ struct dce_i2c_shift {
 	uint8_t DC_I2C_INDEX;
 	uint8_t DC_I2C_INDEX_WRITE;
 	uint8_t XTAL_REF_DIV;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint8_t DC_I2C_DDC1_SEND_RESET_LENGTH;
-#endif
 	uint8_t DC_I2C_REG_RW_CNTL_STATUS;
 };
 
@@ -220,17 +218,13 @@ struct dce_i2c_mask {
 	uint32_t DC_I2C_INDEX;
 	uint32_t DC_I2C_INDEX_WRITE;
 	uint32_t XTAL_REF_DIV;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t DC_I2C_DDC1_SEND_RESET_LENGTH;
-#endif
 	uint32_t DC_I2C_REG_RW_CNTL_STATUS;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define I2C_COMMON_MASK_SH_LIST_DCN2(mask_sh)\
 	I2C_COMMON_MASK_SH_LIST_DCE110(mask_sh),\
 	I2C_SF(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_SEND_RESET_LENGTH, mask_sh)
-#endif
 
 struct dce_i2c_registers {
 	uint32_t SETUP;
@@ -312,7 +306,6 @@ void dcn1_i2c_hw_construct(
 	const struct dce_i2c_shift *shifts,
 	const struct dce_i2c_mask *masks);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 void dcn2_i2c_hw_construct(
 	struct dce_i2c_hw *dce_i2c_hw,
 	struct dc_context *ctx,
@@ -320,7 +313,6 @@ void dcn2_i2c_hw_construct(
 	const struct dce_i2c_registers *regs,
 	const struct dce_i2c_shift *shifts,
 	const struct dce_i2c_mask *masks);
-#endif
 
 bool dce_i2c_submit_command_hw(
 	struct resource_pool *pool,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
index a5a11c251e25..87d8428df6c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
@@ -73,31 +73,6 @@ static void release_engine_dce_sw(
 	dce_i2c_sw->ddc = NULL;
 }
 
-static bool get_hw_supported_ddc_line(
-	struct ddc *ddc,
-	enum gpio_ddc_line *line)
-{
-	enum gpio_ddc_line line_found;
-
-	*line = GPIO_DDC_LINE_UNKNOWN;
-
-	if (!ddc) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-
-	if (!ddc->hw_info.hw_supported)
-		return false;
-
-	line_found = dal_ddc_get_line(ddc);
-
-	if (line_found >= GPIO_DDC_LINE_COUNT)
-		return false;
-
-	*line = line_found;
-
-	return true;
-}
 static bool wait_for_scl_high_sw(
 	struct dc_context *ctx,
 	struct ddc *ddc,
@@ -524,21 +499,3 @@ bool dce_i2c_submit_command_sw(
 
 	return result;
 }
-struct dce_i2c_sw *dce_i2c_acquire_i2c_sw_engine(
-	struct resource_pool *pool,
-	struct ddc *ddc)
-{
-	enum gpio_ddc_line line;
-	struct dce_i2c_sw *engine = NULL;
-
-	if (get_hw_supported_ddc_line(ddc, &line))
-		engine = pool->sw_i2cs[line];
-
-	if (!engine)
-		return NULL;
-
-	if (!dce_i2c_engine_acquire_sw(engine, ddc))
-		return NULL;
-
-	return engine;
-}
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.h b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.h
index 5bbcdd455614..019fc47bb767 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.h
@@ -49,9 +49,9 @@ bool dce_i2c_submit_command_sw(
 	struct i2c_command *cmd,
 	struct dce_i2c_sw *dce_i2c_sw);
 
-struct dce_i2c_sw *dce_i2c_acquire_i2c_sw_engine(
-	struct resource_pool *pool,
-	struct ddc *ddc);
+bool dce_i2c_engine_acquire_sw(
+	struct dce_i2c_sw *dce_i2c_sw,
+	struct ddc *ddc_handle);
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index 6ed922a3c1cd..451574971b96 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -137,7 +137,7 @@ static void dce110_update_generic_info_packet(
 			AFMT_GENERIC0_UPDATE, (packet_index == 0),
 			AFMT_GENERIC2_UPDATE, (packet_index == 2));
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (REG(AFMT_VBI_PACKET_CONTROL1)) {
 		switch (packet_index) {
 		case 0:
@@ -231,7 +231,7 @@ static void dce110_update_hdmi_info_packet(
 				HDMI_GENERIC1_SEND, send,
 				HDMI_GENERIC1_LINE, line);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case 4:
 		if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 			REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL2,
@@ -275,9 +275,10 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	uint32_t h_active_start;
 	uint32_t v_active_start;
 	uint32_t misc0 = 0;
@@ -329,7 +330,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		if (enc110->se_mask->DP_VID_M_DOUBLE_VALUE_EN)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_M_DOUBLE_VALUE_EN, 1);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 		if (enc110->se_mask->DP_VID_N_MUL)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_N_MUL, 1);
 #endif
@@ -340,7 +341,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		break;
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (REG(DP_MSA_MISC))
 		misc1 = REG_READ(DP_MSA_MISC);
 #endif
@@ -374,7 +375,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	/* set dynamic range and YCbCr range */
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	switch (hw_crtc_timing.display_color_depth) {
 	case COLOR_DEPTH_666:
 		colorimetry_bpc = 0;
@@ -454,7 +455,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				DP_DYN_RANGE, dynamic_range_rgb,
 				DP_YCBCR_RANGE, dynamic_range_ycbcr);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 		if (REG(DP_MSA_COLORIMETRY))
 			REG_SET(DP_MSA_COLORIMETRY, 0, DP_MSA_MISC0, misc0);
 
@@ -489,7 +490,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				hw_crtc_timing.v_front_porch;
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 		/* start at begining of left border */
 		if (REG(DP_MSA_TIMING_PARAM2))
 			REG_SET_2(DP_MSA_TIMING_PARAM2, 0,
@@ -786,7 +787,7 @@ static void dce110_stream_encoder_update_hdmi_info_packets(
 		dce110_update_hdmi_info_packet(enc110, 3, &info_frame->hdrsmd);
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (enc110->se_mask->HDMI_DB_DISABLE) {
 		/* for bring up, disable dp double  TODO */
 		if (REG(HDMI_DB_CONTROL))
@@ -824,7 +825,7 @@ static void dce110_stream_encoder_stop_hdmi_info_packets(
 		HDMI_GENERIC1_LINE, 0,
 		HDMI_GENERIC1_SEND, 0);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	/* stop generic packets 2 & 3 on HDMI */
 	if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 		REG_SET_6(HDMI_GENERIC_PACKET_CONTROL2, 0,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
new file mode 100644
index 000000000000..225955ec6d39
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -0,0 +1,220 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dmub_psr.h"
+#include "dc.h"
+#include "dc_dmub_srv.h"
+#include "../../dmub/inc/dmub_srv.h"
+#include "dmub_fw_state.h"
+#include "core_types.h"
+#include "ipp.h"
+
+#define MAX_PIPES 6
+
+/**
+ * Get PSR state from firmware.
+ */
+static void dmub_get_psr_state(uint32_t *psr_state)
+{
+	// Not yet implemented
+	// Trigger GPINT interrupt from firmware
+}
+
+/**
+ * Enable/Disable PSR.
+ */
+static void dmub_set_psr_enable(struct dmub_psr *dmub, bool enable)
+{
+	union dmub_rb_cmd cmd;
+	struct dc_context *dc = dmub->ctx;
+
+	cmd.psr_enable.header.type = DMUB_CMD__PSR;
+
+	if (enable)
+		cmd.psr_enable.header.sub_type = DMUB_CMD__PSR_ENABLE;
+	else
+		cmd.psr_enable.header.sub_type = DMUB_CMD__PSR_DISABLE;
+
+	cmd.psr_enable.header.payload_bytes = 0; // Send header only
+
+	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_enable.header);
+	dc_dmub_srv_cmd_execute(dc->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->dmub_srv);
+}
+
+/**
+ * Set PSR level.
+ */
+static void dmub_set_psr_level(struct dmub_psr *dmub, uint16_t psr_level)
+{
+	union dmub_rb_cmd cmd;
+	uint32_t psr_state = 0;
+	struct dc_context *dc = dmub->ctx;
+
+	dmub_get_psr_state(&psr_state);
+
+	if (psr_state == 0)
+		return;
+
+	cmd.psr_set_level.header.type = DMUB_CMD__PSR;
+	cmd.psr_set_level.header.sub_type = DMUB_CMD__PSR_SET_LEVEL;
+	cmd.psr_set_level.header.payload_bytes = sizeof(struct dmub_cmd_psr_set_level_data);
+	cmd.psr_set_level.psr_set_level_data.psr_level = psr_level;
+
+	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_set_level.header);
+	dc_dmub_srv_cmd_execute(dc->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->dmub_srv);
+}
+
+/**
+ * Setup PSR by programming phy registers and sending psr hw context values to firmware.
+ */
+static bool dmub_setup_psr(struct dmub_psr *dmub,
+		struct dc_link *link,
+		struct psr_context *psr_context)
+{
+	union dmub_rb_cmd cmd;
+	struct dc_context *dc = dmub->ctx;
+	struct dmub_cmd_psr_copy_settings_data *copy_settings_data
+		= &cmd.psr_copy_settings.psr_copy_settings_data;
+	struct pipe_ctx *pipe_ctx = NULL;
+	struct resource_context *res_ctx = &link->ctx->dc->current_state->res_ctx;
+
+	for (int i = 0; i < MAX_PIPES; i++) {
+		if (res_ctx &&
+				res_ctx->pipe_ctx[i].stream &&
+				res_ctx->pipe_ctx[i].stream->link &&
+				res_ctx->pipe_ctx[i].stream->link == link &&
+				res_ctx->pipe_ctx[i].stream->link->connector_signal == SIGNAL_TYPE_EDP) {
+			pipe_ctx = &res_ctx->pipe_ctx[i];
+			break;
+		}
+	}
+
+	if (!pipe_ctx ||
+			!&pipe_ctx->plane_res ||
+			!&pipe_ctx->stream_res)
+		return false;
+
+	// Program DP DPHY fast training registers
+	link->link_enc->funcs->psr_program_dp_dphy_fast_training(link->link_enc,
+			psr_context->psrExitLinkTrainingRequired);
+
+	// Program DP_SEC_CNTL1 register to set transmission GPS0 line num and priority to high
+	link->link_enc->funcs->psr_program_secondary_packet(link->link_enc,
+			psr_context->sdpTransmitLineNumDeadline);
+
+	cmd.psr_copy_settings.header.type = DMUB_CMD__PSR;
+	cmd.psr_copy_settings.header.sub_type = DMUB_CMD__PSR_COPY_SETTINGS;
+	cmd.psr_copy_settings.header.payload_bytes = sizeof(struct dmub_cmd_psr_copy_settings_data);
+
+	// Hw insts
+	copy_settings_data->dpphy_inst				= psr_context->phyType;
+	copy_settings_data->aux_inst				= psr_context->channel;
+	copy_settings_data->digfe_inst				= psr_context->engineId;
+	copy_settings_data->digbe_inst				= psr_context->transmitterId;
+
+	copy_settings_data->mpcc_inst				= pipe_ctx->plane_res.mpcc_inst;
+
+	if (pipe_ctx->plane_res.hubp)
+		copy_settings_data->hubp_inst			= pipe_ctx->plane_res.hubp->inst;
+	else
+		copy_settings_data->hubp_inst			= 0;
+	if (pipe_ctx->plane_res.dpp)
+		copy_settings_data->dpp_inst			= pipe_ctx->plane_res.dpp->inst;
+	else
+		copy_settings_data->dpp_inst			= 0;
+	if (pipe_ctx->stream_res.opp)
+		copy_settings_data->opp_inst			= pipe_ctx->stream_res.opp->inst;
+	else
+		copy_settings_data->opp_inst			= 0;
+	if (pipe_ctx->stream_res.tg)
+		copy_settings_data->otg_inst			= pipe_ctx->stream_res.tg->inst;
+	else
+		copy_settings_data->otg_inst			= 0;
+
+	// Misc
+	copy_settings_data->psr_level				= psr_context->psr_level.u32all;
+	copy_settings_data->hyst_frames				= psr_context->timehyst_frames;
+	copy_settings_data->hyst_lines				= psr_context->hyst_lines;
+	copy_settings_data->phy_type				= psr_context->phyType;
+	copy_settings_data->aux_repeat				= psr_context->aux_repeats;
+	copy_settings_data->smu_optimizations_en	= psr_context->allow_smu_optimizations;
+	copy_settings_data->skip_wait_for_pll_lock	= psr_context->skipPsrWaitForPllLock;
+	copy_settings_data->frame_delay				= psr_context->frame_delay;
+	copy_settings_data->smu_phy_id				= psr_context->smuPhyId;
+	copy_settings_data->num_of_controllers		= psr_context->numberOfControllers;
+	copy_settings_data->frame_cap_ind			= psr_context->psrFrameCaptureIndicationReq;
+	copy_settings_data->phy_num					= psr_context->frame_delay & 0x7;
+	copy_settings_data->link_rate				= psr_context->frame_delay & 0xF;
+
+	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_copy_settings.header);
+	dc_dmub_srv_cmd_execute(dc->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->dmub_srv);
+
+	return true;
+}
+
+static const struct dmub_psr_funcs psr_funcs = {
+	.set_psr_enable			= dmub_set_psr_enable,
+	.setup_psr				= dmub_setup_psr,
+	.get_psr_state			= dmub_get_psr_state,
+	.set_psr_level			= dmub_set_psr_level,
+};
+
+/**
+ * Construct PSR object.
+ */
+static void dmub_psr_construct(struct dmub_psr *psr, struct dc_context *ctx)
+{
+	psr->ctx = ctx;
+	psr->funcs = &psr_funcs;
+}
+
+/**
+ * Allocate and initialize PSR object.
+ */
+struct dmub_psr *dmub_psr_create(struct dc_context *ctx)
+{
+	struct dmub_psr *psr = kzalloc(sizeof(struct dmub_psr), GFP_KERNEL);
+
+	if (psr == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dmub_psr_construct(psr, ctx);
+
+	return psr;
+}
+
+/**
+ * Deallocate PSR object.
+ */
+void dmub_psr_destroy(struct dmub_psr **dmub)
+{
+	kfree(dmub);
+	*dmub = NULL;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h
new file mode 100644
index 000000000000..229958de3035
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright 2012-16 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_PSR_H_
+#define _DMUB_PSR_H_
+
+#include "os_types.h"
+
+struct dmub_psr {
+	struct dc_context *ctx;
+	const struct dmub_psr_funcs *funcs;
+};
+
+struct dmub_psr_funcs {
+	void (*set_psr_enable)(struct dmub_psr *dmub, bool enable);
+	bool (*setup_psr)(struct dmub_psr *dmub, struct dc_link *link, struct psr_context *psr_context);
+	void (*get_psr_state)(uint32_t *psr_state);
+	void (*set_psr_level)(struct dmub_psr *dmub, uint16_t psr_level);
+};
+
+struct dmub_psr *dmub_psr_create(struct dc_context *ctx);
+void dmub_psr_destroy(struct dmub_psr **dmub);
+
+
+#endif /* _DCE_DMUB_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
index 799d36299c9b..753cb8edd996 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
@@ -26,7 +26,6 @@
 #include "dc.h"
 #include "core_types.h"
 #include "clk_mgr.h"
-#include "hw_sequencer.h"
 #include "dce100_hw_sequencer.h"
 #include "resource.h"
 
@@ -136,7 +135,7 @@ void dce100_hw_sequencer_construct(struct dc *dc)
 {
 	dce110_hw_sequencer_construct(dc);
 
-	dc->hwss.enable_display_power_gating = dce100_enable_display_power_gating;
+	dc->hwseq->funcs.enable_display_power_gating = dce100_enable_display_power_gating;
 	dc->hwss.prepare_bandwidth = dce100_prepare_bandwidth;
 	dc->hwss.optimize_bandwidth = dce100_optimize_bandwidth;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
index a6b80fdaa666..34518da20009 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
@@ -27,6 +27,7 @@
 #define __DC_HWSS_DCE100_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 struct dc_state;
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index a5e122c721ec..8f78bf9abbca 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -725,7 +725,7 @@ void dce100_clock_source_destroy(struct clock_source **clk_src)
 	*clk_src = NULL;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce100_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -885,7 +885,7 @@ static void dce100_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce100_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -950,7 +950,7 @@ static const struct resource_funcs dce100_res_pool_funcs = {
 	.find_first_free_match_stream_enc_for_link = dce100_find_first_free_match_stream_enc_for_link
 };
 
-static bool construct(
+static bool dce100_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc  *dc,
 	struct dce110_resource_pool *pool)
@@ -1122,7 +1122,7 @@ static bool construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce100_resource_destruct(pool);
 
 	return false;
 }
@@ -1137,7 +1137,7 @@ struct resource_pool *dce100_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(num_virtual_links, dc, pool))
+	if (dce100_resource_construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index f0e837d14000..5b689273ff44 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -61,6 +61,8 @@
 
 #include "atomfirmware.h"
 
+#define GAMMA_HW_POINTS_NUM 256
+
 /*
  * All values are in milliseconds;
  * For eDP, after power-up/power/down,
@@ -268,7 +270,7 @@ static void build_prescale_params(struct ipp_prescale_params *prescale_params,
 }
 
 static bool
-dce110_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
+dce110_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 			       const struct dc_plane_state *plane_state)
 {
 	struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp;
@@ -596,7 +598,7 @@ dce110_translate_regamma_to_hw_format(const struct dc_transfer_func *output_tf,
 }
 
 static bool
-dce110_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
+dce110_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 				const struct dc_stream_state *stream)
 {
 	struct transform *xfm = pipe_ctx->plane_res.xfm;
@@ -651,10 +653,9 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx)
 {
 	enum dc_lane_count lane_count =
 		pipe_ctx->stream->link->cur_link_settings.lane_count;
-
 	struct dc_crtc_timing *timing = &pipe_ctx->stream->timing;
 	struct dc_link *link = pipe_ctx->stream->link;
-
+	const struct dc *dc = link->dc;
 
 	uint32_t active_total_with_borders;
 	uint32_t early_control = 0;
@@ -667,7 +668,7 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx)
 	link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc,
 						    pipe_ctx->stream_res.stream_enc->id, true);
 
-	link->dc->hwss.update_info_frame(pipe_ctx);
+	dc->hwss.update_info_frame(pipe_ctx);
 
 	/* enable early control to avoid corruption on DP monitor*/
 	active_total_with_borders =
@@ -943,15 +944,15 @@ void dce110_edp_backlight_control(
 void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 {
 	/* notify audio driver for audio modes of monitor */
-	struct dc *core_dc;
+	struct dc *dc;
 	struct clk_mgr *clk_mgr;
 	unsigned int i, num_audio = 1;
 
 	if (!pipe_ctx->stream)
 		return;
 
-	core_dc = pipe_ctx->stream->ctx->dc;
-	clk_mgr = core_dc->clk_mgr;
+	dc = pipe_ctx->stream->ctx->dc;
+	clk_mgr = dc->clk_mgr;
 
 	if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == true)
 		return;
@@ -959,7 +960,7 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->stream_res.audio) {
 		for (i = 0; i < MAX_PIPES; i++) {
 			/*current_state not updated yet*/
-			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL)
+			if (dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL)
 				num_audio++;
 		}
 
@@ -1047,6 +1048,7 @@ void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
 	struct encoder_unblank_param params = { { 0 } };
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
+	struct dce_hwseq *hws = link->dc->hwseq;
 
 	/* only 3 items below are used by unblank */
 	params.timing = pipe_ctx->stream->timing;
@@ -1056,7 +1058,7 @@ void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
 		pipe_ctx->stream_res.stream_enc->funcs->dp_unblank(pipe_ctx->stream_res.stream_enc, &params);
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, true);
+		hws->funcs.edp_backlight_control(link, true);
 	}
 }
 
@@ -1064,9 +1066,10 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
+	struct dce_hwseq *hws = link->dc->hwseq;
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, false);
+		hws->funcs.edp_backlight_control(link, false);
 		dc_link_set_abm_disable(link);
 	}
 
@@ -1223,7 +1226,7 @@ static void program_scaler(const struct dc *dc,
 {
 	struct tg_color color = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	/* TOFPGA */
 	if (pipe_ctx->plane_res.xfm->funcs->transform_set_pixel_storage_depth == NULL)
 		return;
@@ -1322,12 +1325,11 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct drr_params params = {0};
 	unsigned int event_triggers = 0;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct pipe_ctx *odm_pipe = pipe_ctx->next_odm_pipe;
-#endif
+	struct dce_hwseq *hws = dc->hwseq;
 
-	if (dc->hwss.disable_stream_gating) {
-		dc->hwss.disable_stream_gating(dc, pipe_ctx);
+	if (hws->funcs.disable_stream_gating) {
+		hws->funcs.disable_stream_gating(dc, pipe_ctx);
 	}
 
 	if (pipe_ctx->stream_res.audio != NULL) {
@@ -1357,10 +1359,10 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	/*  */
 	/* Do not touch stream timing on seamless boot optimization. */
 	if (!pipe_ctx->stream->apply_seamless_boot_optimization)
-		dc->hwss.enable_stream_timing(pipe_ctx, context, dc);
+		hws->funcs.enable_stream_timing(pipe_ctx, context, dc);
 
-	if (dc->hwss.setup_vupdate_interrupt)
-		dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+	if (hws->funcs.setup_vupdate_interrupt)
+		hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;
@@ -1371,9 +1373,13 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	// DRR should set trigger event to monitor surface update event
 	if (stream->adjust.v_total_min != 0 && stream->adjust.v_total_max != 0)
 		event_triggers = 0x80;
+	/* Event triggers and num frames initialized for DRR, but can be
+	 * later updated for PSR use. Note DRR trigger events are generated
+	 * regardless of whether num frames met.
+	 */
 	if (pipe_ctx->stream_res.tg->funcs->set_static_screen_control)
 		pipe_ctx->stream_res.tg->funcs->set_static_screen_control(
-				pipe_ctx->stream_res.tg, event_triggers);
+				pipe_ctx->stream_res.tg, event_triggers, 2);
 
 	if (!dc_is_virtual_signal(pipe_ctx->stream->signal))
 		pipe_ctx->stream_res.stream_enc->funcs->dig_connect_to_otg(
@@ -1390,7 +1396,6 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 		pipe_ctx->stream_res.opp,
 		&stream->bit_depth_params,
 		&stream->clamping);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	while (odm_pipe) {
 		odm_pipe->stream_res.opp->funcs->opp_set_dyn_expansion(
 				odm_pipe->stream_res.opp,
@@ -1404,7 +1409,6 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 				&stream->clamping);
 		odm_pipe = odm_pipe->next_odm_pipe;
 	}
-#endif
 
 	if (!stream->dpms_off)
 		core_link_enable_stream(context, pipe_ctx);
@@ -1438,6 +1442,9 @@ static void power_down_encoders(struct dc *dc)
 			if (!dc->links[i]->wa_flags.dp_keep_receiver_powered)
 				dp_receiver_power_ctrl(dc->links[i], false);
 
+		if (signal != SIGNAL_TYPE_EDP)
+			signal = SIGNAL_TYPE_NONE;
+
 		dc->links[i]->link_enc->funcs->disable_output(
 				dc->links[i]->link_enc, signal);
 	}
@@ -1552,9 +1559,10 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
 	bool can_apply_edp_fast_boot = false;
 	bool can_apply_seamless_boot = false;
 	bool keep_edp_vdd_on = false;
+	struct dce_hwseq *hws = dc->hwseq;
 
-	if (dc->hwss.init_pipes)
-		dc->hwss.init_pipes(dc, context);
+	if (hws->funcs.init_pipes)
+		hws->funcs.init_pipes(dc, context);
 
 	edp_stream = get_edp_stream(context);
 
@@ -1591,7 +1599,7 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
 	if (!can_apply_edp_fast_boot && !can_apply_seamless_boot) {
 		if (edp_link_with_sink && !keep_edp_vdd_on) {
 			/*turn off backlight before DP_blank and encoder powered down*/
-			dc->hwss.edp_backlight_control(edp_link_with_sink, false);
+			hws->funcs.edp_backlight_control(edp_link_with_sink, false);
 		}
 		/*resume from S3, no vbios posting, no need to power down again*/
 		power_down_all_hw_blocks(dc);
@@ -1702,6 +1710,8 @@ static void set_drr(struct pipe_ctx **pipe_ctx,
 	struct drr_params params = {0};
 	// DRR should set trigger event to monitor surface update event
 	unsigned int event_triggers = 0x80;
+	// Note DRR trigger events are generated regardless of whether num frames met.
+	unsigned int num_frames = 2;
 
 	params.vertical_total_max = vmax;
 	params.vertical_total_min = vmin;
@@ -1717,7 +1727,7 @@ static void set_drr(struct pipe_ctx **pipe_ctx,
 		if (vmax != 0 && vmin != 0)
 			pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(
 					pipe_ctx[i]->stream_res.tg,
-					event_triggers);
+					event_triggers, num_frames);
 	}
 }
 
@@ -1734,30 +1744,31 @@ static void get_position(struct pipe_ctx **pipe_ctx,
 }
 
 static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
-		int num_pipes, const struct dc_static_screen_events *events)
+		int num_pipes, const struct dc_static_screen_params *params)
 {
 	unsigned int i;
-	unsigned int value = 0;
+	unsigned int triggers = 0;
 
-	if (events->overlay_update)
-		value |= 0x100;
-	if (events->surface_update)
-		value |= 0x80;
-	if (events->cursor_update)
-		value |= 0x2;
-	if (events->force_trigger)
-		value |= 0x1;
+	if (params->triggers.overlay_update)
+		triggers |= 0x100;
+	if (params->triggers.surface_update)
+		triggers |= 0x80;
+	if (params->triggers.cursor_update)
+		triggers |= 0x2;
+	if (params->triggers.force_trigger)
+		triggers |= 0x1;
 
 	if (num_pipes) {
 		struct dc *dc = pipe_ctx[0]->stream->ctx->dc;
 
 		if (dc->fbc_compressor)
-			value |= 0x84;
+			triggers |= 0x84;
 	}
 
 	for (i = 0; i < num_pipes; i++)
 		pipe_ctx[i]->stream_res.tg->funcs->
-			set_static_screen_control(pipe_ctx[i]->stream_res.tg, value);
+			set_static_screen_control(pipe_ctx[i]->stream_res.tg,
+					triggers, params->num_frames);
 }
 
 /*
@@ -2006,13 +2017,14 @@ enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct dc_bios *dcb = dc->ctx->dc_bios;
 	enum dc_status status;
 	int i;
 
 	/* Reset old context */
 	/* look up the targets that have been removed since last commit */
-	dc->hwss.reset_hw_ctx_wrap(dc, context);
+	hws->funcs.reset_hw_ctx_wrap(dc, context);
 
 	/* Skip applying if no targets */
 	if (context->stream_count <= 0)
@@ -2037,7 +2049,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 			continue;
 		}
 
-		dc->hwss.enable_display_power_gating(
+		hws->funcs.enable_display_power_gating(
 				dc, i, dc->ctx->dc_bios,
 				PIPE_GATING_CONTROL_DISABLE);
 	}
@@ -2346,19 +2358,20 @@ static void init_hw(struct dc *dc)
 	struct transform *xfm;
 	struct abm *abm;
 	struct dmcu *dmcu;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	bp = dc->ctx->dc_bios;
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		xfm = dc->res_pool->transforms[i];
 		xfm->funcs->transform_reset(xfm);
 
-		dc->hwss.enable_display_power_gating(
+		hws->funcs.enable_display_power_gating(
 				dc, i, bp,
 				PIPE_GATING_CONTROL_INIT);
-		dc->hwss.enable_display_power_gating(
+		hws->funcs.enable_display_power_gating(
 				dc, i, bp,
 				PIPE_GATING_CONTROL_DISABLE);
-		dc->hwss.enable_display_pipe_clock_gating(
+		hws->funcs.enable_display_pipe_clock_gating(
 			dc->ctx,
 			true);
 	}
@@ -2444,6 +2457,8 @@ static void dce110_program_front_end_for_pipe(
 	struct xfm_grph_csc_adjustment adjust;
 	struct out_csc_color_matrix tbl_entry;
 	unsigned int i;
+	struct dce_hwseq *hws = dc->hwseq;
+
 	DC_LOGGER_INIT();
 	memset(&tbl_entry, 0, sizeof(tbl_entry));
 
@@ -2502,10 +2517,10 @@ static void dce110_program_front_end_for_pipe(
 	if (pipe_ctx->plane_state->update_flags.bits.full_update ||
 			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
 			pipe_ctx->plane_state->update_flags.bits.gamma_change)
-		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+		hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state);
 
 	if (pipe_ctx->plane_state->update_flags.bits.full_update)
-		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 
 	DC_LOG_SURFACE(
 			"Pipe:%d %p: addr hi:0x%x, "
@@ -2608,6 +2623,7 @@ static void dce110_apply_ctx_for_surface(
 
 static void dce110_power_down_fe(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	int fe_idx = pipe_ctx->plane_res.mi ?
 		pipe_ctx->plane_res.mi->inst : pipe_ctx->pipe_idx;
 
@@ -2615,7 +2631,7 @@ static void dce110_power_down_fe(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	if (dc->current_state->res_ctx.pipe_ctx[fe_idx].stream)
 		return;
 
-	dc->hwss.enable_display_power_gating(
+	hws->funcs.enable_display_power_gating(
 		dc, fe_idx, dc->ctx->dc_bios, PIPE_GATING_CONTROL_ENABLE);
 
 	dc->res_pool->transforms[fe_idx]->funcs->transform_reset(
@@ -2704,14 +2720,10 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.program_gamut_remap = program_gamut_remap,
 	.program_output_csc = program_output_csc,
 	.init_hw = init_hw,
-	.init_pipes = init_pipes,
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = dce110_apply_ctx_for_surface,
 	.update_plane_addr = update_plane_addr,
 	.update_pending_status = dce110_update_pending_status,
-	.set_input_transfer_func = dce110_set_input_transfer_func,
-	.set_output_transfer_func = dce110_set_output_transfer_func,
-	.power_down = dce110_power_down,
 	.enable_accelerated_mode = dce110_enable_accelerated_mode,
 	.enable_timing_synchronization = dce110_enable_timing_synchronization,
 	.enable_per_frame_crtc_position_reset = dce110_enable_per_frame_crtc_position_reset,
@@ -2722,8 +2734,6 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.blank_stream = dce110_blank_stream,
 	.enable_audio_stream = dce110_enable_audio_stream,
 	.disable_audio_stream = dce110_disable_audio_stream,
-	.enable_display_pipe_clock_gating = enable_display_pipe_clock_gating,
-	.enable_display_power_gating = dce110_enable_display_power_gating,
 	.disable_plane = dce110_power_down_fe,
 	.pipe_control_lock = dce_pipe_control_lock,
 	.prepare_bandwidth = dce110_prepare_bandwidth,
@@ -2731,22 +2741,33 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.set_drr = set_drr,
 	.get_position = get_position,
 	.set_static_screen_control = set_static_screen_control,
-	.reset_hw_ctx_wrap = dce110_reset_hw_ctx_wrap,
-	.enable_stream_timing = dce110_enable_stream_timing,
-	.disable_stream_gating = NULL,
-	.enable_stream_gating = NULL,
 	.setup_stereo = NULL,
 	.set_avmute = dce110_set_avmute,
 	.wait_for_mpcc_disconnect = dce110_wait_for_mpcc_disconnect,
-	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dce110_set_cursor_position,
 	.set_cursor_attribute = dce110_set_cursor_attribute
 };
 
+static const struct hwseq_private_funcs dce110_private_funcs = {
+	.init_pipes = init_pipes,
+	.update_plane_addr = update_plane_addr,
+	.set_input_transfer_func = dce110_set_input_transfer_func,
+	.set_output_transfer_func = dce110_set_output_transfer_func,
+	.power_down = dce110_power_down,
+	.enable_display_pipe_clock_gating = enable_display_pipe_clock_gating,
+	.enable_display_power_gating = dce110_enable_display_power_gating,
+	.reset_hw_ctx_wrap = dce110_reset_hw_ctx_wrap,
+	.enable_stream_timing = dce110_enable_stream_timing,
+	.disable_stream_gating = NULL,
+	.enable_stream_gating = NULL,
+	.edp_backlight_control = dce110_edp_backlight_control,
+};
+
 void dce110_hw_sequencer_construct(struct dc *dc)
 {
 	dc->hwss = dce110_funcs;
+	dc->hwseq->funcs = dce110_private_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
index 2f9b7dbdf415..26a9c14a58b1 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
@@ -27,8 +27,8 @@
 #define __DC_HWSS_DCE110_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
-#define GAMMA_HW_POINTS_NUM 256
 struct dc;
 struct dc_state;
 struct dm_pp_display_configuration;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 83a4dbf6d76e..bf14e9ab040c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -782,7 +782,7 @@ void dce110_clock_source_destroy(struct clock_source **clk_src)
 	*clk_src = NULL;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce110_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -1097,6 +1097,7 @@ static struct pipe_ctx *dce110_acquire_underlay(
 		struct dc_stream_state *stream)
 {
 	struct dc *dc = stream->ctx->dc;
+	struct dce_hwseq *hws = dc->hwseq;
 	struct resource_context *res_ctx = &context->res_ctx;
 	unsigned int underlay_idx = pool->underlay_pipe_index;
 	struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[underlay_idx];
@@ -1117,7 +1118,7 @@ static struct pipe_ctx *dce110_acquire_underlay(
 		struct tg_color black_color = {0};
 		struct dc_bios *dcb = dc->ctx->dc_bios;
 
-		dc->hwss.enable_display_power_gating(
+		hws->funcs.enable_display_power_gating(
 				dc,
 				pipe_ctx->stream_res.tg->inst,
 				dcb, PIPE_GATING_CONTROL_DISABLE);
@@ -1161,7 +1162,7 @@ static void dce110_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce110_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -1313,7 +1314,7 @@ const struct resource_caps *dce110_resource_cap(
 		return &carrizo_resource_cap;
 }
 
-static bool construct(
+static bool dce110_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dce110_resource_pool *pool,
@@ -1492,7 +1493,7 @@ static bool construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce110_resource_destruct(pool);
 	return false;
 }
 
@@ -1507,7 +1508,7 @@ struct resource_pool *dce110_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(num_virtual_links, dc, pool, asic_id))
+	if (dce110_resource_construct(num_virtual_links, dc, pool, asic_id))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
index 5f7c2c5641c4..1ea7db8eeb98 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
@@ -469,22 +469,27 @@ void dce110_timing_generator_set_drr(
 
 void dce110_timing_generator_set_static_screen_control(
 	struct timing_generator *tg,
-	uint32_t value)
+	uint32_t event_triggers,
+	uint32_t num_frames)
 {
 	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
 	uint32_t static_screen_cntl = 0;
 	uint32_t addr = 0;
 
+	// By register spec, it only takes 8 bit value
+	if (num_frames > 0xFF)
+		num_frames = 0xFF;
+
 	addr = CRTC_REG(mmCRTC_STATIC_SCREEN_CONTROL);
 	static_screen_cntl = dm_read_reg(tg->ctx, addr);
 
 	set_reg_field_value(static_screen_cntl,
-				value,
+				event_triggers,
 				CRTC_STATIC_SCREEN_CONTROL,
 				CRTC_STATIC_SCREEN_EVENT_MASK);
 
 	set_reg_field_value(static_screen_cntl,
-				2,
+				num_frames,
 				CRTC_STATIC_SCREEN_CONTROL,
 				CRTC_STATIC_SCREEN_FRAME_COUNT);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
index 768ccf27ada9..d8a5ed7b485d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
@@ -231,7 +231,8 @@ void dce110_timing_generator_set_drr(
 
 void dce110_timing_generator_set_static_screen_control(
 	struct timing_generator *tg,
-	uint32_t value);
+	uint32_t event_triggers,
+	uint32_t num_frames);
 
 void dce110_timing_generator_get_crtc_scanoutpos(
 	struct timing_generator *tg,
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.c
index 1e4a7c13f0ed..19873ee1f78d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.c
@@ -158,6 +158,6 @@ void dce112_hw_sequencer_construct(struct dc *dc)
 	 * structure
 	 */
 	dce110_hw_sequencer_construct(dc);
-	dc->hwss.enable_display_power_gating = dce112_enable_display_power_gating;
+	dc->hwseq->funcs.enable_display_power_gating = dce112_enable_display_power_gating;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.h
index e646f4a37fa2..943f1b2c5b2f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.h
@@ -27,6 +27,7 @@
 #define __DC_HWSS_DCE112_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 97dcc5d0862b..700ad8b3e54b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -744,7 +744,7 @@ void dce112_clock_source_destroy(struct clock_source **clk_src)
 	*clk_src = NULL;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce112_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -1013,7 +1013,7 @@ static void dce112_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce112_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -1186,7 +1186,7 @@ const struct resource_caps *dce112_resource_cap(
 		return &polaris_10_resource_cap;
 }
 
-static bool construct(
+static bool dce112_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dce110_resource_pool *pool)
@@ -1372,7 +1372,7 @@ static bool construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce112_resource_destruct(pool);
 	return false;
 }
 
@@ -1386,7 +1386,7 @@ struct resource_pool *dce112_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(num_virtual_links, dc, pool))
+	if (dce112_resource_construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
index 1ca30928025e..66a13aa39c95 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
@@ -265,7 +265,7 @@ void dce120_hw_sequencer_construct(struct dc *dc)
 	 * structure
 	 */
 	dce110_hw_sequencer_construct(dc);
-	dc->hwss.enable_display_power_gating = dce120_enable_display_power_gating;
+	dc->hwseq->funcs.enable_display_power_gating = dce120_enable_display_power_gating;
 	dc->hwss.update_dchub = dce120_update_dchub;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.h
index c51afbd0b012..bc024534732f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.h
@@ -27,6 +27,7 @@
 #define __DC_HWSS_DCE120_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 63543f6918ff..53ab88ef71f5 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -63,8 +63,8 @@
 #include "soc15_hw_ip.h"
 #include "vega10_ip_offset.h"
 #include "nbio/nbio_6_1_offset.h"
-#include "mmhub/mmhub_9_4_0_offset.h"
-#include "mmhub/mmhub_9_4_0_sh_mask.h"
+#include "mmhub/mmhub_1_0_offset.h"
+#include "mmhub/mmhub_1_0_sh_mask.h"
 #include "reg_helper.h"
 
 #include "dce100/dce100_resource.h"
@@ -587,7 +587,7 @@ static void dce120_transform_destroy(struct transform **xfm)
 	*xfm = NULL;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce120_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -872,7 +872,7 @@ static void dce120_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce120_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -1024,7 +1024,7 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
 	return value;
 }
 
-static bool construct(
+static bool dce120_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dce110_resource_pool *pool)
@@ -1237,7 +1237,7 @@ controller_create_fail:
 clk_src_create_fail:
 res_create_fail:
 
-	destruct(pool);
+	dce120_resource_destruct(pool);
 
 	return false;
 }
@@ -1252,7 +1252,7 @@ struct resource_pool *dce120_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(num_virtual_links, dc, pool))
+	if (dce120_resource_construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
index 098e56962f2a..82bc4e192bbf 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
@@ -819,13 +819,18 @@ void dce120_tg_set_colors(struct timing_generator *tg,
 
 static void dce120_timing_generator_set_static_screen_control(
 	struct timing_generator *tg,
-	uint32_t value)
+	uint32_t event_triggers,
+	uint32_t num_frames)
 {
 	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
 
+	// By register spec, it only takes 8 bit value
+	if (num_frames > 0xFF)
+		num_frames = 0xFF;
+
 	CRTC_REG_UPDATE_2(CRTC0_CRTC_STATIC_SCREEN_CONTROL,
-			CRTC_STATIC_SCREEN_EVENT_MASK, value,
-			CRTC_STATIC_SCREEN_FRAME_COUNT, 2);
+			CRTC_STATIC_SCREEN_EVENT_MASK, event_triggers,
+			CRTC_STATIC_SCREEN_FRAME_COUNT, num_frames);
 }
 
 void dce120_timing_generator_set_test_pattern(
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
index c4543178ba20..893261c81854 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
@@ -74,7 +74,7 @@ void dce80_hw_sequencer_construct(struct dc *dc)
 {
 	dce110_hw_sequencer_construct(dc);
 
-	dc->hwss.enable_display_power_gating = dce100_enable_display_power_gating;
+	dc->hwseq->funcs.enable_display_power_gating = dce100_enable_display_power_gating;
 	dc->hwss.pipe_control_lock = dce_pipe_control_lock;
 	dc->hwss.prepare_bandwidth = dce100_prepare_bandwidth;
 	dc->hwss.optimize_bandwidth = dce100_optimize_bandwidth;
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.h
index 7a1b31def66f..e43af832d00c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.h
@@ -27,6 +27,7 @@
 #define __DC_HWSS_DCE80_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 3e8d4b49f279..2ad5c28c6e66 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -773,7 +773,7 @@ static struct input_pixel_processor *dce80_ipp_create(
 	return &ipp->base;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce80_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -901,7 +901,7 @@ static void dce80_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce80_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -1093,7 +1093,7 @@ static bool dce80_construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce80_resource_destruct(pool);
 	return false;
 }
 
@@ -1290,7 +1290,7 @@ static bool dce81_construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce80_resource_destruct(pool);
 	return false;
 }
 
@@ -1483,7 +1483,7 @@ static bool dce83_construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce80_resource_destruct(pool);
 	return false;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
index 032f872be89c..62ad1a11bff9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
@@ -22,7 +22,8 @@
 #
 # Makefile for DCN.
 
-DCN10 = dcn10_resource.o dcn10_ipp.o dcn10_hw_sequencer.o dcn10_hw_sequencer_debug.o \
+DCN10 = dcn10_init.o dcn10_resource.o dcn10_ipp.o dcn10_hw_sequencer.o \
+		dcn10_hw_sequencer_debug.o \
 		dcn10_dpp.o dcn10_opp.o dcn10_optc.o \
 		dcn10_hubp.o dcn10_mpc.o \
 		dcn10_dpp_dscl.o dcn10_dpp_cm.o dcn10_cm_common.o \
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index 997e9582edc7..0e682b5aa3eb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -290,12 +290,8 @@ void dpp1_cnv_setup (
 		enum surface_pixel_format format,
 		enum expansion_mode mode,
 		struct dc_csc_transform input_csc_color_matrix,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		enum dc_color_space input_color_space,
 		struct cnv_alpha_2bit_lut *alpha_2bit_lut)
-#else
-		enum dc_color_space input_color_space)
-#endif
 {
 	uint32_t pixel_format;
 	uint32_t alpha_en;
@@ -542,11 +538,9 @@ static const struct dpp_funcs dcn10_dpp_funcs = {
 		.set_optional_cursor_attributes = dpp1_cnv_set_optional_cursor_attributes,
 		.dpp_dppclk_control = dpp1_dppclk_control,
 		.dpp_set_hdr_multiplier = dpp1_set_hdr_multiplier,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		.dpp_program_blnd_lut = NULL,
 		.dpp_program_shaper_lut = NULL,
 		.dpp_program_3dlut = NULL
-#endif
 };
 
 static struct dpp_caps dcn10_dpp_cap = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
index 1d4a7d640334..2edf566b3a72 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
@@ -1486,12 +1486,8 @@ void dpp1_cnv_setup (
 		enum surface_pixel_format format,
 		enum expansion_mode mode,
 		struct dc_csc_transform input_csc_color_matrix,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		enum dc_color_space input_color_space,
 		struct cnv_alpha_2bit_lut *alpha_2bit_lut);
-#else
-		enum dc_color_space input_color_space);
-#endif
 
 void dpp1_full_bypass(struct dpp *dpp_base);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
index aa0c7a7d13a0..4d3f7d5e1473 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
@@ -88,26 +88,6 @@ enum dscl_mode_sel {
 	DSCL_MODE_DSCL_BYPASS = 6
 };
 
-static const struct dpp_input_csc_matrix dpp_input_csc_matrix[] = {
-	{COLOR_SPACE_SRGB,
-		{0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
-	{COLOR_SPACE_SRGB_LIMITED,
-		{0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
-	{COLOR_SPACE_YCBCR601,
-		{0x2cdd, 0x2000, 0, 0xe991, 0xe926, 0x2000, 0xf4fd, 0x10ef,
-						0, 0x2000, 0x38b4, 0xe3a6} },
-	{COLOR_SPACE_YCBCR601_LIMITED,
-		{0x3353, 0x2568, 0, 0xe400, 0xe5dc, 0x2568, 0xf367, 0x1108,
-						0, 0x2568, 0x40de, 0xdd3a} },
-	{COLOR_SPACE_YCBCR709,
-		{0x3265, 0x2000, 0, 0xe6ce, 0xf105, 0x2000, 0xfa01, 0xa7d, 0,
-						0x2000, 0x3b61, 0xe24f} },
-
-	{COLOR_SPACE_YCBCR709_LIMITED,
-		{0x39a6, 0x2568, 0, 0xe0d6, 0xeedd, 0x2568, 0xf925, 0x9a8, 0,
-						0x2568, 0x43ee, 0xdbb2} }
-};
-
 static void program_gamut_remap(
 		struct dcn10_dpp *dpp,
 		const uint16_t *regval,
@@ -352,6 +332,8 @@ void dpp1_cm_program_regamma_lut(struct dpp *dpp_base,
 	uint32_t i;
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
 
+	REG_SEQ_START();
+
 	for (i = 0 ; i < num; i++) {
 		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].red_reg);
 		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].green_reg);
@@ -626,10 +608,16 @@ void dpp1_set_degamma(
 	case IPP_DEGAMMA_MODE_HW_xvYCC:
 		REG_UPDATE(CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, 2);
 			break;
+	case IPP_DEGAMMA_MODE_USER_PWL:
+		REG_UPDATE(CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, 3);
+		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
 	}
+
+	REG_SEQ_SUBMIT();
+	REG_SEQ_WAIT_DONE();
 }
 
 void dpp1_degamma_ram_select(
@@ -731,10 +719,8 @@ void dpp1_full_bypass(struct dpp *dpp_base)
 	/* COLOR_KEYER_CONTROL.COLOR_KEYER_EN = 0 this should be default */
 	if (dpp->tf_mask->CM_BYPASS_EN)
 		REG_SET(CM_CONTROL, 0, CM_BYPASS_EN, 1);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	else
 		REG_SET(CM_CONTROL, 0, CM_BYPASS, 1);
-#endif
 
 	/* Setting degamma bypass for now */
 	REG_SET(CM_DGAM_CONTROL, 0, CM_DGAM_LUT_MODE, 0);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index d67e0abeee93..fce37c527a0b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -218,14 +218,12 @@ static void dpp1_dscl_set_lb(
 			INTERLEAVE_EN, lb_params->interleave_en, /* Interleave source enable */
 			LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	else {
 		/* DSCL caps: pixel data processed in float format */
 		REG_SET_2(LB_DATA_FORMAT, 0,
 			INTERLEAVE_EN, lb_params->interleave_en, /* Interleave source enable */
 			LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */
 	}
-#endif
 
 	REG_SET_2(LB_MEMORY_CTRL, 0,
 		MEMORY_CONFIG, mem_size_config,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.c
index 374cc9acda3b..b6391a5ead78 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.c
@@ -23,7 +23,7 @@
  *
  */
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 
 #include "reg_helper.h"
 #include "resource.h"
@@ -109,9 +109,7 @@ const struct dwbc_funcs dcn10_dwbc_funcs = {
 	.update				= NULL,
 	.set_stereo			= NULL,
 	.set_new_content		= NULL,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	.set_warmup			= NULL,
-#endif
 	.dwb_set_scaler			= NULL,
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.h
index c175edd0bae7..d56ea7c8171e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.h
@@ -24,7 +24,7 @@
 #ifndef __DC_DWBC_DCN10_H__
 #define __DC_DWBC_DCN10_H__
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 
 /* DCN */
 #define BASE_INNER(seg) \
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index a02c10e23e0d..f36a0d8cedfe 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -930,6 +930,9 @@ static bool hubbub1_get_dcc_compression_cap(struct hubbub *hubbub,
 		output->grph.rgb.max_compressed_blk_size = 64;
 		output->grph.rgb.independent_64b_blks = true;
 		break;
+	default:
+		ASSERT(false);
+		break;
 	}
 
 	output->capable = true;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
index 69d903d68661..af57751253de 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -121,7 +121,6 @@ struct dcn_hubbub_registers {
 	uint32_t DCN_VM_AGP_BASE;
 	uint32_t DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_MSB;
 	uint32_t DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_A;
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_B;
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_C;
@@ -140,7 +139,6 @@ struct dcn_hubbub_registers {
 	uint32_t DCHVM_CLK_CTRL;
 	uint32_t DCHVM_RIOMMU_CTRL0;
 	uint32_t DCHVM_RIOMMU_STAT0;
-#endif
 };
 
 /* set field name */
@@ -232,7 +230,6 @@ struct dcn_hubbub_registers {
 		type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C;\
 		type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define HUBBUB_HVM_REG_FIELD_LIST(type) \
 		type DCHUBBUB_ARB_MIN_REQ_OUTSTAND_COMMIT_THRESHOLD;\
 		type DCHUBBUB_ARB_VM_ROW_URGENCY_WATERMARK_A;\
@@ -278,22 +275,17 @@ struct dcn_hubbub_registers {
 		type HOSTVM_POWERSTATUS; \
 		type RIOMMU_ACTIVE; \
 		type HOSTVM_PREFETCH_DONE
-#endif
 
 struct dcn_hubbub_shift {
 	DCN_HUBBUB_REG_FIELD_LIST(uint8_t);
 	HUBBUB_STUTTER_REG_FIELD_LIST(uint8_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	HUBBUB_HVM_REG_FIELD_LIST(uint8_t);
-#endif
 };
 
 struct dcn_hubbub_mask {
 	DCN_HUBBUB_REG_FIELD_LIST(uint32_t);
 	HUBBUB_STUTTER_REG_FIELD_LIST(uint32_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	HUBBUB_HVM_REG_FIELD_LIST(uint32_t);
-#endif
 };
 
 struct dc;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 14d1be6c66e6..31b64733d693 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -306,7 +306,6 @@ void hubp1_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 12);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX:
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 112);
@@ -327,7 +326,6 @@ void hubp1_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 119);
 		break;
-#endif
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
@@ -1014,6 +1012,9 @@ void hubp1_read_state_common(struct hubp *hubp)
 			HUBP_TTU_DISABLE, &s->ttu_disable,
 			HUBP_UNDERFLOW_STATUS, &s->underflow_status);
 
+	REG_GET(HUBP_CLK_CNTL,
+			HUBP_CLOCK_ENABLE, &s->clock_en);
+
 	REG_GET(DCN_GLOBAL_TTU_CNTL,
 			MIN_TTU_VBLANK, &s->min_ttu_vblank);
 
@@ -1248,10 +1249,8 @@ static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_get_underflow_status = hubp1_get_underflow_status,
 	.hubp_init = hubp1_init,
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	.dmdata_set_attributes = NULL,
 	.dmdata_load = NULL,
-#endif
 };
 
 /*****************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index ae70d9c0aa1d..780af5b3c16f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -670,6 +670,7 @@ struct dcn_hubp_state {
 	uint32_t sw_mode;
 	uint32_t dcc_en;
 	uint32_t blank_en;
+	uint32_t clock_en;
 	uint32_t underflow_status;
 	uint32_t ttu_disable;
 	uint32_t min_ttu_vblank;
@@ -728,13 +729,11 @@ void hubp1_dcc_control(struct hubp *hubp,
 		bool enable,
 		enum hubp_ind_block_size independent_64b_blks);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 bool hubp1_program_surface_flip_and_addr(
 	struct hubp *hubp,
 	const struct dc_plane_address *address,
 	bool flip_immediate);
 
-#endif
 bool hubp1_is_flip_pending(struct hubp *hubp);
 
 void hubp1_cursor_set_attributes(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index eb91432621ab..f2127afb37b2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -25,17 +25,18 @@
 
 #include <linux/delay.h>
 #include "dm_services.h"
+#include "basics/dc_common.h"
 #include "core_types.h"
 #include "resource.h"
 #include "custom_float.h"
 #include "dcn10_hw_sequencer.h"
-#include "dce110/dce110_hw_sequencer.h"
+#include "dcn10_hw_sequencer_debug.h"
 #include "dce/dce_hwseq.h"
 #include "abm.h"
 #include "dmcu.h"
 #include "dcn10_optc.h"
-#include "dcn10/dcn10_dpp.h"
-#include "dcn10/dcn10_mpc.h"
+#include "dcn10_dpp.h"
+#include "dcn10_mpc.h"
 #include "timing_generator.h"
 #include "opp.h"
 #include "ipp.h"
@@ -49,9 +50,7 @@
 #include "clk_mgr.h"
 
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dsc.h"
-#endif
 
 #define DC_LOGGER_INIT(logger)
 
@@ -68,6 +67,8 @@
 #define DTN_INFO_MICRO_SEC(ref_cycle) \
 	print_microsec(dc_ctx, log_ctx, ref_cycle)
 
+#define GAMMA_HW_POINTS_NUM 256
+
 void print_microsec(struct dc_context *dc_ctx,
 	struct dc_log_buffer_ctx *log_ctx,
 	uint32_t ref_cycle)
@@ -81,6 +82,33 @@ void print_microsec(struct dc_context *dc_ctx,
 			us_x10 % frac);
 }
 
+static void dcn10_lock_all_pipes(struct dc *dc,
+	struct dc_state *context,
+	bool lock)
+{
+	struct pipe_ctx *pipe_ctx;
+	struct timing_generator *tg;
+	int i;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe_ctx = &context->res_ctx.pipe_ctx[i];
+		tg = pipe_ctx->stream_res.tg;
+		/*
+		 * Only lock the top pipe's tg to prevent redundant
+		 * (un)locking. Also skip if pipe is disabled.
+		 */
+		if (pipe_ctx->top_pipe ||
+		    !pipe_ctx->stream || !pipe_ctx->plane_state ||
+		    !tg->funcs->is_tg_enabled(tg))
+			continue;
+
+		if (lock)
+			tg->funcs->lock(tg);
+		else
+			tg->funcs->unlock(tg);
+	}
+}
+
 static void log_mpc_crc(struct dc *dc,
 	struct dc_log_buffer_ctx *log_ctx)
 {
@@ -129,9 +157,8 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 	struct resource_pool *pool = dc->res_pool;
 	int i;
 
-	DTN_INFO("HUBP:  format  addr_hi  width  height"
-			"  rot  mir  sw_mode  dcc_en  blank_en  ttu_dis  underflow"
-			"   min_ttu_vblank       qos_low_wm      qos_high_wm\n");
+	DTN_INFO(
+		"HUBP:  format  addr_hi  width  height  rot  mir  sw_mode  dcc_en  blank_en  clock_en  ttu_dis  underflow   min_ttu_vblank       qos_low_wm      qos_high_wm\n");
 	for (i = 0; i < pool->pipe_count; i++) {
 		struct hubp *hubp = pool->hubps[i];
 		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(hubp)->state);
@@ -139,8 +166,7 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 		hubp->funcs->hubp_read_state(hubp);
 
 		if (!s->blank_en) {
-			DTN_INFO("[%2d]:  %5xh  %6xh  %5d  %6d  %2xh  %2xh  %6xh"
-					"  %6d  %8d  %7d  %8xh",
+			DTN_INFO("[%2d]:  %5xh  %6xh  %5d  %6d  %2xh  %2xh  %6xh  %6d  %8d  %8d  %7d  %8xh",
 					hubp->inst,
 					s->pixel_format,
 					s->inuse_addr_hi,
@@ -151,6 +177,7 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 					s->sw_mode,
 					s->dcc_en,
 					s->blank_en,
+					s->clock_en,
 					s->ttu_disable,
 					s->underflow_status);
 			DTN_INFO_MICRO_SEC(s->min_ttu_vblank);
@@ -308,21 +335,31 @@ void dcn10_log_hw_state(struct dc *dc,
 	}
 	DTN_INFO("\n");
 
-	DTN_INFO("OTG:  v_bs  v_be  v_ss  v_se  vpol  vmax  vmin  vmax_sel  vmin_sel"
-			"  h_bs  h_be  h_ss  h_se  hpol  htot  vtot  underflow\n");
+	DTN_INFO("OTG:  v_bs  v_be  v_ss  v_se  vpol  vmax  vmin  vmax_sel  vmin_sel  h_bs  h_be  h_ss  h_se  hpol  htot  vtot  underflow blank_en\n");
 
 	for (i = 0; i < pool->timing_generator_count; i++) {
 		struct timing_generator *tg = pool->timing_generators[i];
 		struct dcn_otg_state s = {0};
-
+		/* Read shared OTG state registers for all DCNx */
 		optc1_read_otg_state(DCN10TG_FROM_TG(tg), &s);
 
+		/*
+		 * For DCN2 and greater, a register on the OPP is used to
+		 * determine if the CRTC is blanked instead of the OTG. So use
+		 * dpg_is_blanked() if exists, otherwise fallback on otg.
+		 *
+		 * TODO: Implement DCN-specific read_otg_state hooks.
+		 */
+		if (pool->opps[i]->funcs->dpg_is_blanked)
+			s.blank_enabled = pool->opps[i]->funcs->dpg_is_blanked(pool->opps[i]);
+		else
+			s.blank_enabled = tg->funcs->is_blanked(tg);
+
 		//only print if OTG master is enabled
 		if ((s.otg_enabled & 1) == 0)
 			continue;
 
-		DTN_INFO("[%d]: %5d %5d %5d %5d %5d %5d %5d %9d %9d %5d %5d %5d"
-				" %5d %5d %5d %5d  %9d\n",
+		DTN_INFO("[%d]: %5d %5d %5d %5d %5d %5d %5d %9d %9d %5d %5d %5d %5d %5d %5d %5d  %9d %8d\n",
 				tg->inst,
 				s.v_blank_start,
 				s.v_blank_end,
@@ -340,7 +377,8 @@ void dcn10_log_hw_state(struct dc *dc,
 				s.h_sync_a_pol,
 				s.h_total,
 				s.v_total,
-				s.underflow_occurred_status);
+				s.underflow_occurred_status,
+				s.blank_enabled);
 
 		// Clear underflow for debug purposes
 		// We want to keep underflow sticky bit on for the longevity tests outside of test environment.
@@ -350,7 +388,6 @@ void dcn10_log_hw_state(struct dc *dc,
 	}
 	DTN_INFO("\n");
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	DTN_INFO("DSC: CLOCK_EN  SLICE_WIDTH  Bytes_pp\n");
 	for (i = 0; i < pool->res_cap->num_dsc; i++) {
 		struct display_stream_compressor *dsc = pool->dscs[i];
@@ -387,7 +424,7 @@ void dcn10_log_hw_state(struct dc *dc,
 	}
 	DTN_INFO("\n");
 
-	DTN_INFO("L_ENC: DPHY_FEC_EN  DPHY_FEC_READY_SHADOW  DPHY_FEC_ACTIVE_STATUS\n");
+	DTN_INFO("L_ENC: DPHY_FEC_EN  DPHY_FEC_READY_SHADOW  DPHY_FEC_ACTIVE_STATUS  DP_LINK_TRAINING_COMPLETE\n");
 	for (i = 0; i < dc->link_count; i++) {
 		struct link_encoder *lenc = dc->links[i]->link_enc;
 
@@ -395,16 +432,16 @@ void dcn10_log_hw_state(struct dc *dc,
 
 		if (lenc->funcs->read_state) {
 			lenc->funcs->read_state(lenc, &s);
-			DTN_INFO("[%-3d]: %-12d %-22d %-22d\n",
+			DTN_INFO("[%-3d]: %-12d %-22d %-22d %-25d\n",
 				i,
 				s.dphy_fec_en,
 				s.dphy_fec_ready_shadow,
-				s.dphy_fec_active_status);
+				s.dphy_fec_active_status,
+				s.dp_link_training_complete);
 			DTN_INFO("\n");
 		}
 	}
 	DTN_INFO("\n");
-#endif
 
 	DTN_INFO("\nCALCULATED Clocks: dcfclk_khz:%d  dcfclk_deep_sleep_khz:%d  dispclk_khz:%d\n"
 		"dppclk_khz:%d  max_supported_dppclk_khz:%d  fclk_khz:%d  socclk_khz:%d\n\n",
@@ -438,14 +475,14 @@ bool dcn10_did_underflow_occur(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	return false;
 }
 
-static void dcn10_enable_power_gating_plane(
+void dcn10_enable_power_gating_plane(
 	struct dce_hwseq *hws,
 	bool enable)
 {
-	bool force_on = 1; /* disable power gating */
+	bool force_on = true; /* disable power gating */
 
 	if (enable)
-		force_on = 0;
+		force_on = false;
 
 	/* DCHUBP0/1/2/3 */
 	REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN0_POWER_FORCEON, force_on);
@@ -460,7 +497,7 @@ static void dcn10_enable_power_gating_plane(
 	REG_UPDATE(DOMAIN7_PG_CONFIG, DOMAIN7_POWER_FORCEON, force_on);
 }
 
-static void dcn10_disable_vga(
+void dcn10_disable_vga(
 	struct dce_hwseq *hws)
 {
 	unsigned int in_vga1_mode = 0;
@@ -493,7 +530,7 @@ static void dcn10_disable_vga(
 	REG_UPDATE(VGA_TEST_CONTROL, VGA_TEST_RENDER_START, 1);
 }
 
-static void dcn10_dpp_pg_control(
+void dcn10_dpp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int dpp_inst,
 		bool power_on)
@@ -545,7 +582,7 @@ static void dcn10_dpp_pg_control(
 	}
 }
 
-static void dcn10_hubp_pg_control(
+void dcn10_hubp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int hubp_inst,
 		bool power_on)
@@ -605,8 +642,8 @@ static void power_on_plane(
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		hws->ctx->dc->hwss.dpp_pg_control(hws, plane_id, true);
-		hws->ctx->dc->hwss.hubp_pg_control(hws, plane_id, true);
+		hws->funcs.dpp_pg_control(hws, plane_id, true);
+		hws->funcs.hubp_pg_control(hws, plane_id, true);
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
 		DC_LOG_DEBUG(
@@ -627,7 +664,7 @@ static void undo_DEGVIDCN10_253_wa(struct dc *dc)
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 1);
 
-	dc->hwss.hubp_pg_control(hws, 0, false);
+	hws->funcs.hubp_pg_control(hws, 0, false);
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 0);
 
@@ -656,7 +693,7 @@ static void apply_DEGVIDCN10_253_wa(struct dc *dc)
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 1);
 
-	dc->hwss.hubp_pg_control(hws, 0, true);
+	hws->funcs.hubp_pg_control(hws, 0, true);
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 0);
 
@@ -664,16 +701,16 @@ static void apply_DEGVIDCN10_253_wa(struct dc *dc)
 	hws->wa_state.DEGVIDCN10_253_applied = true;
 }
 
-static void dcn10_bios_golden_init(struct dc *dc)
+void dcn10_bios_golden_init(struct dc *dc)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct dc_bios *bp = dc->ctx->dc_bios;
 	int i;
 	bool allow_self_fresh_force_enable = true;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
-	if (dc->hwss.s0i3_golden_init_wa && dc->hwss.s0i3_golden_init_wa(dc))
+	if (hws->funcs.s0i3_golden_init_wa && hws->funcs.s0i3_golden_init_wa(dc))
 		return;
-#endif
+
 	if (dc->res_pool->hubbub->funcs->is_allow_self_refresh_enabled)
 		allow_self_fresh_force_enable =
 				dc->res_pool->hubbub->funcs->is_allow_self_refresh_enabled(dc->res_pool->hubbub);
@@ -732,7 +769,7 @@ static void false_optc_underflow_wa(
 		tg->funcs->clear_optc_underflow(tg);
 }
 
-static enum dc_status dcn10_enable_stream_timing(
+enum dc_status dcn10_enable_stream_timing(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -823,6 +860,7 @@ static void dcn10_reset_back_end_for_pipe(
 		struct dc_state *context)
 {
 	int i;
+	struct dc_link *link;
 	DC_LOGGER_INIT(dc->ctx->logger);
 	if (pipe_ctx->stream_res.stream_enc == NULL) {
 		pipe_ctx->stream = NULL;
@@ -830,8 +868,14 @@ static void dcn10_reset_back_end_for_pipe(
 	}
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-		/* DPMS may already disable */
-		if (!pipe_ctx->stream->dpms_off)
+		link = pipe_ctx->stream->link;
+		/* DPMS may already disable or */
+		/* dpms_off status is incorrect due to fastboot
+		 * feature. When system resume from S4 with second
+		 * screen only, the dpms_off would be true but
+		 * VBIOS lit up eDP, so check link status too.
+		 */
+		if (!pipe_ctx->stream->dpms_off || link->link_status.link_active)
 			core_link_disable_stream(pipe_ctx);
 		else if (pipe_ctx->stream_res.audio)
 			dc->hwss.disable_audio_stream(pipe_ctx);
@@ -978,8 +1022,9 @@ void dcn10_verify_allow_pstate_change_high(struct dc *dc)
 }
 
 /* trigger HW to start disconnect plane from stream on the next vsync */
-void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	int dpp_id = pipe_ctx->plane_res.dpp->inst;
 	struct mpc *mpc = dc->res_pool->mpc;
@@ -1004,10 +1049,10 @@ void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		hubp->funcs->hubp_disconnect(hubp);
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
-static void dcn10_plane_atomic_power_down(struct dc *dc,
+void dcn10_plane_atomic_power_down(struct dc *dc,
 		struct dpp *dpp,
 		struct hubp *hubp)
 {
@@ -1017,8 +1062,8 @@ static void dcn10_plane_atomic_power_down(struct dc *dc,
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		dc->hwss.dpp_pg_control(hws, dpp->inst, false);
-		dc->hwss.hubp_pg_control(hws, hubp->inst, false);
+		hws->funcs.dpp_pg_control(hws, dpp->inst, false);
+		hws->funcs.hubp_pg_control(hws, hubp->inst, false);
 		dpp->funcs->dpp_reset(dpp);
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
@@ -1030,8 +1075,9 @@ static void dcn10_plane_atomic_power_down(struct dc *dc,
 /* disable HW used by plane.
  * note:  cannot disable until disconnect is complete
  */
-static void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 	int opp_id = hubp->opp_id;
@@ -1050,7 +1096,7 @@ static void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	hubp->power_gated = true;
 	dc->optimized_required = false; /* We're powering off, no need to optimize */
 
-	dc->hwss.plane_atomic_power_down(dc,
+	hws->funcs.plane_atomic_power_down(dc,
 			pipe_ctx->plane_res.dpp,
 			pipe_ctx->plane_res.hubp);
 
@@ -1062,14 +1108,15 @@ static void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_state = NULL;
 }
 
-static void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 	if (!pipe_ctx->plane_res.hubp || pipe_ctx->plane_res.hubp->power_gated)
 		return;
 
-	dc->hwss.plane_atomic_disable(dc, pipe_ctx);
+	hws->funcs.plane_atomic_disable(dc, pipe_ctx);
 
 	apply_DEGVIDCN10_253_wa(dc);
 
@@ -1077,9 +1124,10 @@ static void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx)
 					pipe_ctx->pipe_idx);
 }
 
-static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
+void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 {
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 	bool can_apply_seamless_boot = false;
 
 	for (i = 0; i < context->stream_count; i++) {
@@ -1104,8 +1152,8 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		 * command table.
 		 */
 		if (tg->funcs->is_tg_enabled(tg)) {
-			if (dc->hwss.init_blank != NULL) {
-				dc->hwss.init_blank(dc, tg);
+			if (hws->funcs.init_blank != NULL) {
+				hws->funcs.init_blank(dc, tg);
 				tg->funcs->lock(tg);
 			} else {
 				tg->funcs->lock(tg);
@@ -1115,7 +1163,8 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		}
 	}
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	/* num_opp will be equal to number of mpcc */
+	for (i = 0; i < dc->res_pool->res_cap->num_opp; i++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
 		/* Cannot reset the MPC mux if seamless boot */
@@ -1139,8 +1188,14 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		if (can_apply_seamless_boot &&
 			pipe_ctx->stream != NULL &&
 			pipe_ctx->stream_res.tg->funcs->is_tg_enabled(
-				pipe_ctx->stream_res.tg))
+				pipe_ctx->stream_res.tg)) {
+			// Enable double buffering for OTG_BLANK no matter if
+			// seamless boot is enabled or not to suppress global sync
+			// signals when OTG blanked. This is to prevent pipe from
+			// requesting data while in PSR.
+			tg->funcs->tg_init(tg);
 			continue;
+		}
 
 		/* Disable on the current state so the new one isn't cleared. */
 		pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
@@ -1162,7 +1217,7 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		dc->res_pool->opps[i]->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 		pipe_ctx->stream_res.opp = dc->res_pool->opps[i];
 
-		dc->hwss.plane_atomic_disconnect(dc, pipe_ctx);
+		hws->funcs.plane_atomic_disconnect(dc, pipe_ctx);
 
 		if (tg->funcs->is_tg_enabled(tg))
 			tg->funcs->unlock(tg);
@@ -1176,7 +1231,7 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 	}
 }
 
-static void dcn10_init_hw(struct dc *dc)
+void dcn10_init_hw(struct dc *dc)
 {
 	int i;
 	struct abm *abm = dc->res_pool->abm;
@@ -1208,15 +1263,15 @@ static void dcn10_init_hw(struct dc *dc)
 		}
 
 		//Enable ability to power gate / don't force power on permanently
-		dc->hwss.enable_power_gating_plane(hws, true);
+		hws->funcs.enable_power_gating_plane(hws, true);
 
 		return;
 	}
 
 	if (!dcb->funcs->is_accelerated_mode(dcb))
-		dc->hwss.disable_vga(dc->hwseq);
+		hws->funcs.disable_vga(dc->hwseq);
 
-	dc->hwss.bios_golden_init(dc);
+	hws->funcs.bios_golden_init(dc);
 	if (dc->ctx->dc_bios->fw_info_valid) {
 		res_pool->ref_clocks.xtalin_clock_inKhz =
 				dc->ctx->dc_bios->fw_info.pll_info.crystal_frequency;
@@ -1258,11 +1313,9 @@ static void dcn10_init_hw(struct dc *dc)
 	}
 
 	/* Power gate DSCs */
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < res_pool->res_cap->num_dsc; i++)
-		if (dc->hwss.dsc_pg_control != NULL)
-			dc->hwss.dsc_pg_control(hws, res_pool->dscs[i]->inst, false);
-#endif
+		if (hws->funcs.dsc_pg_control != NULL)
+			hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false);
 
 	/* If taking control over from VBIOS, we may want to optimize our first
 	 * mode set, so we need to skip powering down pipes until we know which
@@ -1271,7 +1324,7 @@ static void dcn10_init_hw(struct dc *dc)
 	 * everything down.
 	 */
 	if (dcb->funcs->is_accelerated_mode(dcb) || dc->config.power_down_display_on_boot) {
-		dc->hwss.init_pipes(dc, dc->current_state);
+		hws->funcs.init_pipes(dc, dc->current_state);
 	}
 
 	for (i = 0; i < res_pool->audio_count; i++) {
@@ -1285,7 +1338,7 @@ static void dcn10_init_hw(struct dc *dc)
 		abm->funcs->abm_init(abm);
 	}
 
-	if (dmcu != NULL)
+	if (dmcu != NULL && !dmcu->auto_load_dmcu)
 		dmcu->funcs->dmcu_init(dmcu);
 
 	if (abm != NULL && dmcu != NULL)
@@ -1303,18 +1356,19 @@ static void dcn10_init_hw(struct dc *dc)
 		REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
 	}
 
-	dc->hwss.enable_power_gating_plane(dc->hwseq, true);
+	hws->funcs.enable_power_gating_plane(dc->hwseq, true);
 
 	if (dc->clk_mgr->funcs->notify_wm_ranges)
 		dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr);
 
 }
 
-static void dcn10_reset_hw_ctx_wrap(
+void dcn10_reset_hw_ctx_wrap(
 		struct dc *dc,
 		struct dc_state *context)
 {
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	/* Reset Back End*/
 	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
@@ -1333,8 +1387,8 @@ static void dcn10_reset_hw_ctx_wrap(
 			struct clock_source *old_clk = pipe_ctx_old->clock_source;
 
 			dcn10_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
-			if (dc->hwss.enable_stream_gating)
-				dc->hwss.enable_stream_gating(dc, pipe_ctx);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx);
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 		}
@@ -1367,9 +1421,7 @@ static bool patch_address_for_sbs_tb_stereo(
 	return false;
 }
 
-
-
-static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	bool addr_patched = false;
 	PHYSICAL_ADDRESS_LOC addr;
@@ -1394,8 +1446,8 @@ static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_c
 		pipe_ctx->plane_state->address.grph_stereo.left_addr = addr;
 }
 
-static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
-					  const struct dc_plane_state *plane_state)
+bool dcn10_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state)
 {
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	const struct dc_transfer_func *tf = NULL;
@@ -1427,6 +1479,11 @@ static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
 			break;
 		case TRANSFER_FUNCTION_PQ:
+			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_USER_PWL);
+			cm_helper_translate_curve_to_degamma_hw_format(tf, &dpp_base->degamma_params);
+			dpp_base->funcs->dpp_program_degamma_pwl(dpp_base, &dpp_base->degamma_params);
+			result = true;
+			break;
 		default:
 			result = false;
 			break;
@@ -1472,9 +1529,8 @@ static void log_tf(struct dc_context *ctx,
 	}
 }
 
-static bool
-dcn10_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
-			       const struct dc_stream_state *stream)
+bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+				const struct dc_stream_state *stream)
 {
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 
@@ -1510,11 +1566,13 @@ dcn10_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
 	return true;
 }
 
-static void dcn10_pipe_control_lock(
+void dcn10_pipe_control_lock(
 	struct dc *dc,
 	struct pipe_ctx *pipe,
 	bool lock)
 {
+	struct dce_hwseq *hws = dc->hwseq;
+
 	/* use TG master update lock to lock everything on the TG
 	 * therefore only top pipe need to lock
 	 */
@@ -1522,7 +1580,7 @@ static void dcn10_pipe_control_lock(
 		return;
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 
 	if (lock)
 		pipe->stream_res.tg->funcs->lock(pipe->stream_res.tg);
@@ -1530,7 +1588,7 @@ static void dcn10_pipe_control_lock(
 		pipe->stream_res.tg->funcs->unlock(pipe->stream_res.tg);
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
 static bool wait_for_reset_trigger_to_occur(
@@ -1570,7 +1628,7 @@ static bool wait_for_reset_trigger_to_occur(
 	return rc;
 }
 
-static void dcn10_enable_timing_synchronization(
+void dcn10_enable_timing_synchronization(
 	struct dc *dc,
 	int group_index,
 	int group_size,
@@ -1600,7 +1658,7 @@ static void dcn10_enable_timing_synchronization(
 	DC_SYNC_INFO("Sync complete\n");
 }
 
-static void dcn10_enable_per_frame_crtc_position_reset(
+void dcn10_enable_per_frame_crtc_position_reset(
 	struct dc *dc,
 	int group_size,
 	struct pipe_ctx *grouped_pipes[])
@@ -1625,10 +1683,10 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 }
 
 /*static void print_rq_dlg_ttu(
-		struct dc *core_dc,
+		struct dc *dc,
 		struct pipe_ctx *pipe_ctx)
 {
-	DC_LOG_BANDWIDTH_CALCS(core_dc->ctx->logger,
+	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
 			"\n============== DML TTU Output parameters [%d] ==============\n"
 			"qos_level_low_wm: %d, \n"
 			"qos_level_high_wm: %d, \n"
@@ -1658,7 +1716,7 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 			pipe_ctx->ttu_regs.refcyc_per_req_delivery_pre_c
 			);
 
-	DC_LOG_BANDWIDTH_CALCS(core_dc->ctx->logger,
+	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
 			"\n============== DML DLG Output parameters [%d] ==============\n"
 			"refcyc_h_blank_end: %d, \n"
 			"dlg_vblank_end: %d, \n"
@@ -1693,7 +1751,7 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 			pipe_ctx->dlg_regs.refcyc_per_pte_group_nom_l
 			);
 
-	DC_LOG_BANDWIDTH_CALCS(core_dc->ctx->logger,
+	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
 			"\ndst_y_per_meta_row_nom_l: %d, \n"
 			"refcyc_per_meta_chunk_nom_l: %d, \n"
 			"refcyc_per_line_delivery_pre_l: %d, \n"
@@ -1723,7 +1781,7 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 			pipe_ctx->dlg_regs.refcyc_per_line_delivery_c
 			);
 
-	DC_LOG_BANDWIDTH_CALCS(core_dc->ctx->logger,
+	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
 			"\n============== DML RQ Output parameters [%d] ==============\n"
 			"chunk_size: %d \n"
 			"min_chunk_size: %d \n"
@@ -1838,7 +1896,7 @@ static void dcn10_enable_plane(
 	struct dce_hwseq *hws = dc->hwseq;
 
 	if (dc->debug.sanity_checks) {
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
 
 	undo_DEGVIDCN10_253_wa(dc);
@@ -1895,11 +1953,11 @@ static void dcn10_enable_plane(
 		dcn10_program_pte_vm(hws, pipe_ctx->plane_res.hubp);
 
 	if (dc->debug.sanity_checks) {
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
 }
 
-static void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx)
+void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx)
 {
 	int i = 0;
 	struct dpp_grph_csc_adjustment adjust;
@@ -1947,7 +2005,7 @@ static void dcn10_set_csc_adjustment_rgb_mpo_fix(struct pipe_ctx *pipe_ctx, uint
 	matrix[11] = rgb_bias;
 }
 
-static void dcn10_program_output_csc(struct dc *dc,
+void dcn10_program_output_csc(struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum dc_color_space colorspace,
 		uint16_t *matrix,
@@ -1979,57 +2037,6 @@ static void dcn10_program_output_csc(struct dc *dc,
 	}
 }
 
-bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
-{
-	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
-		return true;
-	if (pipe_ctx->bottom_pipe && is_lower_pipe_tree_visible(pipe_ctx->bottom_pipe))
-		return true;
-	return false;
-}
-
-bool is_upper_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
-{
-	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
-		return true;
-	if (pipe_ctx->top_pipe && is_upper_pipe_tree_visible(pipe_ctx->top_pipe))
-		return true;
-	return false;
-}
-
-bool is_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
-{
-	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
-		return true;
-	if (pipe_ctx->top_pipe && is_upper_pipe_tree_visible(pipe_ctx->top_pipe))
-		return true;
-	if (pipe_ctx->bottom_pipe && is_lower_pipe_tree_visible(pipe_ctx->bottom_pipe))
-		return true;
-	return false;
-}
-
-bool is_rgb_cspace(enum dc_color_space output_color_space)
-{
-	switch (output_color_space) {
-	case COLOR_SPACE_SRGB:
-	case COLOR_SPACE_SRGB_LIMITED:
-	case COLOR_SPACE_2020_RGB_FULLRANGE:
-	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
-	case COLOR_SPACE_ADOBERGB:
-		return true;
-	case COLOR_SPACE_YCBCR601:
-	case COLOR_SPACE_YCBCR709:
-	case COLOR_SPACE_YCBCR601_LIMITED:
-	case COLOR_SPACE_YCBCR709_LIMITED:
-	case COLOR_SPACE_2020_YCBCR:
-		return false;
-	default:
-		/* Add a case to switch */
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-}
-
 void dcn10_get_surface_visual_confirm_color(
 		const struct pipe_ctx *pipe_ctx,
 		struct tg_color *color)
@@ -2103,70 +2110,7 @@ void dcn10_get_hdr_visual_confirm_color(
 	}
 }
 
-static uint16_t fixed_point_to_int_frac(
-	struct fixed31_32 arg,
-	uint8_t integer_bits,
-	uint8_t fractional_bits)
-{
-	int32_t numerator;
-	int32_t divisor = 1 << fractional_bits;
-
-	uint16_t result;
-
-	uint16_t d = (uint16_t)dc_fixpt_floor(
-		dc_fixpt_abs(
-			arg));
-
-	if (d <= (uint16_t)(1 << integer_bits) - (1 / (uint16_t)divisor))
-		numerator = (uint16_t)dc_fixpt_floor(
-			dc_fixpt_mul_int(
-				arg,
-				divisor));
-	else {
-		numerator = dc_fixpt_floor(
-			dc_fixpt_sub(
-				dc_fixpt_from_int(
-					1LL << integer_bits),
-				dc_fixpt_recip(
-					dc_fixpt_from_int(
-						divisor))));
-	}
-
-	if (numerator >= 0)
-		result = (uint16_t)numerator;
-	else
-		result = (uint16_t)(
-		(1 << (integer_bits + fractional_bits + 1)) + numerator);
-
-	if ((result != 0) && dc_fixpt_lt(
-		arg, dc_fixpt_zero))
-		result |= 1 << (integer_bits + fractional_bits);
-
-	return result;
-}
-
-void dcn10_build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
-		const struct dc_plane_state *plane_state)
-{
-	if (plane_state->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN
-			&& plane_state->format != SURFACE_PIXEL_FORMAT_INVALID
-			&& plane_state->input_csc_color_matrix.enable_adjustment
-			&& plane_state->coeff_reduction_factor.value != 0) {
-		bias_and_scale->scale_blue = fixed_point_to_int_frac(
-			dc_fixpt_mul(plane_state->coeff_reduction_factor,
-					dc_fixpt_from_fraction(256, 255)),
-				2,
-				13);
-		bias_and_scale->scale_red = bias_and_scale->scale_blue;
-		bias_and_scale->scale_green = bias_and_scale->scale_blue;
-	} else {
-		bias_and_scale->scale_blue = 0x2000;
-		bias_and_scale->scale_red = 0x2000;
-		bias_and_scale->scale_green = 0x2000;
-	}
-}
-
-static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
+static void dcn10_update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 {
 	struct dc_bias_and_scale bns_params = {0};
 
@@ -2175,21 +2119,18 @@ static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 			plane_state->format,
 			EXPANSION_MODE_ZERO,
 			plane_state->input_csc_color_matrix,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 			plane_state->color_space,
 			NULL);
-#else
-			plane_state->color_space);
-#endif
 
 	//set scale and bias registers
-	dcn10_build_prescale_params(&bns_params, plane_state);
+	build_prescale_params(&bns_params, plane_state);
 	if (dpp->funcs->dpp_program_bias_and_scale)
 		dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
 }
 
-static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct mpcc_blnd_cfg blnd_cfg = {{0}};
 	bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
@@ -2199,10 +2140,10 @@ static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params);
 
 	if (dc->debug.visual_confirm == VISUAL_CONFIRM_HDR) {
-		dcn10_get_hdr_visual_confirm_color(
+		hws->funcs.get_hdr_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
 	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE) {
-		dcn10_get_surface_visual_confirm_color(
+		hws->funcs.get_surface_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
 	} else {
 		color_space_to_black_color(
@@ -2284,11 +2225,12 @@ static void update_scaler(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data);
 }
 
-void update_dchubp_dpp(
+static void dcn10_update_dchubp_dpp(
 	struct dc *dc,
 	struct pipe_ctx *pipe_ctx,
 	struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
@@ -2342,12 +2284,12 @@ void update_dchubp_dpp(
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.bpp_change)
-		update_dpp(dpp, plane_state);
+		dcn10_update_dpp(dpp, plane_state);
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change ||
 		plane_state->update_flags.bits.global_alpha_change)
-		dc->hwss.update_mpcc(dc, pipe_ctx);
+		hws->funcs.update_mpcc(dc, pipe_ctx);
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change ||
@@ -2407,13 +2349,13 @@ void update_dchubp_dpp(
 
 	hubp->power_gated = false;
 
-	dc->hwss.update_plane_addr(dc, pipe_ctx);
+	hws->funcs.update_plane_addr(dc, pipe_ctx);
 
 	if (is_pipe_tree_visible(pipe_ctx))
 		hubp->funcs->set_blank(hubp, false);
 }
 
-static void dcn10_blank_pixel_data(
+void dcn10_blank_pixel_data(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		bool blank)
@@ -2456,10 +2398,9 @@ static void dcn10_blank_pixel_data(
 	}
 }
 
-void set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
+void dcn10_set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
 {
-	struct fixed31_32 multiplier = dc_fixpt_from_fraction(
-			pipe_ctx->plane_state->sdr_white_level, 80);
+	struct fixed31_32 multiplier = pipe_ctx->plane_state->hdr_mult;
 	uint32_t hw_mult = 0x1f000; // 1.0 default multiplier
 	struct custom_float_format fmt;
 
@@ -2467,7 +2408,8 @@ void set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
 	fmt.mantissa_bits = 12;
 	fmt.sign = true;
 
-	if (pipe_ctx->plane_state->sdr_white_level > 80)
+
+	if (!dc_fixpt_eq(multiplier, dc_fixpt_from_int(0))) // check != 0
 		convert_to_custom_float_format(multiplier, &fmt, &hw_mult);
 
 	pipe_ctx->plane_res.dpp->funcs->dpp_set_hdr_multiplier(
@@ -2479,17 +2421,19 @@ void dcn10_program_pipe(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
+
 	if (pipe_ctx->plane_state->update_flags.bits.full_update)
 		dcn10_enable_plane(dc, pipe_ctx, context);
 
-	update_dchubp_dpp(dc, pipe_ctx, context);
+	dcn10_update_dchubp_dpp(dc, pipe_ctx, context);
 
-	set_hdr_multiplier(pipe_ctx);
+	hws->funcs.set_hdr_multiplier(pipe_ctx);
 
 	if (pipe_ctx->plane_state->update_flags.bits.full_update ||
 			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
 			pipe_ctx->plane_state->update_flags.bits.gamma_change)
-		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+		hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state);
 
 	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
 	 * only do gamma programming for full update.
@@ -2498,14 +2442,16 @@ void dcn10_program_pipe(
 	 * doing heavy calculation and programming
 	 */
 	if (pipe_ctx->plane_state->update_flags.bits.full_update)
-		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 }
 
-static void program_all_pipe_in_tree(
+static void dcn10_program_all_pipe_in_tree(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
+
 	if (pipe_ctx->top_pipe == NULL) {
 		bool blank = !is_pipe_tree_visible(pipe_ctx);
 
@@ -2519,20 +2465,20 @@ static void program_all_pipe_in_tree(
 		pipe_ctx->stream_res.tg->funcs->set_vtg_params(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-		if (dc->hwss.setup_vupdate_interrupt)
-			dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+		if (hws->funcs.setup_vupdate_interrupt)
+			hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
 
-		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+		hws->funcs.blank_pixel_data(dc, pipe_ctx, blank);
 	}
 
 	if (pipe_ctx->plane_state != NULL)
-		dcn10_program_pipe(dc, pipe_ctx, context);
+		hws->funcs.program_pipe(dc, pipe_ctx, context);
 
 	if (pipe_ctx->bottom_pipe != NULL && pipe_ctx->bottom_pipe != pipe_ctx)
-		program_all_pipe_in_tree(dc, pipe_ctx->bottom_pipe, context);
+		dcn10_program_all_pipe_in_tree(dc, pipe_ctx->bottom_pipe, context);
 }
 
-struct pipe_ctx *find_top_pipe_for_stream(
+static struct pipe_ctx *dcn10_find_top_pipe_for_stream(
 		struct dc *dc,
 		struct dc_state *context,
 		const struct dc_stream_state *stream)
@@ -2556,19 +2502,20 @@ struct pipe_ctx *find_top_pipe_for_stream(
 	return NULL;
 }
 
-static void dcn10_apply_ctx_for_surface(
+void dcn10_apply_ctx_for_surface(
 		struct dc *dc,
 		const struct dc_stream_state *stream,
 		int num_planes,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	int i;
 	struct timing_generator *tg;
 	uint32_t underflow_check_delay_us;
 	bool removed_pipe[4] = { false };
 	bool interdependent_update = false;
 	struct pipe_ctx *top_pipe_to_program =
-			find_top_pipe_for_stream(dc, context, stream);
+			dcn10_find_top_pipe_for_stream(dc, context, stream);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 	if (!top_pipe_to_program)
@@ -2581,23 +2528,23 @@ static void dcn10_apply_ctx_for_surface(
 
 	underflow_check_delay_us = dc->debug.underflow_assert_delay_us;
 
-	if (underflow_check_delay_us != 0xFFFFFFFF && dc->hwss.did_underflow_occur)
-		ASSERT(dc->hwss.did_underflow_occur(dc, top_pipe_to_program));
+	if (underflow_check_delay_us != 0xFFFFFFFF && hws->funcs.did_underflow_occur)
+		ASSERT(hws->funcs.did_underflow_occur(dc, top_pipe_to_program));
 
 	if (interdependent_update)
-		lock_all_pipes(dc, context, true);
+		dcn10_lock_all_pipes(dc, context, true);
 	else
 		dcn10_pipe_control_lock(dc, top_pipe_to_program, true);
 
 	if (underflow_check_delay_us != 0xFFFFFFFF)
 		udelay(underflow_check_delay_us);
 
-	if (underflow_check_delay_us != 0xFFFFFFFF && dc->hwss.did_underflow_occur)
-		ASSERT(dc->hwss.did_underflow_occur(dc, top_pipe_to_program));
+	if (underflow_check_delay_us != 0xFFFFFFFF && hws->funcs.did_underflow_occur)
+		ASSERT(hws->funcs.did_underflow_occur(dc, top_pipe_to_program));
 
 	if (num_planes == 0) {
 		/* OTG blank before remove all front end */
-		dc->hwss.blank_pixel_data(dc, top_pipe_to_program, true);
+		hws->funcs.blank_pixel_data(dc, top_pipe_to_program, true);
 	}
 
 	/* Disconnect unused mpcc */
@@ -2623,7 +2570,7 @@ static void dcn10_apply_ctx_for_surface(
 		    old_pipe_ctx->plane_state &&
 		    old_pipe_ctx->stream_res.tg == tg) {
 
-			dc->hwss.plane_atomic_disconnect(dc, old_pipe_ctx);
+			hws->funcs.plane_atomic_disconnect(dc, old_pipe_ctx);
 			removed_pipe[i] = true;
 
 			DC_LOG_DC("Reset mpcc for pipe %d\n",
@@ -2632,13 +2579,11 @@ static void dcn10_apply_ctx_for_surface(
 	}
 
 	if (num_planes > 0)
-		program_all_pipe_in_tree(dc, top_pipe_to_program, context);
+		dcn10_program_all_pipe_in_tree(dc, top_pipe_to_program, context);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* Program secondary blending tree and writeback pipes */
-	if ((stream->num_wb_info > 0) && (dc->hwss.program_all_writeback_pipes_in_tree))
-		dc->hwss.program_all_writeback_pipes_in_tree(dc, stream, context);
-#endif
+	if ((stream->num_wb_info > 0) && (hws->funcs.program_all_writeback_pipes_in_tree))
+		hws->funcs.program_all_writeback_pipes_in_tree(dc, stream, context);
 	if (interdependent_update)
 		for (i = 0; i < dc->res_pool->pipe_count; i++) {
 			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
@@ -2654,7 +2599,7 @@ static void dcn10_apply_ctx_for_surface(
 		}
 
 	if (interdependent_update)
-		lock_all_pipes(dc, context, false);
+		dcn10_lock_all_pipes(dc, context, false);
 	else
 		dcn10_pipe_control_lock(dc, top_pipe_to_program, false);
 
@@ -2691,14 +2636,15 @@ static void dcn10_stereo_hw_frame_pack_wa(struct dc *dc, struct dc_state *contex
 	}
 }
 
-static void dcn10_prepare_bandwidth(
+void dcn10_prepare_bandwidth(
 		struct dc *dc,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubbub *hubbub = dc->res_pool->hubbub;
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (context->stream_count == 0)
@@ -2720,17 +2666,18 @@ static void dcn10_prepare_bandwidth(
 		dcn_bw_notify_pplib_of_wm_ranges(dc);
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
-static void dcn10_optimize_bandwidth(
+void dcn10_optimize_bandwidth(
 		struct dc *dc,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubbub *hubbub = dc->res_pool->hubbub;
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (context->stream_count == 0)
@@ -2752,10 +2699,10 @@ static void dcn10_optimize_bandwidth(
 		dcn_bw_notify_pplib_of_wm_ranges(dc);
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
-static void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
+void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
 		int num_pipes, unsigned int vmin, unsigned int vmax,
 		unsigned int vmid, unsigned int vmid_frame_number)
 {
@@ -2763,6 +2710,8 @@ static void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
 	struct drr_params params = {0};
 	// DRR set trigger event mapped to OTG_TRIG_A (bit 11) for manual control flow
 	unsigned int event_triggers = 0x800;
+	// Note DRR trigger events are generated regardless of whether num frames met.
+	unsigned int num_frames = 2;
 
 	params.vertical_total_max = vmax;
 	params.vertical_total_min = vmin;
@@ -2779,11 +2728,11 @@ static void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
 		if (vmax != 0 && vmin != 0)
 			pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(
 					pipe_ctx[i]->stream_res.tg,
-					event_triggers);
+					event_triggers, num_frames);
 	}
 }
 
-static void dcn10_get_position(struct pipe_ctx **pipe_ctx,
+void dcn10_get_position(struct pipe_ctx **pipe_ctx,
 		int num_pipes,
 		struct crtc_position *position)
 {
@@ -2795,22 +2744,23 @@ static void dcn10_get_position(struct pipe_ctx **pipe_ctx,
 		pipe_ctx[i]->stream_res.tg->funcs->get_position(pipe_ctx[i]->stream_res.tg, position);
 }
 
-static void dcn10_set_static_screen_control(struct pipe_ctx **pipe_ctx,
-		int num_pipes, const struct dc_static_screen_events *events)
+void dcn10_set_static_screen_control(struct pipe_ctx **pipe_ctx,
+		int num_pipes, const struct dc_static_screen_params *params)
 {
 	unsigned int i;
-	unsigned int value = 0;
+	unsigned int triggers = 0;
 
-	if (events->surface_update)
-		value |= 0x80;
-	if (events->cursor_update)
-		value |= 0x2;
-	if (events->force_trigger)
-		value |= 0x1;
+	if (params->triggers.surface_update)
+		triggers |= 0x80;
+	if (params->triggers.cursor_update)
+		triggers |= 0x2;
+	if (params->triggers.force_trigger)
+		triggers |= 0x1;
 
 	for (i = 0; i < num_pipes; i++)
 		pipe_ctx[i]->stream_res.tg->funcs->
-			set_static_screen_control(pipe_ctx[i]->stream_res.tg, value);
+			set_static_screen_control(pipe_ctx[i]->stream_res.tg,
+					triggers, params->num_frames);
 }
 
 static void dcn10_config_stereo_parameters(
@@ -2850,7 +2800,7 @@ static void dcn10_config_stereo_parameters(
 	return;
 }
 
-static void dcn10_setup_stereo(struct pipe_ctx *pipe_ctx, struct dc *dc)
+void dcn10_setup_stereo(struct pipe_ctx *pipe_ctx, struct dc *dc)
 {
 	struct crtc_stereo_flags flags = { 0 };
 	struct dc_stream_state *stream = pipe_ctx->stream;
@@ -2889,15 +2839,16 @@ static struct hubp *get_hubp_by_inst(struct resource_pool *res_pool, int mpcc_in
 	return NULL;
 }
 
-static void dcn10_wait_for_mpcc_disconnect(
+void dcn10_wait_for_mpcc_disconnect(
 		struct dc *dc,
 		struct resource_pool *res_pool,
 		struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	int mpcc_inst;
 
 	if (dc->debug.sanity_checks) {
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
 
 	if (!pipe_ctx->stream_res.opp)
@@ -2914,12 +2865,12 @@ static void dcn10_wait_for_mpcc_disconnect(
 	}
 
 	if (dc->debug.sanity_checks) {
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
 
 }
 
-static bool dcn10_dummy_display_power_gating(
+bool dcn10_dummy_display_power_gating(
 	struct dc *dc,
 	uint8_t controller_id,
 	struct dc_bios *dcb,
@@ -2928,7 +2879,7 @@ static bool dcn10_dummy_display_power_gating(
 	return true;
 }
 
-static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
+void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
@@ -2952,7 +2903,7 @@ static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 	}
 }
 
-static void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data)
+void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data)
 {
 	struct hubbub *hubbub = hws->ctx->dc->res_pool->hubbub;
 
@@ -2960,7 +2911,7 @@ static void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh
 	hubbub->funcs->update_dchub(hubbub, dh_data);
 }
 
-static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
+void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
@@ -2974,15 +2925,32 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 		.rotation = pipe_ctx->plane_state->rotation,
 		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
-	uint32_t x_plane = pipe_ctx->plane_state->dst_rect.x;
-	uint32_t y_plane = pipe_ctx->plane_state->dst_rect.y;
-	uint32_t x_offset = min(x_plane, pos_cpy.x);
-	uint32_t y_offset = min(y_plane, pos_cpy.y);
+	bool pipe_split_on = (pipe_ctx->top_pipe != NULL) ||
+		(pipe_ctx->bottom_pipe != NULL);
+
+	int x_plane = pipe_ctx->plane_state->dst_rect.x;
+	int y_plane = pipe_ctx->plane_state->dst_rect.y;
+	int x_pos = pos_cpy.x;
+	int y_pos = pos_cpy.y;
+
+	// translate cursor from stream space to plane space
+	x_pos = (x_pos - x_plane) * pipe_ctx->plane_state->src_rect.width /
+			pipe_ctx->plane_state->dst_rect.width;
+	y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.height /
+			pipe_ctx->plane_state->dst_rect.height;
 
-	pos_cpy.x -= x_offset;
-	pos_cpy.y -= y_offset;
-	pos_cpy.x_hotspot += (x_plane - x_offset);
-	pos_cpy.y_hotspot += (y_plane - y_offset);
+	if (x_pos < 0) {
+		pos_cpy.x_hotspot -= x_pos;
+		x_pos = 0;
+	}
+
+	if (y_pos < 0) {
+		pos_cpy.y_hotspot -= y_pos;
+		y_pos = 0;
+	}
+
+	pos_cpy.x = (uint32_t)x_pos;
+	pos_cpy.y = (uint32_t)y_pos;
 
 	if (pipe_ctx->plane_state->address.type
 			== PLN_ADDR_TYPE_VIDEO_PROGRESSIVE)
@@ -2991,6 +2959,7 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	// Swap axis and mirror horizontally
 	if (param.rotation == ROTATION_ANGLE_90) {
 		uint32_t temp_x = pos_cpy.x;
+
 		pos_cpy.x = pipe_ctx->plane_res.scl_data.viewport.width -
 				(pos_cpy.y - pipe_ctx->plane_res.scl_data.viewport.x) + pipe_ctx->plane_res.scl_data.viewport.x;
 		pos_cpy.y = temp_x;
@@ -2998,26 +2967,44 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	// Swap axis and mirror vertically
 	else if (param.rotation == ROTATION_ANGLE_270) {
 		uint32_t temp_y = pos_cpy.y;
-		if (pos_cpy.x >  pipe_ctx->plane_res.scl_data.viewport.height) {
-			pos_cpy.x = pos_cpy.x - pipe_ctx->plane_res.scl_data.viewport.height;
-			pos_cpy.y = pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.x;
-		} else {
-			pos_cpy.y = 2 * pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.x;
-		}
+		int viewport_height =
+			pipe_ctx->plane_res.scl_data.viewport.height;
+
+		if (pipe_split_on) {
+			if (pos_cpy.x > viewport_height) {
+				pos_cpy.x = pos_cpy.x - viewport_height;
+				pos_cpy.y = viewport_height - pos_cpy.x;
+			} else {
+				pos_cpy.y = 2 * viewport_height - pos_cpy.x;
+			}
+		} else
+			pos_cpy.y = viewport_height - pos_cpy.x;
 		pos_cpy.x = temp_y;
 	}
 	// Mirror horizontally and vertically
 	else if (param.rotation == ROTATION_ANGLE_180) {
-		if (pos_cpy.x >= pipe_ctx->plane_res.scl_data.viewport.width + pipe_ctx->plane_res.scl_data.viewport.x) {
-			pos_cpy.x = 2 * pipe_ctx->plane_res.scl_data.viewport.width
-					- pos_cpy.x + 2 * pipe_ctx->plane_res.scl_data.viewport.x;
-		} else {
-			uint32_t temp_x = pos_cpy.x;
-			pos_cpy.x = 2 * pipe_ctx->plane_res.scl_data.viewport.x - pos_cpy.x;
-			if (temp_x >= pipe_ctx->plane_res.scl_data.viewport.x + (int)hubp->curs_attr.width
-					|| pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) {
-				pos_cpy.x = temp_x + pipe_ctx->plane_res.scl_data.viewport.width;
+		int viewport_width =
+			pipe_ctx->plane_res.scl_data.viewport.width;
+		int viewport_x =
+			pipe_ctx->plane_res.scl_data.viewport.x;
+
+		if (pipe_split_on) {
+			if (pos_cpy.x >= viewport_width + viewport_x) {
+				pos_cpy.x = 2 * viewport_width
+						- pos_cpy.x + 2 * viewport_x;
+			} else {
+				uint32_t temp_x = pos_cpy.x;
+
+				pos_cpy.x = 2 * viewport_x - pos_cpy.x;
+				if (temp_x >= viewport_x +
+					(int)hubp->curs_attr.width || pos_cpy.x
+					<= (int)hubp->curs_attr.width +
+					pipe_ctx->plane_state->src_rect.x) {
+					pos_cpy.x = temp_x + viewport_width;
+				}
 			}
+		} else {
+			pos_cpy.x = viewport_width - pos_cpy.x + 2 * viewport_x;
 		}
 		pos_cpy.y = pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.y;
 	}
@@ -3026,7 +3013,7 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	dpp->funcs->set_cursor_position(dpp, &pos_cpy, &param, hubp->curs_attr.width, hubp->curs_attr.height);
 }
 
-static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
+void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes;
 
@@ -3036,7 +3023,7 @@ static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
 		pipe_ctx->plane_res.dpp, attributes);
 }
 
-static void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx)
+void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx)
 {
 	uint32_t sdr_white_level = pipe_ctx->stream->cursor_attributes.sdr_white_level;
 	struct fixed31_32 multiplier;
@@ -3063,12 +3050,12 @@ static void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.dpp, &opt_attr);
 }
 
-/**
-* apply_front_porch_workaround  TODO FPGA still need?
-*
-* This is a workaround for a bug that has existed since R5xx and has not been
-* fixed keep Front porch at minimum 2 for Interlaced mode or 1 for progressive.
-*/
+/*
+ * apply_front_porch_workaround  TODO FPGA still need?
+ *
+ * This is a workaround for a bug that has existed since R5xx and has not been
+ * fixed keep Front porch at minimum 2 for Interlaced mode or 1 for progressive.
+ */
 static void apply_front_porch_workaround(
 	struct dc_crtc_timing *timing)
 {
@@ -3081,7 +3068,7 @@ static void apply_front_porch_workaround(
 	}
 }
 
-int get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx)
+int dcn10_get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx)
 {
 	const struct dc_crtc_timing *dc_crtc_timing = &pipe_ctx->stream->timing;
 	struct dc_crtc_timing patched_crtc_timing;
@@ -3110,34 +3097,8 @@ int get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx)
 	return vertical_line_start;
 }
 
-void lock_all_pipes(struct dc *dc,
-	struct dc_state *context,
-	bool lock)
-{
-	struct pipe_ctx *pipe_ctx;
-	struct timing_generator *tg;
-	int i;
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		pipe_ctx = &context->res_ctx.pipe_ctx[i];
-		tg = pipe_ctx->stream_res.tg;
-		/*
-		 * Only lock the top pipe's tg to prevent redundant
-		 * (un)locking. Also skip if pipe is disabled.
-		 */
-		if (pipe_ctx->top_pipe ||
-		    !pipe_ctx->stream || !pipe_ctx->plane_state ||
-		    !tg->funcs->is_tg_enabled(tg))
-			continue;
-
-		if (lock)
-			tg->funcs->lock(tg);
-		else
-			tg->funcs->unlock(tg);
-	}
-}
-
-static void calc_vupdate_position(
+static void dcn10_calc_vupdate_position(
+		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		uint32_t *start_line,
 		uint32_t *end_line)
@@ -3145,7 +3106,7 @@ static void calc_vupdate_position(
 	const struct dc_crtc_timing *dc_crtc_timing = &pipe_ctx->stream->timing;
 	int vline_int_offset_from_vupdate =
 			pipe_ctx->stream->periodic_interrupt0.lines_offset;
-	int vupdate_offset_from_vsync = get_vupdate_offset_from_vsync(pipe_ctx);
+	int vupdate_offset_from_vsync = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
 	int start_position;
 
 	if (vline_int_offset_from_vupdate > 0)
@@ -3166,7 +3127,8 @@ static void calc_vupdate_position(
 		*end_line = 2;
 }
 
-static void cal_vline_position(
+static void dcn10_cal_vline_position(
+		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum vline_select vline,
 		uint32_t *start_line,
@@ -3181,7 +3143,8 @@ static void cal_vline_position(
 
 	switch (ref_point) {
 	case START_V_UPDATE:
-		calc_vupdate_position(
+		dcn10_calc_vupdate_position(
+				dc,
 				pipe_ctx,
 				start_line,
 				end_line);
@@ -3195,7 +3158,8 @@ static void cal_vline_position(
 	}
 }
 
-static void dcn10_setup_periodic_interrupt(
+void dcn10_setup_periodic_interrupt(
+		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum vline_select vline)
 {
@@ -3205,7 +3169,7 @@ static void dcn10_setup_periodic_interrupt(
 		uint32_t start_line = 0;
 		uint32_t end_line = 0;
 
-		cal_vline_position(pipe_ctx, vline, &start_line, &end_line);
+		dcn10_cal_vline_position(dc, pipe_ctx, vline, &start_line, &end_line);
 
 		tg->funcs->setup_vertical_interrupt0(tg, start_line, end_line);
 
@@ -3216,10 +3180,10 @@ static void dcn10_setup_periodic_interrupt(
 	}
 }
 
-static void dcn10_setup_vupdate_interrupt(struct pipe_ctx *pipe_ctx)
+void dcn10_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
-	int start_line = get_vupdate_offset_from_vsync(pipe_ctx);
+	int start_line = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
 
 	if (start_line < 0) {
 		ASSERT(0);
@@ -3230,12 +3194,13 @@ static void dcn10_setup_vupdate_interrupt(struct pipe_ctx *pipe_ctx)
 		tg->funcs->setup_vertical_interrupt2(tg, start_line);
 }
 
-static void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx,
+void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx,
 		struct dc_link_settings *link_settings)
 {
 	struct encoder_unblank_param params = { { 0 } };
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
+	struct dce_hwseq *hws = link->dc->hwseq;
 
 	/* only 3 items below are used by unblank */
 	params.timing = pipe_ctx->stream->timing;
@@ -3249,11 +3214,11 @@ static void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx,
 	}
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, true);
+		hws->funcs.edp_backlight_control(link, true);
 	}
 }
 
-static void dcn10_send_immediate_sdp_message(struct pipe_ctx *pipe_ctx,
+void dcn10_send_immediate_sdp_message(struct pipe_ctx *pipe_ctx,
 				const uint8_t *custom_sdp_message,
 				unsigned int sdp_message_size)
 {
@@ -3264,7 +3229,7 @@ static void dcn10_send_immediate_sdp_message(struct pipe_ctx *pipe_ctx,
 				sdp_message_size);
 	}
 }
-static enum dc_status dcn10_set_clock(struct dc *dc,
+enum dc_status dcn10_set_clock(struct dc *dc,
 			enum dc_clock_type clock_type,
 			uint32_t clk_khz,
 			uint32_t stepping)
@@ -3304,7 +3269,7 @@ static enum dc_status dcn10_set_clock(struct dc *dc,
 
 }
 
-static void dcn10_get_clock(struct dc *dc,
+void dcn10_get_clock(struct dc *dc,
 			enum dc_clock_type clock_type,
 			struct dc_clock_config *clock_cfg)
 {
@@ -3314,77 +3279,3 @@ static void dcn10_get_clock(struct dc *dc,
 				dc->clk_mgr->funcs->get_clock(dc->clk_mgr, context, clock_type, clock_cfg);
 
 }
-
-static const struct hw_sequencer_funcs dcn10_funcs = {
-	.program_gamut_remap = dcn10_program_gamut_remap,
-	.init_hw = dcn10_init_hw,
-	.init_pipes = dcn10_init_pipes,
-	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
-	.apply_ctx_for_surface = dcn10_apply_ctx_for_surface,
-	.update_plane_addr = dcn10_update_plane_addr,
-	.plane_atomic_disconnect = hwss1_plane_atomic_disconnect,
-	.update_dchub = dcn10_update_dchub,
-	.update_mpcc = dcn10_update_mpcc,
-	.update_pending_status = dcn10_update_pending_status,
-	.set_input_transfer_func = dcn10_set_input_transfer_func,
-	.set_output_transfer_func = dcn10_set_output_transfer_func,
-	.program_output_csc = dcn10_program_output_csc,
-	.power_down = dce110_power_down,
-	.enable_accelerated_mode = dce110_enable_accelerated_mode,
-	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
-	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
-	.update_info_frame = dce110_update_info_frame,
-	.send_immediate_sdp_message = dcn10_send_immediate_sdp_message,
-	.enable_stream = dce110_enable_stream,
-	.disable_stream = dce110_disable_stream,
-	.unblank_stream = dcn10_unblank_stream,
-	.blank_stream = dce110_blank_stream,
-	.enable_audio_stream = dce110_enable_audio_stream,
-	.disable_audio_stream = dce110_disable_audio_stream,
-	.enable_display_power_gating = dcn10_dummy_display_power_gating,
-	.disable_plane = dcn10_disable_plane,
-	.blank_pixel_data = dcn10_blank_pixel_data,
-	.pipe_control_lock = dcn10_pipe_control_lock,
-	.prepare_bandwidth = dcn10_prepare_bandwidth,
-	.optimize_bandwidth = dcn10_optimize_bandwidth,
-	.reset_hw_ctx_wrap = dcn10_reset_hw_ctx_wrap,
-	.enable_stream_timing = dcn10_enable_stream_timing,
-	.set_drr = dcn10_set_drr,
-	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
-	.setup_stereo = dcn10_setup_stereo,
-	.set_avmute = dce110_set_avmute,
-	.log_hw_state = dcn10_log_hw_state,
-	.get_hw_state = dcn10_get_hw_state,
-	.clear_status_bits = dcn10_clear_status_bits,
-	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
-	.edp_backlight_control = dce110_edp_backlight_control,
-	.edp_power_control = dce110_edp_power_control,
-	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
-	.set_cursor_position = dcn10_set_cursor_position,
-	.set_cursor_attribute = dcn10_set_cursor_attribute,
-	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
-	.disable_stream_gating = NULL,
-	.enable_stream_gating = NULL,
-	.setup_periodic_interrupt = dcn10_setup_periodic_interrupt,
-	.setup_vupdate_interrupt = dcn10_setup_vupdate_interrupt,
-	.set_clock = dcn10_set_clock,
-	.get_clock = dcn10_get_clock,
-	.did_underflow_occur = dcn10_did_underflow_occur,
-	.init_blank = NULL,
-	.disable_vga = dcn10_disable_vga,
-	.bios_golden_init = dcn10_bios_golden_init,
-	.plane_atomic_disable = dcn10_plane_atomic_disable,
-	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
-	.enable_power_gating_plane = dcn10_enable_power_gating_plane,
-	.dpp_pg_control = dcn10_dpp_pg_control,
-	.hubp_pg_control = dcn10_hubp_pg_control,
-	.dsc_pg_control = NULL,
-};
-
-
-void dcn10_hw_sequencer_construct(struct dc *dc)
-{
-	dc->hwss = dcn10_funcs;
-}
-
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index d3616b1948cc..4d20f6586bb5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -27,68 +27,160 @@
 #define __DC_HWSS_DCN10_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 
 void dcn10_hw_sequencer_construct(struct dc *dc);
-extern void fill_display_configs(
-	const struct dc_state *context,
-	struct dm_pp_display_configuration *pp_display_cfg);
-
-bool is_rgb_cspace(enum dc_color_space output_color_space);
-
-void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-void dcn10_verify_allow_pstate_change_high(struct dc *dc);
 
+int dcn10_get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx);
+void dcn10_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+enum dc_status dcn10_enable_stream_timing(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
+void dcn10_optimize_bandwidth(
+		struct dc *dc,
+		struct dc_state *context);
+void dcn10_prepare_bandwidth(
+		struct dc *dc,
+		struct dc_state *context);
+void dcn10_pipe_control_lock(
+	struct dc *dc,
+	struct pipe_ctx *pipe,
+	bool lock);
+void dcn10_blank_pixel_data(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		bool blank);
+void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx,
+		struct dc_link_settings *link_settings);
+void dcn10_program_output_csc(struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		enum dc_color_space colorspace,
+		uint16_t *matrix,
+		int opp_id);
+bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+				const struct dc_stream_state *stream);
+bool dcn10_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state);
+void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_reset_hw_ctx_wrap(
+		struct dc *dc,
+		struct dc_state *context);
+void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_apply_ctx_for_surface(
+		struct dc *dc,
+		const struct dc_stream_state *stream,
+		int num_planes,
+		struct dc_state *context);
+void dcn10_hubp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int hubp_inst,
+		bool power_on);
+void dcn10_dpp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int dpp_inst,
+		bool power_on);
+void dcn10_enable_power_gating_plane(
+	struct dce_hwseq *hws,
+	bool enable);
+void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_disable_vga(
+	struct dce_hwseq *hws);
 void dcn10_program_pipe(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context);
-
-void dcn10_get_hw_state(
+void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx);
+void dcn10_init_hw(struct dc *dc);
+void dcn10_init_pipes(struct dc *dc, struct dc_state *context);
+enum dc_status dce110_apply_ctx_to_hw(
+		struct dc *dc,
+		struct dc_state *context);
+void dcn10_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data);
+void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx);
+void dce110_power_down(struct dc *dc);
+void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context);
+void dcn10_enable_timing_synchronization(
+		struct dc *dc,
+		int group_index,
+		int group_size,
+		struct pipe_ctx *grouped_pipes[]);
+void dcn10_enable_per_frame_crtc_position_reset(
+		struct dc *dc,
+		int group_size,
+		struct pipe_ctx *grouped_pipes[]);
+void dce110_update_info_frame(struct pipe_ctx *pipe_ctx);
+void dcn10_send_immediate_sdp_message(struct pipe_ctx *pipe_ctx,
+		const uint8_t *custom_sdp_message,
+		unsigned int sdp_message_size);
+void dce110_blank_stream(struct pipe_ctx *pipe_ctx);
+void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx);
+void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx);
+bool dcn10_dummy_display_power_gating(
 		struct dc *dc,
-		char *pBuf, unsigned int bufSize,
+		uint8_t controller_id,
+		struct dc_bios *dcb,
+		enum pipe_gating_control power_gating);
+void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
+		int num_pipes, unsigned int vmin, unsigned int vmax,
+		unsigned int vmid, unsigned int vmid_frame_number);
+void dcn10_get_position(struct pipe_ctx **pipe_ctx,
+		int num_pipes,
+		struct crtc_position *position);
+void dcn10_set_static_screen_control(struct pipe_ctx **pipe_ctx,
+		int num_pipes, const struct dc_static_screen_params *params);
+void dcn10_setup_stereo(struct pipe_ctx *pipe_ctx, struct dc *dc);
+void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable);
+void dcn10_log_hw_state(struct dc *dc,
+		struct dc_log_buffer_ctx *log_ctx);
+void dcn10_get_hw_state(struct dc *dc,
+		char *pBuf,
+		unsigned int bufSize,
 		unsigned int mask);
-
 void dcn10_clear_status_bits(struct dc *dc, unsigned int mask);
-
-bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
-
-bool is_upper_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
-
-bool is_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
-
-void dcn10_program_pte_vm(struct dce_hwseq *hws, struct hubp *hubp);
-
-void set_hdr_multiplier(struct pipe_ctx *pipe_ctx);
-
+void dcn10_wait_for_mpcc_disconnect(
+		struct dc *dc,
+		struct resource_pool *res_pool,
+		struct pipe_ctx *pipe_ctx);
+void dce110_edp_backlight_control(
+		struct dc_link *link,
+		bool enable);
+void dce110_edp_power_control(
+		struct dc_link *link,
+		bool power_up);
+void dce110_edp_wait_for_hpd_ready(
+		struct dc_link *link,
+		bool power_up);
+void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx);
+void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx);
+void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx);
+void dcn10_setup_periodic_interrupt(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		enum vline_select vline);
+enum dc_status dcn10_set_clock(struct dc *dc,
+		enum dc_clock_type clock_type,
+		uint32_t clk_khz,
+		uint32_t stepping);
+void dcn10_get_clock(struct dc *dc,
+		enum dc_clock_type clock_type,
+		struct dc_clock_config *clock_cfg);
+bool dcn10_did_underflow_occur(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_bios_golden_init(struct dc *dc);
+void dcn10_plane_atomic_power_down(struct dc *dc,
+		struct dpp *dpp,
+		struct hubp *hubp);
 void dcn10_get_surface_visual_confirm_color(
 		const struct pipe_ctx *pipe_ctx,
 		struct tg_color *color);
-
 void dcn10_get_hdr_visual_confirm_color(
 		struct pipe_ctx *pipe_ctx,
 		struct tg_color *color);
-
-bool dcn10_did_underflow_occur(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-void update_dchubp_dpp(
-	struct dc *dc,
-	struct pipe_ctx *pipe_ctx,
-	struct dc_state *context);
-
-struct pipe_ctx *find_top_pipe_for_stream(
-		struct dc *dc,
-		struct dc_state *context,
-		const struct dc_stream_state *stream);
-
-int get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx);
-
-void dcn10_build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
-		const struct dc_plane_state *plane_state);
-void lock_all_pipes(struct dc *dc,
-	struct dc_state *context,
-	bool lock);
+void dcn10_set_hdr_multiplier(struct pipe_ctx *pipe_ctx);
+void dcn10_verify_allow_pstate_change_high(struct dc *dc);
 
 #endif /* __DC_HWSS_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.h
new file mode 100644
index 000000000000..596f95c22e85
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.h
@@ -0,0 +1,43 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_HWSS_DCN10_DEBUG_H__
+#define __DC_HWSS_DCN10_DEBUG_H__
+
+#include "core_types.h"
+
+struct dc;
+
+void dcn10_clear_status_bits(struct dc *dc, unsigned int mask);
+
+void dcn10_log_hw_state(struct dc *dc,
+		struct dc_log_buffer_ctx *log_ctx);
+
+void dcn10_get_hw_state(struct dc *dc,
+		char *pBuf,
+		unsigned int bufSize,
+		unsigned int mask);
+
+#endif /* __DC_HWSS_DCN10_DEBUG_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
new file mode 100644
index 000000000000..e7e5352ec424
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "hw_sequencer_private.h"
+#include "dce110/dce110_hw_sequencer.h"
+#include "dcn10_hw_sequencer.h"
+
+static const struct hw_sequencer_funcs dcn10_funcs = {
+	.program_gamut_remap = dcn10_program_gamut_remap,
+	.init_hw = dcn10_init_hw,
+	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
+	.apply_ctx_for_surface = dcn10_apply_ctx_for_surface,
+	.update_plane_addr = dcn10_update_plane_addr,
+	.update_dchub = dcn10_update_dchub,
+	.update_pending_status = dcn10_update_pending_status,
+	.program_output_csc = dcn10_program_output_csc,
+	.enable_accelerated_mode = dce110_enable_accelerated_mode,
+	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
+	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
+	.update_info_frame = dce110_update_info_frame,
+	.send_immediate_sdp_message = dcn10_send_immediate_sdp_message,
+	.enable_stream = dce110_enable_stream,
+	.disable_stream = dce110_disable_stream,
+	.unblank_stream = dcn10_unblank_stream,
+	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
+	.disable_plane = dcn10_disable_plane,
+	.pipe_control_lock = dcn10_pipe_control_lock,
+	.prepare_bandwidth = dcn10_prepare_bandwidth,
+	.optimize_bandwidth = dcn10_optimize_bandwidth,
+	.set_drr = dcn10_set_drr,
+	.get_position = dcn10_get_position,
+	.set_static_screen_control = dcn10_set_static_screen_control,
+	.setup_stereo = dcn10_setup_stereo,
+	.set_avmute = dce110_set_avmute,
+	.log_hw_state = dcn10_log_hw_state,
+	.get_hw_state = dcn10_get_hw_state,
+	.clear_status_bits = dcn10_clear_status_bits,
+	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_power_control = dce110_edp_power_control,
+	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
+	.set_cursor_position = dcn10_set_cursor_position,
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
+	.setup_periodic_interrupt = dcn10_setup_periodic_interrupt,
+	.set_clock = dcn10_set_clock,
+	.get_clock = dcn10_get_clock,
+	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+};
+
+static const struct hwseq_private_funcs dcn10_private_funcs = {
+	.init_pipes = dcn10_init_pipes,
+	.update_plane_addr = dcn10_update_plane_addr,
+	.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
+	.program_pipe = dcn10_program_pipe,
+	.update_mpcc = dcn10_update_mpcc,
+	.set_input_transfer_func = dcn10_set_input_transfer_func,
+	.set_output_transfer_func = dcn10_set_output_transfer_func,
+	.power_down = dce110_power_down,
+	.enable_display_power_gating = dcn10_dummy_display_power_gating,
+	.blank_pixel_data = dcn10_blank_pixel_data,
+	.reset_hw_ctx_wrap = dcn10_reset_hw_ctx_wrap,
+	.enable_stream_timing = dcn10_enable_stream_timing,
+	.edp_backlight_control = dce110_edp_backlight_control,
+	.disable_stream_gating = NULL,
+	.enable_stream_gating = NULL,
+	.setup_vupdate_interrupt = dcn10_setup_vupdate_interrupt,
+	.did_underflow_occur = dcn10_did_underflow_occur,
+	.init_blank = NULL,
+	.disable_vga = dcn10_disable_vga,
+	.bios_golden_init = dcn10_bios_golden_init,
+	.plane_atomic_disable = dcn10_plane_atomic_disable,
+	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
+	.enable_power_gating_plane = dcn10_enable_power_gating_plane,
+	.dpp_pg_control = dcn10_dpp_pg_control,
+	.hubp_pg_control = dcn10_hubp_pg_control,
+	.dsc_pg_control = NULL,
+	.get_surface_visual_confirm_color = dcn10_get_surface_visual_confirm_color,
+	.get_hdr_visual_confirm_color = dcn10_get_hdr_visual_confirm_color,
+	.set_hdr_multiplier = dcn10_set_hdr_multiplier,
+	.verify_allow_pstate_change_high = dcn10_verify_allow_pstate_change_high,
+};
+
+void dcn10_hw_sequencer_construct(struct dc *dc)
+{
+	dc->hwss = dcn10_funcs;
+	dc->hwseq->funcs = dcn10_private_funcs;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.h
new file mode 100644
index 000000000000..8c6fd7b844a4
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_DCN10_INIT_H__
+#define __DC_DCN10_INIT_H__
+
+struct dc;
+
+void dcn10_hw_sequencer_construct(struct dc *dc);
+
+#endif /* __DC_DCN10_INIT_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.c
index 0fb9e440cb9d..f05371c1fc36 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.c
@@ -53,11 +53,9 @@ static const struct ipp_funcs dcn10_ipp_funcs = {
 	.ipp_destroy			= dcn10_ipp_destroy
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 static const struct ipp_funcs dcn20_ipp_funcs = {
 	.ipp_destroy			= dcn10_ipp_destroy
 };
-#endif
 
 void dcn10_ipp_construct(
 	struct dcn10_ipp *ippn10,
@@ -76,7 +74,6 @@ void dcn10_ipp_construct(
 	ippn10->ipp_mask = ipp_mask;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 void dcn20_ipp_construct(
 	struct dcn10_ipp *ippn10,
 	struct dc_context *ctx,
@@ -93,4 +90,3 @@ void dcn20_ipp_construct(
 	ippn10->ipp_shift = ipp_shift;
 	ippn10->ipp_mask = ipp_mask;
 }
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.h
index cfa24459242b..f0e0d07b0311 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.h
@@ -49,7 +49,6 @@
 	SRI(CURSOR_HOT_SPOT, CURSOR, id), \
 	SRI(CURSOR_DST_OFFSET, CURSOR, id)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define IPP_REG_LIST_DCN20(id) \
 	IPP_REG_LIST_DCN(id), \
 	SRI(CURSOR_SETTINGS, HUBPREQ, id), \
@@ -60,7 +59,6 @@
 	SRI(CURSOR_POSITION, CURSOR0_, id), \
 	SRI(CURSOR_HOT_SPOT, CURSOR0_, id), \
 	SRI(CURSOR_DST_OFFSET, CURSOR0_, id)
-#endif
 
 #define CURSOR0_CURSOR_CONTROL__CURSOR_2X_MAGNIFY__SHIFT	0x4
 #define CURSOR0_CURSOR_CONTROL__CURSOR_2X_MAGNIFY_MASK		0x00000010L
@@ -105,7 +103,6 @@
 	IPP_SF(CURSOR0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh), \
 	IPP_SF(CNVC_CFG0_FORMAT_CONTROL, OUTPUT_FP, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define IPP_MASK_SH_LIST_DCN20(mask_sh) \
 	IPP_MASK_SH_LIST_DCN(mask_sh), \
 	IPP_SF(HUBPREQ0_CURSOR_SETTINGS, CURSOR0_DST_Y_OFFSET, mask_sh), \
@@ -124,7 +121,6 @@
 	IPP_SF(CURSOR0_0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_X, mask_sh), \
 	IPP_SF(CURSOR0_0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_Y, mask_sh), \
 	IPP_SF(CURSOR0_0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh)
-#endif
 
 #define IPP_DCN10_REG_FIELD_LIST(type) \
 	type CNVC_SURFACE_PIXEL_FORMAT; \
@@ -196,13 +192,11 @@ void dcn10_ipp_construct(struct dcn10_ipp *ippn10,
 	const struct dcn10_ipp_shift *ipp_shift,
 	const struct dcn10_ipp_mask *ipp_mask);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 void dcn20_ipp_construct(struct dcn10_ipp *ippn10,
 	struct dc_context *ctx,
 	int inst,
 	const struct dcn10_ipp_registers *regs,
 	const struct dcn10_ipp_shift *ipp_shift,
 	const struct dcn10_ipp_mask *ipp_mask);
-#endif
 
 #endif /* _DCN10_IPP_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
index 88fcc395adf5..eb13589b9a81 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -72,9 +72,7 @@
 struct dcn10_link_enc_aux_registers {
 	uint32_t AUX_CONTROL;
 	uint32_t AUX_DPHY_RX_CONTROL0;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	uint32_t AUX_DPHY_TX_CONTROL;
-#endif
 };
 
 struct dcn10_link_enc_hpd_registers {
@@ -106,7 +104,6 @@ struct dcn10_link_enc_registers {
 	uint32_t DP_DPHY_HBR2_PATTERN_CONTROL;
 	uint32_t DP_SEC_CNTL1;
 	uint32_t TMDS_CTL_BITS;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* DCCG  */
 	uint32_t CLOCK_ENABLE;
 	/* DIG */
@@ -127,6 +124,26 @@ struct dcn10_link_enc_registers {
 	uint32_t RDPCSTX_PHY_CNTL13;
 	uint32_t RDPCSTX_PHY_CNTL14;
 	uint32_t RDPCSTX_PHY_CNTL15;
+	uint32_t RDPCSTX_CNTL;
+	uint32_t RDPCSTX_CLOCK_CNTL;
+	uint32_t RDPCSTX_PHY_CNTL0;
+	uint32_t RDPCSTX_PHY_CNTL2;
+	uint32_t RDPCSTX_PLL_UPDATE_DATA;
+	uint32_t RDPCS_TX_CR_ADDR;
+	uint32_t RDPCS_TX_CR_DATA;
+	uint32_t DPCSTX_TX_CLOCK_CNTL;
+	uint32_t DPCSTX_TX_CNTL;
+	uint32_t RDPCSTX_INTERRUPT_CONTROL;
+	uint32_t RDPCSTX_PHY_FUSE0;
+	uint32_t RDPCSTX_PHY_FUSE1;
+	uint32_t RDPCSTX_PHY_FUSE2;
+	uint32_t RDPCSTX_PHY_FUSE3;
+	uint32_t RDPCSTX_PHY_RX_LD_VAL;
+	uint32_t DPCSTX_DEBUG_CONFIG;
+	uint32_t RDPCSTX_DEBUG_CONFIG;
+	uint32_t RDPCSTX0_RDPCSTX_SCRATCH;
+	uint32_t RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG;
+	uint32_t DCIO_SOFT_RESET;
 	/* indirect registers */
 	uint32_t RAWLANE0_DIG_PCS_XF_RX_OVRD_IN_2;
 	uint32_t RAWLANE0_DIG_PCS_XF_RX_OVRD_IN_3;
@@ -136,7 +153,6 @@ struct dcn10_link_enc_registers {
 	uint32_t RAWLANE2_DIG_PCS_XF_RX_OVRD_IN_3;
 	uint32_t RAWLANE3_DIG_PCS_XF_RX_OVRD_IN_2;
 	uint32_t RAWLANE3_DIG_PCS_XF_RX_OVRD_IN_3;
-#endif
 };
 
 #define LE_SF(reg_name, field_name, post_fix)\
@@ -242,7 +258,6 @@ struct dcn10_link_enc_registers {
 	type AUX_LS_READ_EN;\
 	type AUX_RX_RECEIVE_WINDOW
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 #define DCN20_LINK_ENCODER_DPCS_REG_FIELD_LIST(type) \
 		type RDPCS_PHY_DP_TX0_DATA_EN;\
@@ -423,20 +438,15 @@ struct dcn10_link_enc_registers {
 	type AUX_TX_PRECHARGE_SYMBOLS; \
 	type AUX_MODE_DET_CHECK_DELAY;\
 	type DPCS_DBG_CBUS_DIS
-#endif
 
 struct dcn10_link_enc_shift {
 	DCN_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	DCN20_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
-#endif
 };
 
 struct dcn10_link_enc_mask {
 	DCN_LINK_ENCODER_REG_FIELD_LIST(uint32_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	DCN20_LINK_ENCODER_REG_FIELD_LIST(uint32_t);
-#endif
 };
 
 struct dcn10_link_encoder {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 8b2f29f6dabd..04f863499cfb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -42,20 +42,27 @@ void mpc1_set_bg_color(struct mpc *mpc,
 		int mpcc_id)
 {
 	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+	struct mpcc *bottommost_mpcc = mpc1_get_mpcc(mpc, mpcc_id);
+	uint32_t bg_r_cr, bg_g_y, bg_b_cb;
+
+	/* find bottommost mpcc. */
+	while (bottommost_mpcc->mpcc_bot) {
+		bottommost_mpcc = bottommost_mpcc->mpcc_bot;
+	}
 
 	/* mpc color is 12 bit.  tg_color is 10 bit */
 	/* todo: might want to use 16 bit to represent color and have each
 	 * hw block translate to correct color depth.
 	 */
-	uint32_t bg_r_cr = bg_color->color_r_cr << 2;
-	uint32_t bg_g_y = bg_color->color_g_y << 2;
-	uint32_t bg_b_cb = bg_color->color_b_cb << 2;
+	bg_r_cr = bg_color->color_r_cr << 2;
+	bg_g_y = bg_color->color_g_y << 2;
+	bg_b_cb = bg_color->color_b_cb << 2;
 
-	REG_SET(MPCC_BG_R_CR[mpcc_id], 0,
+	REG_SET(MPCC_BG_R_CR[bottommost_mpcc->mpcc_id], 0,
 			MPCC_BG_R_CR, bg_r_cr);
-	REG_SET(MPCC_BG_G_Y[mpcc_id], 0,
+	REG_SET(MPCC_BG_G_Y[bottommost_mpcc->mpcc_id], 0,
 			MPCC_BG_G_Y, bg_g_y);
-	REG_SET(MPCC_BG_B_CB[mpcc_id], 0,
+	REG_SET(MPCC_BG_B_CB[bottommost_mpcc->mpcc_id], 0,
 			MPCC_BG_B_CB, bg_b_cb);
 }
 
@@ -457,12 +464,10 @@ static const struct mpc_funcs dcn10_mpc_funcs = {
 	.assert_mpcc_idle_before_connect = mpc1_assert_mpcc_idle_before_connect,
 	.init_mpcc_list_from_hw = mpc1_init_mpcc_list_from_hw,
 	.update_blending = mpc1_update_blending,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	.set_denorm = NULL,
 	.set_denorm_clamp = NULL,
 	.set_output_csc = NULL,
 	.set_output_gamma = NULL,
-#endif
 };
 
 void dcn10_mpc_construct(struct dcn10_mpc *mpc10,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
index 0a9ad692f541..d79718fde5a6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
@@ -373,11 +373,9 @@ void opp1_program_oppbuf(
 	 */
 	REG_UPDATE(OPPBUF_CONTROL, OPPBUF_PIXEL_REPETITION, oppbuf->pixel_repetition);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* Controls the number of padded pixels at the end of a segment */
 	if (REG(OPPBUF_CONTROL1))
 		REG_UPDATE(OPPBUF_CONTROL1, OPPBUF_NUM_SEGMENT_PADDED_PIXELS, oppbuf->num_segment_padded_pixels);
-#endif
 }
 
 void opp1_pipe_clock_control(struct output_pixel_processor *opp, bool enable)
@@ -404,9 +402,8 @@ static const struct opp_funcs dcn10_opp_funcs = {
 		.opp_program_bit_depth_reduction = opp1_program_bit_depth_reduction,
 		.opp_program_stereo = opp1_program_stereo,
 		.opp_pipe_clock_control = opp1_pipe_clock_control,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		.opp_set_disp_pattern_generator = NULL,
-#endif
+		.dpg_is_blanked = NULL,
 		.opp_destroy = opp1_destroy
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index dabccbd49ad4..a9a43b397db9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -457,11 +457,16 @@ static bool optc1_enable_crtc(struct timing_generator *optc)
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 1);
 
+	REG_SEQ_START();
+
 	/* Enable CRTC */
 	REG_UPDATE_2(OTG_CONTROL,
 			OTG_DISABLE_POINT_CNTL, 3,
 			OTG_MASTER_EN, 1);
 
+	REG_SEQ_SUBMIT();
+	REG_SEQ_WAIT_DONE();
+
 	return true;
 }
 
@@ -784,21 +789,26 @@ void optc1_set_early_control(
 
 void optc1_set_static_screen_control(
 	struct timing_generator *optc,
-	uint32_t value)
+	uint32_t event_triggers,
+	uint32_t num_frames)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
+	// By register spec, it only takes 8 bit value
+	if (num_frames > 0xFF)
+		num_frames = 0xFF;
+
 	/* Bit 8 is no longer applicable in RV for PSR case,
 	 * set bit 8 to 0 if given
 	 */
-	if ((value & STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN)
+	if ((event_triggers & STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN)
 			!= 0)
-		value = value &
+		event_triggers = event_triggers &
 		~STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN;
 
 	REG_SET_2(OTG_STATIC_SCREEN_CONTROL, 0,
-			OTG_STATIC_SCREEN_EVENT_MASK, value,
-			OTG_STATIC_SCREEN_FRAME_COUNT, 2);
+			OTG_STATIC_SCREEN_EVENT_MASK, event_triggers,
+			OTG_STATIC_SCREEN_FRAME_COUNT, num_frames);
 }
 
 void optc1_setup_manual_trigger(struct timing_generator *optc)
@@ -1497,7 +1507,6 @@ void dcn10_timing_generator_init(struct optc *optc1)
 	optc1->min_v_sync_width = 1;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* "Containter" vs. "pixel" is a concept within HW blocks, mostly those closer to the back-end. It works like this:
  *
  * - In most of the formats (RGB or YCbCr 4:4:4, 4:2:2 uncompressed and DSC 4:2:2 Simple) pixel rate is the same as
@@ -1510,15 +1519,12 @@ void dcn10_timing_generator_init(struct optc *optc1)
  *   to it) and has to be treated the same as 4:2:0, i.e. target containter rate has to be halved in this case as well.
  *
  */
-#endif
 bool optc1_is_two_pixels_per_containter(const struct dc_crtc_timing *timing)
 {
 	bool two_pix = timing->pixel_encoding == PIXEL_ENCODING_YCBCR420;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	two_pix = two_pix || (timing->flags.DSC && timing->pixel_encoding == PIXEL_ENCODING_YCBCR422
 			&& !timing->dsc_cfg.ycbcr422_simple);
-#endif
 	return two_pix;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index c8d795b335ba..f277656d5464 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -165,13 +165,11 @@ struct dcn_optc_registers {
 	uint32_t OTG_CRC0_WINDOWB_X_CONTROL;
 	uint32_t OTG_CRC0_WINDOWB_Y_CONTROL;
 	uint32_t GSL_SOURCE_SELECT;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	uint32_t DWB_SOURCE_SELECT;
 	uint32_t OTG_DSC_START_POSITION;
 	uint32_t OPTC_DATA_FORMAT_CONTROL;
 	uint32_t OPTC_BYTES_PER_PIXEL;
 	uint32_t OPTC_WIDTH_CONTROL;
-#endif
 };
 
 #define TG_COMMON_MASK_SH_LIST_DCN(mask_sh)\
@@ -456,7 +454,6 @@ struct dcn_optc_registers {
 	type MANUAL_FLOW_CONTROL;\
 	type MANUAL_FLOW_CONTROL_SEL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #define TG_REG_FIELD_LIST(type) \
 	TG_REG_FIELD_LIST_DCN1_0(type)\
@@ -479,12 +476,6 @@ struct dcn_optc_registers {
 	type OPTC_DWB0_SOURCE_SELECT;\
 	type OPTC_DWB1_SOURCE_SELECT;
 
-#else
-
-#define TG_REG_FIELD_LIST(type) \
-	TG_REG_FIELD_LIST_DCN1_0(type)
-
-#endif
 
 
 struct dcn_optc_shift {
@@ -542,6 +533,7 @@ struct dcn_otg_state {
 	uint32_t h_total;
 	uint32_t underflow_occurred_status;
 	uint32_t otg_enabled;
+	uint32_t blank_enabled;
 };
 
 void optc1_read_otg_state(struct optc *optc1,
@@ -633,7 +625,8 @@ void optc1_set_drr(
 
 void optc1_set_static_screen_control(
 	struct timing_generator *optc,
-	uint32_t value);
+	uint32_t event_triggers,
+	uint32_t num_frames);
 
 void optc1_program_stereo(struct timing_generator *optc,
 	const struct dc_crtc_timing *timing, struct crtc_stereo_flags *flags);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 15640aedd664..3b71898e859e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -28,6 +28,8 @@
 #include "dm_services.h"
 #include "dc.h"
 
+#include "dcn10_init.h"
+
 #include "resource.h"
 #include "include/irq_service_interface.h"
 #include "dcn10_resource.h"
@@ -919,7 +921,7 @@ static struct pp_smu_funcs *dcn10_pp_smu_create(struct dc_context *ctx)
 	return pp_smu;
 }
 
-static void destruct(struct dcn10_resource_pool *pool)
+static void dcn10_resource_destruct(struct dcn10_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -1166,7 +1168,7 @@ static void dcn10_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dcn10_resource_pool *dcn10_pool = TO_DCN10_RES_POOL(*pool);
 
-	destruct(dcn10_pool);
+	dcn10_resource_destruct(dcn10_pool);
 	kfree(dcn10_pool);
 	*pool = NULL;
 }
@@ -1305,7 +1307,7 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
 	return value;
 }
 
-static bool construct(
+static bool dcn10_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dcn10_resource_pool *pool)
@@ -1592,7 +1594,7 @@ static bool construct(
 
 fail:
 
-	destruct(pool);
+	dcn10_resource_destruct(pool);
 
 	return false;
 }
@@ -1607,7 +1609,7 @@ struct resource_pool *dcn10_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(init_data->num_virtual_links, dc, pool))
+	if (dcn10_resource_construct(init_data->num_virtual_links, dc, pool))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index 06e5bbb4545c..376c4264d295 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -247,6 +247,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting)
 {
 	uint32_t h_active_start;
@@ -312,10 +313,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	 * Pixel Encoding/Colorimetry Format and that a Sink device shall ignore MISC1, bit 7,
 	 * and MISC0, bits 7:1 (MISC1, bit 7, and MISC0, bits 7:1, become "don't care").
 	 */
-	if ((hw_crtc_timing.pixel_encoding == PIXEL_ENCODING_YCBCR420) ||
-			(output_color_space == COLOR_SPACE_2020_YCBCR) ||
-			(output_color_space == COLOR_SPACE_2020_RGB_FULLRANGE) ||
-			(output_color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE))
+	if (use_vsc_sdp_for_colorimetry)
 		misc1 = misc1 | 0x40;
 	else
 		misc1 = misc1 & ~0x40;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
index c9cbc21d121e..f9b9e221c698 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
@@ -163,14 +163,12 @@ struct dcn10_stream_enc_registers {
 	uint32_t DP_MSA_TIMING_PARAM3;
 	uint32_t DP_MSA_TIMING_PARAM4;
 	uint32_t HDMI_DB_CONTROL;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t DP_DSC_CNTL;
 	uint32_t DP_DSC_BYTES_PER_PIXEL;
 	uint32_t DME_CONTROL;
 	uint32_t DP_SEC_METADATA_TRANSMISSION;
 	uint32_t HDMI_METADATA_PACKET_CONTROL;
 	uint32_t DP_SEC_FRAMING4;
-#endif
 	uint32_t DIG_CLOCK_PATTERN;
 };
 
@@ -466,7 +464,6 @@ struct dcn10_stream_enc_registers {
 	type DIG_SOURCE_SELECT;\
 	type DIG_CLOCK_PATTERN
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define SE_REG_FIELD_LIST_DCN2_0(type) \
 	type DP_DSC_MODE;\
 	type DP_DSC_SLICE_WIDTH;\
@@ -485,20 +482,15 @@ struct dcn10_stream_enc_registers {
 	type DOLBY_VISION_EN;\
 	type DP_PIXEL_COMBINE;\
 	type DP_SST_SDP_SPLITTING
-#endif
 
 struct dcn10_stream_encoder_shift {
 	SE_REG_FIELD_LIST_DCN1_0(uint8_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	SE_REG_FIELD_LIST_DCN2_0(uint8_t);
-#endif
 };
 
 struct dcn10_stream_encoder_mask {
 	SE_REG_FIELD_LIST_DCN1_0(uint32_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	SE_REG_FIELD_LIST_DCN2_0(uint32_t);
-#endif
 };
 
 struct dcn10_stream_encoder {
@@ -526,6 +518,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting);
 
 void enc1_stream_encoder_hdmi_set_stream_attribute(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
index 10b47986526b..5fcaf78334ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -2,16 +2,20 @@
 #
 # Makefile for DCN.
 
-DCN20 = dcn20_resource.o dcn20_hwseq.o dcn20_dpp.o dcn20_dpp_cm.o dcn20_hubp.o \
+DCN20 = dcn20_resource.o dcn20_init.o dcn20_hwseq.o dcn20_dpp.o dcn20_dpp_cm.o dcn20_hubp.o \
 		dcn20_mpc.o dcn20_opp.o dcn20_hubbub.o dcn20_optc.o dcn20_mmhubbub.o \
 		dcn20_stream_encoder.o dcn20_link_encoder.o dcn20_dccg.o \
 		dcn20_vmid.o dcn20_dwb.o dcn20_dwb_scl.o
 
-ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 DCN20 += dcn20_dsc.o
-endif
 
+ifdef CONFIG_X86
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -19,6 +23,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -27,6 +32,7 @@ CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4
 else
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2
 endif
+endif
 
 AMD_DAL_DCN20 = $(addprefix $(AMDDALPATH)/dc/dcn20/,$(DCN20))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
index 1e1151356e60..50bffbfdd394 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
@@ -50,20 +50,20 @@ void dccg2_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk)
 
 	if (dccg->ref_dppclk && req_dppclk) {
 		int ref_dppclk = dccg->ref_dppclk;
+		int modulo, phase;
 
-		ASSERT(req_dppclk <= ref_dppclk);
-		/* need to clamp to 8 bits */
-		if (ref_dppclk > 0xff) {
-			int divider = (ref_dppclk + 0xfe) / 0xff;
+		// phase / modulo = dpp pipe clk / dpp global clk
+		modulo = 0xff;   // use FF at the end
+		phase = ((modulo * req_dppclk) + ref_dppclk - 1) / ref_dppclk;
 
-			ref_dppclk /= divider;
-			req_dppclk = (req_dppclk + divider - 1) / divider;
-			if (req_dppclk > ref_dppclk)
-				req_dppclk = ref_dppclk;
+		if (phase > 0xff) {
+			ASSERT(false);
+			phase = 0xff;
 		}
+
 		REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
-				DPPCLK0_DTO_PHASE, req_dppclk,
-				DPPCLK0_DTO_MODULO, ref_dppclk);
+				DPPCLK0_DTO_PHASE, phase,
+				DPPCLK0_DTO_MODULO, modulo);
 		REG_UPDATE(DPPCLK_DTO_CTRL,
 				DPPCLK_DTO_ENABLE[dpp_inst], 1);
 	} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
index 4d7e45892f08..13e057d7ee93 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
@@ -104,7 +104,7 @@ static void dpp2_cnv_setup (
 	uint32_t pixel_format = 0;
 	uint32_t alpha_en = 1;
 	enum dc_color_space color_space = COLOR_SPACE_SRGB;
-	enum dcn10_input_csc_select select = INPUT_CSC_SELECT_BYPASS;
+	enum dcn20_input_csc_select select = DCN2_ICSC_SELECT_BYPASS;
 	bool force_disable_cursor = false;
 	struct out_csc_color_matrix tbl_entry;
 	uint32_t is_2bit = 0;
@@ -145,25 +145,25 @@ static void dpp2_cnv_setup (
 		force_disable_cursor = false;
 		pixel_format = 65;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb:
 		force_disable_cursor = true;
 		pixel_format = 64;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr:
 		force_disable_cursor = true;
 		pixel_format = 67;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb:
 		force_disable_cursor = true;
 		pixel_format = 66;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
 		pixel_format = 22;
@@ -177,7 +177,7 @@ static void dpp2_cnv_setup (
 	case SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888:
 		pixel_format = 12;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX:
 		pixel_format = 112;
@@ -188,13 +188,13 @@ static void dpp2_cnv_setup (
 	case SURFACE_PIXEL_FORMAT_VIDEO_ACrYCb2101010:
 		pixel_format = 114;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		is_2bit = 1;
 		break;
 	case SURFACE_PIXEL_FORMAT_VIDEO_CrYCbA1010102:
 		pixel_format = 115;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		is_2bit = 1;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FLOAT:
@@ -227,13 +227,13 @@ static void dpp2_cnv_setup (
 		tbl_entry.color_space = input_color_space;
 
 		if (color_space >= COLOR_SPACE_YCBCR601)
-			select = INPUT_CSC_SELECT_ICSC;
+			select = DCN2_ICSC_SELECT_ICSC_A;
 		else
-			select = INPUT_CSC_SELECT_BYPASS;
+			select = DCN2_ICSC_SELECT_BYPASS;
 
-		dpp1_program_input_csc(dpp_base, color_space, select, &tbl_entry);
+		dpp2_program_input_csc(dpp_base, color_space, select, &tbl_entry);
 	} else
-	dpp1_program_input_csc(dpp_base, color_space, select, NULL);
+	dpp2_program_input_csc(dpp_base, color_space, select, NULL);
 
 	if (force_disable_cursor) {
 		REG_UPDATE(CURSOR_CONTROL,
@@ -458,7 +458,7 @@ static struct dpp_funcs dcn20_dpp_funcs = {
 	.dpp_reset = dpp_reset,
 	.dpp_set_scaler = dpp1_dscl_set_scaler_manual_scale,
 	.dpp_get_optimal_number_of_taps = dpp1_get_optimal_number_of_taps,
-	.dpp_set_gamut_remap = dpp1_cm_set_gamut_remap,
+	.dpp_set_gamut_remap = dpp2_cm_set_gamut_remap,
 	.dpp_set_csc_adjustment = NULL,
 	.dpp_set_csc_default = NULL,
 	.dpp_program_regamma_pwl = oppn20_dummy_program_regamma_pwl,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
index 5b03b737b1d6..27610251c57f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
@@ -150,6 +150,16 @@
 	SRI(CM_SHAPER_RAMA_REGION_32_33, CM, id), \
 	SRI(CM_SHAPER_LUT_INDEX, CM, id)
 
+#define TF_REG_LIST_DCN20_COMMON_APPEND(id) \
+	SRI(CM_GAMUT_REMAP_B_C11_C12, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C13_C14, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C21_C22, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C23_C24, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C31_C32, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C33_C34, CM, id),\
+	SRI(CM_ICSC_B_C11_C12, CM, id), \
+	SRI(CM_ICSC_B_C33_C34, CM, id)
+
 #define TF_REG_LIST_DCN20(id) \
 	TF_REG_LIST_DCN(id), \
 	TF_REG_LIST_DCN20_COMMON(id), \
@@ -572,10 +582,29 @@
 	TF_SF(DSCL0_OBUF_MEM_PWR_CTRL, OBUF_MEM_PWR_FORCE, mask_sh),\
 	TF_SF(DSCL0_DSCL_MEM_PWR_CTRL, LUT_MEM_PWR_FORCE, mask_sh)
 
+/* DPP CM debug status register:
+ *
+ *		Status index including current ICSC, Gamut Remap Mode is 9
+ *			ICSC Mode: [4..3]
+ *			Gamut Remap Mode: [10..9]
+ */
+#define CM_TEST_DEBUG_DATA_STATUS_IDX 9
+
+#define TF_DEBUG_REG_LIST_SH_DCN20 \
+	TF_DEBUG_REG_LIST_SH_DCN10, \
+	.CM_TEST_DEBUG_DATA_ICSC_MODE = 3, \
+	.CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE = 9
+
+#define TF_DEBUG_REG_LIST_MASK_DCN20 \
+	TF_DEBUG_REG_LIST_MASK_DCN10, \
+	.CM_TEST_DEBUG_DATA_ICSC_MODE = 0x18, \
+	.CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE = 0x600
 
 #define TF_REG_FIELD_LIST_DCN2_0(type) \
 	TF_REG_FIELD_LIST(type) \
 	type CM_BLNDGAM_LUT_DATA; \
+	type CM_TEST_DEBUG_DATA_ICSC_MODE; \
+	type CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE; \
 	type FORMAT_CNV16; \
 	type CNVC_BYPASS_MSB_ALIGN; \
 	type CLAMP_POSITIVE; \
@@ -630,11 +659,22 @@ struct dcn2_dpp_mask {
 	uint32_t COLOR_KEYER_RED; \
 	uint32_t COLOR_KEYER_GREEN; \
 	uint32_t COLOR_KEYER_BLUE; \
-	uint32_t OBUF_MEM_PWR_CTRL;\
+	uint32_t OBUF_MEM_PWR_CTRL; \
 	uint32_t DSCL_MEM_PWR_CTRL
 
+#define DPP_DCN2_REG_VARIABLE_LIST_CM_APPEND \
+	uint32_t CM_GAMUT_REMAP_B_C11_C12; \
+	uint32_t CM_GAMUT_REMAP_B_C13_C14; \
+	uint32_t CM_GAMUT_REMAP_B_C21_C22; \
+	uint32_t CM_GAMUT_REMAP_B_C23_C24; \
+	uint32_t CM_GAMUT_REMAP_B_C31_C32; \
+	uint32_t CM_GAMUT_REMAP_B_C33_C34; \
+	uint32_t CM_ICSC_B_C11_C12; \
+	uint32_t CM_ICSC_B_C33_C34
+
 struct dcn2_dpp_registers {
 	DPP_DCN2_REG_VARIABLE_LIST;
+	DPP_DCN2_REG_VARIABLE_LIST_CM_APPEND;
 };
 
 struct dcn20_dpp {
@@ -656,6 +696,18 @@ struct dcn20_dpp {
 	struct pwl_params pwl_data;
 };
 
+enum dcn20_input_csc_select {
+	DCN2_ICSC_SELECT_BYPASS = 0,
+	DCN2_ICSC_SELECT_ICSC_A = 1,
+	DCN2_ICSC_SELECT_ICSC_B = 2
+};
+
+enum dcn20_gamut_remap_select {
+	DCN2_GAMUT_REMAP_BYPASS = 0,
+	DCN2_GAMUT_REMAP_COEF_A = 1,
+	DCN2_GAMUT_REMAP_COEF_B = 2
+};
+
 void dpp20_read_state(struct dpp *dpp_base,
 		struct dcn_dpp_state *s);
 
@@ -667,6 +719,16 @@ void dpp2_set_degamma(
 		struct dpp *dpp_base,
 		enum ipp_degamma_mode mode);
 
+void dpp2_cm_set_gamut_remap(
+	struct dpp *dpp_base,
+	const struct dpp_grph_csc_adjustment *adjust);
+
+void dpp2_program_input_csc(
+		struct dpp *dpp_base,
+		enum dc_color_space color_space,
+		enum dcn20_input_csc_select input_select,
+		const struct out_csc_color_matrix *tbl_entry);
+
 bool dpp20_program_blnd_lut(
 	struct dpp *dpp_base, const struct pwl_params *params);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c
index 2d112c316424..8dc3d1f73984 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c
@@ -36,6 +36,9 @@
 #define REG(reg)\
 	dpp->tf_regs->reg
 
+#define IND_REG(index) \
+	(index)
+
 #define CTX \
 	dpp->base.ctx
 
@@ -44,9 +47,6 @@
 	dpp->tf_shift->field_name, dpp->tf_mask->field_name
 
 
-
-
-
 static void dpp2_enable_cm_block(
 		struct dpp *dpp_base)
 {
@@ -149,12 +149,164 @@ void dpp2_set_degamma(
 	case IPP_DEGAMMA_MODE_HW_xvYCC:
 		REG_UPDATE(CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, 2);
 			break;
+	case IPP_DEGAMMA_MODE_USER_PWL:
+		REG_UPDATE(CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, 3);
+		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
 	}
 }
 
+static void program_gamut_remap(
+		struct dcn20_dpp *dpp,
+		const uint16_t *regval,
+		enum dcn20_gamut_remap_select select)
+{
+	uint32_t cur_select = 0;
+	struct color_matrices_reg gam_regs;
+
+	if (regval == NULL || select == DCN2_GAMUT_REMAP_BYPASS) {
+		REG_SET(CM_GAMUT_REMAP_CONTROL, 0,
+				CM_GAMUT_REMAP_MODE, 0);
+		return;
+	}
+
+	/* determine which gamut_remap coefficients (A or B) we are using
+	 * currently. select the alternate set to double buffer
+	 * the update so gamut_remap is updated on frame boundary
+	 */
+	IX_REG_GET(CM_TEST_DEBUG_INDEX, CM_TEST_DEBUG_DATA,
+					CM_TEST_DEBUG_DATA_STATUS_IDX,
+					CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE, &cur_select);
+
+	/* value stored in dbg reg will be 1 greater than mode we want */
+	if (cur_select != DCN2_GAMUT_REMAP_COEF_A)
+		select = DCN2_GAMUT_REMAP_COEF_A;
+	else
+		select = DCN2_GAMUT_REMAP_COEF_B;
+
+	gam_regs.shifts.csc_c11 = dpp->tf_shift->CM_GAMUT_REMAP_C11;
+	gam_regs.masks.csc_c11  = dpp->tf_mask->CM_GAMUT_REMAP_C11;
+	gam_regs.shifts.csc_c12 = dpp->tf_shift->CM_GAMUT_REMAP_C12;
+	gam_regs.masks.csc_c12 = dpp->tf_mask->CM_GAMUT_REMAP_C12;
+
+	if (select == DCN2_GAMUT_REMAP_COEF_A) {
+		gam_regs.csc_c11_c12 = REG(CM_GAMUT_REMAP_C11_C12);
+		gam_regs.csc_c33_c34 = REG(CM_GAMUT_REMAP_C33_C34);
+	} else {
+		gam_regs.csc_c11_c12 = REG(CM_GAMUT_REMAP_B_C11_C12);
+		gam_regs.csc_c33_c34 = REG(CM_GAMUT_REMAP_B_C33_C34);
+	}
+
+	cm_helper_program_color_matrices(
+				dpp->base.ctx,
+				regval,
+				&gam_regs);
+
+	REG_SET(
+			CM_GAMUT_REMAP_CONTROL, 0,
+			CM_GAMUT_REMAP_MODE, select);
+
+}
+
+void dpp2_cm_set_gamut_remap(
+	struct dpp *dpp_base,
+	const struct dpp_grph_csc_adjustment *adjust)
+{
+	struct dcn20_dpp *dpp = TO_DCN20_DPP(dpp_base);
+	int i = 0;
+
+	if (adjust->gamut_adjust_type != GRAPHICS_GAMUT_ADJUST_TYPE_SW)
+		/* Bypass if type is bypass or hw */
+		program_gamut_remap(dpp, NULL, DCN2_GAMUT_REMAP_BYPASS);
+	else {
+		struct fixed31_32 arr_matrix[12];
+		uint16_t arr_reg_val[12];
+
+		for (i = 0; i < 12; i++)
+			arr_matrix[i] = adjust->temperature_matrix[i];
+
+		convert_float_matrix(
+			arr_reg_val, arr_matrix, 12);
+
+		program_gamut_remap(dpp, arr_reg_val, DCN2_GAMUT_REMAP_COEF_A);
+	}
+}
+
+void dpp2_program_input_csc(
+		struct dpp *dpp_base,
+		enum dc_color_space color_space,
+		enum dcn20_input_csc_select input_select,
+		const struct out_csc_color_matrix *tbl_entry)
+{
+	struct dcn20_dpp *dpp = TO_DCN20_DPP(dpp_base);
+	int i;
+	int arr_size = sizeof(dpp_input_csc_matrix)/sizeof(struct dpp_input_csc_matrix);
+	const uint16_t *regval = NULL;
+	uint32_t cur_select = 0;
+	enum dcn20_input_csc_select select;
+	struct color_matrices_reg icsc_regs;
+
+	if (input_select == DCN2_ICSC_SELECT_BYPASS) {
+		REG_SET(CM_ICSC_CONTROL, 0, CM_ICSC_MODE, 0);
+		return;
+	}
+
+	if (tbl_entry == NULL) {
+		for (i = 0; i < arr_size; i++)
+			if (dpp_input_csc_matrix[i].color_space == color_space) {
+				regval = dpp_input_csc_matrix[i].regval;
+				break;
+			}
+
+		if (regval == NULL) {
+			BREAK_TO_DEBUGGER();
+			return;
+		}
+	} else {
+		regval = tbl_entry->regval;
+	}
+
+	/* determine which CSC coefficients (A or B) we are using
+	 * currently.  select the alternate set to double buffer
+	 * the CSC update so CSC is updated on frame boundary
+	 */
+	IX_REG_GET(CM_TEST_DEBUG_INDEX, CM_TEST_DEBUG_DATA,
+					CM_TEST_DEBUG_DATA_STATUS_IDX,
+					CM_TEST_DEBUG_DATA_ICSC_MODE, &cur_select);
+
+	if (cur_select != DCN2_ICSC_SELECT_ICSC_A)
+		select = DCN2_ICSC_SELECT_ICSC_A;
+	else
+		select = DCN2_ICSC_SELECT_ICSC_B;
+
+	icsc_regs.shifts.csc_c11 = dpp->tf_shift->CM_ICSC_C11;
+	icsc_regs.masks.csc_c11  = dpp->tf_mask->CM_ICSC_C11;
+	icsc_regs.shifts.csc_c12 = dpp->tf_shift->CM_ICSC_C12;
+	icsc_regs.masks.csc_c12 = dpp->tf_mask->CM_ICSC_C12;
+
+	if (select == DCN2_ICSC_SELECT_ICSC_A) {
+
+		icsc_regs.csc_c11_c12 = REG(CM_ICSC_C11_C12);
+		icsc_regs.csc_c33_c34 = REG(CM_ICSC_C33_C34);
+
+	} else {
+
+		icsc_regs.csc_c11_c12 = REG(CM_ICSC_B_C11_C12);
+		icsc_regs.csc_c33_c34 = REG(CM_ICSC_B_C33_C34);
+
+	}
+
+	cm_helper_program_color_matrices(
+			dpp->base.ctx,
+			regval,
+			&icsc_regs);
+
+	REG_SET(CM_ICSC_CONTROL, 0,
+				CM_ICSC_MODE, select);
+}
+
 static void dpp20_power_on_blnd_lut(
 	struct dpp *dpp_base,
 	bool power_on)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
index 63eb377ed9c0..6bdfee20b6a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "reg_helper.h"
 #include "dcn20_dsc.h"
 #include "dsc/dscc_types.h"
@@ -207,6 +206,9 @@ static bool dsc2_get_packed_pps(struct display_stream_compressor *dsc, const str
 	struct dsc_reg_values dsc_reg_vals;
 	struct dsc_optc_config dsc_optc_cfg;
 
+	memset(&dsc_reg_vals, 0, sizeof(dsc_reg_vals));
+	memset(&dsc_optc_cfg, 0, sizeof(dsc_optc_cfg));
+
 	DC_LOG_DSC("Getting packed DSC PPS for DSC Config:");
 	dsc_config_log(dsc, dsc_cfg);
 	DC_LOG_DSC("DSC Picture Parameter Set (PPS):");
@@ -222,9 +224,18 @@ static bool dsc2_get_packed_pps(struct display_stream_compressor *dsc, const str
 static void dsc2_enable(struct display_stream_compressor *dsc, int opp_pipe)
 {
 	struct dcn20_dsc *dsc20 = TO_DCN20_DSC(dsc);
+	int dsc_clock_en;
+	int dsc_fw_config;
+	int enabled_opp_pipe;
+
+	DC_LOG_DSC("enable DSC %d at opp pipe %d", dsc->inst, opp_pipe);
 
-	/* TODO Check if DSC alreay in use? */
-	DC_LOG_DSC("enable DSC at opp pipe %d", opp_pipe);
+	REG_GET(DSC_TOP_CONTROL, DSC_CLOCK_EN, &dsc_clock_en);
+	REG_GET_2(DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_FORWARD_EN, &dsc_fw_config, DSCRM_DSC_OPP_PIPE_SOURCE, &enabled_opp_pipe);
+	if ((dsc_clock_en || dsc_fw_config) && enabled_opp_pipe != opp_pipe) {
+		DC_LOG_DSC("ERROR: DSC %d at opp pipe %d already enabled!", dsc->inst, enabled_opp_pipe);
+		ASSERT(0);
+	}
 
 	REG_UPDATE(DSC_TOP_CONTROL,
 		DSC_CLOCK_EN, 1);
@@ -238,8 +249,18 @@ static void dsc2_enable(struct display_stream_compressor *dsc, int opp_pipe)
 static void dsc2_disable(struct display_stream_compressor *dsc)
 {
 	struct dcn20_dsc *dsc20 = TO_DCN20_DSC(dsc);
+	int dsc_clock_en;
+	int dsc_fw_config;
+	int enabled_opp_pipe;
 
-	DC_LOG_DSC("disable DSC");
+	DC_LOG_DSC("disable DSC %d", dsc->inst);
+
+	REG_GET(DSC_TOP_CONTROL, DSC_CLOCK_EN, &dsc_clock_en);
+	REG_GET_2(DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_FORWARD_EN, &dsc_fw_config, DSCRM_DSC_OPP_PIPE_SOURCE, &enabled_opp_pipe);
+	if (!dsc_clock_en || !dsc_fw_config) {
+		DC_LOG_DSC("ERROR: DSC %d at opp pipe %d already disabled!", dsc->inst, enabled_opp_pipe);
+		ASSERT(0);
+	}
 
 	REG_UPDATE(DSCRM_DSC_FORWARD_CONFIG,
 		DSCRM_DSC_FORWARD_EN, 0);
@@ -715,4 +736,3 @@ static void dsc_write_to_registers(struct display_stream_compressor *dsc, const
 	}
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
index 4e2fb38390a4..9855a7ed0387 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
@@ -21,7 +21,6 @@
  * Authors: AMD
  *
  */
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #ifndef __DCN20_DSC_H__
 #define __DCN20_DSC_H__
 
@@ -572,4 +571,3 @@ void dsc2_construct(struct dcn20_dsc *dsc,
 
 #endif
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
index 8b8438566101..9235f7d29454 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
@@ -293,6 +293,9 @@ bool hubbub2_get_dcc_compression_cap(struct hubbub *hubbub,
 		output->grph.rgb.max_compressed_blk_size = 64;
 		output->grph.rgb.independent_64b_blks = true;
 		break;
+	default:
+		ASSERT(false);
+		break;
 	}
 	output->capable = true;
 	output->const_color_support = true;
@@ -601,7 +604,8 @@ static const struct hubbub_funcs hubbub2_funcs = {
 	.wm_read_state = hubbub2_wm_read_state,
 	.get_dchub_ref_freq = hubbub2_get_dchub_ref_freq,
 	.program_watermarks = hubbub2_program_watermarks,
-	.allow_self_refresh_control = hubbub1_allow_self_refresh_control
+	.is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled,
+	.allow_self_refresh_control = hubbub1_allow_self_refresh_control,
 };
 
 void hubbub2_construct(struct dcn20_hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 69e2aae42394..84d7ac5dd206 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -30,6 +30,8 @@
 #include "reg_helper.h"
 #include "basics/conversion.h"
 
+#define DC_LOGGER_INIT(logger)
+
 #define REG(reg)\
 	hubp2->hubp_regs->reg
 
@@ -483,7 +485,6 @@ void hubp2_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 12);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX:
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 112);
@@ -504,7 +505,6 @@ void hubp2_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 119);
 		break;
-#endif
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
@@ -1204,6 +1204,9 @@ void hubp2_read_state_common(struct hubp *hubp)
 			HUBP_TTU_DISABLE, &s->ttu_disable,
 			HUBP_UNDERFLOW_STATUS, &s->underflow_status);
 
+	REG_GET(HUBP_CLK_CNTL,
+			HUBP_CLOCK_ENABLE, &s->clock_en);
+
 	REG_GET(DCN_GLOBAL_TTU_CNTL,
 			MIN_TTU_VBLANK, &s->min_ttu_vblank);
 
@@ -1243,6 +1246,314 @@ void hubp2_read_state(struct hubp *hubp)
 
 }
 
+void hubp2_validate_dml_output(struct hubp *hubp,
+		struct dc_context *ctx,
+		struct _vcs_dpi_display_rq_regs_st *dml_rq_regs,
+		struct _vcs_dpi_display_dlg_regs_st *dml_dlg_attr,
+		struct _vcs_dpi_display_ttu_regs_st *dml_ttu_attr)
+{
+	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
+	struct _vcs_dpi_display_rq_regs_st rq_regs = {0};
+	struct _vcs_dpi_display_dlg_regs_st dlg_attr = {0};
+	struct _vcs_dpi_display_ttu_regs_st ttu_attr = {0};
+	DC_LOGGER_INIT(ctx->logger);
+	DC_LOG_DEBUG("DML Validation | Running Validation");
+
+	/* Requestor Regs */
+	REG_GET(HUBPRET_CONTROL,
+		DET_BUF_PLANE1_BASE_ADDRESS, &rq_regs.plane1_base_address);
+	REG_GET_4(DCN_EXPANSION_MODE,
+		DRQ_EXPANSION_MODE, &rq_regs.drq_expansion_mode,
+		PRQ_EXPANSION_MODE, &rq_regs.prq_expansion_mode,
+		MRQ_EXPANSION_MODE, &rq_regs.mrq_expansion_mode,
+		CRQ_EXPANSION_MODE, &rq_regs.crq_expansion_mode);
+	REG_GET_8(DCHUBP_REQ_SIZE_CONFIG,
+		CHUNK_SIZE, &rq_regs.rq_regs_l.chunk_size,
+		MIN_CHUNK_SIZE, &rq_regs.rq_regs_l.min_chunk_size,
+		META_CHUNK_SIZE, &rq_regs.rq_regs_l.meta_chunk_size,
+		MIN_META_CHUNK_SIZE, &rq_regs.rq_regs_l.min_meta_chunk_size,
+		DPTE_GROUP_SIZE, &rq_regs.rq_regs_l.dpte_group_size,
+		MPTE_GROUP_SIZE, &rq_regs.rq_regs_l.mpte_group_size,
+		SWATH_HEIGHT, &rq_regs.rq_regs_l.swath_height,
+		PTE_ROW_HEIGHT_LINEAR, &rq_regs.rq_regs_l.pte_row_height_linear);
+	REG_GET_8(DCHUBP_REQ_SIZE_CONFIG_C,
+		CHUNK_SIZE_C, &rq_regs.rq_regs_c.chunk_size,
+		MIN_CHUNK_SIZE_C, &rq_regs.rq_regs_c.min_chunk_size,
+		META_CHUNK_SIZE_C, &rq_regs.rq_regs_c.meta_chunk_size,
+		MIN_META_CHUNK_SIZE_C, &rq_regs.rq_regs_c.min_meta_chunk_size,
+		DPTE_GROUP_SIZE_C, &rq_regs.rq_regs_c.dpte_group_size,
+		MPTE_GROUP_SIZE_C, &rq_regs.rq_regs_c.mpte_group_size,
+		SWATH_HEIGHT_C, &rq_regs.rq_regs_c.swath_height,
+		PTE_ROW_HEIGHT_LINEAR_C, &rq_regs.rq_regs_c.pte_row_height_linear);
+
+	if (rq_regs.plane1_base_address != dml_rq_regs->plane1_base_address)
+		DC_LOG_DEBUG("DML Validation | HUBPRET_CONTROL:DET_BUF_PLANE1_BASE_ADDRESS - Expected: %u  Actual: %u\n",
+				dml_rq_regs->plane1_base_address, rq_regs.plane1_base_address);
+	if (rq_regs.drq_expansion_mode != dml_rq_regs->drq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:DRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->drq_expansion_mode, rq_regs.drq_expansion_mode);
+	if (rq_regs.prq_expansion_mode != dml_rq_regs->prq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:MRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->prq_expansion_mode, rq_regs.prq_expansion_mode);
+	if (rq_regs.mrq_expansion_mode != dml_rq_regs->mrq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:DET_BUF_PLANE1_BASE_ADDRESS - Expected: %u  Actual: %u\n",
+				dml_rq_regs->mrq_expansion_mode, rq_regs.mrq_expansion_mode);
+	if (rq_regs.crq_expansion_mode != dml_rq_regs->crq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:CRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->crq_expansion_mode, rq_regs.crq_expansion_mode);
+
+	if (rq_regs.rq_regs_l.chunk_size != dml_rq_regs->rq_regs_l.chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.chunk_size, rq_regs.rq_regs_l.chunk_size);
+	if (rq_regs.rq_regs_l.min_chunk_size != dml_rq_regs->rq_regs_l.min_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MIN_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.min_chunk_size, rq_regs.rq_regs_l.min_chunk_size);
+	if (rq_regs.rq_regs_l.meta_chunk_size != dml_rq_regs->rq_regs_l.meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:META_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.meta_chunk_size, rq_regs.rq_regs_l.meta_chunk_size);
+	if (rq_regs.rq_regs_l.min_meta_chunk_size != dml_rq_regs->rq_regs_l.min_meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MIN_META_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.min_meta_chunk_size, rq_regs.rq_regs_l.min_meta_chunk_size);
+	if (rq_regs.rq_regs_l.dpte_group_size != dml_rq_regs->rq_regs_l.dpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:DPTE_GROUP_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.dpte_group_size, rq_regs.rq_regs_l.dpte_group_size);
+	if (rq_regs.rq_regs_l.mpte_group_size != dml_rq_regs->rq_regs_l.mpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MPTE_GROUP_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.mpte_group_size, rq_regs.rq_regs_l.mpte_group_size);
+	if (rq_regs.rq_regs_l.swath_height != dml_rq_regs->rq_regs_l.swath_height)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:SWATH_HEIGHT - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.swath_height, rq_regs.rq_regs_l.swath_height);
+	if (rq_regs.rq_regs_l.pte_row_height_linear != dml_rq_regs->rq_regs_l.pte_row_height_linear)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:PTE_ROW_HEIGHT_LINEAR - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.pte_row_height_linear, rq_regs.rq_regs_l.pte_row_height_linear);
+
+	if (rq_regs.rq_regs_c.chunk_size != dml_rq_regs->rq_regs_c.chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.chunk_size, rq_regs.rq_regs_c.chunk_size);
+	if (rq_regs.rq_regs_c.min_chunk_size != dml_rq_regs->rq_regs_c.min_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MIN_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.min_chunk_size, rq_regs.rq_regs_c.min_chunk_size);
+	if (rq_regs.rq_regs_c.meta_chunk_size != dml_rq_regs->rq_regs_c.meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:META_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.meta_chunk_size, rq_regs.rq_regs_c.meta_chunk_size);
+	if (rq_regs.rq_regs_c.min_meta_chunk_size != dml_rq_regs->rq_regs_c.min_meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MIN_META_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.min_meta_chunk_size, rq_regs.rq_regs_c.min_meta_chunk_size);
+	if (rq_regs.rq_regs_c.dpte_group_size != dml_rq_regs->rq_regs_c.dpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:DPTE_GROUP_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.dpte_group_size, rq_regs.rq_regs_c.dpte_group_size);
+	if (rq_regs.rq_regs_c.mpte_group_size != dml_rq_regs->rq_regs_c.mpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MPTE_GROUP_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.mpte_group_size, rq_regs.rq_regs_c.mpte_group_size);
+	if (rq_regs.rq_regs_c.swath_height != dml_rq_regs->rq_regs_c.swath_height)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:SWATH_HEIGHT_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.swath_height, rq_regs.rq_regs_c.swath_height);
+	if (rq_regs.rq_regs_c.pte_row_height_linear != dml_rq_regs->rq_regs_c.pte_row_height_linear)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:PTE_ROW_HEIGHT_LINEAR_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.pte_row_height_linear, rq_regs.rq_regs_c.pte_row_height_linear);
+
+	/* DLG - Per hubp */
+	REG_GET_2(BLANK_OFFSET_0,
+		REFCYC_H_BLANK_END, &dlg_attr.refcyc_h_blank_end,
+		DLG_V_BLANK_END, &dlg_attr.dlg_vblank_end);
+	REG_GET(BLANK_OFFSET_1,
+		MIN_DST_Y_NEXT_START, &dlg_attr.min_dst_y_next_start);
+	REG_GET(DST_DIMENSIONS,
+		REFCYC_PER_HTOTAL, &dlg_attr.refcyc_per_htotal);
+	REG_GET_2(DST_AFTER_SCALER,
+		REFCYC_X_AFTER_SCALER, &dlg_attr.refcyc_x_after_scaler,
+		DST_Y_AFTER_SCALER, &dlg_attr.dst_y_after_scaler);
+	REG_GET(REF_FREQ_TO_PIX_FREQ,
+		REF_FREQ_TO_PIX_FREQ, &dlg_attr.ref_freq_to_pix_freq);
+
+	if (dlg_attr.refcyc_h_blank_end != dml_dlg_attr->refcyc_h_blank_end)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_0:REFCYC_H_BLANK_END - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_h_blank_end, dlg_attr.refcyc_h_blank_end);
+	if (dlg_attr.dlg_vblank_end != dml_dlg_attr->dlg_vblank_end)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_0:DLG_V_BLANK_END - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dlg_vblank_end, dlg_attr.dlg_vblank_end);
+	if (dlg_attr.min_dst_y_next_start != dml_dlg_attr->min_dst_y_next_start)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_1:MIN_DST_Y_NEXT_START - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->min_dst_y_next_start, dlg_attr.min_dst_y_next_start);
+	if (dlg_attr.refcyc_per_htotal != dml_dlg_attr->refcyc_per_htotal)
+		DC_LOG_DEBUG("DML Validation | DST_DIMENSIONS:REFCYC_PER_HTOTAL - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_htotal, dlg_attr.refcyc_per_htotal);
+	if (dlg_attr.refcyc_x_after_scaler != dml_dlg_attr->refcyc_x_after_scaler)
+		DC_LOG_DEBUG("DML Validation | DST_AFTER_SCALER:REFCYC_X_AFTER_SCALER - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_x_after_scaler, dlg_attr.refcyc_x_after_scaler);
+	if (dlg_attr.dst_y_after_scaler != dml_dlg_attr->dst_y_after_scaler)
+		DC_LOG_DEBUG("DML Validation | DST_AFTER_SCALER:DST_Y_AFTER_SCALER - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_after_scaler, dlg_attr.dst_y_after_scaler);
+	if (dlg_attr.ref_freq_to_pix_freq != dml_dlg_attr->ref_freq_to_pix_freq)
+		DC_LOG_DEBUG("DML Validation | REF_FREQ_TO_PIX_FREQ:REF_FREQ_TO_PIX_FREQ - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->ref_freq_to_pix_freq, dlg_attr.ref_freq_to_pix_freq);
+
+	/* DLG - Per luma/chroma */
+	REG_GET(VBLANK_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_VBLANK_L, &dlg_attr.refcyc_per_pte_group_vblank_l);
+	if (REG(NOM_PARAMETERS_0))
+		REG_GET(NOM_PARAMETERS_0,
+			DST_Y_PER_PTE_ROW_NOM_L, &dlg_attr.dst_y_per_pte_row_nom_l);
+	if (REG(NOM_PARAMETERS_1))
+		REG_GET(NOM_PARAMETERS_1,
+			REFCYC_PER_PTE_GROUP_NOM_L, &dlg_attr.refcyc_per_pte_group_nom_l);
+	REG_GET(NOM_PARAMETERS_4,
+		DST_Y_PER_META_ROW_NOM_L, &dlg_attr.dst_y_per_meta_row_nom_l);
+	REG_GET(NOM_PARAMETERS_5,
+		REFCYC_PER_META_CHUNK_NOM_L, &dlg_attr.refcyc_per_meta_chunk_nom_l);
+	REG_GET_2(PER_LINE_DELIVERY,
+		REFCYC_PER_LINE_DELIVERY_L, &dlg_attr.refcyc_per_line_delivery_l,
+		REFCYC_PER_LINE_DELIVERY_C, &dlg_attr.refcyc_per_line_delivery_c);
+	REG_GET_2(PER_LINE_DELIVERY_PRE,
+		REFCYC_PER_LINE_DELIVERY_PRE_L, &dlg_attr.refcyc_per_line_delivery_pre_l,
+		REFCYC_PER_LINE_DELIVERY_PRE_C, &dlg_attr.refcyc_per_line_delivery_pre_c);
+	REG_GET(VBLANK_PARAMETERS_2,
+		REFCYC_PER_PTE_GROUP_VBLANK_C, &dlg_attr.refcyc_per_pte_group_vblank_c);
+	if (REG(NOM_PARAMETERS_2))
+		REG_GET(NOM_PARAMETERS_2,
+			DST_Y_PER_PTE_ROW_NOM_C, &dlg_attr.dst_y_per_pte_row_nom_c);
+	if (REG(NOM_PARAMETERS_3))
+		REG_GET(NOM_PARAMETERS_3,
+			REFCYC_PER_PTE_GROUP_NOM_C, &dlg_attr.refcyc_per_pte_group_nom_c);
+	REG_GET(NOM_PARAMETERS_6,
+		DST_Y_PER_META_ROW_NOM_C, &dlg_attr.dst_y_per_meta_row_nom_c);
+	REG_GET(NOM_PARAMETERS_7,
+		REFCYC_PER_META_CHUNK_NOM_C, &dlg_attr.refcyc_per_meta_chunk_nom_c);
+	REG_GET(VBLANK_PARAMETERS_3,
+			REFCYC_PER_META_CHUNK_VBLANK_L, &dlg_attr.refcyc_per_meta_chunk_vblank_l);
+	REG_GET(VBLANK_PARAMETERS_4,
+			REFCYC_PER_META_CHUNK_VBLANK_C, &dlg_attr.refcyc_per_meta_chunk_vblank_c);
+
+	if (dlg_attr.refcyc_per_pte_group_vblank_l != dml_dlg_attr->refcyc_per_pte_group_vblank_l)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_1:REFCYC_PER_PTE_GROUP_VBLANK_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_vblank_l, dlg_attr.refcyc_per_pte_group_vblank_l);
+	if (dlg_attr.dst_y_per_pte_row_nom_l != dml_dlg_attr->dst_y_per_pte_row_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_0:DST_Y_PER_PTE_ROW_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_pte_row_nom_l, dlg_attr.dst_y_per_pte_row_nom_l);
+	if (dlg_attr.refcyc_per_pte_group_nom_l != dml_dlg_attr->refcyc_per_pte_group_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_1:REFCYC_PER_PTE_GROUP_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_nom_l, dlg_attr.refcyc_per_pte_group_nom_l);
+	if (dlg_attr.dst_y_per_meta_row_nom_l != dml_dlg_attr->dst_y_per_meta_row_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_4:DST_Y_PER_META_ROW_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_meta_row_nom_l, dlg_attr.dst_y_per_meta_row_nom_l);
+	if (dlg_attr.refcyc_per_meta_chunk_nom_l != dml_dlg_attr->refcyc_per_meta_chunk_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_5:REFCYC_PER_META_CHUNK_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_nom_l, dlg_attr.refcyc_per_meta_chunk_nom_l);
+	if (dlg_attr.refcyc_per_line_delivery_l != dml_dlg_attr->refcyc_per_line_delivery_l)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY:REFCYC_PER_LINE_DELIVERY_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_l, dlg_attr.refcyc_per_line_delivery_l);
+	if (dlg_attr.refcyc_per_line_delivery_c != dml_dlg_attr->refcyc_per_line_delivery_c)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY:REFCYC_PER_LINE_DELIVERY_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_c, dlg_attr.refcyc_per_line_delivery_c);
+	if (dlg_attr.refcyc_per_pte_group_vblank_c != dml_dlg_attr->refcyc_per_pte_group_vblank_c)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_2:REFCYC_PER_PTE_GROUP_VBLANK_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_vblank_c, dlg_attr.refcyc_per_pte_group_vblank_c);
+	if (dlg_attr.dst_y_per_pte_row_nom_c != dml_dlg_attr->dst_y_per_pte_row_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_2:DST_Y_PER_PTE_ROW_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_pte_row_nom_c, dlg_attr.dst_y_per_pte_row_nom_c);
+	if (dlg_attr.refcyc_per_pte_group_nom_c != dml_dlg_attr->refcyc_per_pte_group_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_3:REFCYC_PER_PTE_GROUP_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_nom_c, dlg_attr.refcyc_per_pte_group_nom_c);
+	if (dlg_attr.dst_y_per_meta_row_nom_c != dml_dlg_attr->dst_y_per_meta_row_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_6:DST_Y_PER_META_ROW_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_meta_row_nom_c, dlg_attr.dst_y_per_meta_row_nom_c);
+	if (dlg_attr.refcyc_per_meta_chunk_nom_c != dml_dlg_attr->refcyc_per_meta_chunk_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_7:REFCYC_PER_META_CHUNK_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_nom_c, dlg_attr.refcyc_per_meta_chunk_nom_c);
+	if (dlg_attr.refcyc_per_line_delivery_pre_l != dml_dlg_attr->refcyc_per_line_delivery_pre_l)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY_PRE:REFCYC_PER_LINE_DELIVERY_PRE_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_pre_l, dlg_attr.refcyc_per_line_delivery_pre_l);
+	if (dlg_attr.refcyc_per_line_delivery_pre_c != dml_dlg_attr->refcyc_per_line_delivery_pre_c)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY_PRE:REFCYC_PER_LINE_DELIVERY_PRE_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_pre_c, dlg_attr.refcyc_per_line_delivery_pre_c);
+	if (dlg_attr.refcyc_per_meta_chunk_vblank_l != dml_dlg_attr->refcyc_per_meta_chunk_vblank_l)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_3:REFCYC_PER_META_CHUNK_VBLANK_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_vblank_l, dlg_attr.refcyc_per_meta_chunk_vblank_l);
+	if (dlg_attr.refcyc_per_meta_chunk_vblank_c != dml_dlg_attr->refcyc_per_meta_chunk_vblank_c)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_4:REFCYC_PER_META_CHUNK_VBLANK_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_vblank_c, dlg_attr.refcyc_per_meta_chunk_vblank_c);
+
+	/* TTU - per hubp */
+	REG_GET_2(DCN_TTU_QOS_WM,
+		QoS_LEVEL_LOW_WM, &ttu_attr.qos_level_low_wm,
+		QoS_LEVEL_HIGH_WM, &ttu_attr.qos_level_high_wm);
+
+	if (ttu_attr.qos_level_low_wm != dml_ttu_attr->qos_level_low_wm)
+		DC_LOG_DEBUG("DML Validation | DCN_TTU_QOS_WM:QoS_LEVEL_LOW_WM - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_low_wm, ttu_attr.qos_level_low_wm);
+	if (ttu_attr.qos_level_high_wm != dml_ttu_attr->qos_level_high_wm)
+		DC_LOG_DEBUG("DML Validation | DCN_TTU_QOS_WM:QoS_LEVEL_HIGH_WM - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_high_wm, ttu_attr.qos_level_high_wm);
+
+	/* TTU - per luma/chroma */
+	/* Assumed surf0 is luma and 1 is chroma */
+	REG_GET_3(DCN_SURF0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_l,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_l,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_l);
+	REG_GET_3(DCN_SURF1_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_c,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_c,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_c);
+	REG_GET_3(DCN_CUR0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_cur0,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_cur0,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_cur0);
+	REG_GET(FLIP_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_FLIP_L, &dlg_attr.refcyc_per_pte_group_flip_l);
+	REG_GET(DCN_CUR0_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_cur0);
+	REG_GET(DCN_CUR1_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_cur1);
+	REG_GET(DCN_SURF0_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_l);
+	REG_GET(DCN_SURF1_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_c);
+
+	if (ttu_attr.refcyc_per_req_delivery_l != dml_ttu_attr->refcyc_per_req_delivery_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_l, ttu_attr.refcyc_per_req_delivery_l);
+	if (ttu_attr.qos_level_fixed_l != dml_ttu_attr->qos_level_fixed_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_l, ttu_attr.qos_level_fixed_l);
+	if (ttu_attr.qos_ramp_disable_l != dml_ttu_attr->qos_ramp_disable_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_l, ttu_attr.qos_ramp_disable_l);
+	if (ttu_attr.refcyc_per_req_delivery_c != dml_ttu_attr->refcyc_per_req_delivery_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_c, ttu_attr.refcyc_per_req_delivery_c);
+	if (ttu_attr.qos_level_fixed_c != dml_ttu_attr->qos_level_fixed_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_c, ttu_attr.qos_level_fixed_c);
+	if (ttu_attr.qos_ramp_disable_c != dml_ttu_attr->qos_ramp_disable_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_c, ttu_attr.qos_ramp_disable_c);
+	if (ttu_attr.refcyc_per_req_delivery_cur0 != dml_ttu_attr->refcyc_per_req_delivery_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_cur0, ttu_attr.refcyc_per_req_delivery_cur0);
+	if (ttu_attr.qos_level_fixed_cur0 != dml_ttu_attr->qos_level_fixed_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_cur0, ttu_attr.qos_level_fixed_cur0);
+	if (ttu_attr.qos_ramp_disable_cur0 != dml_ttu_attr->qos_ramp_disable_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_cur0, ttu_attr.qos_ramp_disable_cur0);
+	if (dlg_attr.refcyc_per_pte_group_flip_l != dml_dlg_attr->refcyc_per_pte_group_flip_l)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_1:REFCYC_PER_PTE_GROUP_FLIP_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_flip_l, dlg_attr.refcyc_per_pte_group_flip_l);
+	if (ttu_attr.refcyc_per_req_delivery_pre_cur0 != dml_ttu_attr->refcyc_per_req_delivery_pre_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_cur0, ttu_attr.refcyc_per_req_delivery_pre_cur0);
+	if (ttu_attr.refcyc_per_req_delivery_pre_cur1 != dml_ttu_attr->refcyc_per_req_delivery_pre_cur1)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR1_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_cur1, ttu_attr.refcyc_per_req_delivery_pre_cur1);
+	if (ttu_attr.refcyc_per_req_delivery_pre_l != dml_ttu_attr->refcyc_per_req_delivery_pre_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_l, ttu_attr.refcyc_per_req_delivery_pre_l);
+	if (ttu_attr.refcyc_per_req_delivery_pre_c != dml_ttu_attr->refcyc_per_req_delivery_pre_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_c, ttu_attr.refcyc_per_req_delivery_pre_c);
+}
+
 static struct hubp_funcs dcn20_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
 	.hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled,
@@ -1266,6 +1577,7 @@ static struct hubp_funcs dcn20_hubp_funcs = {
 	.hubp_clear_underflow = hubp2_clear_underflow,
 	.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
 	.hubp_init = hubp1_init,
+	.validate_dml_output = hubp2_validate_dml_output,
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h
index d5c8615af45e..8c04a3606a54 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h
@@ -148,7 +148,6 @@
 	uint32_t VMID_SETTINGS_0
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define DCN21_HUBP_REG_COMMON_VARIABLE_LIST \
 	DCN2_HUBP_REG_COMMON_VARIABLE_LIST; \
 	uint32_t FLIP_PARAMETERS_3;\
@@ -157,7 +156,6 @@
 	uint32_t FLIP_PARAMETERS_6;\
 	uint32_t VBLANK_PARAMETERS_5;\
 	uint32_t VBLANK_PARAMETERS_6
-#endif
 
 #define DCN2_HUBP_REG_FIELD_VARIABLE_LIST(type) \
 	DCN_HUBP_REG_FIELD_BASE_LIST(type); \
@@ -184,7 +182,6 @@
 	type SURFACE_TRIPLE_BUFFER_ENABLE;\
 	type VMID
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 #define DCN21_HUBP_REG_FIELD_VARIABLE_LIST(type) \
 	DCN2_HUBP_REG_FIELD_VARIABLE_LIST(type);\
 	type REFCYC_PER_VM_GROUP_FLIP;\
@@ -194,31 +191,18 @@
 	type REFCYC_PER_PTE_GROUP_FLIP_C; \
 	type REFCYC_PER_META_CHUNK_FLIP_C; \
 	type VM_GROUP_SIZE
-#endif
 
 
 struct dcn_hubp2_registers {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	DCN21_HUBP_REG_COMMON_VARIABLE_LIST;
-#else
-	DCN2_HUBP_REG_COMMON_VARIABLE_LIST;
-#endif
 };
 
 struct dcn_hubp2_shift {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	DCN21_HUBP_REG_FIELD_VARIABLE_LIST(uint8_t);
-#else
-	DCN2_HUBP_REG_FIELD_VARIABLE_LIST(uint8_t);
-#endif
 };
 
 struct dcn_hubp2_mask {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	DCN21_HUBP_REG_FIELD_VARIABLE_LIST(uint32_t);
-#else
-	DCN2_HUBP_REG_FIELD_VARIABLE_LIST(uint32_t);
-#endif
 };
 
 struct dcn20_hubp {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index ac8c18fadefc..cfbbaffa8654 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -25,17 +25,15 @@
 #include <linux/delay.h>
 
 #include "dm_services.h"
+#include "basics/dc_common.h"
 #include "dm_helpers.h"
 #include "core_types.h"
 #include "resource.h"
-#include "dcn20/dcn20_resource.h"
-#include "dce110/dce110_hw_sequencer.h"
-#include "dcn10/dcn10_hw_sequencer.h"
+#include "dcn20_resource.h"
 #include "dcn20_hwseq.h"
 #include "dce/dce_hwseq.h"
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-#include "dcn20/dcn20_dsc.h"
-#endif
+#include "dcn20_dsc.h"
+#include "dcn20_optc.h"
 #include "abm.h"
 #include "clk_mgr.h"
 #include "dmcu.h"
@@ -45,10 +43,9 @@
 #include "ipp.h"
 #include "mpc.h"
 #include "mcif_wb.h"
+#include "dchubbub.h"
 #include "reg_helper.h"
 #include "dcn10/dcn10_cm_common.h"
-#include "dcn10/dcn10_hubbub.h"
-#include "dcn10/dcn10_optc.h"
 #include "dc_link_dp.h"
 #include "vm_helper.h"
 #include "dccg.h"
@@ -64,14 +61,132 @@
 #define FN(reg_name, field_name) \
 	hws->shifts->field_name, hws->masks->field_name
 
-static void dcn20_enable_power_gating_plane(
+static int find_free_gsl_group(const struct dc *dc)
+{
+	if (dc->res_pool->gsl_groups.gsl_0 == 0)
+		return 1;
+	if (dc->res_pool->gsl_groups.gsl_1 == 0)
+		return 2;
+	if (dc->res_pool->gsl_groups.gsl_2 == 0)
+		return 3;
+
+	return 0;
+}
+
+/* NOTE: This is not a generic setup_gsl function (hence the suffix as_lock)
+ * This is only used to lock pipes in pipe splitting case with immediate flip
+ * Ordinary MPC/OTG locks suppress VUPDATE which doesn't help with immediate,
+ * so we get tearing with freesync since we cannot flip multiple pipes
+ * atomically.
+ * We use GSL for this:
+ * - immediate flip: find first available GSL group if not already assigned
+ *                   program gsl with that group, set current OTG as master
+ *                   and always us 0x4 = AND of flip_ready from all pipes
+ * - vsync flip: disable GSL if used
+ *
+ * Groups in stream_res are stored as +1 from HW registers, i.e.
+ * gsl_0 <=> pipe_ctx->stream_res.gsl_group == 1
+ * Using a magic value like -1 would require tracking all inits/resets
+ */
+static void dcn20_setup_gsl_group_as_lock(
+		const struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		bool enable)
+{
+	struct gsl_params gsl;
+	int group_idx;
+
+	memset(&gsl, 0, sizeof(struct gsl_params));
+
+	if (enable) {
+		/* return if group already assigned since GSL was set up
+		 * for vsync flip, we would unassign so it can't be "left over"
+		 */
+		if (pipe_ctx->stream_res.gsl_group > 0)
+			return;
+
+		group_idx = find_free_gsl_group(dc);
+		ASSERT(group_idx != 0);
+		pipe_ctx->stream_res.gsl_group = group_idx;
+
+		/* set gsl group reg field and mark resource used */
+		switch (group_idx) {
+		case 1:
+			gsl.gsl0_en = 1;
+			dc->res_pool->gsl_groups.gsl_0 = 1;
+			break;
+		case 2:
+			gsl.gsl1_en = 1;
+			dc->res_pool->gsl_groups.gsl_1 = 1;
+			break;
+		case 3:
+			gsl.gsl2_en = 1;
+			dc->res_pool->gsl_groups.gsl_2 = 1;
+			break;
+		default:
+			BREAK_TO_DEBUGGER();
+			return; // invalid case
+		}
+		gsl.gsl_master_en = 1;
+	} else {
+		group_idx = pipe_ctx->stream_res.gsl_group;
+		if (group_idx == 0)
+			return; // if not in use, just return
+
+		pipe_ctx->stream_res.gsl_group = 0;
+
+		/* unset gsl group reg field and mark resource free */
+		switch (group_idx) {
+		case 1:
+			gsl.gsl0_en = 0;
+			dc->res_pool->gsl_groups.gsl_0 = 0;
+			break;
+		case 2:
+			gsl.gsl1_en = 0;
+			dc->res_pool->gsl_groups.gsl_1 = 0;
+			break;
+		case 3:
+			gsl.gsl2_en = 0;
+			dc->res_pool->gsl_groups.gsl_2 = 0;
+			break;
+		default:
+			BREAK_TO_DEBUGGER();
+			return;
+		}
+		gsl.gsl_master_en = 0;
+	}
+
+	/* at this point we want to program whether it's to enable or disable */
+	if (pipe_ctx->stream_res.tg->funcs->set_gsl != NULL &&
+		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select != NULL) {
+		pipe_ctx->stream_res.tg->funcs->set_gsl(
+			pipe_ctx->stream_res.tg,
+			&gsl);
+
+		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select(
+			pipe_ctx->stream_res.tg, group_idx,	enable ? 4 : 0);
+	} else
+		BREAK_TO_DEBUGGER();
+}
+
+void dcn20_set_flip_control_gsl(
+		struct pipe_ctx *pipe_ctx,
+		bool flip_immediate)
+{
+	if (pipe_ctx && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_control_surface_gsl)
+		pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_control_surface_gsl(
+				pipe_ctx->plane_res.hubp, flip_immediate);
+
+}
+
+void dcn20_enable_power_gating_plane(
 	struct dce_hwseq *hws,
 	bool enable)
 {
-	bool force_on = 1; /* disable power gating */
+	bool force_on = true; /* disable power gating */
 
 	if (enable)
-		force_on = 0;
+		force_on = false;
 
 	/* DCHUBP0/1/2/3/4/5 */
 	REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN0_POWER_FORCEON, force_on);
@@ -128,44 +243,6 @@ void dcn20_dccg_init(struct dce_hwseq *hws)
 	/* This value is dependent on the hardware pipeline delay so set once per SOC */
 	REG_WRITE(DISPCLK_FREQ_CHANGE_CNTL, 0x801003c);
 }
-void dcn20_display_init(struct dc *dc)
-{
-	struct dce_hwseq *hws = dc->hwseq;
-
-	/* RBBMIF
-	 * disable RBBMIF timeout detection for all clients
-	 * Ensure RBBMIF does not drop register accesses due to the per-client timeout
-	 */
-	REG_WRITE(RBBMIF_TIMEOUT_DIS, 0xFFFFFFFF);
-	REG_WRITE(RBBMIF_TIMEOUT_DIS_2, 0xFFFFFFFF);
-
-	/* DCCG */
-	dcn20_dccg_init(hws);
-
-	REG_UPDATE(DC_MEM_GLOBAL_PWR_REQ_CNTL, DC_MEM_GLOBAL_PWR_REQ_DIS, 0);
-
-	/* DCHUB/MMHUBBUB
-	 * set global timer refclk divider
-	 * 100Mhz refclk -> 2
-	 * 27Mhz refclk ->  1
-	 * 48Mhz refclk ->  1
-	 */
-	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, 2);
-	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1);
-	REG_WRITE(REFCLK_CNTL, 0);
-
-	/* OPTC
-	 * OTG_CONTROL.OTG_DISABLE_POINT_CNTL = 0x3; will be set during optc2_enable_crtc
-	 */
-
-	/* AZ
-	 * default value is 0x64 for 100Mhz ref clock, if the ref clock is 100Mhz, no need to program this regiser,
-	 * if not, it should be programmed according to the ref clock
-	 */
-	REG_UPDATE(AZALIA_AUDIO_DTO, AZALIA_AUDIO_DTO_MODULE, 0x64);
-	/* Enable controller clock gating */
-	REG_WRITE(AZALIA_CONTROLLER_CLOCK_GATING, 0x1);
-}
 
 void dcn20_disable_vga(
 	struct dce_hwseq *hws)
@@ -178,15 +255,15 @@ void dcn20_disable_vga(
 	REG_WRITE(D6VGA_CONTROL, 0);
 }
 
-void dcn20_program_tripleBuffer(
+void dcn20_program_triple_buffer(
 	const struct dc *dc,
 	struct pipe_ctx *pipe_ctx,
-	bool enableTripleBuffer)
+	bool enable_triple_buffer)
 {
 	if (pipe_ctx->plane_res.hubp && pipe_ctx->plane_res.hubp->funcs) {
 		pipe_ctx->plane_res.hubp->funcs->hubp_enable_tripleBuffer(
 			pipe_ctx->plane_res.hubp,
-			enableTripleBuffer);
+			enable_triple_buffer);
 	}
 }
 
@@ -195,6 +272,7 @@ void dcn20_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	enum dc_color_space color_space;
 	struct tg_color black_color = {0};
 	struct output_pixel_processor *opp = NULL;
@@ -225,6 +303,7 @@ void dcn20_init_blank(
 	opp->funcs->opp_set_disp_pattern_generator(
 			opp,
 			CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR,
+			CONTROLLER_DP_COLOR_SPACE_UDEFINED,
 			COLOR_DEPTH_UNDEFINED,
 			&black_color,
 			otg_active_width,
@@ -234,17 +313,17 @@ void dcn20_init_blank(
 		bottom_opp->funcs->opp_set_disp_pattern_generator(
 				bottom_opp,
 				CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR,
+				CONTROLLER_DP_COLOR_SPACE_UDEFINED,
 				COLOR_DEPTH_UNDEFINED,
 				&black_color,
 				otg_active_width,
 				otg_active_height);
 	}
 
-	dcn20_hwss_wait_for_blank_complete(opp);
+	hws->funcs.wait_for_blank_complete(opp);
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-static void dcn20_dsc_pg_control(
+void dcn20_dsc_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int dsc_inst,
 		bool power_on)
@@ -320,9 +399,8 @@ static void dcn20_dsc_pg_control(
 	if (org_ip_request_cntl == 0)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0);
 }
-#endif
 
-static void dcn20_dpp_pg_control(
+void dcn20_dpp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int dpp_inst,
 		bool power_on)
@@ -396,7 +474,7 @@ static void dcn20_dpp_pg_control(
 }
 
 
-static void dcn20_hubp_pg_control(
+void dcn20_hubp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int hubp_inst,
 		bool power_on)
@@ -473,8 +551,9 @@ static void dcn20_hubp_pg_control(
 /* disable HW used by plane.
  * note:  cannot disable until disconnect is complete
  */
-static void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 
@@ -495,7 +574,7 @@ static void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	hubp->power_gated = true;
 	dc->optimized_required = false; /* We're powering off, no need to optimize */
 
-	dc->hwss.plane_atomic_power_down(dc,
+	hws->funcs.plane_atomic_power_down(dc,
 			pipe_ctx->plane_res.dpp,
 			pipe_ctx->plane_res.hubp);
 
@@ -526,6 +605,7 @@ enum dc_status dcn20_enable_stream_timing(
 		struct dc_state *context,
 		struct dc *dc)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct drr_params params = {0};
 	unsigned int event_triggers = 0;
@@ -585,7 +665,7 @@ enum dc_status dcn20_enable_stream_timing(
 			pipe_ctx->stream_res.opp,
 			true);
 
-	dc->hwss.blank_pixel_data(dc, pipe_ctx, true);
+	hws->funcs.blank_pixel_data(dc, pipe_ctx, true);
 
 	/* VTG is  within DCHUB command block. DCFCLK is always on */
 	if (false == pipe_ctx->stream_res.tg->funcs->enable_crtc(pipe_ctx->stream_res.tg)) {
@@ -593,7 +673,7 @@ enum dc_status dcn20_enable_stream_timing(
 		return DC_ERROR_UNEXPECTED;
 	}
 
-	dcn20_hwss_wait_for_blank_complete(pipe_ctx->stream_res.opp);
+	hws->funcs.wait_for_blank_complete(pipe_ctx->stream_res.opp);
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;
@@ -606,9 +686,13 @@ enum dc_status dcn20_enable_stream_timing(
 	// DRR should set trigger event to monitor surface update event
 	if (stream->adjust.v_total_min != 0 && stream->adjust.v_total_max != 0)
 		event_triggers = 0x80;
+	/* Event triggers and num frames initialized for DRR, but can be
+	 * later updated for PSR use. Note DRR trigger events are generated
+	 * regardless of whether num frames met.
+	 */
 	if (pipe_ctx->stream_res.tg->funcs->set_static_screen_control)
 		pipe_ctx->stream_res.tg->funcs->set_static_screen_control(
-				pipe_ctx->stream_res.tg, event_triggers);
+				pipe_ctx->stream_res.tg, event_triggers, 2);
 
 	/* TODO program crtc source select for non-virtual signal*/
 	/* TODO program FMT */
@@ -649,7 +733,7 @@ void dcn20_program_output_csc(struct dc *dc,
 	}
 }
 
-bool dcn20_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
+bool dcn20_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 				const struct dc_stream_state *stream)
 {
 	int mpcc_id = pipe_ctx->plane_res.hubp->inst;
@@ -736,20 +820,14 @@ bool dcn20_set_shaper_3dlut(
 	else
 		result = dpp_base->funcs->dpp_program_3dlut(dpp_base, NULL);
 
-	if (plane_state->lut3d_func &&
-		plane_state->lut3d_func->state.bits.initialized == 1 &&
-		plane_state->lut3d_func->hdr_multiplier != 0)
-		dpp_base->funcs->dpp_set_hdr_multiplier(dpp_base,
-				plane_state->lut3d_func->hdr_multiplier);
-	else
-		dpp_base->funcs->dpp_set_hdr_multiplier(dpp_base, 0x1f000);
-
 	return result;
 }
 
-bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
-					  const struct dc_plane_state *plane_state)
+bool dcn20_set_input_transfer_func(struct dc *dc,
+				struct pipe_ctx *pipe_ctx,
+				const struct dc_plane_state *plane_state)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	const struct dc_transfer_func *tf = NULL;
 	bool result = true;
@@ -758,8 +836,8 @@ bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 	if (dpp_base == NULL || plane_state == NULL)
 		return false;
 
-	dcn20_set_shaper_3dlut(pipe_ctx, plane_state);
-	dcn20_set_blend_lut(pipe_ctx, plane_state);
+	hws->funcs.set_shaper_3dlut(pipe_ctx, plane_state);
+	hws->funcs.set_blend_lut(pipe_ctx, plane_state);
 
 	if (plane_state->in_transfer_func)
 		tf = plane_state->in_transfer_func;
@@ -804,6 +882,11 @@ bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 					IPP_DEGAMMA_MODE_BYPASS);
 			break;
 		case TRANSFER_FUNCTION_PQ:
+			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_USER_PWL);
+			cm_helper_translate_curve_to_degamma_hw_format(tf, &dpp_base->degamma_params);
+			dpp_base->funcs->dpp_program_degamma_pwl(dpp_base, &dpp_base->degamma_params);
+			result = true;
+			break;
 		default:
 			result = false;
 			break;
@@ -824,7 +907,7 @@ bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 	return result;
 }
 
-static void dcn20_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx)
+void dcn20_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx)
 {
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 1;
@@ -855,12 +938,16 @@ void dcn20_blank_pixel_data(
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	enum dc_color_space color_space = stream->output_color_space;
 	enum controller_dp_test_pattern test_pattern = CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR;
+	enum controller_dp_color_space test_pattern_color_space = CONTROLLER_DP_COLOR_SPACE_UDEFINED;
 	struct pipe_ctx *odm_pipe;
 	int odm_cnt = 1;
 
 	int width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right;
 	int height = stream->timing.v_addressable + stream->timing.v_border_bottom + stream->timing.v_border_top;
 
+	if (stream->link->test_pattern_enabled)
+		return;
+
 	/* get opp dpg blank color */
 	color_space_to_black_color(dc, color_space, &black_color);
 
@@ -873,8 +960,10 @@ void dcn20_blank_pixel_data(
 		if (stream_res->abm)
 			stream_res->abm->funcs->set_abm_immediate_disable(stream_res->abm);
 
-		if (dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE)
+		if (dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE) {
 			test_pattern = CONTROLLER_DP_TEST_PATTERN_COLORSQUARES;
+			test_pattern_color_space = CONTROLLER_DP_COLOR_SPACE_RGB;
+		}
 	} else {
 		test_pattern = CONTROLLER_DP_TEST_PATTERN_VIDEOMODE;
 	}
@@ -882,6 +971,7 @@ void dcn20_blank_pixel_data(
 	stream_res->opp->funcs->opp_set_disp_pattern_generator(
 			stream_res->opp,
 			test_pattern,
+			test_pattern_color_space,
 			stream->timing.display_color_depth,
 			&black_color,
 			width,
@@ -892,6 +982,7 @@ void dcn20_blank_pixel_data(
 				odm_pipe->stream_res.opp,
 				dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE && blank ?
 						CONTROLLER_DP_TEST_PATTERN_COLORRAMP : test_pattern,
+				test_pattern_color_space,
 				stream->timing.display_color_depth,
 				&black_color,
 				width,
@@ -1217,9 +1308,11 @@ static void dcn20_update_dchubp_dpp(
 	struct pipe_ctx *pipe_ctx,
 	struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
+	bool viewport_changed = false;
 
 	if (pipe_ctx->update_flags.bits.dppclk)
 		dpp->funcs->dpp_dppclk_control(dpp, false, true);
@@ -1261,7 +1354,7 @@ static void dcn20_update_dchubp_dpp(
 
 		if (dpp->funcs->dpp_program_bias_and_scale) {
 			//TODO :for CNVC set scale and bias registers if necessary
-			dcn10_build_prescale_params(&bns_params, plane_state);
+			build_prescale_params(&bns_params, plane_state);
 			dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
 		}
 	}
@@ -1269,19 +1362,19 @@ static void dcn20_update_dchubp_dpp(
 	if (pipe_ctx->update_flags.bits.mpcc
 			|| plane_state->update_flags.bits.global_alpha_change
 			|| plane_state->update_flags.bits.per_pixel_alpha_change) {
-		/* Need mpcc to be idle if changing opp */
-		if (pipe_ctx->update_flags.bits.opp_changed) {
-			struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx];
-			int mpcc_inst;
-
-			for (mpcc_inst = 0; mpcc_inst < MAX_PIPES; mpcc_inst++) {
-				if (!old_pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst])
-					continue;
+		// MPCC inst is equal to pipe index in practice
+		int mpcc_inst = hubp->inst;
+		int opp_inst;
+		int opp_count = dc->res_pool->pipe_count;
+
+		for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
+			if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
 				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
-				old_pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst] = false;
+				dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
+				break;
 			}
 		}
-		dc->hwss.update_mpcc(dc, pipe_ctx);
+		hws->funcs.update_mpcc(dc, pipe_ctx);
 	}
 
 	if (pipe_ctx->update_flags.bits.scaler ||
@@ -1298,14 +1391,18 @@ static void dcn20_update_dchubp_dpp(
 
 	if (pipe_ctx->update_flags.bits.viewport ||
 			(context == dc->current_state && plane_state->update_flags.bits.scaling_change) ||
-			(context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling))
+			(context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling)) {
+
 		hubp->funcs->mem_program_viewport(
 			hubp,
 			&pipe_ctx->plane_res.scl_data.viewport,
 			&pipe_ctx->plane_res.scl_data.viewport_c);
+		viewport_changed = true;
+	}
 
 	/* Any updates are handled in dc interface, just need to apply existing for plane enable */
-	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed)
+	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed ||
+			pipe_ctx->update_flags.bits.scaler || pipe_ctx->update_flags.bits.viewport)
 			&& pipe_ctx->stream->cursor_attributes.address.quad_part != 0) {
 		dc->hwss.set_cursor_position(pipe_ctx);
 		dc->hwss.set_cursor_attribute(pipe_ctx);
@@ -1355,8 +1452,13 @@ static void dcn20_update_dchubp_dpp(
 		hubp->power_gated = false;
 	}
 
+	if (hubp->funcs->apply_PLAT_54186_wa && viewport_changed)
+		hubp->funcs->apply_PLAT_54186_wa(hubp, &plane_state->address);
+
 	if (pipe_ctx->update_flags.bits.enable || plane_state->update_flags.bits.addr_update)
-		dc->hwss.update_plane_addr(dc, pipe_ctx);
+		hws->funcs.update_plane_addr(dc, pipe_ctx);
+
+
 
 	if (pipe_ctx->update_flags.bits.enable)
 		hubp->funcs->set_blank(hubp, false);
@@ -1368,10 +1470,11 @@ static void dcn20_program_pipe(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	/* Only need to unblank on top pipe */
 	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.abm_level)
 			&& !pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe)
-		dc->hwss.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible);
+		hws->funcs.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible);
 
 	if (pipe_ctx->update_flags.bits.global_sync) {
 		pipe_ctx->stream_res.tg->funcs->program_global_sync(
@@ -1384,12 +1487,12 @@ static void dcn20_program_pipe(
 		pipe_ctx->stream_res.tg->funcs->set_vtg_params(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-		if (dc->hwss.setup_vupdate_interrupt)
-			dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+		if (hws->funcs.setup_vupdate_interrupt)
+			hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
 	}
 
 	if (pipe_ctx->update_flags.bits.odm)
-		dc->hwss.update_odm(dc, context, pipe_ctx);
+		hws->funcs.update_odm(dc, context, pipe_ctx);
 
 	if (pipe_ctx->update_flags.bits.enable)
 		dcn20_enable_plane(dc, pipe_ctx, context);
@@ -1398,20 +1501,20 @@ static void dcn20_program_pipe(
 		dcn20_update_dchubp_dpp(dc, pipe_ctx, context);
 
 	if (pipe_ctx->update_flags.bits.enable
-			|| pipe_ctx->plane_state->update_flags.bits.sdr_white_level)
-		set_hdr_multiplier(pipe_ctx);
+			|| pipe_ctx->plane_state->update_flags.bits.hdr_mult)
+		hws->funcs.set_hdr_multiplier(pipe_ctx);
 
 	if (pipe_ctx->update_flags.bits.enable ||
 			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
 			pipe_ctx->plane_state->update_flags.bits.gamma_change)
-		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+		hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state);
 
 	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
 	 * only do gamma programming for powering on, internal memcmp to avoid
 	 * updating on slave planes
 	 */
 	if (pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.out_tf)
-		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 
 	/* If the pipe has been enabled or has a different opp, we
 	 * should reprogram the fmt. This deals with cases where
@@ -1445,12 +1548,13 @@ static bool does_pipe_need_lock(struct pipe_ctx *pipe)
 	return false;
 }
 
-static void dcn20_program_front_end_for_ctx(
+void dcn20_program_front_end_for_ctx(
 		struct dc *dc,
 		struct dc_state *context)
 {
 	const unsigned int TIMEOUT_FOR_PIPE_ENABLE_MS = 100;
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 	bool pipe_locked[MAX_PIPES] = {false};
 	DC_LOGGER_INIT(dc->ctx->logger);
 
@@ -1482,13 +1586,13 @@ static void dcn20_program_front_end_for_ctx(
 				&& !context->res_ctx.pipe_ctx[i].top_pipe
 				&& !context->res_ctx.pipe_ctx[i].prev_odm_pipe
 				&& context->res_ctx.pipe_ctx[i].stream)
-			dc->hwss.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true);
+			hws->funcs.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true);
 
 	/* Disconnect mpcc */
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
 		if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable
 				|| context->res_ctx.pipe_ctx[i].update_flags.bits.opp_changed) {
-			dc->hwss.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
+			hws->funcs.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
 			DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx);
 		}
 
@@ -1508,8 +1612,8 @@ static void dcn20_program_front_end_for_ctx(
 			pipe = &context->res_ctx.pipe_ctx[i];
 			if (!pipe->prev_odm_pipe && pipe->stream->num_wb_info > 0
 					&& (pipe->update_flags.raw || pipe->plane_state->update_flags.raw || pipe->stream->update_flags.raw)
-					&& dc->hwss.program_all_writeback_pipes_in_tree)
-				dc->hwss.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
+					&& hws->funcs.program_all_writeback_pipes_in_tree)
+				hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
 		}
 	}
 
@@ -1541,9 +1645,9 @@ static void dcn20_program_front_end_for_ctx(
 			struct hubp *hubp = pipe->plane_res.hubp;
 			int j = 0;
 
-			for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS
+			for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS*1000
 					&& hubp->funcs->hubp_is_flip_pending(hubp); j++)
-				msleep(1);
+				mdelay(1);
 		}
 	}
 
@@ -1594,6 +1698,7 @@ bool dcn20_update_bandwidth(
 		struct dc_state *context)
 {
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	/* recalculate DML parameters */
 	if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false))
@@ -1623,10 +1728,10 @@ bool dcn20_update_bandwidth(
 					pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
 			if (pipe_ctx->prev_odm_pipe == NULL)
-				dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+				hws->funcs.blank_pixel_data(dc, pipe_ctx, blank);
 
-			if (dc->hwss.setup_vupdate_interrupt)
-				dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+			if (hws->funcs.setup_vupdate_interrupt)
+				hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
 		}
 
 		pipe_ctx->plane_res.hubp->funcs->hubp_setup(
@@ -1640,9 +1745,8 @@ bool dcn20_update_bandwidth(
 	return true;
 }
 
-static void dcn20_enable_writeback(
+void dcn20_enable_writeback(
 		struct dc *dc,
-		const struct dc_stream_status *stream_status,
 		struct dc_writeback_info *wb_info,
 		struct dc_state *context)
 {
@@ -1656,8 +1760,7 @@ static void dcn20_enable_writeback(
 	mcif_wb = dc->res_pool->mcif_wb[wb_info->dwb_pipe_inst];
 
 	/* set the OPTC source mux */
-	ASSERT(stream_status->primary_otg_inst < MAX_PIPES);
-	optc = dc->res_pool->timing_generators[stream_status->primary_otg_inst];
+	optc = dc->res_pool->timing_generators[dwb->otg_inst];
 	optc->funcs->set_dwb_source(optc, wb_info->dwb_pipe_inst);
 	/* set MCIF_WB buffer and arbitration configuration */
 	mcif_wb->funcs->config_mcif_buf(mcif_wb, &wb_info->mcif_buf_params, wb_info->dwb_params.dest_height);
@@ -1684,7 +1787,7 @@ void dcn20_disable_writeback(
 	mcif_wb->funcs->disable_mcif(mcif_wb);
 }
 
-bool dcn20_hwss_wait_for_blank_complete(
+bool dcn20_wait_for_blank_complete(
 		struct output_pixel_processor *opp)
 {
 	int counter;
@@ -1713,9 +1816,8 @@ bool dcn20_dmdata_status_done(struct pipe_ctx *pipe_ctx)
 	return hubp->funcs->dmdata_status_done(hubp);
 }
 
-static void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct dce_hwseq *hws = dc->hwseq;
 
 	if (pipe_ctx->stream_res.dsc) {
@@ -1727,12 +1829,10 @@ static void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx
 			odm_pipe = odm_pipe->next_odm_pipe;
 		}
 	}
-#endif
 }
 
-static void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct dce_hwseq *hws = dc->hwseq;
 
 	if (pipe_ctx->stream_res.dsc) {
@@ -1744,7 +1844,6 @@ static void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
 			odm_pipe = odm_pipe->next_odm_pipe;
 		}
 	}
-#endif
 }
 
 void dcn20_set_dmdata_attributes(struct pipe_ctx *pipe_ctx)
@@ -1767,12 +1866,7 @@ void dcn20_set_dmdata_attributes(struct pipe_ctx *pipe_ctx)
 	hubp->funcs->dmdata_set_attributes(hubp, &attr);
 }
 
-void dcn20_disable_stream(struct pipe_ctx *pipe_ctx)
-{
-	dce110_disable_stream(pipe_ctx);
-}
-
-static void dcn20_init_vm_ctx(
+void dcn20_init_vm_ctx(
 		struct dce_hwseq *hws,
 		struct dc *dc,
 		struct dc_virtual_addr_space_config *va_config,
@@ -1794,7 +1888,7 @@ static void dcn20_init_vm_ctx(
 	dc->res_pool->hubbub->funcs->init_vm_ctx(dc->res_pool->hubbub, &config, vmid);
 }
 
-static int dcn20_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
+int dcn20_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
 {
 	struct dcn_hubbub_phys_addr_config config;
 
@@ -1838,8 +1932,7 @@ static bool patch_address_for_sbs_tb_stereo(
 	return false;
 }
 
-
-static void dcn20_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	bool addr_patched = false;
 	PHYSICAL_ADDRESS_LOC addr;
@@ -1873,6 +1966,7 @@ void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx,
 	struct encoder_unblank_param params = { { 0 } };
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
+	struct dce_hwseq *hws = link->dc->hwseq;
 	struct pipe_ctx *odm_pipe;
 
 	params.opp_cnt = 1;
@@ -1885,7 +1979,7 @@ void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx,
 	params.link_settings.link_rate = link_settings->link_rate;
 
 	if (dc_is_dp_signal(pipe_ctx->stream->signal)) {
-		if (optc1_is_two_pixels_per_containter(&stream->timing) || params.opp_cnt > 1)
+		if (optc2_is_two_pixels_per_containter(&stream->timing) || params.opp_cnt > 1)
 			params.timing.pix_clk_100hz /= 2;
 		pipe_ctx->stream_res.stream_enc->funcs->dp_set_odm_combine(
 				pipe_ctx->stream_res.stream_enc, params.opp_cnt > 1);
@@ -1893,14 +1987,14 @@ void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx,
 	}
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, true);
+		hws->funcs.edp_backlight_control(link, true);
 	}
 }
 
-void dcn20_setup_vupdate_interrupt(struct pipe_ctx *pipe_ctx)
+void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
-	int start_line = get_vupdate_offset_from_vsync(pipe_ctx);
+	int start_line = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
 
 	if (start_line < 0)
 		start_line = 0;
@@ -1915,6 +2009,7 @@ static void dcn20_reset_back_end_for_pipe(
 		struct dc_state *context)
 {
 	int i;
+	struct dc_link *link;
 	DC_LOGGER_INIT(dc->ctx->logger);
 	if (pipe_ctx->stream_res.stream_enc == NULL) {
 		pipe_ctx->stream = NULL;
@@ -1922,8 +2017,14 @@ static void dcn20_reset_back_end_for_pipe(
 	}
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-		/* DPMS may already disable */
-		if (!pipe_ctx->stream->dpms_off)
+		link = pipe_ctx->stream->link;
+		/* DPMS may already disable or */
+		/* dpms_off status is incorrect due to fastboot
+		 * feature. When system resume from S4 with second
+		 * screen only, the dpms_off would be true but
+		 * VBIOS lit up eDP, so check link status too.
+		 */
+		if (!pipe_ctx->stream->dpms_off || link->link_status.link_active)
 			core_link_disable_stream(pipe_ctx);
 		else if (pipe_ctx->stream_res.audio)
 			dc->hwss.disable_audio_stream(pipe_ctx);
@@ -1943,11 +2044,9 @@ static void dcn20_reset_back_end_for_pipe(
 			}
 		}
 	}
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	else if (pipe_ctx->stream_res.dsc) {
 		dp_set_dsc_enable(pipe_ctx, false);
 	}
-#endif
 
 	/* by upper caller loop, parent pipe: pipe0, will be reset last.
 	 * back end share by all pipes and will be disable only when disable
@@ -1978,11 +2077,12 @@ static void dcn20_reset_back_end_for_pipe(
 					pipe_ctx->pipe_idx, pipe_ctx->stream_res.tg->inst);
 }
 
-static void dcn20_reset_hw_ctx_wrap(
+void dcn20_reset_hw_ctx_wrap(
 		struct dc *dc,
 		struct dc_state *context)
 {
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	/* Reset Back End*/
 	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
@@ -2001,8 +2101,8 @@ static void dcn20_reset_hw_ctx_wrap(
 			struct clock_source *old_clk = pipe_ctx_old->clock_source;
 
 			dcn20_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
-			if (dc->hwss.enable_stream_gating)
-				dc->hwss.enable_stream_gating(dc, pipe_ctx);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx);
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 		}
@@ -2031,8 +2131,9 @@ void dcn20_get_mpctree_visual_confirm_color(
 	*color = pipe_colors[top_pipe->pipe_idx];
 }
 
-static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct mpcc_blnd_cfg blnd_cfg = { {0} };
 	bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha;
@@ -2043,10 +2144,10 @@ static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 
 	// input to MPCC is always RGB, by default leave black_color at 0
 	if (dc->debug.visual_confirm == VISUAL_CONFIRM_HDR) {
-		dcn10_get_hdr_visual_confirm_color(
+		hws->funcs.get_hdr_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
 	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE) {
-		dcn10_get_surface_visual_confirm_color(
+		hws->funcs.get_surface_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
 	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_MPCTREE) {
 		dcn20_get_mpctree_visual_confirm_color(
@@ -2083,12 +2184,6 @@ static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	 */
 	mpcc_id = hubp->inst;
 
-	/* If there is no full update, don't need to touch MPC tree*/
-	if (!pipe_ctx->plane_state->update_flags.bits.full_update) {
-		mpc->funcs->update_blending(mpc, &blnd_cfg, mpcc_id);
-		return;
-	}
-
 	/* check if this MPCC is already being used */
 	new_mpcc = mpc->funcs->get_mpcc_for_dpp(mpc_tree_params, mpcc_id);
 	/* remove MPCC if being used */
@@ -2113,125 +2208,7 @@ static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	hubp->mpcc_id = mpcc_id;
 }
 
-static int find_free_gsl_group(const struct dc *dc)
-{
-	if (dc->res_pool->gsl_groups.gsl_0 == 0)
-		return 1;
-	if (dc->res_pool->gsl_groups.gsl_1 == 0)
-		return 2;
-	if (dc->res_pool->gsl_groups.gsl_2 == 0)
-		return 3;
-
-	return 0;
-}
-
-/* NOTE: This is not a generic setup_gsl function (hence the suffix as_lock)
- * This is only used to lock pipes in pipe splitting case with immediate flip
- * Ordinary MPC/OTG locks suppress VUPDATE which doesn't help with immediate,
- * so we get tearing with freesync since we cannot flip multiple pipes
- * atomically.
- * We use GSL for this:
- * - immediate flip: find first available GSL group if not already assigned
- *                   program gsl with that group, set current OTG as master
- *                   and always us 0x4 = AND of flip_ready from all pipes
- * - vsync flip: disable GSL if used
- *
- * Groups in stream_res are stored as +1 from HW registers, i.e.
- * gsl_0 <=> pipe_ctx->stream_res.gsl_group == 1
- * Using a magic value like -1 would require tracking all inits/resets
- */
-void dcn20_setup_gsl_group_as_lock(
-		const struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		bool enable)
-{
-	struct gsl_params gsl;
-	int group_idx;
-
-	memset(&gsl, 0, sizeof(struct gsl_params));
-
-	if (enable) {
-		/* return if group already assigned since GSL was set up
-		 * for vsync flip, we would unassign so it can't be "left over"
-		 */
-		if (pipe_ctx->stream_res.gsl_group > 0)
-			return;
-
-		group_idx = find_free_gsl_group(dc);
-		ASSERT(group_idx != 0);
-		pipe_ctx->stream_res.gsl_group = group_idx;
-
-		/* set gsl group reg field and mark resource used */
-		switch (group_idx) {
-		case 1:
-			gsl.gsl0_en = 1;
-			dc->res_pool->gsl_groups.gsl_0 = 1;
-			break;
-		case 2:
-			gsl.gsl1_en = 1;
-			dc->res_pool->gsl_groups.gsl_1 = 1;
-			break;
-		case 3:
-			gsl.gsl2_en = 1;
-			dc->res_pool->gsl_groups.gsl_2 = 1;
-			break;
-		default:
-			BREAK_TO_DEBUGGER();
-			return; // invalid case
-		}
-		gsl.gsl_master_en = 1;
-	} else {
-		group_idx = pipe_ctx->stream_res.gsl_group;
-		if (group_idx == 0)
-			return; // if not in use, just return
-
-		pipe_ctx->stream_res.gsl_group = 0;
-
-		/* unset gsl group reg field and mark resource free */
-		switch (group_idx) {
-		case 1:
-			gsl.gsl0_en = 0;
-			dc->res_pool->gsl_groups.gsl_0 = 0;
-			break;
-		case 2:
-			gsl.gsl1_en = 0;
-			dc->res_pool->gsl_groups.gsl_1 = 0;
-			break;
-		case 3:
-			gsl.gsl2_en = 0;
-			dc->res_pool->gsl_groups.gsl_2 = 0;
-			break;
-		default:
-			BREAK_TO_DEBUGGER();
-			return;
-		}
-		gsl.gsl_master_en = 0;
-	}
-
-	/* at this point we want to program whether it's to enable or disable */
-	if (pipe_ctx->stream_res.tg->funcs->set_gsl != NULL &&
-		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select != NULL) {
-		pipe_ctx->stream_res.tg->funcs->set_gsl(
-			pipe_ctx->stream_res.tg,
-			&gsl);
-
-		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select(
-			pipe_ctx->stream_res.tg, group_idx,	enable ? 4 : 0);
-	} else
-		BREAK_TO_DEBUGGER();
-}
-
-static void dcn20_set_flip_control_gsl(
-		struct pipe_ctx *pipe_ctx,
-		bool flip_immediate)
-{
-	if (pipe_ctx && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_control_surface_gsl)
-		pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_control_surface_gsl(
-				pipe_ctx->plane_res.hubp, flip_immediate);
-
-}
-
-static void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
+void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 {
 	enum dc_lane_count lane_count =
 		pipe_ctx->stream->link->cur_link_settings.lane_count;
@@ -2279,7 +2256,7 @@ static void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	}
 }
 
-static void dcn20_program_dmdata_engine(struct pipe_ctx *pipe_ctx)
+void dcn20_program_dmdata_engine(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state    *stream     = pipe_ctx->stream;
 	struct hubp               *hubp       = pipe_ctx->plane_res.hubp;
@@ -2305,7 +2282,7 @@ static void dcn20_program_dmdata_engine(struct pipe_ctx *pipe_ctx)
 						hubp->inst, mode);
 }
 
-static void dcn20_fpga_init_hw(struct dc *dc)
+void dcn20_fpga_init_hw(struct dc *dc)
 {
 	int i, j;
 	struct dce_hwseq *hws = dc->hwseq;
@@ -2320,13 +2297,13 @@ static void dcn20_fpga_init_hw(struct dc *dc)
 		res_pool->dccg->funcs->dccg_init(res_pool->dccg);
 
 	//Enable ability to power gate / don't force power on permanently
-	dc->hwss.enable_power_gating_plane(hws, true);
+	hws->funcs.enable_power_gating_plane(hws, true);
 
 	// Specific to FPGA dccg and registers
 	REG_WRITE(RBBMIF_TIMEOUT_DIS, 0xFFFFFFFF);
 	REG_WRITE(RBBMIF_TIMEOUT_DIS_2, 0xFFFFFFFF);
 
-	dcn20_dccg_init(hws);
+	hws->funcs.dccg_init(hws);
 
 	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, 2);
 	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1);
@@ -2390,7 +2367,7 @@ static void dcn20_fpga_init_hw(struct dc *dc)
 		dc->res_pool->opps[i]->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 		pipe_ctx->stream_res.opp = dc->res_pool->opps[i];
 		/*to do*/
-		hwss1_plane_atomic_disconnect(dc, pipe_ctx);
+		hws->funcs.plane_atomic_disconnect(dc, pipe_ctx);
 	}
 
 	/* initialize DWB pointer to MCIF_WB */
@@ -2419,57 +2396,3 @@ static void dcn20_fpga_init_hw(struct dc *dc)
 		tg->funcs->tg_init(tg);
 	}
 }
-
-void dcn20_hw_sequencer_construct(struct dc *dc)
-{
-	dcn10_hw_sequencer_construct(dc);
-	dc->hwss.unblank_stream = dcn20_unblank_stream;
-	dc->hwss.update_plane_addr = dcn20_update_plane_addr;
-	dc->hwss.enable_stream_timing = dcn20_enable_stream_timing;
-	dc->hwss.program_triplebuffer = dcn20_program_tripleBuffer;
-	dc->hwss.set_input_transfer_func = dcn20_set_input_transfer_func;
-	dc->hwss.set_output_transfer_func = dcn20_set_output_transfer_func;
-	dc->hwss.apply_ctx_for_surface = NULL;
-	dc->hwss.program_front_end_for_ctx = dcn20_program_front_end_for_ctx;
-	dc->hwss.pipe_control_lock = dcn20_pipe_control_lock;
-	dc->hwss.pipe_control_lock_global = dcn20_pipe_control_lock_global;
-	dc->hwss.optimize_bandwidth = dcn20_optimize_bandwidth;
-	dc->hwss.prepare_bandwidth = dcn20_prepare_bandwidth;
-	dc->hwss.update_bandwidth = dcn20_update_bandwidth;
-	dc->hwss.enable_writeback = dcn20_enable_writeback;
-	dc->hwss.disable_writeback = dcn20_disable_writeback;
-	dc->hwss.program_output_csc = dcn20_program_output_csc;
-	dc->hwss.update_odm = dcn20_update_odm;
-	dc->hwss.blank_pixel_data = dcn20_blank_pixel_data;
-	dc->hwss.dmdata_status_done = dcn20_dmdata_status_done;
-	dc->hwss.program_dmdata_engine = dcn20_program_dmdata_engine;
-	dc->hwss.enable_stream = dcn20_enable_stream;
-	dc->hwss.disable_stream = dcn20_disable_stream;
-	dc->hwss.init_sys_ctx = dcn20_init_sys_ctx;
-	dc->hwss.init_vm_ctx = dcn20_init_vm_ctx;
-	dc->hwss.disable_stream_gating = dcn20_disable_stream_gating;
-	dc->hwss.enable_stream_gating = dcn20_enable_stream_gating;
-	dc->hwss.setup_vupdate_interrupt = dcn20_setup_vupdate_interrupt;
-	dc->hwss.reset_hw_ctx_wrap = dcn20_reset_hw_ctx_wrap;
-	dc->hwss.update_mpcc = dcn20_update_mpcc;
-	dc->hwss.set_flip_control_gsl = dcn20_set_flip_control_gsl;
-	dc->hwss.init_blank = dcn20_init_blank;
-	dc->hwss.disable_plane = dcn20_disable_plane;
-	dc->hwss.plane_atomic_disable = dcn20_plane_atomic_disable;
-	dc->hwss.enable_power_gating_plane = dcn20_enable_power_gating_plane;
-	dc->hwss.dpp_pg_control = dcn20_dpp_pg_control;
-	dc->hwss.hubp_pg_control = dcn20_hubp_pg_control;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-	dc->hwss.dsc_pg_control = dcn20_dsc_pg_control;
-#else
-	dc->hwss.dsc_pg_control = NULL;
-#endif
-	dc->hwss.disable_vga = dcn20_disable_vga;
-
-	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-		dc->hwss.init_hw = dcn20_fpga_init_hw;
-		dc->hwss.init_pipes = NULL;
-	}
-
-
-}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
index 3098f1049ed7..02c9be5ebd47 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
@@ -26,90 +26,112 @@
 #ifndef __DC_HWSS_DCN20_H__
 #define __DC_HWSS_DCN20_H__
 
-struct dc;
+#include "hw_sequencer_private.h"
 
-void dcn20_hw_sequencer_construct(struct dc *dc);
-
-enum dc_status dcn20_enable_stream_timing(
-		struct pipe_ctx *pipe_ctx,
-		struct dc_state *context,
-		struct dc *dc);
-
-void dcn20_blank_pixel_data(
+bool dcn20_set_blend_lut(
+	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
+bool dcn20_set_shaper_3dlut(
+	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
+void dcn20_program_front_end_for_ctx(
 		struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		bool blank);
-
+		struct dc_state *context);
+void dcn20_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx);
+bool dcn20_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state);
+bool dcn20_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			const struct dc_stream_state *stream);
 void dcn20_program_output_csc(struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum dc_color_space colorspace,
 		uint16_t *matrix,
 		int opp_id);
-
+void dcn20_enable_stream(struct pipe_ctx *pipe_ctx);
+void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx,
+		struct dc_link_settings *link_settings);
+void dcn20_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_blank_pixel_data(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		bool blank);
+void dcn20_pipe_control_lock(
+	struct dc *dc,
+	struct pipe_ctx *pipe,
+	bool lock);
+void dcn20_pipe_control_lock_global(
+		struct dc *dc,
+		struct pipe_ctx *pipe,
+		bool lock);
 void dcn20_prepare_bandwidth(
 		struct dc *dc,
 		struct dc_state *context);
-
 void dcn20_optimize_bandwidth(
 		struct dc *dc,
 		struct dc_state *context);
-
 bool dcn20_update_bandwidth(
 		struct dc *dc,
 		struct dc_state *context);
-
+void dcn20_reset_hw_ctx_wrap(
+		struct dc *dc,
+		struct dc_state *context);
+enum dc_status dcn20_enable_stream_timing(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
+void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_init_blank(
+		struct dc *dc,
+		struct timing_generator *tg);
+void dcn20_disable_vga(
+	struct dce_hwseq *hws);
+void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_enable_power_gating_plane(
+	struct dce_hwseq *hws,
+	bool enable);
+void dcn20_dpp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int dpp_inst,
+		bool power_on);
+void dcn20_hubp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int hubp_inst,
+		bool power_on);
+void dcn20_program_triple_buffer(
+	const struct dc *dc,
+	struct pipe_ctx *pipe_ctx,
+	bool enable_triple_buffer);
+void dcn20_enable_writeback(
+		struct dc *dc,
+		struct dc_writeback_info *wb_info,
+		struct dc_state *context);
 void dcn20_disable_writeback(
 		struct dc *dc,
 		unsigned int dwb_pipe_inst);
-
-bool dcn20_hwss_wait_for_blank_complete(
-		struct output_pixel_processor *opp);
-
-bool dcn20_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
-			const struct dc_stream_state *stream);
-
-bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
-			const struct dc_plane_state *plane_state);
-
+void dcn20_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx);
 bool dcn20_dmdata_status_done(struct pipe_ctx *pipe_ctx);
-
+void dcn20_program_dmdata_engine(struct pipe_ctx *pipe_ctx);
 void dcn20_set_dmdata_attributes(struct pipe_ctx *pipe_ctx);
-
-void dcn20_disable_stream(struct pipe_ctx *pipe_ctx);
-
-void dcn20_program_tripleBuffer(
-		const struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		bool enableTripleBuffer);
-
-void dcn20_setup_vupdate_interrupt(struct pipe_ctx *pipe_ctx);
-
-void dcn20_pipe_control_lock_global(
+void dcn20_init_vm_ctx(
+		struct dce_hwseq *hws,
 		struct dc *dc,
-		struct pipe_ctx *pipe,
-		bool lock);
-void dcn20_setup_gsl_group_as_lock(const struct dc *dc,
-				struct pipe_ctx *pipe_ctx,
-				bool enable);
-void dcn20_dccg_init(struct dce_hwseq *hws);
-void dcn20_init_blank(
-	   struct dc *dc,
-	   struct timing_generator *tg);
-void dcn20_display_init(struct dc *dc);
-void dcn20_pipe_control_lock(
-	struct dc *dc,
-	struct pipe_ctx *pipe,
-	bool lock);
-void dcn20_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx);
-void dcn20_enable_plane(
-	struct dc *dc,
-	struct pipe_ctx *pipe_ctx,
-	struct dc_state *context);
-bool dcn20_set_blend_lut(
-	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
-bool dcn20_set_shaper_3dlut(
-	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
-void dcn20_get_mpctree_visual_confirm_color(
+		struct dc_virtual_addr_space_config *va_config,
+		int vmid);
+void dcn20_set_flip_control_gsl(
 		struct pipe_ctx *pipe_ctx,
-		struct tg_color *color);
+		bool flip_immediate);
+void dcn20_dsc_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int dsc_inst,
+		bool power_on);
+void dcn20_fpga_init_hw(struct dc *dc);
+bool dcn20_wait_for_blank_complete(
+		struct output_pixel_processor *opp);
+void dcn20_dccg_init(struct dce_hwseq *hws);
+int dcn20_init_sys_ctx(struct dce_hwseq *hws,
+		struct dc *dc,
+		struct dc_phy_addr_space_config *pa_config);
+
 #endif /* __DC_HWSS_DCN20_H__ */
+
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
new file mode 100644
index 000000000000..d51e02fdab4d
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
@@ -0,0 +1,133 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dce110/dce110_hw_sequencer.h"
+#include "dcn10/dcn10_hw_sequencer.h"
+#include "dcn20_hwseq.h"
+
+static const struct hw_sequencer_funcs dcn20_funcs = {
+	.program_gamut_remap = dcn10_program_gamut_remap,
+	.init_hw = dcn10_init_hw,
+	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
+	.apply_ctx_for_surface = NULL,
+	.program_front_end_for_ctx = dcn20_program_front_end_for_ctx,
+	.update_plane_addr = dcn20_update_plane_addr,
+	.update_dchub = dcn10_update_dchub,
+	.update_pending_status = dcn10_update_pending_status,
+	.program_output_csc = dcn20_program_output_csc,
+	.enable_accelerated_mode = dce110_enable_accelerated_mode,
+	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
+	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
+	.update_info_frame = dce110_update_info_frame,
+	.send_immediate_sdp_message = dcn10_send_immediate_sdp_message,
+	.enable_stream = dcn20_enable_stream,
+	.disable_stream = dce110_disable_stream,
+	.unblank_stream = dcn20_unblank_stream,
+	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
+	.disable_plane = dcn20_disable_plane,
+	.pipe_control_lock = dcn20_pipe_control_lock,
+	.pipe_control_lock_global = dcn20_pipe_control_lock_global,
+	.prepare_bandwidth = dcn20_prepare_bandwidth,
+	.optimize_bandwidth = dcn20_optimize_bandwidth,
+	.update_bandwidth = dcn20_update_bandwidth,
+	.set_drr = dcn10_set_drr,
+	.get_position = dcn10_get_position,
+	.set_static_screen_control = dcn10_set_static_screen_control,
+	.setup_stereo = dcn10_setup_stereo,
+	.set_avmute = dce110_set_avmute,
+	.log_hw_state = dcn10_log_hw_state,
+	.get_hw_state = dcn10_get_hw_state,
+	.clear_status_bits = dcn10_clear_status_bits,
+	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_power_control = dce110_edp_power_control,
+	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
+	.set_cursor_position = dcn10_set_cursor_position,
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
+	.setup_periodic_interrupt = dcn10_setup_periodic_interrupt,
+	.set_clock = dcn10_set_clock,
+	.get_clock = dcn10_get_clock,
+	.program_triplebuffer = dcn20_program_triple_buffer,
+	.enable_writeback = dcn20_enable_writeback,
+	.disable_writeback = dcn20_disable_writeback,
+	.dmdata_status_done = dcn20_dmdata_status_done,
+	.program_dmdata_engine = dcn20_program_dmdata_engine,
+	.set_dmdata_attributes = dcn20_set_dmdata_attributes,
+	.init_sys_ctx = dcn20_init_sys_ctx,
+	.init_vm_ctx = dcn20_init_vm_ctx,
+	.set_flip_control_gsl = dcn20_set_flip_control_gsl,
+	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+};
+
+static const struct hwseq_private_funcs dcn20_private_funcs = {
+	.init_pipes = dcn10_init_pipes,
+	.update_plane_addr = dcn20_update_plane_addr,
+	.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
+	.update_mpcc = dcn20_update_mpcc,
+	.set_input_transfer_func = dcn20_set_input_transfer_func,
+	.set_output_transfer_func = dcn20_set_output_transfer_func,
+	.power_down = dce110_power_down,
+	.enable_display_power_gating = dcn10_dummy_display_power_gating,
+	.blank_pixel_data = dcn20_blank_pixel_data,
+	.reset_hw_ctx_wrap = dcn20_reset_hw_ctx_wrap,
+	.enable_stream_timing = dcn20_enable_stream_timing,
+	.edp_backlight_control = dce110_edp_backlight_control,
+	.disable_stream_gating = dcn20_disable_stream_gating,
+	.enable_stream_gating = dcn20_enable_stream_gating,
+	.setup_vupdate_interrupt = dcn20_setup_vupdate_interrupt,
+	.did_underflow_occur = dcn10_did_underflow_occur,
+	.init_blank = dcn20_init_blank,
+	.disable_vga = dcn20_disable_vga,
+	.bios_golden_init = dcn10_bios_golden_init,
+	.plane_atomic_disable = dcn20_plane_atomic_disable,
+	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
+	.enable_power_gating_plane = dcn20_enable_power_gating_plane,
+	.dpp_pg_control = dcn20_dpp_pg_control,
+	.hubp_pg_control = dcn20_hubp_pg_control,
+	.dsc_pg_control = NULL,
+	.update_odm = dcn20_update_odm,
+	.dsc_pg_control = dcn20_dsc_pg_control,
+	.get_surface_visual_confirm_color = dcn10_get_surface_visual_confirm_color,
+	.get_hdr_visual_confirm_color = dcn10_get_hdr_visual_confirm_color,
+	.set_hdr_multiplier = dcn10_set_hdr_multiplier,
+	.verify_allow_pstate_change_high = dcn10_verify_allow_pstate_change_high,
+	.wait_for_blank_complete = dcn20_wait_for_blank_complete,
+	.dccg_init = dcn20_dccg_init,
+	.set_blend_lut = dcn20_set_blend_lut,
+	.set_shaper_3dlut = dcn20_set_shaper_3dlut,
+};
+
+void dcn20_hw_sequencer_construct(struct dc *dc)
+{
+	dc->hwss = dcn20_funcs;
+	dc->hwseq->funcs = dcn20_private_funcs;
+
+	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		dc->hwss.init_hw = dcn20_fpga_init_hw;
+		dc->hwseq->funcs.init_pipes = NULL;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.h
new file mode 100644
index 000000000000..12277797cd71
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_DCN20_INIT_H__
+#define __DC_DCN20_INIT_H__
+
+struct dc;
+
+void dcn20_hw_sequencer_construct(struct dc *dc);
+
+#endif /* __DC_DCN20_INIT_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
index e476f27aa3a9..e4ac73035c84 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
@@ -168,10 +168,8 @@ static struct mpll_cfg dcn2_mpll_cfg[] = {
 void enc2_fec_set_enable(struct link_encoder *enc, bool enable)
 {
 	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	DC_LOG_DSC("%s FEC at link encoder inst %d",
 			enable ? "Enabling" : "Disabling", enc->id.enum_id);
-#endif
 	REG_UPDATE(DP_DPHY_CNTL, DPHY_FEC_EN, enable);
 }
 
@@ -192,7 +190,6 @@ bool enc2_fec_is_active(struct link_encoder *enc)
 	return (active != 0);
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* this function reads dsc related register fields to be logged later in dcn10_log_hw_state
  * into a dcn_dsc_state struct.
  */
@@ -203,8 +200,8 @@ void link_enc2_read_state(struct link_encoder *enc, struct link_enc_state *s)
 	REG_GET(DP_DPHY_CNTL, DPHY_FEC_EN, &s->dphy_fec_en);
 	REG_GET(DP_DPHY_CNTL, DPHY_FEC_READY_SHADOW, &s->dphy_fec_ready_shadow);
 	REG_GET(DP_DPHY_CNTL, DPHY_FEC_ACTIVE_STATUS, &s->dphy_fec_active_status);
+	REG_GET(DP_LINK_CNTL, DP_LINK_TRAINING_COMPLETE, &s->dp_link_training_complete);
 }
-#endif
 
 static bool update_cfg_data(
 		struct dcn10_link_encoder *enc10,
@@ -315,9 +312,7 @@ void enc2_hw_init(struct link_encoder *enc)
 }
 
 static const struct link_encoder_funcs dcn20_link_enc_funcs = {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.read_state = link_enc2_read_state,
-#endif
 	.validate_output_with_stream =
 		dcn10_link_encoder_validate_output_with_stream,
 	.hw_init = enc2_hw_init,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
index 0c98a0bbbd14..8cab8107fd94 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
@@ -33,7 +33,142 @@
 	SRI(AUX_DPHY_TX_CONTROL, DP_AUX, id)
 
 #define UNIPHY_MASK_SH_LIST(mask_sh)\
-	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_LINK_ENABLE, mask_sh)
+	LE_SF(SYMCLKA_CLOCK_ENABLE, SYMCLKA_CLOCK_ENABLE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_LINK_ENABLE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL0_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL1_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL2_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL3_XBAR_SOURCE, mask_sh)
+
+#define DPCS_MASK_SH_LIST(mask_sh)\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_CLK_RDY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_DATA_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_CLK_RDY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_DATA_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_CLK_RDY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_DATA_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_CLK_RDY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_DATA_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX0_TERM_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX1_TERM_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX2_TERM_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX3_TERM_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_DP_MPLLB_MULTIPLIER, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX0_WIDTH, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX0_RATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX1_WIDTH, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX1_RATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX2_PSTATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX3_PSTATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX2_MPLL_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX3_MPLL_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_QUOT, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_DEN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL8, RDPCS_PHY_DP_MPLLB_SSC_PEAK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL9, RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL9, RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL10, RDPCS_PHY_DP_MPLLB_FRACN_REM, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_DP_REF_CLK_MPLLB_DIV, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_HDMI_MPLLB_HDMI_DIV, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_SSC_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_TX_CLK_DIV, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_STATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL13, RDPCS_PHY_DP_MPLLB_DIV_CLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL13, RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL14, RDPCS_PHY_DP_MPLLB_FRACN_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL14, RDPCS_PHY_DP_MPLLB_PMIX_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE0_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE1_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE2_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE3_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_RD_START_DELAY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_EXT_REFCLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_BYPASS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_CLOCK_ON, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_CLOCK_ON, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_GATE_DIS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_REQ, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_REQ, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_REQ, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_REQ, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_CR_MUX_SEL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_REF_RANGE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_BYPASS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_EXT_LD_DONE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_HDMIMODE_ENABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_INIT_DONE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL2, RDPCS_PHY_DP4_POR, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA, RDPCS_PLL_UPDATE_DATA, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_REG_FIFO_ERROR_MASK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_TX_FIFO_ERROR_MASK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_DPALT_DISABLE_TOGGLE_MASK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_DPALT_4LANE_TOGGLE_MASK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCS_TX_CR_ADDR, RDPCS_TX_CR_ADDR, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCS_TX_CR_DATA, RDPCS_TX_CR_DATA, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_V2I, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_FREQ_VCO, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_MPLLB_CP_INT, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_MPLLB_CP_PROP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_FINETUNE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_RANGE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_POST, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_CLOCK_ON, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_GATE_DIS, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_EN, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_SWAP, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_ORDER_INVERT, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_FIFO_EN, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_FIFO_RD_START_DELAY, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_DEBUG_CONFIG, DPCS_DBG_CBUS_DIS, mask_sh)
+
+#define DPCS_DCN2_MASK_SH_LIST(mask_sh)\
+	DPCS_MASK_SH_LIST(mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL, RDPCS_PHY_RX_REF_LD_VAL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL, RDPCS_PHY_RX_VCO_LD_VAL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX0_PSTATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX1_PSTATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX0_MPLL_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX1_MPLL_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_REF_CLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX2_WIDTH, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX2_RATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX3_WIDTH, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX3_RATE, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYA_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh)
 
 #define LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh)\
 	LINK_ENCODER_MASK_SH_LIST_DCN10(mask_sh),\
@@ -63,6 +198,49 @@
 	SRI(CLOCK_ENABLE, SYMCLK, id), \
 	SRI(CHANNEL_XBAR_CNTL, UNIPHY, id)
 
+#define DPCS_DCN2_CMN_REG_LIST(id) \
+	SRI(DIG_LANE_ENABLE, DIG, id), \
+	SRI(TMDS_CTL_BITS, DIG, id), \
+	SRI(RDPCSTX_PHY_CNTL3, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL4, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL5, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL6, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL7, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL8, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL9, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL10, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL11, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL12, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL13, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL14, RDPCSTX, id), \
+	SRI(RDPCSTX_CNTL, RDPCSTX, id), \
+	SRI(RDPCSTX_CLOCK_CNTL, RDPCSTX, id), \
+	SRI(RDPCSTX_INTERRUPT_CONTROL, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL0, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL2, RDPCSTX, id), \
+	SRI(RDPCSTX_PLL_UPDATE_DATA, RDPCSTX, id), \
+	SRI(RDPCS_TX_CR_ADDR, RDPCSTX, id), \
+	SRI(RDPCS_TX_CR_DATA, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE0, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE1, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE2, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE3, RDPCSTX, id), \
+	SRI(DPCSTX_TX_CLOCK_CNTL, DPCSTX, id), \
+	SRI(DPCSTX_TX_CNTL, DPCSTX, id), \
+	SRI(DPCSTX_DEBUG_CONFIG, DPCSTX, id), \
+	SRI(RDPCSTX_DEBUG_CONFIG, RDPCSTX, id), \
+	SR(RDPCSTX0_RDPCSTX_SCRATCH)
+
+
+#define DPCS_DCN2_REG_LIST(id) \
+	DPCS_DCN2_CMN_REG_LIST(id), \
+	SRI(RDPCSTX_PHY_RX_LD_VAL, RDPCSTX, id),\
+	SRI(RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCSTX, id)
+
+#define LE_DCN2_REG_LIST(id) \
+		LE_DCN10_REG_LIST(id), \
+		SR(DCIO_SOFT_RESET)
+
 struct mpll_cfg {
 	uint32_t mpllb_ana_v2i;
 	uint32_t mpllb_ana_freq_vco;
@@ -158,9 +336,7 @@ void enc2_fec_set_ready(struct link_encoder *enc, bool ready);
 bool enc2_fec_is_active(struct link_encoder *enc);
 void enc2_hw_init(struct link_encoder *enc);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 void link_enc2_read_state(struct link_encoder *enc, struct link_enc_state *s);
-#endif
 
 void dcn20_link_encoder_enable_dp_output(
 	struct link_encoder *enc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
index 5a188b2bc033..de9c857ab3e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
@@ -33,6 +33,9 @@
 #define REG(reg)\
 	mpc20->mpc_regs->reg
 
+#define IND_REG(index) \
+	(index)
+
 #define CTX \
 	mpc20->base.ctx
 
@@ -132,19 +135,33 @@ void mpc2_set_output_csc(
 		const uint16_t *regval,
 		enum mpc_output_csc_mode ocsc_mode)
 {
+	uint32_t cur_mode;
 	struct dcn20_mpc *mpc20 = TO_DCN20_MPC(mpc);
 	struct color_matrices_reg ocsc_regs;
 
-	REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
-
-	if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE)
+	if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE) {
+		REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
 		return;
+	}
 
 	if (regval == NULL) {
 		BREAK_TO_DEBUGGER();
 		return;
 	}
 
+	/* determine which CSC coefficients (A or B) we are using
+	 * currently.  select the alternate set to double buffer
+	 * the CSC update so CSC is updated on frame boundary
+	 */
+	IX_REG_GET(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_DATA,
+						MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX,
+						MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE, &cur_mode);
+
+	if (cur_mode != MPC_OUTPUT_CSC_COEF_A)
+		ocsc_mode = MPC_OUTPUT_CSC_COEF_A;
+	else
+		ocsc_mode = MPC_OUTPUT_CSC_COEF_B;
+
 	ocsc_regs.shifts.csc_c11 = mpc20->mpc_shift->MPC_OCSC_C11_A;
 	ocsc_regs.masks.csc_c11  = mpc20->mpc_mask->MPC_OCSC_C11_A;
 	ocsc_regs.shifts.csc_c12 = mpc20->mpc_shift->MPC_OCSC_C12_A;
@@ -157,10 +174,13 @@ void mpc2_set_output_csc(
 		ocsc_regs.csc_c11_c12 = REG(CSC_C11_C12_B[opp_id]);
 		ocsc_regs.csc_c33_c34 = REG(CSC_C33_C34_B[opp_id]);
 	}
+
 	cm_helper_program_color_matrices(
 			mpc20->base.ctx,
 			regval,
 			&ocsc_regs);
+
+	REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
 }
 
 void mpc2_set_ocsc_default(
@@ -169,14 +189,16 @@ void mpc2_set_ocsc_default(
 		enum dc_color_space color_space,
 		enum mpc_output_csc_mode ocsc_mode)
 {
+	uint32_t cur_mode;
 	struct dcn20_mpc *mpc20 = TO_DCN20_MPC(mpc);
 	uint32_t arr_size;
 	struct color_matrices_reg ocsc_regs;
 	const uint16_t *regval = NULL;
 
-	REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
-	if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE)
+	if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE) {
+		REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
 		return;
+	}
 
 	regval = find_color_matrix(color_space, &arr_size);
 
@@ -185,6 +207,19 @@ void mpc2_set_ocsc_default(
 		return;
 	}
 
+	/* determine which CSC coefficients (A or B) we are using
+	 * currently.  select the alternate set to double buffer
+	 * the CSC update so CSC is updated on frame boundary
+	 */
+	IX_REG_GET(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_DATA,
+						MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX,
+						MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE, &cur_mode);
+
+	if (cur_mode != MPC_OUTPUT_CSC_COEF_A)
+		ocsc_mode = MPC_OUTPUT_CSC_COEF_A;
+	else
+		ocsc_mode = MPC_OUTPUT_CSC_COEF_B;
+
 	ocsc_regs.shifts.csc_c11 = mpc20->mpc_shift->MPC_OCSC_C11_A;
 	ocsc_regs.masks.csc_c11  = mpc20->mpc_mask->MPC_OCSC_C11_A;
 	ocsc_regs.shifts.csc_c12 = mpc20->mpc_shift->MPC_OCSC_C12_A;
@@ -203,6 +238,8 @@ void mpc2_set_ocsc_default(
 			mpc20->base.ctx,
 			regval,
 			&ocsc_regs);
+
+	REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
 }
 
 static void mpc2_ogam_get_reg_field(
@@ -345,6 +382,9 @@ static void mpc20_program_ogam_pwl(
 	uint32_t i;
 	struct dcn20_mpc *mpc20 = TO_DCN20_MPC(mpc);
 
+	PERF_TRACE();
+	REG_SEQ_START();
+
 	for (i = 0 ; i < num; i++) {
 		REG_SET(MPCC_OGAM_LUT_DATA[mpcc_id], 0, MPCC_OGAM_LUT_DATA, rgb[i].red_reg);
 		REG_SET(MPCC_OGAM_LUT_DATA[mpcc_id], 0, MPCC_OGAM_LUT_DATA, rgb[i].green_reg);
@@ -463,6 +503,11 @@ void mpc2_assert_mpcc_idle_before_connect(struct mpc *mpc, int mpcc_id)
 		ASSERT(!mpc_disabled);
 		ASSERT(!mpc_idle);
 	}
+
+	REG_SEQ_SUBMIT();
+	PERF_TRACE();
+	REG_SEQ_WAIT_DONE();
+	PERF_TRACE();
 }
 
 static void mpc2_init_mpcc(struct mpcc *mpcc, int mpcc_inst)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
index 9f53192da2dc..c78fd5123497 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
@@ -80,6 +80,10 @@
 	SRII(DENORM_CLAMP_G_Y, MPC_OUT, inst),\
 	SRII(DENORM_CLAMP_B_CB, MPC_OUT, inst)
 
+#define MPC_DBG_REG_LIST_DCN2_0() \
+	SR(MPC_OCSC_TEST_DEBUG_DATA),\
+	SR(MPC_OCSC_TEST_DEBUG_INDEX)
+
 #define MPC_REG_VARIABLE_LIST_DCN2_0 \
 	MPC_COMMON_REG_VARIABLE_LIST \
 	uint32_t MPCC_TOP_GAIN[MAX_MPCC]; \
@@ -118,6 +122,8 @@
 	uint32_t MPCC_OGAM_LUT_RAM_CONTROL[MAX_MPCC];\
 	uint32_t MPCC_OGAM_LUT_DATA[MAX_MPCC];\
 	uint32_t MPCC_OGAM_MODE[MAX_MPCC];\
+	uint32_t MPC_OCSC_TEST_DEBUG_DATA;\
+	uint32_t MPC_OCSC_TEST_DEBUG_INDEX;\
 	uint32_t CSC_MODE[MAX_OPP]; \
 	uint32_t CSC_C11_C12_A[MAX_OPP]; \
 	uint32_t CSC_C33_C34_A[MAX_OPP]; \
@@ -134,6 +140,7 @@
 	SF(MPCC0_MPCC_TOP_GAIN, MPCC_TOP_GAIN, mask_sh),\
 	SF(MPCC0_MPCC_BOT_GAIN_INSIDE, MPCC_BOT_GAIN_INSIDE, mask_sh),\
 	SF(MPCC0_MPCC_BOT_GAIN_OUTSIDE, MPCC_BOT_GAIN_OUTSIDE, mask_sh),\
+	SF(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_INDEX, mask_sh),\
 	SF(MPC_OUT0_CSC_MODE, MPC_OCSC_MODE, mask_sh),\
 	SF(MPC_OUT0_CSC_C11_C12_A, MPC_OCSC_C11_A, mask_sh),\
 	SF(MPC_OUT0_CSC_C11_C12_A, MPC_OCSC_C12_A, mask_sh),\
@@ -174,6 +181,19 @@
 	SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MAX_B_CB, mask_sh),\
 	SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MIN_B_CB, mask_sh)
 
+/*
+ *	DCN2 MPC_OCSC debug status register:
+ *
+ *		Status index including current OCSC Mode is 1
+ *			OCSC Mode: [1..0]
+ */
+#define MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX 1
+
+#define MPC_DEBUG_REG_LIST_SH_DCN20 \
+	.MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE = 0
+
+#define MPC_DEBUG_REG_LIST_MASK_DCN20 \
+	.MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE = 0x3
 
 #define MPC_REG_FIELD_LIST_DCN2_0(type) \
 	MPC_REG_FIELD_LIST(type)\
@@ -182,6 +202,8 @@
 	type MPCC_TOP_GAIN;\
 	type MPCC_BOT_GAIN_INSIDE;\
 	type MPCC_BOT_GAIN_OUTSIDE;\
+	type MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE;\
+	type MPC_OCSC_TEST_DEBUG_INDEX;\
 	type MPC_OCSC_MODE;\
 	type MPC_OCSC_C11_A;\
 	type MPC_OCSC_C12_A;\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
index 40164ed015ea..023cc71fad0f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
@@ -41,6 +41,7 @@
 void opp2_set_disp_pattern_generator(
 		struct output_pixel_processor *opp,
 		enum controller_dp_test_pattern test_pattern,
+		enum controller_dp_color_space color_space,
 		enum dc_color_depth color_depth,
 		const struct tg_color *solid_color,
 		int width,
@@ -100,9 +101,22 @@ void opp2_set_disp_pattern_generator(
 				TEST_PATTERN_DYN_RANGE_CEA :
 				TEST_PATTERN_DYN_RANGE_VESA);
 
+		switch (color_space) {
+		case CONTROLLER_DP_COLOR_SPACE_YCBCR601:
+			mode = TEST_PATTERN_MODE_COLORSQUARES_YCBCR601;
+		break;
+		case CONTROLLER_DP_COLOR_SPACE_YCBCR709:
+			mode = TEST_PATTERN_MODE_COLORSQUARES_YCBCR709;
+		break;
+		case CONTROLLER_DP_COLOR_SPACE_RGB:
+		default:
+			mode = TEST_PATTERN_MODE_COLORSQUARES_RGB;
+		break;
+		}
+
 		REG_UPDATE_6(DPG_CONTROL,
 			DPG_EN, 1,
-			DPG_MODE, TEST_PATTERN_MODE_COLORSQUARES_RGB,
+			DPG_MODE, mode,
 			DPG_DYNAMIC_RANGE, dyn_range,
 			DPG_BIT_DEPTH, bit_depth,
 			DPG_VRES, 6,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
index abd8de9a78f8..4093bec172c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
@@ -140,6 +140,7 @@ void dcn20_opp_construct(struct dcn20_opp *oppn20,
 void opp2_set_disp_pattern_generator(
 	struct output_pixel_processor *opp,
 	enum controller_dp_test_pattern test_pattern,
+	enum controller_dp_color_space color_space,
 	enum dc_color_depth color_depth,
 	const struct tg_color *solid_color,
 	int width,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
index 3b613fb93ef8..d875b0c38fde 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
@@ -59,11 +59,16 @@ bool optc2_enable_crtc(struct timing_generator *optc)
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 1);
 
+	REG_SEQ_START();
+
 	/* Enable CRTC */
 	REG_UPDATE_2(OTG_CONTROL,
 			OTG_DISABLE_POINT_CNTL, 3,
 			OTG_MASTER_EN, 1);
 
+	REG_SEQ_SUBMIT();
+	REG_SEQ_WAIT_DONE();
+
 	return true;
 }
 
@@ -167,7 +172,6 @@ void optc2_set_gsl_source_select(
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* DSC encoder frame start controls: x = h position, line_num = # of lines from vstartup */
 void optc2_set_dsc_encoder_frame_start(struct timing_generator *optc,
 					int x_position,
@@ -201,13 +205,12 @@ void optc2_set_dsc_config(struct timing_generator *optc,
 	REG_UPDATE(OPTC_WIDTH_CONTROL,
 		OPTC_DSC_SLICE_WIDTH, dsc_slice_width);
 }
-#endif
 
-/**
- * PTI i think is already done somewhere else for 2ka
- * (opp?, please double check.
- * OPTC side only has 1 register to set for PTI_ENABLE)
- */
+/*TEMP: Need to figure out inheritance model here.*/
+bool optc2_is_two_pixels_per_containter(const struct dc_crtc_timing *timing)
+{
+	return optc1_is_two_pixels_per_containter(timing);
+}
 
 void optc2_set_odm_bypass(struct timing_generator *optc,
 		const struct dc_crtc_timing *dc_crtc_timing)
@@ -221,7 +224,7 @@ void optc2_set_odm_bypass(struct timing_generator *optc,
 			OPTC_SEG1_SRC_SEL, 0xf);
 	REG_WRITE(OTG_H_TIMING_CNTL, 0);
 
-	h_div_2 = optc1_is_two_pixels_per_containter(dc_crtc_timing);
+	h_div_2 = optc2_is_two_pixels_per_containter(dc_crtc_timing);
 	REG_UPDATE(OTG_H_TIMING_CNTL,
 			OTG_H_TIMING_DIV_BY2, h_div_2);
 	REG_SET(OPTC_MEMORY_CONFIG, 0,
@@ -233,12 +236,13 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c
 		struct dc_crtc_timing *timing)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
-	/* 2 pieces of memory required for up to 5120 displays, 4 for up to 8192 */
 	int mpcc_hactive = (timing->h_addressable + timing->h_border_left + timing->h_border_right)
 			/ opp_cnt;
-	int memory_mask = mpcc_hactive <= 2560 ? 0x3 : 0xf;
+	uint32_t memory_mask;
 	uint32_t data_fmt = 0;
 
+	ASSERT(opp_cnt == 2);
+
 	/* TODO: In pseudocode but does not affect maximus, delete comment if we dont need on asic
 	 * REG_SET(OTG_GLOBAL_CONTROL2, 0, GLOBAL_UPDATE_LOCK_EN, 1);
 	 * Program OTG register MASTER_UPDATE_LOCK_DB_X/Y to the position before DP frame start
@@ -246,9 +250,17 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c
 	 *		MASTER_UPDATE_LOCK_DB_X, 160,
 	 *		MASTER_UPDATE_LOCK_DB_Y, 240);
 	 */
+
+	/* 2 pieces of memory required for up to 5120 displays, 4 for up to 8192,
+	 * however, for ODM combine we can simplify by always using 4.
+	 * To make sure there's no overlap, each instance "reserves" 2 memories and
+	 * they are uniquely combined here.
+	 */
+	memory_mask = 0x3 << (opp_id[0] * 2) | 0x3 << (opp_id[1] * 2);
+
 	if (REG(OPTC_MEMORY_CONFIG))
 		REG_SET(OPTC_MEMORY_CONFIG, 0,
-			OPTC_MEM_SEL, memory_mask << (optc->inst * 4));
+			OPTC_MEM_SEL, memory_mask);
 
 	if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
 		data_fmt = 1;
@@ -257,7 +269,6 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c
 
 	REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt);
 
-	ASSERT(opp_cnt == 2);
 	REG_SET_3(OPTC_DATA_SOURCE_SELECT, 0,
 			OPTC_NUM_OF_INPUT_SEGMENT, 1,
 			OPTC_SEG0_SRC_SEL, opp_id[0],
@@ -379,14 +390,8 @@ void optc2_setup_manual_trigger(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
-	REG_SET(OTG_MANUAL_FLOW_CONTROL, 0,
-			MANUAL_FLOW_CONTROL, 1);
-
-	REG_SET(OTG_GLOBAL_CONTROL2, 0,
-			MANUAL_FLOW_CONTROL_SEL, optc->inst);
-
 	REG_SET_8(OTG_TRIGA_CNTL, 0,
-			OTG_TRIGA_SOURCE_SELECT, 22,
+			OTG_TRIGA_SOURCE_SELECT, 21,
 			OTG_TRIGA_SOURCE_PIPE_SELECT, optc->inst,
 			OTG_TRIGA_RISING_EDGE_DETECT_CNTL, 1,
 			OTG_TRIGA_FALLING_EDGE_DETECT_CNTL, 0,
@@ -448,9 +453,7 @@ static struct timing_generator_funcs dcn20_tg_funcs = {
 		.setup_global_swap_lock = NULL,
 		.get_crc = optc1_get_crc,
 		.configure_crc = optc1_configure_crc,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.set_dsc_config = optc2_set_dsc_config,
-#endif
 		.set_dwb_source = optc2_set_dwb_source,
 		.set_odm_bypass = optc2_set_odm_bypass,
 		.set_odm_combine = optc2_set_odm_combine,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h
index 32a58431fd09..239cc40ae474 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h
@@ -86,12 +86,10 @@ void optc2_set_gsl_source_select(struct timing_generator *optc,
 		int group_idx,
 		uint32_t gsl_ready_signal);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 void optc2_set_dsc_config(struct timing_generator *optc,
 					enum optc_dsc_mode dsc_mode,
 					uint32_t dsc_bytes_per_pixel,
 					uint32_t dsc_slice_width);
-#endif
 
 void optc2_set_odm_bypass(struct timing_generator *optc,
 		const struct dc_crtc_timing *dc_crtc_timing);
@@ -108,6 +106,7 @@ void optc2_triplebuffer_lock(struct timing_generator *optc);
 void optc2_triplebuffer_unlock(struct timing_generator *optc);
 void optc2_lock_doublebuffer_disable(struct timing_generator *optc);
 void optc2_lock_doublebuffer_enable(struct timing_generator *optc);
+void optc2_setup_manual_trigger(struct timing_generator *optc);
 void optc2_program_manual_trigger(struct timing_generator *optc);
-
+bool optc2_is_two_pixels_per_containter(const struct dc_crtc_timing *timing);
 #endif /* __DC_OPTC_DCN20_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 23ff2f1c75b5..85f90f3e24cb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -1,5 +1,6 @@
 /*
 * Copyright 2016 Advanced Micro Devices, Inc.
+ * Copyright 2019 Raptor Engineering, LLC
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -28,6 +29,8 @@
 #include "dm_services.h"
 #include "dc.h"
 
+#include "dcn20_init.h"
+
 #include "resource.h"
 #include "include/irq_service_interface.h"
 #include "dcn20/dcn20_resource.h"
@@ -45,9 +48,7 @@
 #include "dcn10/dcn10_resource.h"
 #include "dcn20_opp.h"
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dcn20_dsc.h"
-#endif
 
 #include "dcn20_link_encoder.h"
 #include "dcn20_stream_encoder.h"
@@ -59,11 +60,14 @@
 #include "dml/display_mode_vba.h"
 #include "dcn20_dccg.h"
 #include "dcn20_vmid.h"
+#include "dc_link_ddc.h"
 
 #include "navi10_ip_offset.h"
 
 #include "dcn/dcn_2_0_0_offset.h"
 #include "dcn/dcn_2_0_0_sh_mask.h"
+#include "dpcs/dpcs_2_0_0_offset.h"
+#include "dpcs/dpcs_2_0_0_sh_mask.h"
 
 #include "nbio/nbio_2_3_offset.h"
 
@@ -82,8 +86,6 @@
 
 #include "amdgpu_socbb.h"
 
-/* NV12 SOC BB is currently in FW, mark SW bounding box invalid. */
-#define SOC_BOUNDING_BOX_VALID false
 #define DC_LOGGER_INIT(logger)
 
 struct _vcs_dpi_ip_params_st dcn2_0_ip = {
@@ -94,11 +96,7 @@ struct _vcs_dpi_ip_params_st dcn2_0_ip = {
 	.hostvm_max_page_table_levels = 4,
 	.hostvm_cached_page_table_levels = 0,
 	.pte_group_size_bytes = 2048,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.num_dsc = 6,
-#else
-	.num_dsc = 0,
-#endif
 	.rob_buffer_size_kbytes = 168,
 	.det_buffer_size_kbytes = 164,
 	.dpte_buffer_size_in_pte_reqs_luma = 84,
@@ -553,6 +551,7 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = {
 [id] = {\
 	LE_DCN10_REG_LIST(id), \
 	UNIPHY_DCN2_REG_LIST(phyid), \
+	DPCS_DCN2_REG_LIST(id), \
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \
 }
 
@@ -566,11 +565,13 @@ static const struct dcn10_link_enc_registers link_enc_regs[] = {
 };
 
 static const struct dcn10_link_enc_shift le_shift = {
-	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT)
+	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT),\
+	DPCS_DCN2_MASK_SH_LIST(__SHIFT)
 };
 
 static const struct dcn10_link_enc_mask le_mask = {
-	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK)
+	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK),\
+	DPCS_DCN2_MASK_SH_LIST(_MASK)
 };
 
 #define ipp_regs(id)\
@@ -637,6 +638,7 @@ static const struct dce110_aux_registers aux_engine_regs[] = {
 #define tf_regs(id)\
 [id] = {\
 	TF_REG_LIST_DCN20(id),\
+	TF_REG_LIST_DCN20_COMMON_APPEND(id),\
 }
 
 static const struct dcn2_dpp_registers tf_regs[] = {
@@ -650,12 +652,12 @@ static const struct dcn2_dpp_registers tf_regs[] = {
 
 static const struct dcn2_dpp_shift tf_shift = {
 		TF_REG_LIST_SH_MASK_DCN20(__SHIFT),
-		TF_DEBUG_REG_LIST_SH_DCN10
+		TF_DEBUG_REG_LIST_SH_DCN20
 };
 
 static const struct dcn2_dpp_mask tf_mask = {
 		TF_REG_LIST_SH_MASK_DCN20(_MASK),
-		TF_DEBUG_REG_LIST_MASK_DCN10
+		TF_DEBUG_REG_LIST_MASK_DCN20
 };
 
 #define dwbc_regs_dcn2(id)\
@@ -705,14 +707,17 @@ static const struct dcn20_mpc_registers mpc_regs = {
 		MPC_OUT_MUX_REG_LIST_DCN2_0(3),
 		MPC_OUT_MUX_REG_LIST_DCN2_0(4),
 		MPC_OUT_MUX_REG_LIST_DCN2_0(5),
+		MPC_DBG_REG_LIST_DCN2_0()
 };
 
 static const struct dcn20_mpc_shift mpc_shift = {
-	MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT)
+	MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT),
+	MPC_DEBUG_REG_LIST_SH_DCN20
 };
 
 static const struct dcn20_mpc_mask mpc_mask = {
-	MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK)
+	MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK),
+	MPC_DEBUG_REG_LIST_MASK_DCN20
 };
 
 #define tg_regs(id)\
@@ -838,7 +843,6 @@ static int map_transmitter_id_to_phy_instance(
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define dsc_regsDCN20(id)\
 [id] = {\
 	DSC_REG_LIST_DCN20(id)\
@@ -860,7 +864,6 @@ static const struct dcn20_dsc_shift dsc_shift = {
 static const struct dcn20_dsc_mask dsc_mask = {
 	DSC_REG_LIST_SH_MASK_DCN20(_MASK)
 };
-#endif
 
 static const struct dccg_registers dccg_regs = {
 		DCCG_REG_LIST_DCN2()
@@ -884,9 +887,7 @@ static const struct resource_caps res_cap_nv10 = {
 		.num_dwb = 1,
 		.num_ddc = 6,
 		.num_vmid = 16,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 6,
-#endif
 };
 
 static const struct dc_plane_cap plane_cap = {
@@ -923,9 +924,7 @@ static const struct resource_caps res_cap_nv14 = {
 		.num_dwb = 1,
 		.num_ddc = 5,
 		.num_vmid = 16,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 5,
-#endif
 };
 
 static const struct dc_debug_options debug_defaults_drv = {
@@ -1284,7 +1283,6 @@ void dcn20_clock_source_destroy(struct clock_source **clk_src)
 	*clk_src = NULL;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 
 struct display_stream_compressor *dcn20_dsc_create(
 	struct dc_context *ctx, uint32_t inst)
@@ -1307,9 +1305,8 @@ void dcn20_dsc_destroy(struct display_stream_compressor **dsc)
 	*dsc = NULL;
 }
 
-#endif
 
-static void destruct(struct dcn20_resource_pool *pool)
+static void dcn20_resource_destruct(struct dcn20_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -1320,12 +1317,10 @@ static void destruct(struct dcn20_resource_pool *pool)
 		}
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		if (pool->base.dscs[i] != NULL)
 			dcn20_dsc_destroy(&pool->base.dscs[i]);
 	}
-#endif
 
 	if (pool->base.mpc != NULL) {
 		kfree(TO_DCN20_MPC(pool->base.mpc));
@@ -1418,6 +1413,8 @@ static void destruct(struct dcn20_resource_pool *pool)
 	if (pool->base.pp_smu != NULL)
 		dcn20_pp_smu_destroy(&pool->base.pp_smu);
 
+	if (pool->base.oem_device != NULL)
+		dal_ddc_service_destroy(&pool->base.oem_device);
 }
 
 struct hubp *dcn20_hubp_create(
@@ -1468,7 +1465,7 @@ static void get_pixel_clock_parameters(
 
 	if (opp_cnt == 4)
 		pixel_clk_params->requested_pix_clk_100hz /= 4;
-	else if (optc1_is_two_pixels_per_containter(&stream->timing) || opp_cnt == 2)
+	else if (optc2_is_two_pixels_per_containter(&stream->timing) || opp_cnt == 2)
 		pixel_clk_params->requested_pix_clk_100hz /= 2;
 
 	if (stream->timing.timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING)
@@ -1534,7 +1531,6 @@ enum dc_status dcn20_build_mapped_resource(const struct dc *dc, struct dc_state
 	return status;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 
 static void acquire_dsc(struct resource_context *res_ctx,
 			const struct resource_pool *pool,
@@ -1575,11 +1571,9 @@ static void release_dsc(struct resource_context *res_ctx,
 		}
 }
 
-#endif
 
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-static enum dc_status add_dsc_to_stream_resource(struct dc *dc,
+enum dc_status dcn20_add_dsc_to_stream_resource(struct dc *dc,
 		struct dc_state *dc_ctx,
 		struct dc_stream_state *dc_stream)
 {
@@ -1594,11 +1588,13 @@ static enum dc_status add_dsc_to_stream_resource(struct dc *dc,
 		if (pipe_ctx->stream != dc_stream)
 			continue;
 
+		if (pipe_ctx->stream_res.dsc)
+			continue;
+
 		acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc, i);
 
 		/* The number of DSCs can be less than the number of pipes */
 		if (!pipe_ctx->stream_res.dsc) {
-			dm_output_to_console("No DSCs available\n");
 			result = DC_NO_DSC_RESOURCE;
 		}
 
@@ -1630,7 +1626,6 @@ static enum dc_status remove_dsc_from_stream_resource(struct dc *dc,
 	else
 		return DC_OK;
 }
-#endif
 
 
 enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream)
@@ -1642,11 +1637,9 @@ enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx,
 	if (result == DC_OK)
 		result = resource_map_phy_clock_resources(dc, new_ctx, dc_stream);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	/* Get a DSC if required and available */
 	if (result == DC_OK && dc_stream->timing.flags.DSC)
-		result = add_dsc_to_stream_resource(dc, new_ctx, dc_stream);
-#endif
+		result = dcn20_add_dsc_to_stream_resource(dc, new_ctx, dc_stream);
 
 	if (result == DC_OK)
 		result = dcn20_build_mapped_resource(dc, new_ctx, dc_stream);
@@ -1659,9 +1652,7 @@ enum dc_status dcn20_remove_stream_from_ctx(struct dc *dc, struct dc_state *new_
 {
 	enum dc_status result = DC_OK;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	result = remove_dsc_from_stream_resource(dc, new_ctx, dc_stream);
-#endif
 
 	return result;
 }
@@ -1744,9 +1735,7 @@ bool dcn20_split_stream_for_odm(
 	next_odm_pipe->plane_res.xfm = pool->transforms[next_odm_pipe->pipe_idx];
 	next_odm_pipe->plane_res.dpp = pool->dpps[next_odm_pipe->pipe_idx];
 	next_odm_pipe->plane_res.mpcc_inst = pool->dpps[next_odm_pipe->pipe_idx]->inst;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	next_odm_pipe->stream_res.dsc = NULL;
-#endif
 	if (prev_odm_pipe->next_odm_pipe && prev_odm_pipe->next_odm_pipe != next_odm_pipe) {
 		next_odm_pipe->next_odm_pipe = prev_odm_pipe->next_odm_pipe;
 		next_odm_pipe->next_odm_pipe->prev_odm_pipe = next_odm_pipe;
@@ -1792,14 +1781,12 @@ bool dcn20_split_stream_for_odm(
 		sd->recout.x = 0;
 	}
 	next_odm_pipe->stream_res.opp = pool->opps[next_odm_pipe->pipe_idx];
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (next_odm_pipe->stream->timing.flags.DSC == 1) {
 		acquire_dsc(res_ctx, pool, &next_odm_pipe->stream_res.dsc, next_odm_pipe->pipe_idx);
 		ASSERT(next_odm_pipe->stream_res.dsc);
 		if (next_odm_pipe->stream_res.dsc == NULL)
 			return false;
 	}
-#endif
 
 	return true;
 }
@@ -1823,9 +1810,7 @@ void dcn20_split_stream_for_mpc(
 	secondary_pipe->plane_res.xfm = pool->transforms[secondary_pipe->pipe_idx];
 	secondary_pipe->plane_res.dpp = pool->dpps[secondary_pipe->pipe_idx];
 	secondary_pipe->plane_res.mpcc_inst = pool->dpps[secondary_pipe->pipe_idx]->inst;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	secondary_pipe->stream_res.dsc = NULL;
-#endif
 	if (primary_pipe->bottom_pipe && primary_pipe->bottom_pipe != secondary_pipe) {
 		ASSERT(!secondary_pipe->bottom_pipe);
 		secondary_pipe->bottom_pipe = primary_pipe->bottom_pipe;
@@ -1876,11 +1861,28 @@ void dcn20_populate_dml_writeback_from_context(
 
 }
 
+static int get_num_odm_heads(struct pipe_ctx *pipe)
+{
+	int odm_head_count = 0;
+	struct pipe_ctx *next_pipe = pipe->next_odm_pipe;
+	while (next_pipe) {
+		odm_head_count++;
+		next_pipe = next_pipe->next_odm_pipe;
+	}
+	pipe = pipe->prev_odm_pipe;
+	while (pipe) {
+		odm_head_count++;
+		pipe = pipe->prev_odm_pipe;
+	}
+	return odm_head_count ? odm_head_count + 1 : 0;
+}
+
 int dcn20_populate_dml_pipes_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes)
+		struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes)
 {
 	int pipe_cnt, i;
 	bool synchronized_vblank = true;
+	struct resource_context *res_ctx = &context->res_ctx;
 
 	for (i = 0, pipe_cnt = -1; i < dc->res_pool->pipe_count; i++) {
 		if (!res_ctx->pipe_ctx[i].stream)
@@ -1900,25 +1902,30 @@ int dcn20_populate_dml_pipes_from_context(
 
 	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
 		struct dc_crtc_timing *timing = &res_ctx->pipe_ctx[i].stream->timing;
+		unsigned int v_total;
+		unsigned int front_porch;
 		int output_bpc;
 
 		if (!res_ctx->pipe_ctx[i].stream)
 			continue;
+
+		v_total = timing->v_total;
+		front_porch = timing->v_front_porch;
 		/* todo:
 		pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = 0;
 		pipes[pipe_cnt].pipe.src.dcc = 0;
 		pipes[pipe_cnt].pipe.src.vm = 0;*/
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+		pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0;
+
 		pipes[pipe_cnt].dout.dsc_enable = res_ctx->pipe_ctx[i].stream->timing.flags.DSC;
 		/* todo: rotation?*/
 		pipes[pipe_cnt].dout.dsc_slices = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.num_slices_h;
-#endif
 		if (res_ctx->pipe_ctx[i].stream->use_dynamic_meta) {
 			pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = true;
 			/* 1/2 vblank */
 			pipes[pipe_cnt].pipe.src.dynamic_metadata_lines_before_active =
-				(timing->v_total - timing->v_addressable
+				(v_total - timing->v_addressable
 					- timing->v_border_top - timing->v_border_bottom) / 2;
 			/* 36 bytes dp, 32 hdmi */
 			pipes[pipe_cnt].pipe.src.dynamic_metadata_xmit_bytes =
@@ -1932,13 +1939,13 @@ int dcn20_populate_dml_pipes_from_context(
 				- timing->h_addressable
 				- timing->h_border_left
 				- timing->h_border_right;
-		pipes[pipe_cnt].pipe.dest.vblank_start = timing->v_total - timing->v_front_porch;
+		pipes[pipe_cnt].pipe.dest.vblank_start = v_total - front_porch;
 		pipes[pipe_cnt].pipe.dest.vblank_end = pipes[pipe_cnt].pipe.dest.vblank_start
 				- timing->v_addressable
 				- timing->v_border_top
 				- timing->v_border_bottom;
 		pipes[pipe_cnt].pipe.dest.htotal = timing->h_total;
-		pipes[pipe_cnt].pipe.dest.vtotal = timing->v_total;
+		pipes[pipe_cnt].pipe.dest.vtotal = v_total;
 		pipes[pipe_cnt].pipe.dest.hactive = timing->h_addressable;
 		pipes[pipe_cnt].pipe.dest.vactive = timing->v_addressable;
 		pipes[pipe_cnt].pipe.dest.interlaced = timing->flags.INTERLACE;
@@ -1949,8 +1956,13 @@ int dcn20_populate_dml_pipes_from_context(
 		pipes[pipe_cnt].dout.dp_lanes = 4;
 		pipes[pipe_cnt].pipe.dest.vtotal_min = res_ctx->pipe_ctx[i].stream->adjust.v_total_min;
 		pipes[pipe_cnt].pipe.dest.vtotal_max = res_ctx->pipe_ctx[i].stream->adjust.v_total_max;
-		pipes[pipe_cnt].pipe.dest.odm_combine = res_ctx->pipe_ctx[i].prev_odm_pipe
-							|| res_ctx->pipe_ctx[i].next_odm_pipe;
+		switch (get_num_odm_heads(&res_ctx->pipe_ctx[i])) {
+		case 2:
+			pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_2to1;
+			break;
+		default:
+			pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_disabled;
+		}
 		pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx;
 		if (res_ctx->pipe_ctx[i].top_pipe && res_ctx->pipe_ctx[i].top_pipe->plane_state
 				== res_ctx->pipe_ctx[i].plane_state)
@@ -2001,14 +2013,12 @@ int dcn20_populate_dml_pipes_from_context(
 		case COLOR_DEPTH_161616:
 			output_bpc = 16;
 			break;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		case COLOR_DEPTH_999:
 			output_bpc = 9;
 			break;
 		case COLOR_DEPTH_111111:
 			output_bpc = 11;
 			break;
-#endif
 		default:
 			output_bpc = 8;
 			break;
@@ -2036,10 +2046,8 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].dout.output_bpp = output_bpc * 3;
 		}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		if (res_ctx->pipe_ctx[i].stream->timing.flags.DSC)
 			pipes[pipe_cnt].dout.output_bpp = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.bits_per_pixel / 16.0;
-#endif
 
 		/* todo: default max for now, until there is logic reflecting this in dc*/
 		pipes[pipe_cnt].dout.output_bpc = 12;
@@ -2063,6 +2071,10 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.src.viewport_height = timing->v_addressable;
 			if (pipes[pipe_cnt].pipe.src.viewport_height > 1080)
 				pipes[pipe_cnt].pipe.src.viewport_height = 1080;
+			pipes[pipe_cnt].pipe.src.surface_height_y = pipes[pipe_cnt].pipe.src.viewport_height;
+			pipes[pipe_cnt].pipe.src.surface_width_y = pipes[pipe_cnt].pipe.src.viewport_width;
+			pipes[pipe_cnt].pipe.src.surface_height_c = pipes[pipe_cnt].pipe.src.viewport_height;
+			pipes[pipe_cnt].pipe.src.surface_width_c = pipes[pipe_cnt].pipe.src.viewport_width;
 			pipes[pipe_cnt].pipe.src.data_pitch = ((pipes[pipe_cnt].pipe.src.viewport_width + 63) / 64) * 64; /* linear sw only */
 			pipes[pipe_cnt].pipe.src.source_format = dm_444_32;
 			pipes[pipe_cnt].pipe.dest.recout_width = pipes[pipe_cnt].pipe.src.viewport_width; /*vp_width/hratio*/
@@ -2077,8 +2089,8 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.scale_taps.vtaps = 1;
 			pipes[pipe_cnt].pipe.src.is_hsplit = 0;
 			pipes[pipe_cnt].pipe.dest.odm_combine = 0;
-			pipes[pipe_cnt].pipe.dest.vtotal_min = timing->v_total;
-			pipes[pipe_cnt].pipe.dest.vtotal_max = timing->v_total;
+			pipes[pipe_cnt].pipe.dest.vtotal_min = v_total;
+			pipes[pipe_cnt].pipe.dest.vtotal_max = v_total;
 		} else {
 			struct dc_plane_state *pln = res_ctx->pipe_ctx[i].plane_state;
 			struct scaler_data *scl = &res_ctx->pipe_ctx[i].plane_res.scl_data;
@@ -2096,6 +2108,10 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.src.viewport_width_c = scl->viewport_c.width;
 			pipes[pipe_cnt].pipe.src.viewport_height = scl->viewport.height;
 			pipes[pipe_cnt].pipe.src.viewport_height_c = scl->viewport_c.height;
+			pipes[pipe_cnt].pipe.src.surface_width_y = pln->plane_size.surface_size.width;
+			pipes[pipe_cnt].pipe.src.surface_height_y = pln->plane_size.surface_size.height;
+			pipes[pipe_cnt].pipe.src.surface_width_c = pln->plane_size.chroma_size.width;
+			pipes[pipe_cnt].pipe.src.surface_height_c = pln->plane_size.chroma_size.height;
 			if (pln->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) {
 				pipes[pipe_cnt].pipe.src.data_pitch = pln->plane_size.surface_pitch;
 				pipes[pipe_cnt].pipe.src.data_pitch_c = pln->plane_size.chroma_pitch;
@@ -2261,7 +2277,6 @@ void dcn20_set_mcif_arb_params(
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx)
 {
 	int i;
@@ -2295,7 +2310,6 @@ bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx)
 	}
 	return true;
 }
-#endif
 
 struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
 		struct resource_context *res_ctx,
@@ -2398,10 +2412,8 @@ void dcn20_merge_pipes_for_validate(
 			odm_pipe->bottom_pipe = NULL;
 			odm_pipe->prev_odm_pipe = NULL;
 			odm_pipe->next_odm_pipe = NULL;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 			if (odm_pipe->stream_res.dsc)
 				release_dsc(&context->res_ctx, dc->res_pool, &odm_pipe->stream_res.dsc);
-#endif
 			/* Clear plane_res and stream_res */
 			memset(&odm_pipe->plane_res, 0, sizeof(odm_pipe->plane_res));
 			memset(&odm_pipe->stream_res, 0, sizeof(odm_pipe->stream_res));
@@ -2513,7 +2525,7 @@ int dcn20_validate_apply_pipe_split_flags(
 			split[i] = true;
 		if (dc->debug.force_odm_combine & (1 << pipe->stream_res.tg->inst)) {
 			split[i] = true;
-			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx] = true;
+			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx] = dm_odm_combine_mode_2to1;
 		}
 		context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx] =
 			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx];
@@ -2544,7 +2556,7 @@ bool dcn20_fast_validate_bw(
 
 	dcn20_merge_pipes_for_validate(dc, context);
 
-	pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, &context->res_ctx, pipes);
+	pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes);
 
 	*pipe_cnt_out = pipe_cnt;
 
@@ -2621,14 +2633,12 @@ bool dcn20_fast_validate_bw(
 			ASSERT(0);
 		}
 	}
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	/* Actual dsc count per stream dsc validation*/
 	if (!dcn20_validate_dsc(dc, context)) {
 		context->bw_ctx.dml.vba.ValidationStatus[context->bw_ctx.dml.vba.soc.num_states] =
 				DML_FAIL_DSC_VALIDATION_FAILURE;
 		goto validate_fail;
 	}
-#endif
 
 	*vlevel_out = vlevel;
 
@@ -2692,10 +2702,10 @@ static void dcn20_calculate_wm(
 	if (pipe_cnt != pipe_idx) {
 		if (dc->res_pool->funcs->populate_dml_pipes)
 			pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc,
-				&context->res_ctx, pipes);
+				context, pipes);
 		else
 			pipe_cnt = dcn20_populate_dml_pipes_from_context(dc,
-				&context->res_ctx, pipes);
+				context, pipes);
 	}
 
 	*out_pipe_cnt = pipe_cnt;
@@ -2715,11 +2725,9 @@ static void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#endif
 
 	if (vlevel < 2) {
 		pipes[0].clks_cfg.voltage = 2;
@@ -2731,10 +2739,8 @@ static void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#endif
 
 	if (vlevel < 3) {
 		pipes[0].clks_cfg.voltage = 3;
@@ -2746,10 +2752,8 @@ static void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#endif
 
 	pipes[0].clks_cfg.voltage = vlevel;
 	pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].dcfclk_mhz;
@@ -2759,10 +2763,8 @@ static void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#endif
 }
 
 void dcn20_calculate_dlg_params(
@@ -2928,11 +2930,19 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 	bool voltage_supported = false;
 	bool full_pstate_supported = false;
 	bool dummy_pstate_supported = false;
-	double p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
+	double p_state_latency_us;
 
-	if (fast_validate)
-		return dcn20_validate_bandwidth_internal(dc, context, true);
+	DC_FP_START();
+	p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
+	context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support =
+		dc->debug.disable_dram_clock_change_vactive_support;
 
+	if (fast_validate) {
+		voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true);
+
+		DC_FP_END();
+		return voltage_supported;
+	}
 
 	// Best case, we support full UCLK switch latency
 	voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
@@ -2940,7 +2950,7 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 
 	if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 ||
 		(voltage_supported && full_pstate_supported)) {
-		context->bw_ctx.bw.dcn.clk.p_state_change_support = true;
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported;
 		goto restore_dml_state;
 	}
 
@@ -2961,6 +2971,7 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 restore_dml_state:
 	context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
 
+	DC_FP_END();
 	return voltage_supported;
 }
 
@@ -3005,7 +3016,7 @@ static void dcn20_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dcn20_resource_pool *dcn20_pool = TO_DCN20_RES_POOL(*pool);
 
-	destruct(dcn20_pool);
+	dcn20_resource_destruct(dcn20_pool);
 	kfree(dcn20_pool);
 	*pool = NULL;
 }
@@ -3252,7 +3263,6 @@ void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 
 void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb)
 {
-	kernel_fpu_begin();
 	if ((int)(bb->sr_exit_time_us * 1000) != dc->bb_overrides.sr_exit_time_ns
 			&& dc->bb_overrides.sr_exit_time_ns) {
 		bb->sr_exit_time_us = dc->bb_overrides.sr_exit_time_ns / 1000.0;
@@ -3276,7 +3286,6 @@ void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st
 		bb->dram_clock_change_latency_us =
 				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
 	}
-	kernel_fpu_end();
 }
 
 static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb(
@@ -3318,12 +3327,13 @@ static bool init_soc_bounding_box(struct dc *dc,
 
 	DC_LOGGER_INIT(dc->ctx->logger);
 
-	if (!bb && !SOC_BOUNDING_BOX_VALID) {
+	/* TODO: upstream NV12 bounding box when its launched */
+	if (!bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
 		DC_LOG_ERROR("%s: not valid soc bounding box/n", __func__);
 		return false;
 	}
 
-	if (bb && !SOC_BOUNDING_BOX_VALID) {
+	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
 		int i;
 
 		dcn2_0_nv12_soc.sr_exit_time_us =
@@ -3465,7 +3475,7 @@ static bool init_soc_bounding_box(struct dc *dc,
 	return true;
 }
 
-static bool construct(
+static bool dcn20_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dcn20_resource_pool *pool)
@@ -3473,6 +3483,7 @@ static bool construct(
 	int i;
 	struct dc_context *ctx = dc->ctx;
 	struct irq_service_init_data init_data;
+	struct ddc_service_init_data ddc_init_data;
 	struct _vcs_dpi_soc_bounding_box_st *loaded_bb =
 			get_asic_rev_soc_bb(ctx->asic_id.hw_internal_rev);
 	struct _vcs_dpi_ip_params_st *loaded_ip =
@@ -3480,6 +3491,8 @@ static bool construct(
 	enum dml_project dml_project_version =
 			get_dml_project_version(ctx->asic_id.hw_internal_rev);
 
+	DC_FP_START();
+
 	ctx->dc_bios->regs = &bios_regs;
 	pool->base.funcs = &dcn20_res_pool_funcs;
 
@@ -3732,7 +3745,6 @@ static bool construct(
 		goto create_fail;
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		pool->base.dscs[i] = dcn20_dsc_create(ctx, i);
 		if (pool->base.dscs[i] == NULL) {
@@ -3741,7 +3753,6 @@ static bool construct(
 			goto create_fail;
 		}
 	}
-#endif
 
 	if (!dcn20_dwbc_create(ctx, &pool->base)) {
 		BREAK_TO_DEBUGGER();
@@ -3768,11 +3779,24 @@ static bool construct(
 
 	dc->cap_funcs = cap_funcs;
 
+	if (dc->ctx->dc_bios->fw_info.oem_i2c_present) {
+		ddc_init_data.ctx = dc->ctx;
+		ddc_init_data.link = NULL;
+		ddc_init_data.id.id = dc->ctx->dc_bios->fw_info.oem_i2c_obj_id;
+		ddc_init_data.id.enum_id = 0;
+		ddc_init_data.id.type = OBJECT_TYPE_GENERIC;
+		pool->base.oem_device = dal_ddc_service_create(&ddc_init_data);
+	} else {
+		pool->base.oem_device = NULL;
+	}
+
+	DC_FP_END();
 	return true;
 
 create_fail:
 
-	destruct(pool);
+	DC_FP_END();
+	dcn20_resource_destruct(pool);
 
 	return false;
 }
@@ -3787,7 +3811,7 @@ struct resource_pool *dcn20_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(init_data->num_virtual_links, dc, pool))
+	if (dcn20_resource_construct(init_data->num_virtual_links, dc, pool))
 		return &pool->base;
 
 	BREAK_TO_DEBUGGER();
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
index fef473d68a4a..f5893840b79b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
@@ -50,7 +50,7 @@ unsigned int dcn20_calc_max_scaled_time(
 		enum mmhubbub_wbif_mode mode,
 		unsigned int urgent_watermark);
 int dcn20_populate_dml_pipes_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes);
+		struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes);
 struct pipe_ctx *dcn20_acquire_idle_pipe_for_layer(
 		struct dc_state *state,
 		const struct resource_pool *pool,
@@ -127,9 +127,7 @@ int dcn20_validate_apply_pipe_split_flags(
 		struct dc_state *context,
 		int vlevel,
 		bool *split);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx);
-#endif
 void dcn20_split_stream_for_mpc(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
@@ -159,6 +157,7 @@ void dcn20_calculate_dlg_params(
 
 enum dc_status dcn20_build_mapped_resource(const struct dc *dc, struct dc_state *context, struct dc_stream_state *stream);
 enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream);
+enum dc_status dcn20_add_dsc_to_stream_resource(struct dc *dc, struct dc_state *dc_ctx, struct dc_stream_state *dc_stream);
 enum dc_status dcn20_remove_stream_from_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream);
 enum dc_status dcn20_get_default_swizzle_mode(struct dc_plane_state *plane_state);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
index fcb3877b4fcb..9b70a1e7b962 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
@@ -205,7 +205,6 @@ static void enc2_stream_encoder_stop_hdmi_info_packets(
 		HDMI_GENERIC7_LINE, 0);
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 
 /* Update GSP7 SDP 128 byte long */
 static void enc2_update_gsp7_128_info_packet(
@@ -360,7 +359,6 @@ static void enc2_read_state(struct stream_encoder *enc, struct enc_state *s)
 		REG_GET(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, &s->sec_stream_enable);
 	}
 }
-#endif
 
 /* Set Dynamic Metadata-configuration.
  *   enable_dme:         TRUE: enables Dynamic Metadata Enfine, FALSE: disables DME
@@ -440,10 +438,8 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing)
 {
 	bool two_pix = timing->pixel_encoding == PIXEL_ENCODING_YCBCR420;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	two_pix = two_pix || (timing->flags.DSC && timing->pixel_encoding == PIXEL_ENCODING_YCBCR422
 			&& !timing->dsc_cfg.ycbcr422_simple);
-#endif
 	return two_pix;
 }
 
@@ -541,11 +537,16 @@ void enc2_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting)
 {
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
-	enc1_stream_encoder_dp_set_stream_attribute(enc, crtc_timing, output_color_space, enable_sdp_splitting);
+	enc1_stream_encoder_dp_set_stream_attribute(enc,
+			crtc_timing,
+			output_color_space,
+			use_vsc_sdp_for_colorimetry,
+			enable_sdp_splitting);
 
 	REG_UPDATE(DP_SEC_FRAMING4,
 		DP_SST_SDP_SPLITTING, enable_sdp_splitting);
@@ -568,6 +569,8 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = {
 		enc2_stream_encoder_stop_hdmi_info_packets,
 	.update_dp_info_packets =
 		enc2_stream_encoder_update_dp_info_packets,
+	.send_immediate_sdp_message =
+		enc1_stream_encoder_send_immediate_sdp_message,
 	.stop_dp_info_packets =
 		enc1_stream_encoder_stop_dp_info_packets,
 	.dp_blank =
@@ -590,11 +593,9 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = {
 	.dp_get_pixel_format =
 		enc1_stream_encoder_dp_get_pixel_format,
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.enc_read_state = enc2_read_state,
 	.dp_set_dsc_config = enc2_dp_set_dsc_config,
 	.dp_set_dsc_pps_info_packet = enc2_dp_set_dsc_pps_info_packet,
-#endif
 	.set_dynamic_metadata = enc2_set_dynamic_metadata,
 	.hdmi_reset_stream_attribute = enc1_reset_hdmi_stream_attribute,
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h
index 3f94a9f13c4a..d2a805bd4573 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h
@@ -98,6 +98,7 @@ void enc2_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting);
 
 void enc2_stream_encoder_dp_unblank(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 5b8c17564bc1..07684d3e375a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -2,9 +2,16 @@
 #
 # Makefile for DCN21.
 
-DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o dcn21_hwseq.o dcn21_link_encoder.o
+DCN21 = dcn21_init.o dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o \
+	 dcn21_hwseq.o dcn21_link_encoder.o
 
+ifdef CONFIG_X86
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -12,6 +19,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -20,6 +28,7 @@ CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4
 else
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
 endif
+endif
 
 AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
index 2f5a5867e674..da63fc53cc4a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
@@ -29,6 +29,10 @@
 #include "dm_services.h"
 #include "reg_helper.h"
 
+#include "dc_dmub_srv.h"
+
+#define DC_LOGGER_INIT(logger)
+
 #define REG(reg)\
 	hubp21->hubp_regs->reg
 
@@ -164,6 +168,158 @@ static void hubp21_setup(
 
 }
 
+void hubp21_set_viewport(
+	struct hubp *hubp,
+	const struct rect *viewport,
+	const struct rect *viewport_c)
+{
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+
+	REG_SET_2(DCSURF_PRI_VIEWPORT_DIMENSION, 0,
+		  PRI_VIEWPORT_WIDTH, viewport->width,
+		  PRI_VIEWPORT_HEIGHT, viewport->height);
+
+	REG_SET_2(DCSURF_PRI_VIEWPORT_START, 0,
+		  PRI_VIEWPORT_X_START, viewport->x,
+		  PRI_VIEWPORT_Y_START, viewport->y);
+
+	/*for stereo*/
+	REG_SET_2(DCSURF_SEC_VIEWPORT_DIMENSION, 0,
+		  SEC_VIEWPORT_WIDTH, viewport->width,
+		  SEC_VIEWPORT_HEIGHT, viewport->height);
+
+	REG_SET_2(DCSURF_SEC_VIEWPORT_START, 0,
+		  SEC_VIEWPORT_X_START, viewport->x,
+		  SEC_VIEWPORT_Y_START, viewport->y);
+
+	/* DC supports NV12 only at the moment */
+	REG_SET_2(DCSURF_PRI_VIEWPORT_DIMENSION_C, 0,
+		  PRI_VIEWPORT_WIDTH_C, viewport_c->width,
+		  PRI_VIEWPORT_HEIGHT_C, viewport_c->height);
+
+	REG_SET_2(DCSURF_PRI_VIEWPORT_START_C, 0,
+		  PRI_VIEWPORT_X_START_C, viewport_c->x,
+		  PRI_VIEWPORT_Y_START_C, viewport_c->y);
+
+	REG_SET_2(DCSURF_SEC_VIEWPORT_DIMENSION_C, 0,
+		  SEC_VIEWPORT_WIDTH_C, viewport_c->width,
+		  SEC_VIEWPORT_HEIGHT_C, viewport_c->height);
+
+	REG_SET_2(DCSURF_SEC_VIEWPORT_START_C, 0,
+		  SEC_VIEWPORT_X_START_C, viewport_c->x,
+		  SEC_VIEWPORT_Y_START_C, viewport_c->y);
+}
+
+static void hubp21_apply_PLAT_54186_wa(
+		struct hubp *hubp,
+		const struct dc_plane_address *address)
+{
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+	struct dc_debug_options *debug = &hubp->ctx->dc->debug;
+	unsigned int chroma_bpe = 2;
+	unsigned int luma_addr_high_part = 0;
+	unsigned int row_height = 0;
+	unsigned int chroma_pitch = 0;
+	unsigned int viewport_c_height = 0;
+	unsigned int viewport_c_width = 0;
+	unsigned int patched_viewport_height = 0;
+	unsigned int patched_viewport_width = 0;
+	unsigned int rotation_angle = 0;
+	unsigned int pix_format = 0;
+	unsigned int h_mirror_en = 0;
+	unsigned int tile_blk_size = 64 * 1024; /* 64KB for 64KB SW, 4KB for 4KB SW */
+
+
+	if (!debug->nv12_iflip_vm_wa)
+		return;
+
+	REG_GET(DCHUBP_REQ_SIZE_CONFIG_C,
+		PTE_ROW_HEIGHT_LINEAR_C, &row_height);
+
+	REG_GET_2(DCSURF_PRI_VIEWPORT_DIMENSION_C,
+			PRI_VIEWPORT_WIDTH_C, &viewport_c_width,
+			PRI_VIEWPORT_HEIGHT_C, &viewport_c_height);
+
+	REG_GET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C,
+			PRIMARY_SURFACE_ADDRESS_HIGH_C, &luma_addr_high_part);
+
+	REG_GET(DCSURF_SURFACE_PITCH_C,
+			PITCH_C, &chroma_pitch);
+
+	chroma_pitch += 1;
+
+	REG_GET_3(DCSURF_SURFACE_CONFIG,
+			SURFACE_PIXEL_FORMAT, &pix_format,
+			ROTATION_ANGLE, &rotation_angle,
+			H_MIRROR_EN, &h_mirror_en);
+
+	/* reset persistent cached data */
+	hubp21->PLAT_54186_wa_chroma_addr_offset = 0;
+	/* apply wa only for NV12 surface with scatter gather enabled with viewport > 512 along
+	 * the vertical direction*/
+	if (address->type != PLN_ADDR_TYPE_VIDEO_PROGRESSIVE ||
+			address->video_progressive.luma_addr.high_part == 0xf4)
+		return;
+
+	if ((rotation_angle == 0 || rotation_angle == 180)
+			&& viewport_c_height <= 512)
+		return;
+
+	if ((rotation_angle == 90 || rotation_angle == 270)
+				&& viewport_c_width <= 512)
+		return;
+
+	switch (rotation_angle) {
+	case 0: /* 0 degree rotation */
+		row_height = 128;
+		patched_viewport_height = (viewport_c_height / row_height + 1) * row_height + 1;
+		patched_viewport_width = viewport_c_width;
+		hubp21->PLAT_54186_wa_chroma_addr_offset = 0;
+		break;
+	case 2: /* 180 degree rotation */
+		row_height = 128;
+		patched_viewport_height = viewport_c_height + row_height;
+		patched_viewport_width = viewport_c_width;
+		hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - chroma_pitch * row_height * chroma_bpe;
+		break;
+	case 1: /* 90 degree rotation */
+		row_height = 256;
+		if (h_mirror_en) {
+			patched_viewport_height = viewport_c_height;
+			patched_viewport_width = viewport_c_width + row_height;
+			hubp21->PLAT_54186_wa_chroma_addr_offset = 0;
+		} else {
+			patched_viewport_height = viewport_c_height;
+			patched_viewport_width = viewport_c_width + row_height;
+			hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - tile_blk_size;
+		}
+		break;
+	case 3:	/* 270 degree rotation */
+		row_height = 256;
+		if (h_mirror_en) {
+			patched_viewport_height = viewport_c_height;
+			patched_viewport_width = viewport_c_width + row_height;
+			hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - tile_blk_size;
+		} else {
+			patched_viewport_height = viewport_c_height;
+			patched_viewport_width = viewport_c_width + row_height;
+			hubp21->PLAT_54186_wa_chroma_addr_offset = 0;
+		}
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+
+	/* catch cases where viewport keep growing */
+	ASSERT(patched_viewport_height && patched_viewport_height < 5000);
+	ASSERT(patched_viewport_width && patched_viewport_width < 5000);
+
+	REG_UPDATE_2(DCSURF_PRI_VIEWPORT_DIMENSION_C,
+			PRI_VIEWPORT_WIDTH_C, patched_viewport_width,
+			PRI_VIEWPORT_HEIGHT_C, patched_viewport_height);
+}
+
 void hubp21_set_vm_system_aperture_settings(struct hubp *hubp,
 		struct vm_system_aperture_param *apt)
 {
@@ -191,6 +347,562 @@ void hubp21_set_vm_system_aperture_settings(struct hubp *hubp,
 			SYSTEM_ACCESS_MODE, 0x3);
 }
 
+void hubp21_validate_dml_output(struct hubp *hubp,
+		struct dc_context *ctx,
+		struct _vcs_dpi_display_rq_regs_st *dml_rq_regs,
+		struct _vcs_dpi_display_dlg_regs_st *dml_dlg_attr,
+		struct _vcs_dpi_display_ttu_regs_st *dml_ttu_attr)
+{
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+	struct _vcs_dpi_display_rq_regs_st rq_regs = {0};
+	struct _vcs_dpi_display_dlg_regs_st dlg_attr = {0};
+	struct _vcs_dpi_display_ttu_regs_st ttu_attr = {0};
+	DC_LOGGER_INIT(ctx->logger);
+	DC_LOG_DEBUG("DML Validation | Running Validation");
+
+	/* Requester - Per hubp */
+	REG_GET(HUBPRET_CONTROL,
+		DET_BUF_PLANE1_BASE_ADDRESS, &rq_regs.plane1_base_address);
+	REG_GET_4(DCN_EXPANSION_MODE,
+		DRQ_EXPANSION_MODE, &rq_regs.drq_expansion_mode,
+		PRQ_EXPANSION_MODE, &rq_regs.prq_expansion_mode,
+		MRQ_EXPANSION_MODE, &rq_regs.mrq_expansion_mode,
+		CRQ_EXPANSION_MODE, &rq_regs.crq_expansion_mode);
+	REG_GET_8(DCHUBP_REQ_SIZE_CONFIG,
+		CHUNK_SIZE, &rq_regs.rq_regs_l.chunk_size,
+		MIN_CHUNK_SIZE, &rq_regs.rq_regs_l.min_chunk_size,
+		META_CHUNK_SIZE, &rq_regs.rq_regs_l.meta_chunk_size,
+		MIN_META_CHUNK_SIZE, &rq_regs.rq_regs_l.min_meta_chunk_size,
+		DPTE_GROUP_SIZE, &rq_regs.rq_regs_l.dpte_group_size,
+		VM_GROUP_SIZE, &rq_regs.rq_regs_l.mpte_group_size,
+		SWATH_HEIGHT, &rq_regs.rq_regs_l.swath_height,
+		PTE_ROW_HEIGHT_LINEAR, &rq_regs.rq_regs_l.pte_row_height_linear);
+	REG_GET_7(DCHUBP_REQ_SIZE_CONFIG_C,
+		CHUNK_SIZE_C, &rq_regs.rq_regs_c.chunk_size,
+		MIN_CHUNK_SIZE_C, &rq_regs.rq_regs_c.min_chunk_size,
+		META_CHUNK_SIZE_C, &rq_regs.rq_regs_c.meta_chunk_size,
+		MIN_META_CHUNK_SIZE_C, &rq_regs.rq_regs_c.min_meta_chunk_size,
+		DPTE_GROUP_SIZE_C, &rq_regs.rq_regs_c.dpte_group_size,
+		SWATH_HEIGHT_C, &rq_regs.rq_regs_c.swath_height,
+		PTE_ROW_HEIGHT_LINEAR_C, &rq_regs.rq_regs_c.pte_row_height_linear);
+
+	if (rq_regs.plane1_base_address != dml_rq_regs->plane1_base_address)
+		DC_LOG_DEBUG("DML Validation | HUBPRET_CONTROL:DET_BUF_PLANE1_BASE_ADDRESS - Expected: %u  Actual: %u\n",
+				dml_rq_regs->plane1_base_address, rq_regs.plane1_base_address);
+	if (rq_regs.drq_expansion_mode != dml_rq_regs->drq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:DRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->drq_expansion_mode, rq_regs.drq_expansion_mode);
+	if (rq_regs.prq_expansion_mode != dml_rq_regs->prq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:MRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->prq_expansion_mode, rq_regs.prq_expansion_mode);
+	if (rq_regs.mrq_expansion_mode != dml_rq_regs->mrq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:DET_BUF_PLANE1_BASE_ADDRESS - Expected: %u  Actual: %u\n",
+				dml_rq_regs->mrq_expansion_mode, rq_regs.mrq_expansion_mode);
+	if (rq_regs.crq_expansion_mode != dml_rq_regs->crq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:CRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->crq_expansion_mode, rq_regs.crq_expansion_mode);
+
+	if (rq_regs.rq_regs_l.chunk_size != dml_rq_regs->rq_regs_l.chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.chunk_size, rq_regs.rq_regs_l.chunk_size);
+	if (rq_regs.rq_regs_l.min_chunk_size != dml_rq_regs->rq_regs_l.min_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MIN_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.min_chunk_size, rq_regs.rq_regs_l.min_chunk_size);
+	if (rq_regs.rq_regs_l.meta_chunk_size != dml_rq_regs->rq_regs_l.meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:META_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.meta_chunk_size, rq_regs.rq_regs_l.meta_chunk_size);
+	if (rq_regs.rq_regs_l.min_meta_chunk_size != dml_rq_regs->rq_regs_l.min_meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MIN_META_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.min_meta_chunk_size, rq_regs.rq_regs_l.min_meta_chunk_size);
+	if (rq_regs.rq_regs_l.dpte_group_size != dml_rq_regs->rq_regs_l.dpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:DPTE_GROUP_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.dpte_group_size, rq_regs.rq_regs_l.dpte_group_size);
+	if (rq_regs.rq_regs_l.mpte_group_size != dml_rq_regs->rq_regs_l.mpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:VM_GROUP_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.mpte_group_size, rq_regs.rq_regs_l.mpte_group_size);
+	if (rq_regs.rq_regs_l.swath_height != dml_rq_regs->rq_regs_l.swath_height)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:SWATH_HEIGHT - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.swath_height, rq_regs.rq_regs_l.swath_height);
+	if (rq_regs.rq_regs_l.pte_row_height_linear != dml_rq_regs->rq_regs_l.pte_row_height_linear)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:PTE_ROW_HEIGHT_LINEAR - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.pte_row_height_linear, rq_regs.rq_regs_l.pte_row_height_linear);
+
+	if (rq_regs.rq_regs_c.chunk_size != dml_rq_regs->rq_regs_c.chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.chunk_size, rq_regs.rq_regs_c.chunk_size);
+	if (rq_regs.rq_regs_c.min_chunk_size != dml_rq_regs->rq_regs_c.min_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MIN_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.min_chunk_size, rq_regs.rq_regs_c.min_chunk_size);
+	if (rq_regs.rq_regs_c.meta_chunk_size != dml_rq_regs->rq_regs_c.meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:META_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.meta_chunk_size, rq_regs.rq_regs_c.meta_chunk_size);
+	if (rq_regs.rq_regs_c.min_meta_chunk_size != dml_rq_regs->rq_regs_c.min_meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MIN_META_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.min_meta_chunk_size, rq_regs.rq_regs_c.min_meta_chunk_size);
+	if (rq_regs.rq_regs_c.dpte_group_size != dml_rq_regs->rq_regs_c.dpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:DPTE_GROUP_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.dpte_group_size, rq_regs.rq_regs_c.dpte_group_size);
+	if (rq_regs.rq_regs_c.swath_height != dml_rq_regs->rq_regs_c.swath_height)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:SWATH_HEIGHT_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.swath_height, rq_regs.rq_regs_c.swath_height);
+	if (rq_regs.rq_regs_c.pte_row_height_linear != dml_rq_regs->rq_regs_c.pte_row_height_linear)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:PTE_ROW_HEIGHT_LINEAR_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.pte_row_height_linear, rq_regs.rq_regs_c.pte_row_height_linear);
+
+
+	/* DLG - Per hubp */
+	REG_GET_2(BLANK_OFFSET_0,
+		REFCYC_H_BLANK_END, &dlg_attr.refcyc_h_blank_end,
+		DLG_V_BLANK_END, &dlg_attr.dlg_vblank_end);
+	REG_GET(BLANK_OFFSET_1,
+		MIN_DST_Y_NEXT_START, &dlg_attr.min_dst_y_next_start);
+	REG_GET(DST_DIMENSIONS,
+		REFCYC_PER_HTOTAL, &dlg_attr.refcyc_per_htotal);
+	REG_GET_2(DST_AFTER_SCALER,
+		REFCYC_X_AFTER_SCALER, &dlg_attr.refcyc_x_after_scaler,
+		DST_Y_AFTER_SCALER, &dlg_attr.dst_y_after_scaler);
+	REG_GET(REF_FREQ_TO_PIX_FREQ,
+		REF_FREQ_TO_PIX_FREQ, &dlg_attr.ref_freq_to_pix_freq);
+
+	if (dlg_attr.refcyc_h_blank_end != dml_dlg_attr->refcyc_h_blank_end)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_0:REFCYC_H_BLANK_END - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_h_blank_end, dlg_attr.refcyc_h_blank_end);
+	if (dlg_attr.dlg_vblank_end != dml_dlg_attr->dlg_vblank_end)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_0:DLG_V_BLANK_END - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dlg_vblank_end, dlg_attr.dlg_vblank_end);
+	if (dlg_attr.min_dst_y_next_start != dml_dlg_attr->min_dst_y_next_start)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_1:MIN_DST_Y_NEXT_START - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->min_dst_y_next_start, dlg_attr.min_dst_y_next_start);
+	if (dlg_attr.refcyc_per_htotal != dml_dlg_attr->refcyc_per_htotal)
+		DC_LOG_DEBUG("DML Validation | DST_DIMENSIONS:REFCYC_PER_HTOTAL - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_htotal, dlg_attr.refcyc_per_htotal);
+	if (dlg_attr.refcyc_x_after_scaler != dml_dlg_attr->refcyc_x_after_scaler)
+		DC_LOG_DEBUG("DML Validation | DST_AFTER_SCALER:REFCYC_X_AFTER_SCALER - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_x_after_scaler, dlg_attr.refcyc_x_after_scaler);
+	if (dlg_attr.dst_y_after_scaler != dml_dlg_attr->dst_y_after_scaler)
+		DC_LOG_DEBUG("DML Validation | DST_AFTER_SCALER:DST_Y_AFTER_SCALER - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_after_scaler, dlg_attr.dst_y_after_scaler);
+	if (dlg_attr.ref_freq_to_pix_freq != dml_dlg_attr->ref_freq_to_pix_freq)
+		DC_LOG_DEBUG("DML Validation | REF_FREQ_TO_PIX_FREQ:REF_FREQ_TO_PIX_FREQ - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->ref_freq_to_pix_freq, dlg_attr.ref_freq_to_pix_freq);
+
+	/* DLG - Per luma/chroma */
+	REG_GET(VBLANK_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_VBLANK_L, &dlg_attr.refcyc_per_pte_group_vblank_l);
+	if (REG(NOM_PARAMETERS_0))
+		REG_GET(NOM_PARAMETERS_0,
+			DST_Y_PER_PTE_ROW_NOM_L, &dlg_attr.dst_y_per_pte_row_nom_l);
+	if (REG(NOM_PARAMETERS_1))
+		REG_GET(NOM_PARAMETERS_1,
+			REFCYC_PER_PTE_GROUP_NOM_L, &dlg_attr.refcyc_per_pte_group_nom_l);
+	REG_GET(NOM_PARAMETERS_4,
+		DST_Y_PER_META_ROW_NOM_L, &dlg_attr.dst_y_per_meta_row_nom_l);
+	REG_GET(NOM_PARAMETERS_5,
+		REFCYC_PER_META_CHUNK_NOM_L, &dlg_attr.refcyc_per_meta_chunk_nom_l);
+	REG_GET_2(PER_LINE_DELIVERY,
+		REFCYC_PER_LINE_DELIVERY_L, &dlg_attr.refcyc_per_line_delivery_l,
+		REFCYC_PER_LINE_DELIVERY_C, &dlg_attr.refcyc_per_line_delivery_c);
+	REG_GET_2(PER_LINE_DELIVERY_PRE,
+		REFCYC_PER_LINE_DELIVERY_PRE_L, &dlg_attr.refcyc_per_line_delivery_pre_l,
+		REFCYC_PER_LINE_DELIVERY_PRE_C, &dlg_attr.refcyc_per_line_delivery_pre_c);
+	REG_GET(VBLANK_PARAMETERS_2,
+		REFCYC_PER_PTE_GROUP_VBLANK_C, &dlg_attr.refcyc_per_pte_group_vblank_c);
+	if (REG(NOM_PARAMETERS_2))
+		REG_GET(NOM_PARAMETERS_2,
+			DST_Y_PER_PTE_ROW_NOM_C, &dlg_attr.dst_y_per_pte_row_nom_c);
+	if (REG(NOM_PARAMETERS_3))
+		REG_GET(NOM_PARAMETERS_3,
+			REFCYC_PER_PTE_GROUP_NOM_C, &dlg_attr.refcyc_per_pte_group_nom_c);
+	REG_GET(NOM_PARAMETERS_6,
+		DST_Y_PER_META_ROW_NOM_C, &dlg_attr.dst_y_per_meta_row_nom_c);
+	REG_GET(NOM_PARAMETERS_7,
+		REFCYC_PER_META_CHUNK_NOM_C, &dlg_attr.refcyc_per_meta_chunk_nom_c);
+	REG_GET(VBLANK_PARAMETERS_3,
+			REFCYC_PER_META_CHUNK_VBLANK_L, &dlg_attr.refcyc_per_meta_chunk_vblank_l);
+	REG_GET(VBLANK_PARAMETERS_4,
+			REFCYC_PER_META_CHUNK_VBLANK_C, &dlg_attr.refcyc_per_meta_chunk_vblank_c);
+
+	if (dlg_attr.refcyc_per_pte_group_vblank_l != dml_dlg_attr->refcyc_per_pte_group_vblank_l)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_1:REFCYC_PER_PTE_GROUP_VBLANK_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_vblank_l, dlg_attr.refcyc_per_pte_group_vblank_l);
+	if (dlg_attr.dst_y_per_pte_row_nom_l != dml_dlg_attr->dst_y_per_pte_row_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_0:DST_Y_PER_PTE_ROW_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_pte_row_nom_l, dlg_attr.dst_y_per_pte_row_nom_l);
+	if (dlg_attr.refcyc_per_pte_group_nom_l != dml_dlg_attr->refcyc_per_pte_group_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_1:REFCYC_PER_PTE_GROUP_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_nom_l, dlg_attr.refcyc_per_pte_group_nom_l);
+	if (dlg_attr.dst_y_per_meta_row_nom_l != dml_dlg_attr->dst_y_per_meta_row_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_4:DST_Y_PER_META_ROW_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_meta_row_nom_l, dlg_attr.dst_y_per_meta_row_nom_l);
+	if (dlg_attr.refcyc_per_meta_chunk_nom_l != dml_dlg_attr->refcyc_per_meta_chunk_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_5:REFCYC_PER_META_CHUNK_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_nom_l, dlg_attr.refcyc_per_meta_chunk_nom_l);
+	if (dlg_attr.refcyc_per_line_delivery_l != dml_dlg_attr->refcyc_per_line_delivery_l)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY:REFCYC_PER_LINE_DELIVERY_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_l, dlg_attr.refcyc_per_line_delivery_l);
+	if (dlg_attr.refcyc_per_line_delivery_c != dml_dlg_attr->refcyc_per_line_delivery_c)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY:REFCYC_PER_LINE_DELIVERY_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_c, dlg_attr.refcyc_per_line_delivery_c);
+	if (dlg_attr.refcyc_per_pte_group_vblank_c != dml_dlg_attr->refcyc_per_pte_group_vblank_c)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_2:REFCYC_PER_PTE_GROUP_VBLANK_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_vblank_c, dlg_attr.refcyc_per_pte_group_vblank_c);
+	if (dlg_attr.dst_y_per_pte_row_nom_c != dml_dlg_attr->dst_y_per_pte_row_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_2:DST_Y_PER_PTE_ROW_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_pte_row_nom_c, dlg_attr.dst_y_per_pte_row_nom_c);
+	if (dlg_attr.refcyc_per_pte_group_nom_c != dml_dlg_attr->refcyc_per_pte_group_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_3:REFCYC_PER_PTE_GROUP_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_nom_c, dlg_attr.refcyc_per_pte_group_nom_c);
+	if (dlg_attr.dst_y_per_meta_row_nom_c != dml_dlg_attr->dst_y_per_meta_row_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_6:DST_Y_PER_META_ROW_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_meta_row_nom_c, dlg_attr.dst_y_per_meta_row_nom_c);
+	if (dlg_attr.refcyc_per_meta_chunk_nom_c != dml_dlg_attr->refcyc_per_meta_chunk_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_7:REFCYC_PER_META_CHUNK_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_nom_c, dlg_attr.refcyc_per_meta_chunk_nom_c);
+	if (dlg_attr.refcyc_per_line_delivery_pre_l != dml_dlg_attr->refcyc_per_line_delivery_pre_l)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY_PRE:REFCYC_PER_LINE_DELIVERY_PRE_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_pre_l, dlg_attr.refcyc_per_line_delivery_pre_l);
+	if (dlg_attr.refcyc_per_line_delivery_pre_c != dml_dlg_attr->refcyc_per_line_delivery_pre_c)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY_PRE:REFCYC_PER_LINE_DELIVERY_PRE_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_pre_c, dlg_attr.refcyc_per_line_delivery_pre_c);
+	if (dlg_attr.refcyc_per_meta_chunk_vblank_l != dml_dlg_attr->refcyc_per_meta_chunk_vblank_l)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_3:REFCYC_PER_META_CHUNK_VBLANK_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_vblank_l, dlg_attr.refcyc_per_meta_chunk_vblank_l);
+	if (dlg_attr.refcyc_per_meta_chunk_vblank_c != dml_dlg_attr->refcyc_per_meta_chunk_vblank_c)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_4:REFCYC_PER_META_CHUNK_VBLANK_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_vblank_c, dlg_attr.refcyc_per_meta_chunk_vblank_c);
+
+	/* TTU - per hubp */
+	REG_GET_2(DCN_TTU_QOS_WM,
+		QoS_LEVEL_LOW_WM, &ttu_attr.qos_level_low_wm,
+		QoS_LEVEL_HIGH_WM, &ttu_attr.qos_level_high_wm);
+
+	if (ttu_attr.qos_level_low_wm != dml_ttu_attr->qos_level_low_wm)
+		DC_LOG_DEBUG("DML Validation | DCN_TTU_QOS_WM:QoS_LEVEL_LOW_WM - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_low_wm, ttu_attr.qos_level_low_wm);
+	if (ttu_attr.qos_level_high_wm != dml_ttu_attr->qos_level_high_wm)
+		DC_LOG_DEBUG("DML Validation | DCN_TTU_QOS_WM:QoS_LEVEL_HIGH_WM - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_high_wm, ttu_attr.qos_level_high_wm);
+
+	/* TTU - per luma/chroma */
+	/* Assumed surf0 is luma and 1 is chroma */
+	REG_GET_3(DCN_SURF0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_l,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_l,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_l);
+	REG_GET_3(DCN_SURF1_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_c,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_c,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_c);
+	REG_GET_3(DCN_CUR0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_cur0,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_cur0,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_cur0);
+	REG_GET(FLIP_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_FLIP_L, &dlg_attr.refcyc_per_pte_group_flip_l);
+	REG_GET(DCN_CUR0_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_cur0);
+	REG_GET(DCN_CUR1_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_cur1);
+	REG_GET(DCN_SURF0_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_l);
+	REG_GET(DCN_SURF1_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_c);
+
+	if (ttu_attr.refcyc_per_req_delivery_l != dml_ttu_attr->refcyc_per_req_delivery_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_l, ttu_attr.refcyc_per_req_delivery_l);
+	if (ttu_attr.qos_level_fixed_l != dml_ttu_attr->qos_level_fixed_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_l, ttu_attr.qos_level_fixed_l);
+	if (ttu_attr.qos_ramp_disable_l != dml_ttu_attr->qos_ramp_disable_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_l, ttu_attr.qos_ramp_disable_l);
+	if (ttu_attr.refcyc_per_req_delivery_c != dml_ttu_attr->refcyc_per_req_delivery_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_c, ttu_attr.refcyc_per_req_delivery_c);
+	if (ttu_attr.qos_level_fixed_c != dml_ttu_attr->qos_level_fixed_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_c, ttu_attr.qos_level_fixed_c);
+	if (ttu_attr.qos_ramp_disable_c != dml_ttu_attr->qos_ramp_disable_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_c, ttu_attr.qos_ramp_disable_c);
+	if (ttu_attr.refcyc_per_req_delivery_cur0 != dml_ttu_attr->refcyc_per_req_delivery_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_cur0, ttu_attr.refcyc_per_req_delivery_cur0);
+	if (ttu_attr.qos_level_fixed_cur0 != dml_ttu_attr->qos_level_fixed_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_cur0, ttu_attr.qos_level_fixed_cur0);
+	if (ttu_attr.qos_ramp_disable_cur0 != dml_ttu_attr->qos_ramp_disable_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_cur0, ttu_attr.qos_ramp_disable_cur0);
+	if (dlg_attr.refcyc_per_pte_group_flip_l != dml_dlg_attr->refcyc_per_pte_group_flip_l)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_1:REFCYC_PER_PTE_GROUP_FLIP_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_flip_l, dlg_attr.refcyc_per_pte_group_flip_l);
+	if (ttu_attr.refcyc_per_req_delivery_pre_cur0 != dml_ttu_attr->refcyc_per_req_delivery_pre_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_cur0, ttu_attr.refcyc_per_req_delivery_pre_cur0);
+	if (ttu_attr.refcyc_per_req_delivery_pre_cur1 != dml_ttu_attr->refcyc_per_req_delivery_pre_cur1)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR1_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_cur1, ttu_attr.refcyc_per_req_delivery_pre_cur1);
+	if (ttu_attr.refcyc_per_req_delivery_pre_l != dml_ttu_attr->refcyc_per_req_delivery_pre_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_l, ttu_attr.refcyc_per_req_delivery_pre_l);
+	if (ttu_attr.refcyc_per_req_delivery_pre_c != dml_ttu_attr->refcyc_per_req_delivery_pre_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_c, ttu_attr.refcyc_per_req_delivery_pre_c);
+
+	/* Host VM deadline regs */
+	REG_GET(VBLANK_PARAMETERS_5,
+		REFCYC_PER_VM_GROUP_VBLANK, &dlg_attr.refcyc_per_vm_group_vblank);
+	REG_GET(VBLANK_PARAMETERS_6,
+		REFCYC_PER_VM_REQ_VBLANK, &dlg_attr.refcyc_per_vm_req_vblank);
+	REG_GET(FLIP_PARAMETERS_3,
+		REFCYC_PER_VM_GROUP_FLIP, &dlg_attr.refcyc_per_vm_group_flip);
+	REG_GET(FLIP_PARAMETERS_4,
+		REFCYC_PER_VM_REQ_FLIP, &dlg_attr.refcyc_per_vm_req_flip);
+	REG_GET(FLIP_PARAMETERS_5,
+		REFCYC_PER_PTE_GROUP_FLIP_C, &dlg_attr.refcyc_per_pte_group_flip_c);
+	REG_GET(FLIP_PARAMETERS_6,
+		REFCYC_PER_META_CHUNK_FLIP_C, &dlg_attr.refcyc_per_meta_chunk_flip_c);
+	REG_GET(FLIP_PARAMETERS_2,
+		REFCYC_PER_META_CHUNK_FLIP_L, &dlg_attr.refcyc_per_meta_chunk_flip_l);
+
+	if (dlg_attr.refcyc_per_vm_group_vblank != dml_dlg_attr->refcyc_per_vm_group_vblank)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_5:REFCYC_PER_VM_GROUP_VBLANK - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_vm_group_vblank, dlg_attr.refcyc_per_vm_group_vblank);
+	if (dlg_attr.refcyc_per_vm_req_vblank != dml_dlg_attr->refcyc_per_vm_req_vblank)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_6:REFCYC_PER_VM_REQ_VBLANK - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_vm_req_vblank, dlg_attr.refcyc_per_vm_req_vblank);
+	if (dlg_attr.refcyc_per_vm_group_flip != dml_dlg_attr->refcyc_per_vm_group_flip)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_3:REFCYC_PER_VM_GROUP_FLIP - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_vm_group_flip, dlg_attr.refcyc_per_vm_group_flip);
+	if (dlg_attr.refcyc_per_vm_req_flip != dml_dlg_attr->refcyc_per_vm_req_flip)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_4:REFCYC_PER_VM_REQ_FLIP - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_vm_req_flip, dlg_attr.refcyc_per_vm_req_flip);
+	if (dlg_attr.refcyc_per_pte_group_flip_c != dml_dlg_attr->refcyc_per_pte_group_flip_c)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_5:REFCYC_PER_PTE_GROUP_FLIP_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_flip_c, dlg_attr.refcyc_per_pte_group_flip_c);
+	if (dlg_attr.refcyc_per_meta_chunk_flip_c != dml_dlg_attr->refcyc_per_meta_chunk_flip_c)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_6:REFCYC_PER_META_CHUNK_FLIP_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_flip_c, dlg_attr.refcyc_per_meta_chunk_flip_c);
+	if (dlg_attr.refcyc_per_meta_chunk_flip_l != dml_dlg_attr->refcyc_per_meta_chunk_flip_l)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_2:REFCYC_PER_META_CHUNK_FLIP_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_flip_l, dlg_attr.refcyc_per_meta_chunk_flip_l);
+}
+
+static void program_surface_flip_and_addr(struct hubp *hubp, struct surface_flip_registers *flip_regs)
+{
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+
+	REG_UPDATE_3(DCSURF_FLIP_CONTROL,
+					SURFACE_FLIP_TYPE, flip_regs->immediate,
+					SURFACE_FLIP_MODE_FOR_STEREOSYNC, flip_regs->grph_stereo,
+					SURFACE_FLIP_IN_STEREOSYNC, flip_regs->grph_stereo);
+
+	REG_UPDATE(VMID_SETTINGS_0,
+				VMID, flip_regs->vmid);
+
+	REG_UPDATE_8(DCSURF_SURFACE_CONTROL,
+			PRIMARY_SURFACE_TMZ, flip_regs->tmz_surface,
+			PRIMARY_SURFACE_TMZ_C, flip_regs->tmz_surface,
+			PRIMARY_META_SURFACE_TMZ, flip_regs->tmz_surface,
+			PRIMARY_META_SURFACE_TMZ_C, flip_regs->tmz_surface,
+			SECONDARY_SURFACE_TMZ, flip_regs->tmz_surface,
+			SECONDARY_SURFACE_TMZ_C, flip_regs->tmz_surface,
+			SECONDARY_META_SURFACE_TMZ, flip_regs->tmz_surface,
+			SECONDARY_META_SURFACE_TMZ_C, flip_regs->tmz_surface);
+
+	REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C, 0,
+			PRIMARY_META_SURFACE_ADDRESS_HIGH_C,
+			flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C);
+
+	REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_C, 0,
+			PRIMARY_META_SURFACE_ADDRESS_C,
+			flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_C);
+
+	REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH, 0,
+			PRIMARY_META_SURFACE_ADDRESS_HIGH,
+			flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH);
+
+	REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS, 0,
+			PRIMARY_META_SURFACE_ADDRESS,
+			flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS);
+
+	REG_SET(DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH, 0,
+			SECONDARY_META_SURFACE_ADDRESS_HIGH,
+			flip_regs->DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH);
+
+	REG_SET(DCSURF_SECONDARY_META_SURFACE_ADDRESS, 0,
+			SECONDARY_META_SURFACE_ADDRESS,
+			flip_regs->DCSURF_SECONDARY_META_SURFACE_ADDRESS);
+
+
+	REG_SET(DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH, 0,
+			SECONDARY_SURFACE_ADDRESS_HIGH,
+			flip_regs->DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH);
+
+	REG_SET(DCSURF_SECONDARY_SURFACE_ADDRESS, 0,
+			SECONDARY_SURFACE_ADDRESS,
+			flip_regs->DCSURF_SECONDARY_SURFACE_ADDRESS);
+
+
+	REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, 0,
+			PRIMARY_SURFACE_ADDRESS_HIGH_C,
+			flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C);
+
+	REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_C, 0,
+			PRIMARY_SURFACE_ADDRESS_C,
+			flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_C);
+
+	REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH, 0,
+			PRIMARY_SURFACE_ADDRESS_HIGH,
+			flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH);
+
+	REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS, 0,
+			PRIMARY_SURFACE_ADDRESS,
+			flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS);
+}
+
+void dmcub_PLAT_54186_wa(struct hubp *hubp, struct surface_flip_registers *flip_regs)
+{
+	struct dc_dmub_srv *dmcub = hubp->ctx->dmub_srv;
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+	struct dmub_rb_cmd_PLAT_54186_wa PLAT_54186_wa = { 0 };
+
+	PLAT_54186_wa.header.type = DMUB_CMD__PLAT_54186_WA;
+	PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS;
+	PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_C = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_C;
+	PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH;
+	PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C;
+	PLAT_54186_wa.flip.flip_params.grph_stereo = flip_regs->grph_stereo;
+	PLAT_54186_wa.flip.flip_params.hubp_inst = hubp->inst;
+	PLAT_54186_wa.flip.flip_params.immediate = flip_regs->immediate;
+	PLAT_54186_wa.flip.flip_params.tmz_surface = flip_regs->tmz_surface;
+	PLAT_54186_wa.flip.flip_params.vmid = flip_regs->vmid;
+
+	PERF_TRACE();  // TODO: remove after performance is stable.
+	dc_dmub_srv_cmd_queue(dmcub, &PLAT_54186_wa.header);
+	PERF_TRACE();  // TODO: remove after performance is stable.
+	dc_dmub_srv_cmd_execute(dmcub);
+	PERF_TRACE();  // TODO: remove after performance is stable.
+	dc_dmub_srv_wait_idle(dmcub);
+	PERF_TRACE();  // TODO: remove after performance is stable.
+}
+
+bool hubp21_program_surface_flip_and_addr(
+		struct hubp *hubp,
+		const struct dc_plane_address *address,
+		bool flip_immediate)
+{
+	struct dc_debug_options *debug = &hubp->ctx->dc->debug;
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+	struct surface_flip_registers flip_regs = { 0 };
+
+	flip_regs.vmid = address->vmid;
+
+	switch (address->type) {
+	case PLN_ADDR_TYPE_GRAPHICS:
+		if (address->grph.addr.quad_part == 0) {
+			BREAK_TO_DEBUGGER();
+			break;
+		}
+
+		if (address->grph.meta_addr.quad_part != 0) {
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS =
+					address->grph.meta_addr.low_part;
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH =
+					address->grph.meta_addr.high_part;
+		}
+
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS =
+				address->grph.addr.low_part;
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH =
+				address->grph.addr.high_part;
+		break;
+	case PLN_ADDR_TYPE_VIDEO_PROGRESSIVE:
+		if (address->video_progressive.luma_addr.quad_part == 0
+				|| address->video_progressive.chroma_addr.quad_part == 0)
+			break;
+
+		if (address->video_progressive.luma_meta_addr.quad_part != 0) {
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS =
+					address->video_progressive.luma_meta_addr.low_part;
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH =
+					address->video_progressive.luma_meta_addr.high_part;
+
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_C =
+					address->video_progressive.chroma_meta_addr.low_part;
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C =
+					address->video_progressive.chroma_meta_addr.high_part;
+		}
+
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS =
+				address->video_progressive.luma_addr.low_part;
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH =
+				address->video_progressive.luma_addr.high_part;
+
+		if (debug->nv12_iflip_vm_wa) {
+			flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_C =
+					address->video_progressive.chroma_addr.low_part + hubp21->PLAT_54186_wa_chroma_addr_offset;
+		} else
+			flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_C =
+					address->video_progressive.chroma_addr.low_part;
+
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C =
+				address->video_progressive.chroma_addr.high_part;
+
+		break;
+	case PLN_ADDR_TYPE_GRPH_STEREO:
+		if (address->grph_stereo.left_addr.quad_part == 0)
+			break;
+		if (address->grph_stereo.right_addr.quad_part == 0)
+			break;
+
+		flip_regs.grph_stereo = true;
+
+		if (address->grph_stereo.right_meta_addr.quad_part != 0) {
+			flip_regs.DCSURF_SECONDARY_META_SURFACE_ADDRESS =
+					address->grph_stereo.right_meta_addr.low_part;
+			flip_regs.DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH =
+					address->grph_stereo.right_meta_addr.high_part;
+		}
+
+		if (address->grph_stereo.left_meta_addr.quad_part != 0) {
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS =
+					address->grph_stereo.left_meta_addr.low_part;
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH =
+					address->grph_stereo.left_meta_addr.high_part;
+		}
+
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS =
+				address->grph_stereo.left_addr.low_part;
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH =
+				address->grph_stereo.left_addr.high_part;
+
+		flip_regs.DCSURF_SECONDARY_SURFACE_ADDRESS =
+				address->grph_stereo.right_addr.low_part;
+		flip_regs.DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH =
+				address->grph_stereo.right_addr.high_part;
+
+		break;
+	default:
+		BREAK_TO_DEBUGGER();
+		break;
+	}
+
+	flip_regs.tmz_surface = address->tmz_surface;
+	flip_regs.immediate = flip_immediate;
+
+	if (hubp->ctx->dc->debug.enable_dmcub_surface_flip && address->type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE)
+		dmcub_PLAT_54186_wa(hubp, &flip_regs);
+	else
+		program_surface_flip_and_addr(hubp, &flip_regs);
+
+	hubp->request_address = *address;
+
+	return true;
+}
+
 void hubp21_init(struct hubp *hubp)
 {
 	// DEDCN21-133: Inconsistent row starting line for flip between DPTE and Meta
@@ -203,7 +915,7 @@ void hubp21_init(struct hubp *hubp)
 static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
 	.hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled,
-	.hubp_program_surface_flip_and_addr = hubp2_program_surface_flip_and_addr,
+	.hubp_program_surface_flip_and_addr = hubp21_program_surface_flip_and_addr,
 	.hubp_program_surface_config = hubp1_program_surface_config,
 	.hubp_is_flip_pending = hubp1_is_flip_pending,
 	.hubp_setup = hubp21_setup,
@@ -211,7 +923,8 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp21_set_vm_system_aperture_settings,
 	.set_blank = hubp1_set_blank,
 	.dcc_control = hubp1_dcc_control,
-	.mem_program_viewport = min_set_viewport,
+	.mem_program_viewport = hubp21_set_viewport,
+	.apply_PLAT_54186_wa = hubp21_apply_PLAT_54186_wa,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp1_cursor_set_position,
 	.hubp_clk_cntl = hubp1_clk_cntl,
@@ -223,6 +936,7 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_clear_underflow = hubp1_clear_underflow,
 	.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
 	.hubp_init = hubp21_init,
+	.validate_dml_output = hubp21_validate_dml_output,
 };
 
 bool hubp21_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h
index aeda719a2a13..9873b6cbc5ba 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h
@@ -108,6 +108,7 @@ struct dcn21_hubp {
 	const struct dcn_hubp2_registers *hubp_regs;
 	const struct dcn_hubp2_shift *hubp_shift;
 	const struct dcn_hubp2_mask *hubp_mask;
+	int PLAT_54186_wa_chroma_addr_offset;
 };
 
 bool hubp21_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c
index b25215cadf85..081ad8e43d58 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c
@@ -28,7 +28,7 @@
 #include "core_types.h"
 #include "resource.h"
 #include "dce/dce_hwseq.h"
-#include "dcn20/dcn20_hwseq.h"
+#include "dcn21_hwseq.h"
 #include "vmid.h"
 #include "reg_helper.h"
 #include "hw/clk_mgr.h"
@@ -61,7 +61,7 @@ static void mmhub_update_page_table_config(struct dcn_hubbub_phys_addr_config *c
 
 }
 
-static int dcn21_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
+int dcn21_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
 {
 	struct dcn_hubbub_phys_addr_config config;
 
@@ -82,7 +82,7 @@ static int dcn21_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_ph
 
 // work around for Renoir s0i3, if register is programmed, bypass golden init.
 
-static bool dcn21_s0i3_golden_init_wa(struct dc *dc)
+bool dcn21_s0i3_golden_init_wa(struct dc *dc)
 {
 	struct dce_hwseq *hws = dc->hwseq;
 	uint32_t value = 0;
@@ -112,11 +112,3 @@ void dcn21_optimize_pwr_state(
 			true);
 }
 
-void dcn21_hw_sequencer_construct(struct dc *dc)
-{
-	dcn20_hw_sequencer_construct(dc);
-	dc->hwss.init_sys_ctx = dcn21_init_sys_ctx;
-	dc->hwss.s0i3_golden_init_wa = dcn21_s0i3_golden_init_wa;
-	dc->hwss.optimize_pwr_state = dcn21_optimize_pwr_state;
-	dc->hwss.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state;
-}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h
index be67b62e6fb1..182736096123 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h
@@ -26,8 +26,22 @@
 #ifndef __DC_HWSS_DCN21_H__
 #define __DC_HWSS_DCN21_H__
 
+#include "hw_sequencer_private.h"
+
 struct dc;
 
-void dcn21_hw_sequencer_construct(struct dc *dc);
+int dcn21_init_sys_ctx(struct dce_hwseq *hws,
+		struct dc *dc,
+		struct dc_phy_addr_space_config *pa_config);
+
+bool dcn21_s0i3_golden_init_wa(struct dc *dc);
+
+void dcn21_exit_optimized_pwr_state(
+		const struct dc *dc,
+		struct dc_state *context);
+
+void dcn21_optimize_pwr_state(
+		const struct dc *dc,
+		struct dc_state *context);
 
 #endif /* __DC_HWSS_DCN21_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
new file mode 100644
index 000000000000..4861aa5c59ae
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
@@ -0,0 +1,142 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dce110/dce110_hw_sequencer.h"
+#include "dcn10/dcn10_hw_sequencer.h"
+#include "dcn20/dcn20_hwseq.h"
+#include "dcn21_hwseq.h"
+
+static const struct hw_sequencer_funcs dcn21_funcs = {
+	.program_gamut_remap = dcn10_program_gamut_remap,
+	.init_hw = dcn10_init_hw,
+	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
+	.apply_ctx_for_surface = NULL,
+	.program_front_end_for_ctx = dcn20_program_front_end_for_ctx,
+	.update_plane_addr = dcn20_update_plane_addr,
+	.update_dchub = dcn10_update_dchub,
+	.update_pending_status = dcn10_update_pending_status,
+	.program_output_csc = dcn20_program_output_csc,
+	.enable_accelerated_mode = dce110_enable_accelerated_mode,
+	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
+	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
+	.update_info_frame = dce110_update_info_frame,
+	.send_immediate_sdp_message = dcn10_send_immediate_sdp_message,
+	.enable_stream = dcn20_enable_stream,
+	.disable_stream = dce110_disable_stream,
+	.unblank_stream = dcn20_unblank_stream,
+	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
+	.disable_plane = dcn20_disable_plane,
+	.pipe_control_lock = dcn20_pipe_control_lock,
+	.pipe_control_lock_global = dcn20_pipe_control_lock_global,
+	.prepare_bandwidth = dcn20_prepare_bandwidth,
+	.optimize_bandwidth = dcn20_optimize_bandwidth,
+	.update_bandwidth = dcn20_update_bandwidth,
+	.set_drr = dcn10_set_drr,
+	.get_position = dcn10_get_position,
+	.set_static_screen_control = dcn10_set_static_screen_control,
+	.setup_stereo = dcn10_setup_stereo,
+	.set_avmute = dce110_set_avmute,
+	.log_hw_state = dcn10_log_hw_state,
+	.get_hw_state = dcn10_get_hw_state,
+	.clear_status_bits = dcn10_clear_status_bits,
+	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_power_control = dce110_edp_power_control,
+	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
+	.set_cursor_position = dcn10_set_cursor_position,
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
+	.setup_periodic_interrupt = dcn10_setup_periodic_interrupt,
+	.set_clock = dcn10_set_clock,
+	.get_clock = dcn10_get_clock,
+	.program_triplebuffer = dcn20_program_triple_buffer,
+	.enable_writeback = dcn20_enable_writeback,
+	.disable_writeback = dcn20_disable_writeback,
+	.dmdata_status_done = dcn20_dmdata_status_done,
+	.program_dmdata_engine = dcn20_program_dmdata_engine,
+	.set_dmdata_attributes = dcn20_set_dmdata_attributes,
+	.init_sys_ctx = dcn21_init_sys_ctx,
+	.init_vm_ctx = dcn20_init_vm_ctx,
+	.set_flip_control_gsl = dcn20_set_flip_control_gsl,
+	.optimize_pwr_state = dcn21_optimize_pwr_state,
+	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
+	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+	.set_cursor_position = dcn10_set_cursor_position,
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
+	.optimize_pwr_state = dcn21_optimize_pwr_state,
+	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
+};
+
+static const struct hwseq_private_funcs dcn21_private_funcs = {
+	.init_pipes = dcn10_init_pipes,
+	.update_plane_addr = dcn20_update_plane_addr,
+	.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
+	.update_mpcc = dcn20_update_mpcc,
+	.set_input_transfer_func = dcn20_set_input_transfer_func,
+	.set_output_transfer_func = dcn20_set_output_transfer_func,
+	.power_down = dce110_power_down,
+	.enable_display_power_gating = dcn10_dummy_display_power_gating,
+	.blank_pixel_data = dcn20_blank_pixel_data,
+	.reset_hw_ctx_wrap = dcn20_reset_hw_ctx_wrap,
+	.enable_stream_timing = dcn20_enable_stream_timing,
+	.edp_backlight_control = dce110_edp_backlight_control,
+	.disable_stream_gating = dcn20_disable_stream_gating,
+	.enable_stream_gating = dcn20_enable_stream_gating,
+	.setup_vupdate_interrupt = dcn20_setup_vupdate_interrupt,
+	.did_underflow_occur = dcn10_did_underflow_occur,
+	.init_blank = dcn20_init_blank,
+	.disable_vga = dcn20_disable_vga,
+	.bios_golden_init = dcn10_bios_golden_init,
+	.plane_atomic_disable = dcn20_plane_atomic_disable,
+	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
+	.enable_power_gating_plane = dcn20_enable_power_gating_plane,
+	.dpp_pg_control = dcn20_dpp_pg_control,
+	.hubp_pg_control = dcn20_hubp_pg_control,
+	.dsc_pg_control = NULL,
+	.update_odm = dcn20_update_odm,
+	.dsc_pg_control = dcn20_dsc_pg_control,
+	.get_surface_visual_confirm_color = dcn10_get_surface_visual_confirm_color,
+	.get_hdr_visual_confirm_color = dcn10_get_hdr_visual_confirm_color,
+	.set_hdr_multiplier = dcn10_set_hdr_multiplier,
+	.verify_allow_pstate_change_high = dcn10_verify_allow_pstate_change_high,
+	.s0i3_golden_init_wa = dcn21_s0i3_golden_init_wa,
+	.wait_for_blank_complete = dcn20_wait_for_blank_complete,
+	.dccg_init = dcn20_dccg_init,
+	.set_blend_lut = dcn20_set_blend_lut,
+	.set_shaper_3dlut = dcn20_set_shaper_3dlut,
+};
+
+void dcn21_hw_sequencer_construct(struct dc *dc)
+{
+	dc->hwss = dcn21_funcs;
+	dc->hwseq->funcs = dcn21_private_funcs;
+
+	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		dc->hwss.init_hw = dcn20_fpga_init_hw;
+		dc->hwseq->funcs.init_pipes = NULL;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.h
new file mode 100644
index 000000000000..3ed24292648a
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_DCN21_INIT_H__
+#define __DC_DCN21_INIT_H__
+
+struct dc;
+
+void dcn21_hw_sequencer_construct(struct dc *dc);
+
+#endif /* __DC_DCN20_INIT_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c
index e8a504ca5890..e45683ac871a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c
@@ -323,9 +323,7 @@ void dcn21_link_encoder_disable_output(
 
 
 static const struct link_encoder_funcs dcn21_link_enc_funcs = {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.read_state = link_enc2_read_state,
-#endif
 	.validate_output_with_stream =
 		dcn10_link_encoder_validate_output_with_stream,
 	.hw_init = enc2_hw_init,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h
index 1d7a1a51f13d..033d5d76f195 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h
@@ -33,6 +33,45 @@ struct dcn21_link_encoder {
 	struct dpcssys_phy_seq_cfg phy_seq_cfg;
 };
 
+#define DPCS_DCN21_MASK_SH_LIST(mask_sh)\
+	DPCS_DCN2_MASK_SH_LIST(mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_TX_VBOOST_LVL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_MPLLB_CP_PROP_GS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_RX_VREF_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_CP_INT_GS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCS_DMCU_DPALT_DIS_BLOCK_REG, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_SUP_PRE_HP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX0_VREGDRV_BYP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX1_VREGDRV_BYP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX2_VREGDRV_BYP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX3_VREGDRV_BYP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_FINETUNE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_RANGE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_POST, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYA_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh)
+
+#define DPCS_DCN21_REG_LIST(id) \
+	DPCS_DCN2_REG_LIST(id),\
+	SRI(RDPCSTX_PHY_CNTL15, RDPCSTX, id),\
+	SRI(RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCSTX, id)
+
 #define LINK_ENCODER_MASK_SH_LIST_DCN21(mask_sh)\
 	LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh),\
 	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL0_XBAR_SOURCE, mask_sh),\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index b29b2c99a564..1d741bca2211 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -1,5 +1,6 @@
 /*
 * Copyright 2018 Advanced Micro Devices, Inc.
+ * Copyright 2019 Raptor Engineering, LLC
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -28,6 +29,8 @@
 #include "dm_services.h"
 #include "dc.h"
 
+#include "dcn21_init.h"
+
 #include "resource.h"
 #include "include/irq_service_interface.h"
 #include "dcn20/dcn20_resource.h"
@@ -60,6 +63,8 @@
 
 #include "dcn20/dcn20_dwb.h"
 #include "dcn20/dcn20_mmhubbub.h"
+#include "dpcs/dpcs_2_1_0_offset.h"
+#include "dpcs/dpcs_2_1_0_sh_mask.h"
 
 #include "renoir_ip_offset.h"
 #include "dcn/dcn_2_1_0_offset.h"
@@ -78,6 +83,7 @@
 #include "dcn21_resource.h"
 #include "vm_helper.h"
 #include "dcn20/dcn20_vmid.h"
+#include "../dce/dmub_psr.h"
 
 #define SOC_BOUNDING_BOX_VALID false
 #define DC_LOGGER_INIT(logger)
@@ -90,11 +96,7 @@ struct _vcs_dpi_ip_params_st dcn2_1_ip = {
 	.gpuvm_max_page_table_levels = 1,
 	.hostvm_max_page_table_levels = 4,
 	.hostvm_cached_page_table_levels = 2,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.num_dsc = 3,
-#else
-	.num_dsc = 0,
-#endif
 	.rob_buffer_size_kbytes = 168,
 	.det_buffer_size_kbytes = 164,
 	.dpte_buffer_size_in_pte_reqs_luma = 44,
@@ -352,7 +354,7 @@ static const struct bios_registers bios_regs = {
 };
 
 static const struct dce_dmcu_registers dmcu_regs = {
-		DMCU_DCN10_REG_LIST()
+		DMCU_DCN20_REG_LIST()
 };
 
 static const struct dce_dmcu_shift dmcu_shift = {
@@ -375,20 +377,6 @@ static const struct dce_abm_mask abm_mask = {
 		ABM_MASK_SH_LIST_DCN20(_MASK)
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DMUB
-static const struct dcn21_dmcub_registers dmcub_regs = {
-		DMCUB_REG_LIST_DCN()
-};
-
-static const struct dcn21_dmcub_shift dmcub_shift = {
-		DMCUB_COMMON_MASK_SH_LIST_BASE(__SHIFT)
-};
-
-static const struct dcn21_dmcub_mask dmcub_mask = {
-		DMCUB_COMMON_MASK_SH_LIST_BASE(_MASK)
-};
-#endif
-
 #define audio_regs(id)\
 [id] = {\
 		AUD_COMMON_REG_LIST(id)\
@@ -478,15 +466,18 @@ static const struct dcn20_mpc_registers mpc_regs = {
 		MPC_OUT_MUX_REG_LIST_DCN2_0(0),
 		MPC_OUT_MUX_REG_LIST_DCN2_0(1),
 		MPC_OUT_MUX_REG_LIST_DCN2_0(2),
-		MPC_OUT_MUX_REG_LIST_DCN2_0(3)
+		MPC_OUT_MUX_REG_LIST_DCN2_0(3),
+		MPC_DBG_REG_LIST_DCN2_0()
 };
 
 static const struct dcn20_mpc_shift mpc_shift = {
-	MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT)
+	MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT),
+	MPC_DEBUG_REG_LIST_SH_DCN20
 };
 
 static const struct dcn20_mpc_mask mpc_mask = {
-	MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK)
+	MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK),
+	MPC_DEBUG_REG_LIST_MASK_DCN20
 };
 
 #define hubp_regs(id)\
@@ -554,7 +545,6 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define dsc_regsDCN20(id)\
 [id] = {\
 	DSC_REG_LIST_DCN20(id)\
@@ -576,7 +566,6 @@ static const struct dcn20_dsc_shift dsc_shift = {
 static const struct dcn20_dsc_mask dsc_mask = {
 	DSC_REG_LIST_SH_MASK_DCN20(_MASK)
 };
-#endif
 
 #define ipp_regs(id)\
 [id] = {\
@@ -623,6 +612,7 @@ static const struct dce110_aux_registers aux_engine_regs[] = {
 #define tf_regs(id)\
 [id] = {\
 	TF_REG_LIST_DCN20(id),\
+	TF_REG_LIST_DCN20_COMMON_APPEND(id),\
 }
 
 static const struct dcn2_dpp_registers tf_regs[] = {
@@ -633,11 +623,13 @@ static const struct dcn2_dpp_registers tf_regs[] = {
 };
 
 static const struct dcn2_dpp_shift tf_shift = {
-		TF_REG_LIST_SH_MASK_DCN20(__SHIFT)
+		TF_REG_LIST_SH_MASK_DCN20(__SHIFT),
+		TF_DEBUG_REG_LIST_SH_DCN20
 };
 
 static const struct dcn2_dpp_mask tf_mask = {
-		TF_REG_LIST_SH_MASK_DCN20(_MASK)
+		TF_REG_LIST_SH_MASK_DCN20(_MASK),
+		TF_DEBUG_REG_LIST_MASK_DCN20
 };
 
 #define stream_enc_regs(id)\
@@ -672,7 +664,7 @@ static const struct dcn10_stream_encoder_mask se_mask = {
 static void dcn21_pp_smu_destroy(struct pp_smu_funcs **pp_smu);
 
 static int dcn21_populate_dml_pipes_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes);
+		struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes);
 
 static struct input_pixel_processor *dcn21_ipp_create(
 	struct dc_context *ctx, uint32_t inst)
@@ -773,9 +765,7 @@ static const struct resource_caps res_cap_rn = {
 		.num_dwb = 1,
 		.num_ddc = 5,
 		.num_vmid = 1,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 3,
-#endif
 };
 
 #ifdef DIAGS_BUILD
@@ -800,9 +790,7 @@ static const struct resource_caps res_cap_rn_FPGA_2pipe_dsc = {
 		.num_pll = 4,
 		.num_dwb = 1,
 		.num_ddc = 4,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 2,
-#endif
 };
 #endif
 
@@ -847,6 +835,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.scl_reset_length10 = true,
 		.sanity_checks = true,
 		.disable_48mhz_pwrdwn = false,
+		.nv12_iflip_vm_wa = true,
+		.usbc_combo_phy_reset_wa = true
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
@@ -869,7 +859,7 @@ enum dcn20_clk_src_array_id {
 	DCN20_CLK_SRC_TOTAL_DCN21
 };
 
-static void destruct(struct dcn21_resource_pool *pool)
+static void dcn21_resource_destruct(struct dcn21_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -880,12 +870,10 @@ static void destruct(struct dcn21_resource_pool *pool)
 		}
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		if (pool->base.dscs[i] != NULL)
 			dcn20_dsc_destroy(&pool->base.dscs[i]);
 	}
-#endif
 
 	if (pool->base.mpc != NULL) {
 		kfree(TO_DCN20_MPC(pool->base.mpc));
@@ -972,11 +960,6 @@ static void destruct(struct dcn21_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-#ifdef CONFIG_DRM_AMD_DC_DMUB
-	if (pool->base.dmcub != NULL)
-		dcn21_dmcub_destroy(&pool->base.dmcub);
-#endif
-
 	if (pool->base.dccg != NULL)
 		dcn_dccg_destroy(&pool->base.dccg);
 
@@ -1010,11 +993,9 @@ static void calculate_wm_set_for_vlevel(
 	wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000;
 	wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000;
 	wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000;
 	wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000;
 	wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000;
-#endif
 	dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached;
 
 }
@@ -1023,7 +1004,8 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 {
 	int i;
 
-	kernel_fpu_begin();
+	DC_FP_START();
+
 	if (dc->bb_overrides.sr_exit_time_ns) {
 		for (i = 0; i < WM_SET_COUNT; i++) {
 			  dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us =
@@ -1049,7 +1031,7 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 		}
 	}
 
-	kernel_fpu_end();
+	DC_FP_END();
 }
 
 void dcn21_calculate_wm(
@@ -1099,10 +1081,10 @@ void dcn21_calculate_wm(
 	if (pipe_cnt != pipe_idx) {
 		if (dc->res_pool->funcs->populate_dml_pipes)
 			pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc,
-				&context->res_ctx, pipes);
+				context, pipes);
 		else
 			pipe_cnt = dcn21_populate_dml_pipes_from_context(dc,
-				&context->res_ctx, pipes);
+				context, pipes);
 	}
 
 	*out_pipe_cnt = pipe_cnt;
@@ -1192,7 +1174,7 @@ static void dcn21_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dcn21_resource_pool *dcn21_pool = TO_DCN21_RES_POOL(*pool);
 
-	destruct(dcn21_pool);
+	dcn21_resource_destruct(dcn21_pool);
 	kfree(dcn21_pool);
 	*pool = NULL;
 }
@@ -1331,7 +1313,6 @@ static void read_dce_straps(
 
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 
 struct display_stream_compressor *dcn21_dsc_create(
 	struct dc_context *ctx, uint32_t inst)
@@ -1347,16 +1328,9 @@ struct display_stream_compressor *dcn21_dsc_create(
 	dsc2_construct(dsc, ctx, inst, &dsc_regs[inst], &dsc_shift, &dsc_mask);
 	return &dsc->base;
 }
-#endif
 
 static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
 {
-	/*
-	TODO: Fix this function to calcualte correct values.
-	There are known issues with this function currently
-	that will need to be investigated. Use hardcoded known good values for now.
-
-
 	struct dcn21_resource_pool *pool = TO_DCN21_RES_POOL(dc->res_pool);
 	struct clk_limit_table *clk_table = &bw_params->clk_table;
 	int i;
@@ -1371,11 +1345,14 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 		dcn2_1_soc.clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
 		dcn2_1_soc.clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
 		dcn2_1_soc.clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
-		dcn2_1_soc.clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 16 / 1000;
+		dcn2_1_soc.clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2;
 	}
-	dcn2_1_soc.clock_limits[i] = dcn2_1_soc.clock_limits[i - i];
+	dcn2_1_soc.clock_limits[i] = dcn2_1_soc.clock_limits[i - 1];
 	dcn2_1_soc.num_states = i;
-	*/
+
+	// diags does not retrieve proper values from SMU, do not update DML instance for diags
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) && !IS_DIAG_DC(dc->ctx->dce_environment))
+		dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21);
 }
 
 /* Temporary Place holder until we can get them from fuse */
@@ -1529,8 +1506,9 @@ static const struct encoder_feature_support link_enc_feature = {
 
 #define link_regs(id, phyid)\
 [id] = {\
-	LE_DCN10_REG_LIST(id), \
+	LE_DCN2_REG_LIST(id), \
 	UNIPHY_DCN2_REG_LIST(phyid), \
+	DPCS_DCN21_REG_LIST(id), \
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \
 }
 
@@ -1569,11 +1547,13 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = {
 };
 
 static const struct dcn10_link_enc_shift le_shift = {
-	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT)
+	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT),\
+	DPCS_DCN21_MASK_SH_LIST(__SHIFT)
 };
 
 static const struct dcn10_link_enc_mask le_mask = {
-	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK)
+	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK),\
+	DPCS_DCN21_MASK_SH_LIST(_MASK)
 };
 
 static int map_transmitter_id_to_phy_instance(
@@ -1639,10 +1619,11 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
 }
 
 static int dcn21_populate_dml_pipes_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes)
+		struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes)
 {
-	uint32_t pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, res_ctx, pipes);
+	uint32_t pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, context, pipes);
 	int i;
+	struct resource_context *res_ctx = &context->res_ctx;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 
@@ -1671,7 +1652,7 @@ static struct resource_funcs dcn21_res_pool_funcs = {
 	.update_bw_bounding_box = update_bw_bounding_box
 };
 
-static bool construct(
+static bool dcn21_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dcn21_resource_pool *pool)
@@ -1711,6 +1692,7 @@ static bool construct(
 	dc->caps.post_blend_color_processing = true;
 	dc->caps.force_dp_tps4_for_cp2520 = true;
 	dc->caps.extended_aux_timeout_support = true;
+	dc->caps.dmcub_support = true;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
@@ -1760,7 +1742,7 @@ static bool construct(
 		goto create_fail;
 	}
 
-	pool->base.dmcu = dcn20_dmcu_create(ctx,
+	pool->base.dmcu = dcn21_dmcu_create(ctx,
 			&dmcu_regs,
 			&dmcu_shift,
 			&dmcu_mask);
@@ -1770,6 +1752,10 @@ static bool construct(
 		goto create_fail;
 	}
 
+	// Leave as NULL to not affect current dmcu psr programming sequence
+	// Will be uncommented when functionality is confirmed to be working
+	pool->base.psr = NULL;
+
 	pool->base.abm = dce_abm_create(ctx,
 			&abm_regs,
 			&abm_shift,
@@ -1780,18 +1766,6 @@ static bool construct(
 		goto create_fail;
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DMUB
-	pool->base.dmcub = dcn21_dmcub_create(ctx,
-			&dmcub_regs,
-			&dmcub_shift,
-			&dmcub_mask);
-	if (pool->base.dmcub == NULL) {
-		dm_error("DC: failed to create dmcub!\n");
-		BREAK_TO_DEBUGGER();
-		goto create_fail;
-	}
-#endif
-
 	pool->base.pp_smu = dcn21_pp_smu_create(ctx);
 
 	num_pipes = dcn2_1_ip.max_num_dpp;
@@ -1818,41 +1792,41 @@ static bool construct(
 		if ((pipe_fuses & (1 << i)) != 0)
 			continue;
 
-		pool->base.hubps[i] = dcn21_hubp_create(ctx, i);
-		if (pool->base.hubps[i] == NULL) {
+		pool->base.hubps[j] = dcn21_hubp_create(ctx, i);
+		if (pool->base.hubps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create memory input!\n");
 			goto create_fail;
 		}
 
-		pool->base.ipps[i] = dcn21_ipp_create(ctx, i);
-		if (pool->base.ipps[i] == NULL) {
+		pool->base.ipps[j] = dcn21_ipp_create(ctx, i);
+		if (pool->base.ipps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create input pixel processor!\n");
 			goto create_fail;
 		}
 
-		pool->base.dpps[i] = dcn21_dpp_create(ctx, i);
-		if (pool->base.dpps[i] == NULL) {
+		pool->base.dpps[j] = dcn21_dpp_create(ctx, i);
+		if (pool->base.dpps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create dpps!\n");
 			goto create_fail;
 		}
 
-		pool->base.opps[i] = dcn21_opp_create(ctx, i);
-		if (pool->base.opps[i] == NULL) {
+		pool->base.opps[j] = dcn21_opp_create(ctx, i);
+		if (pool->base.opps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create output pixel processor!\n");
 			goto create_fail;
 		}
 
-		pool->base.timing_generators[i] = dcn21_timing_generator_create(
+		pool->base.timing_generators[j] = dcn21_timing_generator_create(
 				ctx, i);
-		if (pool->base.timing_generators[i] == NULL) {
+		if (pool->base.timing_generators[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error("DC: failed to create tg!\n");
 			goto create_fail;
@@ -1896,7 +1870,6 @@ static bool construct(
 		goto create_fail;
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		pool->base.dscs[i] = dcn21_dsc_create(ctx, i);
 		if (pool->base.dscs[i] == NULL) {
@@ -1905,7 +1878,6 @@ static bool construct(
 			goto create_fail;
 		}
 	}
-#endif
 
 	if (!dcn20_dwbc_create(ctx, &pool->base)) {
 		BREAK_TO_DEBUGGER();
@@ -1936,7 +1908,7 @@ static bool construct(
 
 create_fail:
 
-	destruct(pool);
+	dcn21_resource_destruct(pool);
 
 	return false;
 }
@@ -1951,7 +1923,7 @@ struct resource_pool *dcn21_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(init_data->num_virtual_links, dc, pool))
+	if (dcn21_resource_construct(init_data->num_virtual_links, dc, pool))
 		return &pool->base;
 
 	BREAK_TO_DEBUGGER();
diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
index 94b75e942607..8bde1d688f2e 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
@@ -118,13 +118,11 @@ bool dm_helpers_submit_i2c(
 		const struct dc_link *link,
 		struct i2c_command *cmd);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 bool dm_helpers_dp_write_dsc_enable(
 		struct dc_context *ctx,
 		const struct dc_stream_state *stream,
 		bool enable
 );
-#endif
 bool dm_helpers_is_dp_sink_present(
 		struct dc_link *link);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
index ef7df9ef6d7e..ae608c329366 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
@@ -41,12 +41,8 @@ enum pp_smu_ver {
 	 */
 	PP_SMU_UNSUPPORTED,
 	PP_SMU_VER_RV,
-#ifndef CONFIG_TRIM_DRM_AMD_DC_DCN2_0
 	PP_SMU_VER_NV,
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	PP_SMU_VER_RN,
-#endif
 
 	PP_SMU_VER_MAX
 };
@@ -143,7 +139,6 @@ struct pp_smu_funcs_rv {
 	void (*set_pme_wa_enable)(struct pp_smu *pp);
 };
 
-#ifndef CONFIG_TRIM_DRM_AMD_DC_DCN2_0
 /* Used by pp_smu_funcs_nv.set_voltage_by_freq
  *
  */
@@ -247,7 +242,6 @@ struct pp_smu_funcs_nv {
 	enum pp_smu_status (*set_pstate_handshake_support)(struct pp_smu *pp,
 			BOOLEAN pstate_handshake_supported);
 };
-#endif
 
 #define PP_SMU_NUM_SOCCLK_DPM_LEVELS  8
 #define PP_SMU_NUM_DCFCLK_DPM_LEVELS  8
@@ -291,12 +285,8 @@ struct pp_smu_funcs {
 	struct pp_smu ctx;
 	union {
 		struct pp_smu_funcs_rv rv_funcs;
-#ifndef CONFIG_TRIM_DRM_AMD_DC_DCN2_0
 		struct pp_smu_funcs_nv nv_funcs;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 		struct pp_smu_funcs_rn rn_funcs;
-#endif
 
 	};
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index 1a0429744630..968ff1fef486 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -40,6 +40,9 @@
 
 #undef DEPRECATED
 
+struct dmub_srv;
+struct dc_dmub_srv;
+
 irq_handler_idx dm_register_interrupt(
 	struct dc_context *ctx,
 	struct dc_interrupt_params *int_params,
@@ -139,6 +142,13 @@ uint32_t generic_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr, int n,
 		uint8_t shift1, uint32_t mask1, uint32_t field_value1, ...);
 
+struct dc_dmub_srv *dc_dmub_srv_create(struct dc *dc, struct dmub_srv *dmub);
+void dc_dmub_srv_destroy(struct dc_dmub_srv **dmub_srv);
+
+void reg_sequence_start_gather(const struct dc_context *ctx);
+void reg_sequence_start_execute(const struct dc_context *ctx);
+void reg_sequence_wait_done(const struct dc_context *ctx);
+
 #define FD(reg_field)	reg_field ## __SHIFT, \
 						reg_field ## _MASK
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
index a3d1be20dd9d..b52ba6ffabe1 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
@@ -220,6 +220,7 @@ struct dm_bl_data_point {
 };
 
 /* Total size of the structure should not exceed 256 bytes */
+#define BL_DATA_POINTS 99
 struct dm_acpi_atif_backlight_caps {
 	uint16_t size; /* Bytes 0-1 (2 bytes) */
 	uint16_t flags; /* Byted 2-3 (2 bytes) */
@@ -229,7 +230,7 @@ struct dm_acpi_atif_backlight_caps {
 	uint8_t  min_input_signal; /* Byte 7 */
 	uint8_t  max_input_signal; /* Byte 8 */
 	uint8_t  num_data_points; /* Byte 9 */
-	struct dm_bl_data_point data_points[99]; /* Bytes 10-207 (198 bytes)*/
+	struct dm_bl_data_point data_points[BL_DATA_POINTS]; /* Bytes 10-207 (198 bytes)*/
 };
 
 enum dm_acpi_display_type {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 8df251626e22..7ee8b8460a9b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -1,5 +1,6 @@
 #
 # Copyright 2017 Advanced Micro Devices, Inc.
+# Copyright 2019 Raptor Engineering, LLC
 #
 # Permission is hereby granted, free of charge, to any person obtaining a
 # copy of this software and associated documentation files (the "Software"),
@@ -24,7 +25,13 @@
 # It provides the general basic services required by other DAL
 # subcomponents.
 
+ifdef CONFIG_X86
 dml_ccflags := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+dml_ccflags := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -32,6 +39,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -40,17 +48,16 @@ dml_ccflags += -mpreferred-stack-boundary=4
 else
 dml_ccflags += -msse2
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-endif
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
 endif
@@ -61,11 +68,9 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dml_common_defs.o := $(dml_ccflags)
 DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
 	dml_common_defs.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 DML += display_mode_vba.o dcn20/display_rq_dlg_calc_20.o dcn20/display_mode_vba_20.o
 DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o
-endif
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
index 6c6c486b774a..e7a8ac7a1f22 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
@@ -937,7 +937,7 @@ static unsigned int CalculateVMAndRowBytes(
 		*MetaRowByte = 0;
 	}
 
-	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) {
+	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) {
 		MacroTileSizeBytes = 256;
 		MacroTileHeight = BlockHeight256Bytes;
 	} else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x
@@ -1335,11 +1335,11 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer
 		else
 			mode_lib->vba.SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k];
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true)
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 			MainPlaneDoesODMCombine = true;
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j)
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true)
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 				MainPlaneDoesODMCombine = true;
 
 		if (MainPlaneDoesODMCombine == true)
@@ -2577,7 +2577,8 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer
 			mode_lib->vba.MinActiveDRAMClockChangeMargin
 					+ mode_lib->vba.DRAMClockChangeLatency;
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+	if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
 		mode_lib->vba.DRAMClockChangeWatermark += 25;
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
 	} else {
@@ -2847,12 +2848,12 @@ static void dml20_DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
 			SwathWidth = mode_lib->vba.ViewportHeight[k];
 		}
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true) {
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 			MainPlaneDoesODMCombine = true;
 		}
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) {
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true) {
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 				MainPlaneDoesODMCombine = true;
 			}
 		}
@@ -3347,7 +3348,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 										== dm_420_10))
 				|| (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl
 						|| mode_lib->vba.SurfaceTiling[k]
-								== dm_sw_gfx7_2d_thin_lvp)
+								== dm_sw_gfx7_2d_thin_l_vp)
 						&& !((mode_lib->vba.SourcePixelFormat[k]
 								== dm_444_64
 								|| mode_lib->vba.SourcePixelFormat[k]
@@ -3445,10 +3446,10 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				locals->FabricAndDRAMBandwidthPerState[i] * 1000)
 				* locals->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100;
 
-		locals->ReturnBWPerState[i] = locals->ReturnBWToDCNPerState;
+		locals->ReturnBWPerState[i][0] = locals->ReturnBWToDCNPerState;
 
 		if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 					locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency /
 					((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 					/ (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i]
@@ -3459,7 +3460,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				+ (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024);
 
 		if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 				4 * locals->ReturnBWToDCNPerState *
 				(locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 				* locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency /
@@ -3471,7 +3472,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				locals->DCFCLKPerState[i], locals->FabricAndDRAMBandwidthPerState[i] * 1000);
 
 		if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 					locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency /
 					((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 					/ (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i]
@@ -3482,7 +3483,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				+ (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024);
 
 		if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 				4 * locals->ReturnBWToDCNPerState *
 				(locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 				* locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency /
@@ -3520,12 +3521,12 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i] =
 				(mode_lib->vba.RoundTripPingLatencyCycles + 32.0) / mode_lib->vba.DCFCLKPerState[i]
-				+ locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i];
-		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i]
+				+ locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0];
+		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0]
 				> locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) {
-			locals->ROBSupport[i] = true;
+			locals->ROBSupport[i][0] = true;
 		} else {
-			locals->ROBSupport[i] = false;
+			locals->ROBSupport[i][0] = false;
 		}
 	}
 	/*Writeback Mode Support Check*/
@@ -3902,7 +3903,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity
 						&& locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]
-						&& locals->ODMCombineEnablePerState[i][k] == false) {
+						&& locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->NoOfDPP[i][j][k] = 1;
 					locals->RequiredDPPCLK[i][j][k] =
 						locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0);
@@ -3991,16 +3992,16 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	/*Viewport Size Check*/
 
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		locals->ViewportSizeSupport[i] = true;
+		locals->ViewportSizeSupport[i][0] = true;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			if (locals->ODMCombineEnablePerState[i][k] == true) {
+			if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 				if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]))
 						> locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			} else {
 				if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			}
 		}
@@ -4182,8 +4183,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						mode_lib->vba.DSCFormatFactor = 1;
 					}
 					if (locals->RequiresDSC[i][k] == true) {
-						if (locals->ODMCombineEnablePerState[i][k]
-								== true) {
+						if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 							if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor
 									> (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) {
 								locals->DSCCLKRequiredMoreThanSupported[i] =
@@ -4206,7 +4206,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 		mode_lib->vba.TotalDSCUnitsRequired = 0.0;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 			if (locals->RequiresDSC[i][k] == true) {
-				if (locals->ODMCombineEnablePerState[i][k] == true) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 					mode_lib->vba.TotalDSCUnitsRequired =
 							mode_lib->vba.TotalDSCUnitsRequired + 2.0;
 				} else {
@@ -4248,7 +4248,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.bpp = locals->OutputBppPerState[i][k];
 			}
 			if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) {
-				if (locals->ODMCombineEnablePerState[i][k] == false) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->DSCDelayPerState[i][k] =
 							dscceComputeDelay(
 									mode_lib->vba.DSCInputBitPerComponent[k],
@@ -4291,7 +4291,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		for (j = 0; j < 2; j++) {
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				if (locals->ODMCombineEnablePerState[i][k] == true)
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1)
 					locals->SwathWidthYPerState[i][j][k] = dml_min(locals->SwathWidthYSingleDPP[k], dml_round(locals->HActive[k] / 2 * locals->HRatio[k]));
 				else
 					locals->SwathWidthYPerState[i][j][k] = locals->SwathWidthYSingleDPP[k] / locals->NoOfDPP[i][j][k];
@@ -4344,28 +4344,28 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 				locals->EffectiveDETLBLinesLuma = dml_floor(locals->LinesInDETLuma +  dml_min(
 						locals->LinesInDETLuma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETY[k] *
-						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i],
+						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesLuma),
 						locals->SwathHeightYPerState[i][j][k]);
 
 				locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min(
 						locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] *
-						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i],
+						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesChroma),
 						locals->SwathHeightCPerState[i][j][k]);
 
 				if (locals->BytePerPixelInDETC[k] == 0) {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
 							/ locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] *
-								dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]);
+								dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]);
 				} else {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = dml_min(
 						locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
 						/ locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] *
-						dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]),
+						dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]),
 							locals->EffectiveDETLBLinesChroma * (locals->HTotal[k] / locals->PixelClock[k]) / (locals->VRatio[k] / 2) -
 							locals->EffectiveDETLBLinesChroma * locals->SwathWidthYPerState[i][j][k] / 2 *
-							dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]));
+							dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]));
 				}
 			}
 		}
@@ -4405,14 +4405,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				locals->SwathHeightYThisState[k] = locals->SwathHeightYPerState[i][j][k];
 				locals->SwathHeightCThisState[k] = locals->SwathHeightCPerState[i][j][k];
 				locals->SwathWidthYThisState[k] = locals->SwathWidthYPerState[i][j][k];
-				mode_lib->vba.ProjectedDCFCLKDeepSleep = dml_max(
-						mode_lib->vba.ProjectedDCFCLKDeepSleep,
+				mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max(
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 						mode_lib->vba.PixelClock[k] / 16.0);
 				if (mode_lib->vba.BytePerPixelInDETC[k] == 0.0) {
 					if (mode_lib->vba.VRatio[k] <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4422,9 +4422,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4435,9 +4435,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					}
 				} else {
 					if (mode_lib->vba.VRatio[k] <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4447,9 +4447,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4459,9 +4459,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 												* mode_lib->vba.RequiredDPPCLK[i][j][k]);
 					}
 					if (mode_lib->vba.VRatio[k] / 2.0 <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETC[k],
@@ -4472,9 +4472,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETC[k],
@@ -4510,7 +4510,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						&mode_lib->vba.PTEBufferSizeNotExceededY[i][j][k],
 						&mode_lib->vba.dpte_row_height[k],
 						&mode_lib->vba.meta_row_height[k]);
-				mode_lib->vba.PrefetchLinesY[k] = CalculatePrefetchSourceLines(
+				mode_lib->vba.PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines(
 						mode_lib,
 						mode_lib->vba.VRatio[k],
 						mode_lib->vba.vtaps[k],
@@ -4549,7 +4549,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							&mode_lib->vba.PTEBufferSizeNotExceededC[i][j][k],
 							&mode_lib->vba.dpte_row_height_chroma[k],
 							&mode_lib->vba.meta_row_height_chroma[k]);
-					mode_lib->vba.PrefetchLinesC[k] = CalculatePrefetchSourceLines(
+					mode_lib->vba.PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines(
 							mode_lib,
 							mode_lib->vba.VRatio[k] / 2.0,
 							mode_lib->vba.VTAPsChroma[k],
@@ -4563,14 +4563,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0;
 					mode_lib->vba.MetaRowBytesC = 0.0;
 					mode_lib->vba.DPTEBytesPerRowC = 0.0;
-					locals->PrefetchLinesC[k] = 0.0;
+					locals->PrefetchLinesC[0][0][k] = 0.0;
 					locals->PTEBufferSizeNotExceededC[i][j][k] = true;
 					locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma;
 				}
-				locals->PDEAndMetaPTEBytesPerFrame[k] =
+				locals->PDEAndMetaPTEBytesPerFrame[0][0][k] =
 						mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC;
-				locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
-				locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
+				locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
+				locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
 
 				CalculateActiveRowBandwidth(
 						mode_lib->vba.GPUVMEnable,
@@ -4597,14 +4597,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 									+ mode_lib->vba.TotalNumberOfDCCActiveDPP[i][j]
 											* mode_lib->vba.MetaChunkSize)
 									* 1024.0
-									/ mode_lib->vba.ReturnBWPerState[i];
+									/ mode_lib->vba.ReturnBWPerState[i][0];
 			if (mode_lib->vba.GPUVMEnable == true) {
 				mode_lib->vba.ExtraLatency = mode_lib->vba.ExtraLatency
 						+ mode_lib->vba.TotalNumberOfActiveDPP[i][j]
 								* mode_lib->vba.PTEGroupSize
-								/ mode_lib->vba.ReturnBWPerState[i];
+								/ mode_lib->vba.ReturnBWPerState[i][0];
 			}
-			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep;
+			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				if (mode_lib->vba.BlendingAndTiming[k] == k) {
@@ -4654,7 +4654,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			}
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
+				locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
 					- dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0));
 			}
 
@@ -4699,7 +4699,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 									mode_lib->vba.RequiredDPPCLK[i][j][k],
 									mode_lib->vba.RequiredDISPCLK[i][j],
 									mode_lib->vba.PixelClock[k],
-									mode_lib->vba.ProjectedDCFCLKDeepSleep,
+									mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 									mode_lib->vba.DSCDelayPerState[i][k],
 									mode_lib->vba.NoOfDPP[i][j][k],
 									mode_lib->vba.ScalerEnabled[k],
@@ -4717,7 +4717,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 											- mode_lib->vba.VActive[k],
 									mode_lib->vba.HTotal[k],
 									mode_lib->vba.MaxInterDCNTileRepeaters,
-									mode_lib->vba.MaximumVStartup[k],
+									mode_lib->vba.MaximumVStartup[0][0][k],
 									mode_lib->vba.GPUVMMaxPageTableLevels,
 									mode_lib->vba.GPUVMEnable,
 									mode_lib->vba.DynamicMetadataEnable[k],
@@ -4727,15 +4727,15 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 									mode_lib->vba.UrgentLatencyPixelDataOnly,
 									mode_lib->vba.ExtraLatency,
 									mode_lib->vba.TimeCalc,
-									mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k],
-									mode_lib->vba.MetaRowBytes[k],
-									mode_lib->vba.DPTEBytesPerRow[k],
-									mode_lib->vba.PrefetchLinesY[k],
+									mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k],
+									mode_lib->vba.MetaRowBytes[0][0][k],
+									mode_lib->vba.DPTEBytesPerRow[0][0][k],
+									mode_lib->vba.PrefetchLinesY[0][0][k],
 									mode_lib->vba.SwathWidthYPerState[i][j][k],
 									mode_lib->vba.BytePerPixelInDETY[k],
 									mode_lib->vba.PrefillY[k],
 									mode_lib->vba.MaxNumSwY[k],
-									mode_lib->vba.PrefetchLinesC[k],
+									mode_lib->vba.PrefetchLinesC[0][0][k],
 									mode_lib->vba.BytePerPixelInDETC[k],
 									mode_lib->vba.PrefillC[k],
 									mode_lib->vba.MaxNumSwC[k],
@@ -4766,19 +4766,19 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				locals->prefetch_vm_bw_valid = true;
 				locals->prefetch_row_bw_valid = true;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-					if (locals->PDEAndMetaPTEBytesPerFrame[k] == 0)
+					if (locals->PDEAndMetaPTEBytesPerFrame[0][0][k] == 0)
 						locals->prefetch_vm_bw[k] = 0;
 					else if (locals->LinesForMetaPTE[k] > 0)
-						locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[k]
+						locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[0][0][k]
 							/ (locals->LinesForMetaPTE[k] * locals->HTotal[k] / locals->PixelClock[k]);
 					else {
 						locals->prefetch_vm_bw[k] = 0;
 						locals->prefetch_vm_bw_valid = false;
 					}
-					if (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k] == 0)
+					if (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k] == 0)
 						locals->prefetch_row_bw[k] = 0;
 					else if (locals->LinesForMetaAndDPTERow[k] > 0)
-						locals->prefetch_row_bw[k] = (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k])
+						locals->prefetch_row_bw[k] = (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k])
 							/ (locals->LinesForMetaAndDPTERow[k] * locals->HTotal[k] / locals->PixelClock[k]);
 					else {
 						locals->prefetch_row_bw[k] = 0;
@@ -4797,13 +4797,13 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 											mode_lib->vba.RequiredPrefetchPixelDataBWLuma[i][j][k])
 											+ mode_lib->vba.meta_row_bw[k] + mode_lib->vba.dpte_row_bw[k]);
 				}
-				locals->BandwidthWithoutPrefetchSupported[i] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i]) {
-					locals->BandwidthWithoutPrefetchSupported[i] = false;
+				locals->BandwidthWithoutPrefetchSupported[i][0] = true;
+				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]) {
+					locals->BandwidthWithoutPrefetchSupported[i][0] = false;
 				}
 
 				locals->PrefetchSupported[i][j] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i]) {
+				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]) {
 					locals->PrefetchSupported[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4828,7 +4828,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			if (mode_lib->vba.PrefetchSupported[i][j] == true
 					&& mode_lib->vba.VRatioInPrefetchSupported[i][j] == true) {
 				mode_lib->vba.BandwidthAvailableForImmediateFlip =
-						mode_lib->vba.ReturnBWPerState[i];
+						mode_lib->vba.ReturnBWPerState[i][0];
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 					mode_lib->vba.BandwidthAvailableForImmediateFlip =
 							mode_lib->vba.BandwidthAvailableForImmediateFlip
@@ -4842,9 +4842,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					if ((mode_lib->vba.SourcePixelFormat[k] != dm_420_8
 							&& mode_lib->vba.SourcePixelFormat[k] != dm_420_10)) {
 						mode_lib->vba.ImmediateFlipBytes[k] =
-								mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k]
-										+ mode_lib->vba.MetaRowBytes[k]
-										+ mode_lib->vba.DPTEBytesPerRow[k];
+								mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k]
+										+ mode_lib->vba.MetaRowBytes[0][0][k]
+										+ mode_lib->vba.DPTEBytesPerRow[0][0][k];
 					}
 				}
 				mode_lib->vba.TotImmediateFlipBytes = 0.0;
@@ -4872,9 +4872,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 									/ mode_lib->vba.PixelClock[k],
 							mode_lib->vba.VRatio[k],
 							mode_lib->vba.Tno_bw[k],
-							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k],
-							mode_lib->vba.MetaRowBytes[k],
-							mode_lib->vba.DPTEBytesPerRow[k],
+							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k],
+							mode_lib->vba.MetaRowBytes[0][0][k],
+							mode_lib->vba.DPTEBytesPerRow[0][0][k],
 							mode_lib->vba.DCCEnable[k],
 							mode_lib->vba.dpte_row_height[k],
 							mode_lib->vba.meta_row_height[k],
@@ -4899,7 +4899,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				mode_lib->vba.ImmediateFlipSupportedForState[i][j] = true;
 				if (mode_lib->vba.total_dcn_read_bw_with_flip
-						> mode_lib->vba.ReturnBWPerState[i]) {
+						> mode_lib->vba.ReturnBWPerState[i][0]) {
 					mode_lib->vba.ImmediateFlipSupportedForState[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4918,13 +4918,13 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; k++)
 		mode_lib->vba.MaxTotalVActiveRDBandwidth = mode_lib->vba.MaxTotalVActiveRDBandwidth + mode_lib->vba.ReadBandwidth[k];
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min(mode_lib->vba.ReturnBusWidth *
+		mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min(mode_lib->vba.ReturnBusWidth *
 				mode_lib->vba.DCFCLKPerState[i], mode_lib->vba.FabricAndDRAMBandwidthPerState[i] * 1000) *
 				mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation / 100;
-		if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i])
-			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = true;
+		if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0])
+			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = true;
 		else
-			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = false;
+			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = false;
 	}
 
 	/*PTE Buffer Size Check*/
@@ -5012,7 +5012,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_SCALE_RATIO_TAP;
 			} else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) {
 				status = DML_FAIL_SOURCE_PIXEL_FORMAT;
-			} else if (locals->ViewportSizeSupport[i] != true) {
+			} else if (locals->ViewportSizeSupport[i][0] != true) {
 				status = DML_FAIL_VIEWPORT_SIZE;
 			} else if (locals->DIOSupport[i] != true) {
 				status = DML_FAIL_DIO_SUPPORT;
@@ -5022,7 +5022,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_DSC_CLK_REQUIRED;
 			} else if (locals->UrgentLatencySupport[i][j] != true) {
 				status = DML_FAIL_URGENT_LATENCY;
-			} else if (locals->ROBSupport[i] != true) {
+			} else if (locals->ROBSupport[i][0] != true) {
 				status = DML_FAIL_REORDERING_BUFFER;
 			} else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) {
 				status = DML_FAIL_DISPCLK_DPPCLK;
@@ -5042,7 +5042,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_PITCH_SUPPORT;
 			} else if (locals->PrefetchSupported[i][j] != true) {
 				status = DML_FAIL_PREFETCH_SUPPORT;
-			} else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) {
+			} else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) {
 				status = DML_FAIL_TOTAL_V_ACTIVE_BW;
 			} else if (locals->VRatioInPrefetchSupported[i][j] != true) {
 				status = DML_FAIL_V_RATIO_PREFETCH;
@@ -5088,7 +5088,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel];
-	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel];
+	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0];
 	mode_lib->vba.FabricAndDRAMBandwidth = locals->FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel];
 	for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 		if (mode_lib->vba.BlendingAndTiming[k] == k) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 3c70dd577292..22f3b5a4b3b9 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -997,7 +997,7 @@ static unsigned int CalculateVMAndRowBytes(
 		*MetaRowByte = 0;
 	}
 
-	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) {
+	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) {
 		MacroTileSizeBytes = 256;
 		MacroTileHeight = BlockHeight256Bytes;
 	} else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x
@@ -1395,11 +1395,11 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
 		else
 			mode_lib->vba.SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k];
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true)
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 			MainPlaneDoesODMCombine = true;
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j)
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true)
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 				MainPlaneDoesODMCombine = true;
 
 		if (MainPlaneDoesODMCombine == true)
@@ -2611,9 +2611,13 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
 			mode_lib->vba.MinActiveDRAMClockChangeMargin
 					+ mode_lib->vba.DRAMClockChangeLatency;
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+	if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
 		mode_lib->vba.DRAMClockChangeWatermark += 25;
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
+	} else if (mode_lib->vba.DummyPStateCheck &&
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) {
+		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
 	} else {
 		if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) {
 			mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vblank;
@@ -2881,12 +2885,12 @@ static void dml20v2_DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
 			SwathWidth = mode_lib->vba.ViewportHeight[k];
 		}
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true) {
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 			MainPlaneDoesODMCombine = true;
 		}
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) {
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true) {
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 				MainPlaneDoesODMCombine = true;
 			}
 		}
@@ -3381,7 +3385,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 										== dm_420_10))
 				|| (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl
 						|| mode_lib->vba.SurfaceTiling[k]
-								== dm_sw_gfx7_2d_thin_lvp)
+								== dm_sw_gfx7_2d_thin_l_vp)
 						&& !((mode_lib->vba.SourcePixelFormat[k]
 								== dm_444_64
 								|| mode_lib->vba.SourcePixelFormat[k]
@@ -3479,10 +3483,10 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				locals->FabricAndDRAMBandwidthPerState[i] * 1000)
 				* locals->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100;
 
-		locals->ReturnBWPerState[i] = locals->ReturnBWToDCNPerState;
+		locals->ReturnBWPerState[i][0] = locals->ReturnBWToDCNPerState;
 
 		if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 					locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency /
 					((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 					/ (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i]
@@ -3493,7 +3497,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				+ (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024);
 
 		if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 				4 * locals->ReturnBWToDCNPerState *
 				(locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 				* locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency /
@@ -3505,7 +3509,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				locals->DCFCLKPerState[i], locals->FabricAndDRAMBandwidthPerState[i] * 1000);
 
 		if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 					locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency /
 					((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 					/ (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i]
@@ -3516,7 +3520,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				+ (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024);
 
 		if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 				4 * locals->ReturnBWToDCNPerState *
 				(locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 				* locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency /
@@ -3554,12 +3558,12 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i] =
 				(mode_lib->vba.RoundTripPingLatencyCycles + 32.0) / mode_lib->vba.DCFCLKPerState[i]
-				+ locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i];
-		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i]
+				+ locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0];
+		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0]
 				> locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) {
-			locals->ROBSupport[i] = true;
+			locals->ROBSupport[i][0] = true;
 		} else {
-			locals->ROBSupport[i] = false;
+			locals->ROBSupport[i][0] = false;
 		}
 	}
 	/*Writeback Mode Support Check*/
@@ -3942,7 +3946,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				}
 				if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity
 						&& locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]
-						&& locals->ODMCombineEnablePerState[i][k] == false) {
+						&& locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->NoOfDPP[i][j][k] = 1;
 					locals->RequiredDPPCLK[i][j][k] =
 						locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0);
@@ -4031,16 +4035,16 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 	/*Viewport Size Check*/
 
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		locals->ViewportSizeSupport[i] = true;
+		locals->ViewportSizeSupport[i][0] = true;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			if (locals->ODMCombineEnablePerState[i][k] == true) {
+			if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 				if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]))
 						> locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			} else {
 				if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			}
 		}
@@ -4222,8 +4226,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 						mode_lib->vba.DSCFormatFactor = 1;
 					}
 					if (locals->RequiresDSC[i][k] == true) {
-						if (locals->ODMCombineEnablePerState[i][k]
-								== true) {
+						if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 							if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor
 									> (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) {
 								locals->DSCCLKRequiredMoreThanSupported[i] =
@@ -4246,7 +4249,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 		mode_lib->vba.TotalDSCUnitsRequired = 0.0;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 			if (locals->RequiresDSC[i][k] == true) {
-				if (locals->ODMCombineEnablePerState[i][k] == true) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 					mode_lib->vba.TotalDSCUnitsRequired =
 							mode_lib->vba.TotalDSCUnitsRequired + 2.0;
 				} else {
@@ -4288,7 +4291,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				mode_lib->vba.bpp = locals->OutputBppPerState[i][k];
 			}
 			if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) {
-				if (locals->ODMCombineEnablePerState[i][k] == false) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->DSCDelayPerState[i][k] =
 							dscceComputeDelay(
 									mode_lib->vba.DSCInputBitPerComponent[k],
@@ -4331,7 +4334,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		for (j = 0; j < 2; j++) {
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				if (locals->ODMCombineEnablePerState[i][k] == true)
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1)
 					locals->SwathWidthYPerState[i][j][k] = dml_min(locals->SwathWidthYSingleDPP[k], dml_round(locals->HActive[k] / 2 * locals->HRatio[k]));
 				else
 					locals->SwathWidthYPerState[i][j][k] = locals->SwathWidthYSingleDPP[k] / locals->NoOfDPP[i][j][k];
@@ -4384,28 +4387,28 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 
 				locals->EffectiveDETLBLinesLuma = dml_floor(locals->LinesInDETLuma +  dml_min(
 						locals->LinesInDETLuma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETY[k] *
-						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i],
+						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesLuma),
 						locals->SwathHeightYPerState[i][j][k]);
 
 				locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min(
 						locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] *
-						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i],
+						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesChroma),
 						locals->SwathHeightCPerState[i][j][k]);
 
 				if (locals->BytePerPixelInDETC[k] == 0) {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
 							/ locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] *
-								dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]);
+								dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]);
 				} else {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = dml_min(
 						locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
 						/ locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] *
-						dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]),
+						dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]),
 							locals->EffectiveDETLBLinesChroma * (locals->HTotal[k] / locals->PixelClock[k]) / (locals->VRatio[k] / 2) -
 							locals->EffectiveDETLBLinesChroma * locals->SwathWidthYPerState[i][j][k] / 2 *
-							dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]));
+							dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]));
 				}
 			}
 		}
@@ -4450,14 +4453,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				locals->SwathHeightYThisState[k] = locals->SwathHeightYPerState[i][j][k];
 				locals->SwathHeightCThisState[k] = locals->SwathHeightCPerState[i][j][k];
 				locals->SwathWidthYThisState[k] = locals->SwathWidthYPerState[i][j][k];
-				mode_lib->vba.ProjectedDCFCLKDeepSleep = dml_max(
-						mode_lib->vba.ProjectedDCFCLKDeepSleep,
+				mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max(
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 						mode_lib->vba.PixelClock[k] / 16.0);
 				if (mode_lib->vba.BytePerPixelInDETC[k] == 0.0) {
 					if (mode_lib->vba.VRatio[k] <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4467,9 +4470,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4480,9 +4483,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 					}
 				} else {
 					if (mode_lib->vba.VRatio[k] <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4492,9 +4495,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4504,9 +4507,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 												* mode_lib->vba.RequiredDPPCLK[i][j][k]);
 					}
 					if (mode_lib->vba.VRatio[k] / 2.0 <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETC[k],
@@ -4517,9 +4520,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETC[k],
@@ -4555,7 +4558,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 						&mode_lib->vba.PTEBufferSizeNotExceededY[i][j][k],
 						&mode_lib->vba.dpte_row_height[k],
 						&mode_lib->vba.meta_row_height[k]);
-				mode_lib->vba.PrefetchLinesY[k] = CalculatePrefetchSourceLines(
+				mode_lib->vba.PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines(
 						mode_lib,
 						mode_lib->vba.VRatio[k],
 						mode_lib->vba.vtaps[k],
@@ -4594,7 +4597,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 							&mode_lib->vba.PTEBufferSizeNotExceededC[i][j][k],
 							&mode_lib->vba.dpte_row_height_chroma[k],
 							&mode_lib->vba.meta_row_height_chroma[k]);
-					mode_lib->vba.PrefetchLinesC[k] = CalculatePrefetchSourceLines(
+					mode_lib->vba.PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines(
 							mode_lib,
 							mode_lib->vba.VRatio[k] / 2.0,
 							mode_lib->vba.VTAPsChroma[k],
@@ -4608,14 +4611,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 					mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0;
 					mode_lib->vba.MetaRowBytesC = 0.0;
 					mode_lib->vba.DPTEBytesPerRowC = 0.0;
-					locals->PrefetchLinesC[k] = 0.0;
+					locals->PrefetchLinesC[0][0][k] = 0.0;
 					locals->PTEBufferSizeNotExceededC[i][j][k] = true;
 					locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma;
 				}
-				locals->PDEAndMetaPTEBytesPerFrame[k] =
+				locals->PDEAndMetaPTEBytesPerFrame[0][0][k] =
 						mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC;
-				locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
-				locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
+				locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
+				locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
 
 				CalculateActiveRowBandwidth(
 						mode_lib->vba.GPUVMEnable,
@@ -4642,14 +4645,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 									+ mode_lib->vba.TotalNumberOfDCCActiveDPP[i][j]
 											* mode_lib->vba.MetaChunkSize)
 									* 1024.0
-									/ mode_lib->vba.ReturnBWPerState[i];
+									/ mode_lib->vba.ReturnBWPerState[i][0];
 			if (mode_lib->vba.GPUVMEnable == true) {
 				mode_lib->vba.ExtraLatency = mode_lib->vba.ExtraLatency
 						+ mode_lib->vba.TotalNumberOfActiveDPP[i][j]
 								* mode_lib->vba.PTEGroupSize
-								/ mode_lib->vba.ReturnBWPerState[i];
+								/ mode_lib->vba.ReturnBWPerState[i][0];
 			}
-			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep;
+			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				if (mode_lib->vba.BlendingAndTiming[k] == k) {
@@ -4699,7 +4702,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 			}
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
+				locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
 					- dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0));
 			}
 
@@ -4739,7 +4742,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 						mode_lib->vba.XFCRemoteSurfaceFlipDelay = 0.0;
 					}
 
-					CalculateDelayAfterScaler(mode_lib, mode_lib->vba.ReturnBWPerState[i], mode_lib->vba.ReadBandwidthLuma[k], mode_lib->vba.ReadBandwidthChroma[k], mode_lib->vba.MaxTotalVActiveRDBandwidth,
+					CalculateDelayAfterScaler(mode_lib, mode_lib->vba.ReturnBWPerState[i][0], mode_lib->vba.ReadBandwidthLuma[k], mode_lib->vba.ReadBandwidthChroma[k], mode_lib->vba.MaxTotalVActiveRDBandwidth,
 						mode_lib->vba.DisplayPipeLineDeliveryTimeLuma[k], mode_lib->vba.DisplayPipeLineDeliveryTimeChroma[k],
 						mode_lib->vba.RequiredDPPCLK[i][j][k], mode_lib->vba.RequiredDISPCLK[i][j], mode_lib->vba.PixelClock[k], mode_lib->vba.DSCDelayPerState[i][k], mode_lib->vba.NoOfDPP[i][j][k], mode_lib->vba.ScalerEnabled[k], mode_lib->vba.NumberOfCursors[k],
 						mode_lib->vba.DPPCLKDelaySubtotal, mode_lib->vba.DPPCLKDelaySCL, mode_lib->vba.DPPCLKDelaySCLLBOnly, mode_lib->vba.DPPCLKDelayCNVCFormater, mode_lib->vba.DPPCLKDelayCNVCCursor, mode_lib->vba.DISPCLKDelaySubtotal,
@@ -4753,14 +4756,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 									mode_lib->vba.RequiredDPPCLK[i][j][k],
 									mode_lib->vba.RequiredDISPCLK[i][j],
 									mode_lib->vba.PixelClock[k],
-									mode_lib->vba.ProjectedDCFCLKDeepSleep,
+									mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 									mode_lib->vba.NoOfDPP[i][j][k],
 									mode_lib->vba.NumberOfCursors[k],
 									mode_lib->vba.VTotal[k]
 											- mode_lib->vba.VActive[k],
 									mode_lib->vba.HTotal[k],
 									mode_lib->vba.MaxInterDCNTileRepeaters,
-									mode_lib->vba.MaximumVStartup[k],
+									mode_lib->vba.MaximumVStartup[0][0][k],
 									mode_lib->vba.GPUVMMaxPageTableLevels,
 									mode_lib->vba.GPUVMEnable,
 									mode_lib->vba.DynamicMetadataEnable[k],
@@ -4770,15 +4773,15 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 									mode_lib->vba.UrgentLatencyPixelDataOnly,
 									mode_lib->vba.ExtraLatency,
 									mode_lib->vba.TimeCalc,
-									mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k],
-									mode_lib->vba.MetaRowBytes[k],
-									mode_lib->vba.DPTEBytesPerRow[k],
-									mode_lib->vba.PrefetchLinesY[k],
+									mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k],
+									mode_lib->vba.MetaRowBytes[0][0][k],
+									mode_lib->vba.DPTEBytesPerRow[0][0][k],
+									mode_lib->vba.PrefetchLinesY[0][0][k],
 									mode_lib->vba.SwathWidthYPerState[i][j][k],
 									mode_lib->vba.BytePerPixelInDETY[k],
 									mode_lib->vba.PrefillY[k],
 									mode_lib->vba.MaxNumSwY[k],
-									mode_lib->vba.PrefetchLinesC[k],
+									mode_lib->vba.PrefetchLinesC[0][0][k],
 									mode_lib->vba.BytePerPixelInDETC[k],
 									mode_lib->vba.PrefillC[k],
 									mode_lib->vba.MaxNumSwC[k],
@@ -4808,19 +4811,19 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				locals->prefetch_vm_bw_valid = true;
 				locals->prefetch_row_bw_valid = true;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-					if (locals->PDEAndMetaPTEBytesPerFrame[k] == 0)
+					if (locals->PDEAndMetaPTEBytesPerFrame[0][0][k] == 0)
 						locals->prefetch_vm_bw[k] = 0;
 					else if (locals->LinesForMetaPTE[k] > 0)
-						locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[k]
+						locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[0][0][k]
 							/ (locals->LinesForMetaPTE[k] * locals->HTotal[k] / locals->PixelClock[k]);
 					else {
 						locals->prefetch_vm_bw[k] = 0;
 						locals->prefetch_vm_bw_valid = false;
 					}
-					if (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k] == 0)
+					if (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k] == 0)
 						locals->prefetch_row_bw[k] = 0;
 					else if (locals->LinesForMetaAndDPTERow[k] > 0)
-						locals->prefetch_row_bw[k] = (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k])
+						locals->prefetch_row_bw[k] = (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k])
 							/ (locals->LinesForMetaAndDPTERow[k] * locals->HTotal[k] / locals->PixelClock[k]);
 					else {
 						locals->prefetch_row_bw[k] = 0;
@@ -4839,13 +4842,13 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 											mode_lib->vba.RequiredPrefetchPixelDataBWLuma[i][j][k])
 											+ mode_lib->vba.meta_row_bw[k] + mode_lib->vba.dpte_row_bw[k]);
 				}
-				locals->BandwidthWithoutPrefetchSupported[i] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i]) {
-					locals->BandwidthWithoutPrefetchSupported[i] = false;
+				locals->BandwidthWithoutPrefetchSupported[i][0] = true;
+				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]) {
+					locals->BandwidthWithoutPrefetchSupported[i][0] = false;
 				}
 
 				locals->PrefetchSupported[i][j] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i]) {
+				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]) {
 					locals->PrefetchSupported[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4870,7 +4873,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 			if (mode_lib->vba.PrefetchSupported[i][j] == true
 					&& mode_lib->vba.VRatioInPrefetchSupported[i][j] == true) {
 				mode_lib->vba.BandwidthAvailableForImmediateFlip =
-						mode_lib->vba.ReturnBWPerState[i];
+						mode_lib->vba.ReturnBWPerState[i][0];
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 					mode_lib->vba.BandwidthAvailableForImmediateFlip =
 							mode_lib->vba.BandwidthAvailableForImmediateFlip
@@ -4884,9 +4887,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 					if ((mode_lib->vba.SourcePixelFormat[k] != dm_420_8
 							&& mode_lib->vba.SourcePixelFormat[k] != dm_420_10)) {
 						mode_lib->vba.ImmediateFlipBytes[k] =
-								mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k]
-										+ mode_lib->vba.MetaRowBytes[k]
-										+ mode_lib->vba.DPTEBytesPerRow[k];
+								mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k]
+										+ mode_lib->vba.MetaRowBytes[0][0][k]
+										+ mode_lib->vba.DPTEBytesPerRow[0][0][k];
 					}
 				}
 				mode_lib->vba.TotImmediateFlipBytes = 0.0;
@@ -4914,9 +4917,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 									/ mode_lib->vba.PixelClock[k],
 							mode_lib->vba.VRatio[k],
 							mode_lib->vba.Tno_bw[k],
-							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k],
-							mode_lib->vba.MetaRowBytes[k],
-							mode_lib->vba.DPTEBytesPerRow[k],
+							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k],
+							mode_lib->vba.MetaRowBytes[0][0][k],
+							mode_lib->vba.DPTEBytesPerRow[0][0][k],
 							mode_lib->vba.DCCEnable[k],
 							mode_lib->vba.dpte_row_height[k],
 							mode_lib->vba.meta_row_height[k],
@@ -4941,7 +4944,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				}
 				mode_lib->vba.ImmediateFlipSupportedForState[i][j] = true;
 				if (mode_lib->vba.total_dcn_read_bw_with_flip
-						> mode_lib->vba.ReturnBWPerState[i]) {
+						> mode_lib->vba.ReturnBWPerState[i][0]) {
 					mode_lib->vba.ImmediateFlipSupportedForState[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4957,13 +4960,13 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 
 	/*Vertical Active BW support*/
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min(mode_lib->vba.ReturnBusWidth *
+		mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min(mode_lib->vba.ReturnBusWidth *
 				mode_lib->vba.DCFCLKPerState[i], mode_lib->vba.FabricAndDRAMBandwidthPerState[i] * 1000) *
 				mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation / 100;
-		if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i])
-			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = true;
+		if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0])
+			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = true;
 		else
-			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = false;
+			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = false;
 	}
 
 	/*PTE Buffer Size Check*/
@@ -5051,7 +5054,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				status = DML_FAIL_SCALE_RATIO_TAP;
 			} else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) {
 				status = DML_FAIL_SOURCE_PIXEL_FORMAT;
-			} else if (locals->ViewportSizeSupport[i] != true) {
+			} else if (locals->ViewportSizeSupport[i][0] != true) {
 				status = DML_FAIL_VIEWPORT_SIZE;
 			} else if (locals->DIOSupport[i] != true) {
 				status = DML_FAIL_DIO_SUPPORT;
@@ -5061,7 +5064,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				status = DML_FAIL_DSC_CLK_REQUIRED;
 			} else if (locals->UrgentLatencySupport[i][j] != true) {
 				status = DML_FAIL_URGENT_LATENCY;
-			} else if (locals->ROBSupport[i] != true) {
+			} else if (locals->ROBSupport[i][0] != true) {
 				status = DML_FAIL_REORDERING_BUFFER;
 			} else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) {
 				status = DML_FAIL_DISPCLK_DPPCLK;
@@ -5081,7 +5084,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				status = DML_FAIL_PITCH_SUPPORT;
 			} else if (locals->PrefetchSupported[i][j] != true) {
 				status = DML_FAIL_PREFETCH_SUPPORT;
-			} else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) {
+			} else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) {
 				status = DML_FAIL_TOTAL_V_ACTIVE_BW;
 			} else if (locals->VRatioInPrefetchSupported[i][j] != true) {
 				status = DML_FAIL_V_RATIO_PREFETCH;
@@ -5127,7 +5130,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 	mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel];
-	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel];
+	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0];
 	mode_lib->vba.FabricAndDRAMBandwidth = locals->FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel];
 	for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 		if (mode_lib->vba.BlendingAndTiming[k] == k) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
index 2c7455e22a65..ca807846032f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
@@ -107,10 +107,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format
 
 static bool is_dual_plane(enum source_format_class source_format)
 {
-	bool ret_val = 0;
+	bool ret_val = false;
 
 	if ((source_format == dm_420_8) || (source_format == dm_420_10))
-		ret_val = 1;
+		ret_val = true;
 
 	return ret_val;
 }
@@ -240,8 +240,8 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 	unsigned int swath_bytes_c = 0;
 	unsigned int full_swath_bytes_packed_l = 0;
 	unsigned int full_swath_bytes_packed_c = 0;
-	bool req128_l = 0;
-	bool req128_c = 0;
+	bool req128_l = false;
+	bool req128_c = false;
 	bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear);
 	bool surf_vert = (pipe_src_param.source_scan == dm_vert);
 	unsigned int log2_swath_height_l = 0;
@@ -264,13 +264,13 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 		total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request
-			req128_l = 0;
-			req128_c = 0;
+			req128_l = false;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		} else { //128b request (for luma only for yuv420 8bpc)
-			req128_l = 1;
-			req128_c = 0;
+			req128_l = true;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l / 2;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		}
@@ -280,9 +280,9 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 		total_swath_bytes = 2 * full_swath_bytes_packed_l;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes)
-			req128_l = 0;
+			req128_l = false;
 		else
-			req128_l = 1;
+			req128_l = true;
 
 		swath_bytes_l = total_swath_bytes;
 		swath_bytes_c = 0;
@@ -670,7 +670,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib,
 		const display_pipe_source_params_st pipe_src_param,
 		bool is_chroma)
 {
-	bool mode_422 = 0;
+	bool mode_422 = false;
 	unsigned int vp_width = 0;
 	unsigned int vp_height = 0;
 	unsigned int data_pitch = 0;
@@ -929,8 +929,7 @@ static void dml20_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 	min_dst_y_ttu_vblank = min_ttu_vblank * pclk_freq_in_mhz / (double) htotal;
 	dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start;
 
-	disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start
-			+ min_dst_y_ttu_vblank) * dml_pow(2, 2));
+	disp_dlg_regs->min_dst_y_next_start = (unsigned int) ((double) dlg_vblank_start * dml_pow(2, 2));
 	ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int) dml_pow(2, 18));
 
 	dml_print("DML_DLG: %s: min_dcfclk_mhz                         = %3.2f\n",
@@ -959,7 +958,7 @@ static void dml20_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 	// Source
 //             dcc_en              = src.dcc;
 	dual_plane = is_dual_plane((enum source_format_class)(src->source_format));
-	mode_422 = 0; // TODO
+	mode_422 = false; // TODO
 	access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed
 //      bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0);
 //      bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
index 1e6aeb1bd2bf..287b7a0ad108 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
@@ -107,10 +107,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format
 
 static bool is_dual_plane(enum source_format_class source_format)
 {
-	bool ret_val = 0;
+	bool ret_val = false;
 
 	if ((source_format == dm_420_8) || (source_format == dm_420_10))
-		ret_val = 1;
+		ret_val = true;
 
 	return ret_val;
 }
@@ -240,8 +240,8 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 	unsigned int swath_bytes_c = 0;
 	unsigned int full_swath_bytes_packed_l = 0;
 	unsigned int full_swath_bytes_packed_c = 0;
-	bool req128_l = 0;
-	bool req128_c = 0;
+	bool req128_l = false;
+	bool req128_c = false;
 	bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear);
 	bool surf_vert = (pipe_src_param.source_scan == dm_vert);
 	unsigned int log2_swath_height_l = 0;
@@ -264,13 +264,13 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 		total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request
-			req128_l = 0;
-			req128_c = 0;
+			req128_l = false;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		} else { //128b request (for luma only for yuv420 8bpc)
-			req128_l = 1;
-			req128_c = 0;
+			req128_l = true;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l / 2;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		}
@@ -280,9 +280,9 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 		total_swath_bytes = 2 * full_swath_bytes_packed_l;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes)
-			req128_l = 0;
+			req128_l = false;
 		else
-			req128_l = 1;
+			req128_l = true;
 
 		swath_bytes_l = total_swath_bytes;
 		swath_bytes_c = 0;
@@ -670,7 +670,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib,
 		const display_pipe_source_params_st pipe_src_param,
 		bool is_chroma)
 {
-	bool mode_422 = 0;
+	bool mode_422 = false;
 	unsigned int vp_width = 0;
 	unsigned int vp_height = 0;
 	unsigned int data_pitch = 0;
@@ -959,7 +959,7 @@ static void dml20v2_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 	// Source
 //             dcc_en              = src.dcc;
 	dual_plane = is_dual_plane((enum source_format_class)(src->source_format));
-	mode_422 = 0; // TODO
+	mode_422 = false; // TODO
 	access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed
 //      bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0);
 //      bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index ba77957aefe3..af35b3bea909 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #include "../display_mode_lib.h"
 #include "../dml_inline_defs.h"
@@ -198,7 +197,7 @@ static unsigned int CalculateVMAndRowBytes(
 		unsigned int *meta_row_width,
 		unsigned int *meta_row_height,
 		unsigned int *vm_group_bytes,
-		long         *dpte_group_bytes,
+		unsigned int *dpte_group_bytes,
 		unsigned int *PixelPTEReqWidth,
 		unsigned int *PixelPTEReqHeight,
 		unsigned int *PTERequestSize,
@@ -296,7 +295,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		double UrgentOutOfOrderReturn,
 		double ReturnBW,
 		bool GPUVMEnable,
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		unsigned int MetaChunkSize,
 		double UrgentLatency,
 		double ExtraLatency,
@@ -310,13 +309,13 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		int DPPPerPlane[],
 		bool DCCEnable[],
 		double DPPCLK[],
-		unsigned int SwathWidthSingleDPPY[],
+		double SwathWidthSingleDPPY[],
 		unsigned int SwathHeightY[],
 		double ReadBandwidthPlaneLuma[],
 		unsigned int SwathHeightC[],
 		double ReadBandwidthPlaneChroma[],
 		unsigned int LBBitPerPixel[],
-		unsigned int SwathWidthY[],
+		double SwathWidthY[],
 		double HRatio[],
 		unsigned int vtaps[],
 		unsigned int VTAPsChroma[],
@@ -345,7 +344,7 @@ static void CalculateDCFCLKDeepSleep(
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
 		double VRatio[],
-		unsigned int SwathWidthY[],
+		double SwathWidthY[],
 		int DPPPerPlane[],
 		double HRatio[],
 		double PixelClock[],
@@ -436,7 +435,7 @@ static void CalculateMetaAndPTETimes(
 		unsigned int           meta_row_height[],
 		unsigned int           meta_req_width[],
 		unsigned int           meta_req_height[],
-		long                   dpte_group_bytes[],
+		int                   dpte_group_bytes[],
 		unsigned int           PTERequestSizeY[],
 		unsigned int           PTERequestSizeC[],
 		unsigned int           PixelPTEReqWidthY[],
@@ -478,7 +477,7 @@ static double CalculateExtraLatency(
 		bool HostVMEnable,
 		int NumberOfActivePlanes,
 		int NumberOfDPP[],
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
 		double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
 		int HostVMMaxPageTableLevels,
@@ -1281,7 +1280,7 @@ static unsigned int CalculateVMAndRowBytes(
 		unsigned int *meta_row_width,
 		unsigned int *meta_row_height,
 		unsigned int *vm_group_bytes,
-		long         *dpte_group_bytes,
+		unsigned int *dpte_group_bytes,
 		unsigned int *PixelPTEReqWidth,
 		unsigned int *PixelPTEReqHeight,
 		unsigned int *PTERequestSize,
@@ -1339,7 +1338,7 @@ static unsigned int CalculateVMAndRowBytes(
 		*MetaRowByte = 0;
 	}
 
-	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) {
+	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) {
 		MacroTileSizeBytes = 256;
 		MacroTileHeight = BlockHeight256Bytes;
 	} else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x
@@ -1684,11 +1683,11 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		else
 			locals->SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k];
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true)
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 			MainPlaneDoesODMCombine = true;
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j)
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true)
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 				MainPlaneDoesODMCombine = true;
 
 		if (MainPlaneDoesODMCombine == true)
@@ -2941,12 +2940,12 @@ static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
 			SwathWidth = mode_lib->vba.ViewportHeight[k];
 		}
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true) {
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 			MainPlaneDoesODMCombine = true;
 		}
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) {
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true) {
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 				MainPlaneDoesODMCombine = true;
 			}
 		}
@@ -3454,7 +3453,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 										== dm_420_10))
 				|| (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl
 						|| mode_lib->vba.SurfaceTiling[k]
-								== dm_sw_gfx7_2d_thin_lvp)
+								== dm_sw_gfx7_2d_thin_l_vp)
 						&& !((mode_lib->vba.SourcePixelFormat[k]
 								== dm_444_64
 								|| mode_lib->vba.SourcePixelFormat[k]
@@ -3543,17 +3542,17 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 		}
 	}
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		locals->IdealSDPPortBandwidthPerState[i] = dml_min3(
+		locals->IdealSDPPortBandwidthPerState[i][0] = dml_min3(
 				mode_lib->vba.ReturnBusWidth * mode_lib->vba.DCFCLKPerState[i],
 				mode_lib->vba.DRAMSpeedPerState[i] * mode_lib->vba.NumberOfChannels
 						* mode_lib->vba.DRAMChannelWidth,
 				mode_lib->vba.FabricClockPerState[i]
 						* mode_lib->vba.FabricDatapathToDCNDataReturn);
 		if (mode_lib->vba.HostVMEnable == false) {
-			locals->ReturnBWPerState[i] = locals->IdealSDPPortBandwidthPerState[i]
+			locals->ReturnBWPerState[i][0] = locals->IdealSDPPortBandwidthPerState[i][0]
 					* mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100.0;
 		} else {
-			locals->ReturnBWPerState[i] = locals->IdealSDPPortBandwidthPerState[i]
+			locals->ReturnBWPerState[i][0] = locals->IdealSDPPortBandwidthPerState[i][0]
 					* mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / 100.0;
 		}
 	}
@@ -3590,12 +3589,12 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				+ dml_max3(mode_lib->vba.UrgentOutOfOrderReturnPerChannelPixelDataOnly,
 						mode_lib->vba.UrgentOutOfOrderReturnPerChannelPixelMixedWithVMData,
 						mode_lib->vba.UrgentOutOfOrderReturnPerChannelVMDataOnly)
-					* mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i];
-		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i]
+					* mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0];
+		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0]
 				> locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) {
-			locals->ROBSupport[i] = true;
+			locals->ROBSupport[i][0] = true;
 		} else {
-			locals->ROBSupport[i] = false;
+			locals->ROBSupport[i][0] = false;
 		}
 	}
 	/*Writeback Mode Support Check*/
@@ -3983,7 +3982,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity
 						&& locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]
-						&& locals->ODMCombineEnablePerState[i][k] == false) {
+						&& locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->NoOfDPP[i][j][k] = 1;
 					locals->RequiredDPPCLK[i][j][k] =
 						locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0);
@@ -4072,16 +4071,16 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	/*Viewport Size Check*/
 
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		locals->ViewportSizeSupport[i] = true;
+		locals->ViewportSizeSupport[i][0] = true;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			if (locals->ODMCombineEnablePerState[i][k] == true) {
+			if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 				if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]))
 						> locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			} else {
 				if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			}
 		}
@@ -4122,11 +4121,11 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	}
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			locals->RequiresDSC[i][k] = 0;
+			locals->RequiresDSC[i][k] = false;
 			locals->RequiresFEC[i][k] = 0;
 			if (mode_lib->vba.BlendingAndTiming[k] == k) {
 				if (mode_lib->vba.Output[k] == dm_hdmi) {
-					locals->RequiresDSC[i][k] = 0;
+					locals->RequiresDSC[i][k] = false;
 					locals->RequiresFEC[i][k] = 0;
 					locals->OutputBppPerState[i][k] = TruncToValidBPP(
 							dml_min(600.0, mode_lib->vba.PHYCLKPerState[i]) / mode_lib->vba.PixelClockBackEnd[k] * 24,
@@ -4270,8 +4269,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						mode_lib->vba.DSCFormatFactor = 1;
 					}
 					if (locals->RequiresDSC[i][k] == true) {
-						if (locals->ODMCombineEnablePerState[i][k]
-								== true) {
+						if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 							if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor
 									> (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) {
 								locals->DSCCLKRequiredMoreThanSupported[i] =
@@ -4294,7 +4292,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 		mode_lib->vba.TotalDSCUnitsRequired = 0.0;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 			if (locals->RequiresDSC[i][k] == true) {
-				if (locals->ODMCombineEnablePerState[i][k] == true) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 					mode_lib->vba.TotalDSCUnitsRequired =
 							mode_lib->vba.TotalDSCUnitsRequired + 2.0;
 				} else {
@@ -4336,7 +4334,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.bpp = locals->OutputBppPerState[i][k];
 			}
 			if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) {
-				if (locals->ODMCombineEnablePerState[i][k] == false) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->DSCDelayPerState[i][k] =
 							dscceComputeDelay(
 									mode_lib->vba.DSCInputBitPerComponent[k],
@@ -4400,7 +4398,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				locals->RequiredDPPCLKThisState[k] = locals->RequiredDPPCLK[i][j][k];
 				locals->NoOfDPPThisState[k]        = locals->NoOfDPP[i][j][k];
-				if (locals->ODMCombineEnablePerState[i][k] == true) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 					locals->SwathWidthYThisState[k] =
 						dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]));
 				} else {
@@ -4452,7 +4450,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					locals->PSCL_FACTOR,
 					locals->PSCL_FACTOR_CHROMA,
 					locals->RequiredDPPCLKThisState,
-					&mode_lib->vba.ProjectedDCFCLKDeepSleep);
+					&mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0]);
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				if ((mode_lib->vba.SourcePixelFormat[k] != dm_444_64
@@ -4497,7 +4495,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							locals->PTERequestSizeC,
 							locals->dpde0_bytes_per_frame_ub_c,
 							locals->meta_pte_bytes_per_frame_ub_c);
-					locals->PrefetchLinesC[k] = CalculatePrefetchSourceLines(
+					locals->PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines(
 							mode_lib,
 							mode_lib->vba.VRatio[k]/2,
 							mode_lib->vba.VTAPsChroma[k],
@@ -4512,7 +4510,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0;
 					mode_lib->vba.MetaRowBytesC = 0.0;
 					mode_lib->vba.DPTEBytesPerRowC = 0.0;
-					locals->PrefetchLinesC[k] = 0.0;
+					locals->PrefetchLinesC[0][0][k] = 0.0;
 					locals->PTEBufferSizeNotExceededC[i][j][k] = true;
 					locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma;
 				}
@@ -4553,7 +4551,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						locals->PTERequestSizeY,
 						locals->dpde0_bytes_per_frame_ub_l,
 						locals->meta_pte_bytes_per_frame_ub_l);
-				locals->PrefetchLinesY[k] = CalculatePrefetchSourceLines(
+				locals->PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines(
 						mode_lib,
 						mode_lib->vba.VRatio[k],
 						mode_lib->vba.vtaps[k],
@@ -4563,10 +4561,10 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						mode_lib->vba.ViewportYStartY[k],
 						&locals->PrefillY[k],
 						&locals->MaxNumSwY[k]);
-				locals->PDEAndMetaPTEBytesPerFrame[k] =
+				locals->PDEAndMetaPTEBytesPerFrame[0][0][k] =
 						mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC;
-				locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
-				locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
+				locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
+				locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
 
 				CalculateActiveRowBandwidth(
 						mode_lib->vba.GPUVMEnable,
@@ -4592,7 +4590,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.PixelChunkSizeInKByte,
 					locals->TotalNumberOfDCCActiveDPP[i][j],
 					mode_lib->vba.MetaChunkSize,
-					locals->ReturnBWPerState[i],
+					locals->ReturnBWPerState[i][0],
 					mode_lib->vba.GPUVMEnable,
 					mode_lib->vba.HostVMEnable,
 					mode_lib->vba.NumberOfActivePlanes,
@@ -4603,7 +4601,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.HostVMMaxPageTableLevels,
 					mode_lib->vba.HostVMCachedPageTableLevels);
 
-			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep;
+			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				if (mode_lib->vba.BlendingAndTiming[k] == k) {
 					if (mode_lib->vba.WritebackEnable[k] == true) {
@@ -4645,15 +4643,15 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					}
 				}
 			}
-			mode_lib->vba.MaxMaxVStartup = 0;
+			mode_lib->vba.MaxMaxVStartup[0][0] = 0;
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
+				locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
 					- dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0));
-				mode_lib->vba.MaxMaxVStartup = dml_max(mode_lib->vba.MaxMaxVStartup, locals->MaximumVStartup[k]);
+				mode_lib->vba.MaxMaxVStartup[0][0] = dml_max(mode_lib->vba.MaxMaxVStartup[0][0], locals->MaximumVStartup[0][0][k]);
 			}
 
 			mode_lib->vba.NextPrefetchMode = mode_lib->vba.MinPrefetchMode;
-			mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup;
+			mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup[0][0];
 			do {
 				mode_lib->vba.PrefetchMode[i][j] = mode_lib->vba.NextPrefetchMode;
 				mode_lib->vba.MaxVStartup = mode_lib->vba.NextMaxVStartup;
@@ -4694,7 +4692,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					myPipe.DPPCLK = locals->RequiredDPPCLK[i][j][k];
 					myPipe.DISPCLK = locals->RequiredDISPCLK[i][j];
 					myPipe.PixelClock = mode_lib->vba.PixelClock[k];
-					myPipe.DCFCLKDeepSleep = mode_lib->vba.ProjectedDCFCLKDeepSleep;
+					myPipe.DCFCLKDeepSleep = mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
 					myPipe.DPPPerPlane = locals->NoOfDPP[i][j][k];
 					myPipe.ScalerEnabled = mode_lib->vba.ScalerEnabled[k];
 					myPipe.SourceScan = mode_lib->vba.SourceScan[k];
@@ -4728,8 +4726,8 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							locals->SwathWidthYThisState[k] / mode_lib->vba.HRatio[k],
 							mode_lib->vba.OutputFormat[k],
 							mode_lib->vba.MaxInterDCNTileRepeaters,
-							dml_min(mode_lib->vba.MaxVStartup, locals->MaximumVStartup[k]),
-							locals->MaximumVStartup[k],
+							dml_min(mode_lib->vba.MaxVStartup, locals->MaximumVStartup[0][0][k]),
+							locals->MaximumVStartup[0][0][k],
 							mode_lib->vba.GPUVMMaxPageTableLevels,
 							mode_lib->vba.GPUVMEnable,
 							&myHostVM,
@@ -4740,15 +4738,15 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							mode_lib->vba.UrgentLatency,
 							mode_lib->vba.ExtraLatency,
 							mode_lib->vba.TimeCalc,
-							locals->PDEAndMetaPTEBytesPerFrame[k],
-							locals->MetaRowBytes[k],
-							locals->DPTEBytesPerRow[k],
-							locals->PrefetchLinesY[k],
+							locals->PDEAndMetaPTEBytesPerFrame[0][0][k],
+							locals->MetaRowBytes[0][0][k],
+							locals->DPTEBytesPerRow[0][0][k],
+							locals->PrefetchLinesY[0][0][k],
 							locals->SwathWidthYThisState[k],
 							locals->BytePerPixelInDETY[k],
 							locals->PrefillY[k],
 							locals->MaxNumSwY[k],
-							locals->PrefetchLinesC[k],
+							locals->PrefetchLinesC[0][0][k],
 							locals->BytePerPixelInDETC[k],
 							locals->PrefillC[k],
 							locals->MaxNumSwC[k],
@@ -4837,14 +4835,14 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						+ locals->RequiredPrefetchPixelDataBWChroma[i][j][k] * locals->UrgentBurstFactorChromaPre[k]
 						+ locals->cursor_bw_pre[k] * locals->UrgentBurstFactorCursorPre[k]);
 				}
-				locals->BandwidthWithoutPrefetchSupported[i] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i]
+				locals->BandwidthWithoutPrefetchSupported[i][0] = true;
+				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]
 						|| locals->NotEnoughUrgentLatencyHiding == 1) {
-					locals->BandwidthWithoutPrefetchSupported[i] = false;
+					locals->BandwidthWithoutPrefetchSupported[i][0] = false;
 				}
 
 				locals->PrefetchSupported[i][j] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i]
+				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]
 						|| locals->NotEnoughUrgentLatencyHiding == 1
 						|| locals->NotEnoughUrgentLatencyHidingPre == 1) {
 					locals->PrefetchSupported[i][j] = false;
@@ -4873,17 +4871,17 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 
 				if (mode_lib->vba.MaxVStartup <= 13 || mode_lib->vba.AnyLinesForVMOrRowTooLarge == false) {
-					mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup;
+					mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup[0][0];
 					mode_lib->vba.NextPrefetchMode = mode_lib->vba.NextPrefetchMode + 1;
 				} else {
 					mode_lib->vba.NextMaxVStartup = mode_lib->vba.NextMaxVStartup - 1;
 				}
 			} while ((locals->PrefetchSupported[i][j] != true || locals->VRatioInPrefetchSupported[i][j] != true)
-					&& (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup
+					&& (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup[0][0]
 						|| mode_lib->vba.NextPrefetchMode < mode_lib->vba.MaxPrefetchMode));
 
 			if (locals->PrefetchSupported[i][j] == true && locals->VRatioInPrefetchSupported[i][j] == true) {
-				mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i];
+				mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i][0];
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 					mode_lib->vba.BandwidthAvailableForImmediateFlip = mode_lib->vba.BandwidthAvailableForImmediateFlip
 						- dml_max(locals->ReadBandwidthLuma[k] * locals->UrgentBurstFactorLuma[k]
@@ -4896,7 +4894,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.TotImmediateFlipBytes = 0.0;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 					mode_lib->vba.TotImmediateFlipBytes = mode_lib->vba.TotImmediateFlipBytes
-						+ locals->PDEAndMetaPTEBytesPerFrame[k] + locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k];
+						+ locals->PDEAndMetaPTEBytesPerFrame[0][0][k] + locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k];
 				}
 
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4911,9 +4909,9 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							mode_lib->vba.HostVMMaxPageTableLevels,
 							mode_lib->vba.HostVMCachedPageTableLevels,
 							mode_lib->vba.GPUVMEnable,
-							locals->PDEAndMetaPTEBytesPerFrame[k],
-							locals->MetaRowBytes[k],
-							locals->DPTEBytesPerRow[k],
+							locals->PDEAndMetaPTEBytesPerFrame[0][0][k],
+							locals->MetaRowBytes[0][0][k],
+							locals->DPTEBytesPerRow[0][0][k],
 							mode_lib->vba.BandwidthAvailableForImmediateFlip,
 							mode_lib->vba.TotImmediateFlipBytes,
 							mode_lib->vba.SourcePixelFormat[k],
@@ -4944,7 +4942,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				locals->ImmediateFlipSupportedForState[i][j] = true;
 				if (mode_lib->vba.total_dcn_read_bw_with_flip
-						> locals->ReturnBWPerState[i]) {
+						> locals->ReturnBWPerState[i][0]) {
 					locals->ImmediateFlipSupportedForState[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4971,7 +4969,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.WritebackInterfaceChromaBufferSize,
 					mode_lib->vba.DCFCLKPerState[i],
 					mode_lib->vba.UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels,
-					locals->ReturnBWPerState[i],
+					locals->ReturnBWPerState[i][0],
 					mode_lib->vba.GPUVMEnable,
 					locals->dpte_group_bytes,
 					mode_lib->vba.MetaChunkSize,
@@ -4983,7 +4981,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.DRAMClockChangeLatency,
 					mode_lib->vba.SRExitTime,
 					mode_lib->vba.SREnterPlusExitTime,
-					mode_lib->vba.ProjectedDCFCLKDeepSleep,
+					mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 					locals->NoOfDPPThisState,
 					mode_lib->vba.DCCEnable,
 					locals->RequiredDPPCLKThisState,
@@ -5026,8 +5024,8 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				MaxTotalVActiveRDBandwidth = MaxTotalVActiveRDBandwidth + locals->ReadBandwidth[k];
 		}
 		for (i = 0; i <= mode_lib->vba.soc.num_states; ++i) {
-			locals->MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min(
-				locals->IdealSDPPortBandwidthPerState[i] *
+			locals->MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min(
+				locals->IdealSDPPortBandwidthPerState[i][0] *
 				mode_lib->vba.MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation
 				/ 100.0, mode_lib->vba.DRAMSpeedPerState[i] *
 				mode_lib->vba.NumberOfChannels *
@@ -5035,10 +5033,10 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation
 				/ 100.0);
 
-			if (MaxTotalVActiveRDBandwidth <= locals->MaxTotalVerticalActiveAvailableBandwidth[i]) {
-				locals->TotalVerticalActiveBandwidthSupport[i] = true;
+			if (MaxTotalVActiveRDBandwidth <= locals->MaxTotalVerticalActiveAvailableBandwidth[i][0]) {
+				locals->TotalVerticalActiveBandwidthSupport[i][0] = true;
 			} else {
-				locals->TotalVerticalActiveBandwidthSupport[i] = false;
+				locals->TotalVerticalActiveBandwidthSupport[i][0] = false;
 			}
 		}
 	}
@@ -5117,7 +5115,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_SCALE_RATIO_TAP;
 			} else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) {
 				status = DML_FAIL_SOURCE_PIXEL_FORMAT;
-			} else if (locals->ViewportSizeSupport[i] != true) {
+			} else if (locals->ViewportSizeSupport[i][0] != true) {
 				status = DML_FAIL_VIEWPORT_SIZE;
 			} else if (locals->DIOSupport[i] != true) {
 				status = DML_FAIL_DIO_SUPPORT;
@@ -5125,7 +5123,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_NOT_ENOUGH_DSC;
 			} else if (locals->DSCCLKRequiredMoreThanSupported[i] != false) {
 				status = DML_FAIL_DSC_CLK_REQUIRED;
-			} else if (locals->ROBSupport[i] != true) {
+			} else if (locals->ROBSupport[i][0] != true) {
 				status = DML_FAIL_REORDERING_BUFFER;
 			} else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) {
 				status = DML_FAIL_DISPCLK_DPPCLK;
@@ -5143,7 +5141,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_CURSOR_SUPPORT;
 			} else if (mode_lib->vba.PitchSupport != true) {
 				status = DML_FAIL_PITCH_SUPPORT;
-			} else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) {
+			} else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) {
 				status = DML_FAIL_TOTAL_V_ACTIVE_BW;
 			} else if (locals->PTEBufferSizeNotExceeded[i][j] != true) {
 				status = DML_FAIL_PTE_BUFFER_SIZE;
@@ -5199,13 +5197,13 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel];
-	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel];
+	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0];
 	for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 		if (mode_lib->vba.BlendingAndTiming[k] == k) {
 			mode_lib->vba.ODMCombineEnabled[k] =
 					locals->ODMCombineEnablePerState[mode_lib->vba.VoltageLevel][k];
 		} else {
-			mode_lib->vba.ODMCombineEnabled[k] = 0;
+			mode_lib->vba.ODMCombineEnabled[k] = false;
 		}
 		mode_lib->vba.DSCEnabled[k] =
 				locals->RequiresDSC[mode_lib->vba.VoltageLevel][k];
@@ -5228,7 +5226,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		double UrgentOutOfOrderReturn,
 		double ReturnBW,
 		bool GPUVMEnable,
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		unsigned int MetaChunkSize,
 		double UrgentLatency,
 		double ExtraLatency,
@@ -5242,13 +5240,13 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		int DPPPerPlane[],
 		bool DCCEnable[],
 		double DPPCLK[],
-		unsigned int SwathWidthSingleDPPY[],
+		double SwathWidthSingleDPPY[],
 		unsigned int SwathHeightY[],
 		double ReadBandwidthPlaneLuma[],
 		unsigned int SwathHeightC[],
 		double ReadBandwidthPlaneChroma[],
 		unsigned int LBBitPerPixel[],
-		unsigned int SwathWidthY[],
+		double SwathWidthY[],
 		double HRatio[],
 		unsigned int vtaps[],
 		unsigned int VTAPsChroma[],
@@ -5504,7 +5502,7 @@ static void CalculateDCFCLKDeepSleep(
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
 		double VRatio[],
-		unsigned int SwathWidthY[],
+		double SwathWidthY[],
 		int DPPPerPlane[],
 		double HRatio[],
 		double PixelClock[],
@@ -5832,7 +5830,7 @@ static void CalculateMetaAndPTETimes(
 		unsigned int meta_row_height[],
 		unsigned int meta_req_width[],
 		unsigned int meta_req_height[],
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		unsigned int PTERequestSizeY[],
 		unsigned int PTERequestSizeC[],
 		unsigned int PixelPTEReqWidthY[],
@@ -6088,7 +6086,7 @@ static double CalculateExtraLatency(
 		bool HostVMEnable,
 		int NumberOfActivePlanes,
 		int NumberOfDPP[],
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
 		double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
 		int HostVMMaxPageTableLevels,
@@ -6126,4 +6124,3 @@ static double CalculateExtraLatency(
 	return CalculateExtraLatency;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
index a1f207cbb966..a38baa73d484 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #include "../display_mode_lib.h"
 #include "../display_mode_vba.h"
@@ -83,10 +82,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format
 
 static bool is_dual_plane(enum source_format_class source_format)
 {
-	bool ret_val = 0;
+	bool ret_val = false;
 
 	if ((source_format == dm_420_8) || (source_format == dm_420_10))
-		ret_val = 1;
+		ret_val = true;
 
 	return ret_val;
 }
@@ -223,8 +222,8 @@ static void handle_det_buf_split(
 	unsigned int swath_bytes_c = 0;
 	unsigned int full_swath_bytes_packed_l = 0;
 	unsigned int full_swath_bytes_packed_c = 0;
-	bool req128_l = 0;
-	bool req128_c = 0;
+	bool req128_l = false;
+	bool req128_c = false;
 	bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear);
 	bool surf_vert = (pipe_src_param.source_scan == dm_vert);
 	unsigned int log2_swath_height_l = 0;
@@ -249,13 +248,13 @@ static void handle_det_buf_split(
 		total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request
-			req128_l = 0;
-			req128_c = 0;
+			req128_l = false;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		} else { //128b request (for luma only for yuv420 8bpc)
-			req128_l = 1;
-			req128_c = 0;
+			req128_l = true;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l / 2;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		}
@@ -265,9 +264,9 @@ static void handle_det_buf_split(
 		total_swath_bytes = 2 * full_swath_bytes_packed_l;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes)
-			req128_l = 0;
+			req128_l = false;
 		else
-			req128_l = 1;
+			req128_l = true;
 
 		swath_bytes_l = total_swath_bytes;
 		swath_bytes_c = 0;
@@ -680,7 +679,7 @@ static void get_surf_rq_param(
 		const display_pipe_params_st pipe_param,
 		bool is_chroma)
 {
-	bool mode_422 = 0;
+	bool mode_422 = false;
 	unsigned int vp_width = 0;
 	unsigned int vp_height = 0;
 	unsigned int data_pitch = 0;
@@ -1011,7 +1010,7 @@ static void dml_rq_dlg_get_dlg_params(
 	// Source
 	//             dcc_en              = src.dcc;
 	dual_plane = is_dual_plane((enum source_format_class) (src->source_format));
-	mode_422 = 0; // FIXME
+	mode_422 = false; // FIXME
 	access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed
 						    //      bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0);
 						    //      bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1);
@@ -1523,8 +1522,8 @@ static void dml_rq_dlg_get_dlg_params(
 
 	disp_dlg_regs->refcyc_per_vm_group_vblank   = get_refcyc_per_vm_group_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
 	disp_dlg_regs->refcyc_per_vm_group_flip     = get_refcyc_per_vm_group_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
-	disp_dlg_regs->refcyc_per_vm_req_vblank     = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;;
-	disp_dlg_regs->refcyc_per_vm_req_flip       = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;;
+	disp_dlg_regs->refcyc_per_vm_req_vblank     = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
+	disp_dlg_regs->refcyc_per_vm_req_flip       = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
 
 	// Clamp to max for now
 	if (disp_dlg_regs->refcyc_per_vm_group_vblank >= (unsigned int)dml_pow(2, 23))
@@ -1820,4 +1819,3 @@ static void calculate_ttu_cursor(
 	}
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
index 1c97083b8d0b..bfc2f39bd1ef 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
@@ -85,7 +85,7 @@ enum dm_swizzle_mode {
 	dm_sw_var_s_x = 29,
 	dm_sw_var_d_x = 30,
 	dm_sw_64kb_r_x,
-	dm_sw_gfx7_2d_thin_lvp,
+	dm_sw_gfx7_2d_thin_l_vp,
 	dm_sw_gfx7_2d_thin_gl,
 };
 enum lb_depth {
@@ -119,6 +119,10 @@ enum mpc_combine_affinity {
 	dm_mpc_never
 };
 
+enum RequestType {
+	REQ_256Bytes, REQ_128BytesNonContiguous, REQ_128BytesContiguous, REQ_NA
+};
+
 enum self_refresh_affinity {
 	dm_try_to_allow_self_refresh_and_mclk_switch,
 	dm_allow_self_refresh_and_mclk_switch,
@@ -135,9 +139,7 @@ enum dm_validation_status {
 	DML_FAIL_DIO_SUPPORT,
 	DML_FAIL_NOT_ENOUGH_DSC,
 	DML_FAIL_DSC_CLK_REQUIRED,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	DML_FAIL_DSC_VALIDATION_FAILURE,
-#endif
 	DML_FAIL_URGENT_LATENCY,
 	DML_FAIL_REORDERING_BUFFER,
 	DML_FAIL_DISPCLK_DPPCLK,
@@ -167,4 +169,16 @@ enum odm_combine_mode {
 	dm_odm_combine_mode_4to1,
 };
 
+enum odm_combine_policy {
+	dm_odm_combine_policy_dal,
+	dm_odm_combine_policy_none,
+	dm_odm_combine_policy_2to1,
+	dm_odm_combine_policy_4to1,
+};
+
+enum immediate_flip_requirement {
+	dm_immediate_flip_not_required,
+	dm_immediate_flip_required,
+};
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
index 704efefdcba8..2689401a03a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
@@ -25,18 +25,13 @@
 
 #include "display_mode_lib.h"
 #include "dc_features.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dcn20/display_mode_vba_20.h"
 #include "dcn20/display_rq_dlg_calc_20.h"
 #include "dcn20/display_mode_vba_20v2.h"
 #include "dcn20/display_rq_dlg_calc_20v2.h"
-#endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 #include "dcn21/display_mode_vba_21.h"
 #include "dcn21/display_rq_dlg_calc_21.h"
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 const struct dml_funcs dml20_funcs = {
 	.validate = dml20_ModeSupportAndSystemConfigurationFull,
 	.recalculate = dml20_recalculate,
@@ -50,16 +45,13 @@ const struct dml_funcs dml20v2_funcs = {
 	.rq_dlg_get_dlg_reg = dml20v2_rq_dlg_get_dlg_reg,
 	.rq_dlg_get_rq_reg = dml20v2_rq_dlg_get_rq_reg
 };
-#endif
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 const struct dml_funcs dml21_funcs = {
         .validate = dml21_ModeSupportAndSystemConfigurationFull,
         .recalculate = dml21_recalculate,
         .rq_dlg_get_dlg_reg = dml21_rq_dlg_get_dlg_reg,
         .rq_dlg_get_rq_reg = dml21_rq_dlg_get_rq_reg
 };
-#endif
 
 void dml_init_instance(struct display_mode_lib *lib,
 		const struct _vcs_dpi_soc_bounding_box_st *soc_bb,
@@ -70,19 +62,15 @@ void dml_init_instance(struct display_mode_lib *lib,
 	lib->ip = *ip_params;
 	lib->project = project;
 	switch (project) {
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	case DML_PROJECT_NAVI10:
 		lib->funcs = dml20_funcs;
 		break;
 	case DML_PROJECT_NAVI10v2:
 		lib->funcs = dml20v2_funcs;
 		break;
-#endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
         case DML_PROJECT_DCN21:
                 lib->funcs = dml21_funcs;
                 break;
-#endif
 
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
index d8c59aa356b6..cf2758ca5b02 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
@@ -27,20 +27,14 @@
 
 
 #include "dml_common_defs.h"
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #include "display_mode_vba.h"
-#endif
 
 enum dml_project {
 	DML_PROJECT_UNDEFINED,
 	DML_PROJECT_RAVEN1,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	DML_PROJECT_NAVI10,
 	DML_PROJECT_NAVI10v2,
-#endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	DML_PROJECT_DCN21,
-#endif
 };
 
 struct display_mode_lib;
@@ -70,9 +64,7 @@ struct display_mode_lib {
 	struct _vcs_dpi_ip_params_st ip;
 	struct _vcs_dpi_soc_bounding_box_st soc;
 	enum dml_project project;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct vba_vars_st vba;
-#endif
 	struct dal_logger *logger;
 	struct dml_funcs funcs;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index cfacd6027467..658f81e757e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -63,6 +63,7 @@ struct _vcs_dpi_voltage_scaling_st {
 	double dispclk_mhz;
 	double phyclk_mhz;
 	double dppclk_mhz;
+	double dtbclk_mhz;
 };
 
 struct _vcs_dpi_soc_bounding_box_st {
@@ -99,6 +100,7 @@ struct _vcs_dpi_soc_bounding_box_st {
 	unsigned int num_chans;
 	unsigned int vmm_page_size_bytes;
 	unsigned int hostvm_min_page_size_bytes;
+	unsigned int gpuvm_min_page_size_bytes;
 	double dram_clock_change_latency_us;
 	double dummy_pstate_latency_us;
 	double writeback_dram_clock_change_latency_us;
@@ -112,6 +114,7 @@ struct _vcs_dpi_soc_bounding_box_st {
 	bool do_urgent_latency_adjustment;
 	double urgent_latency_adjustment_fabric_clock_component_us;
 	double urgent_latency_adjustment_fabric_clock_reference_mhz;
+	bool disable_dram_clock_change_vactive_support;
 };
 
 struct _vcs_dpi_ip_params_st {
@@ -145,7 +148,6 @@ struct _vcs_dpi_ip_params_st {
 	unsigned int writeback_interface_buffer_size_kbytes;
 	unsigned int writeback_line_buffer_buffer_size;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	unsigned int writeback_10bpc420_supported;
 	double writeback_max_hscl_ratio;
 	double writeback_max_vscl_ratio;
@@ -155,7 +157,6 @@ struct _vcs_dpi_ip_params_st {
 	unsigned int writeback_max_vscl_taps;
 	unsigned int writeback_line_buffer_luma_buffer_size;
 	unsigned int writeback_line_buffer_chroma_buffer_size;
-#endif
 
 	unsigned int max_page_table_levels;
 	unsigned int max_num_dpp;
@@ -214,6 +215,7 @@ struct _vcs_dpi_display_pipe_source_params_st {
 	int source_format;
 	unsigned char dcc;
 	unsigned int dcc_rate;
+	unsigned int dcc_rate_chroma;
 	unsigned char dcc_use_global;
 	unsigned char vm;
 	bool gpuvm;    // gpuvm enabled
@@ -225,6 +227,10 @@ struct _vcs_dpi_display_pipe_source_params_st {
 	int source_scan;
 	int sw_mode;
 	int macro_tile_size;
+	unsigned int surface_width_y;
+	unsigned int surface_height_y;
+	unsigned int surface_width_c;
+	unsigned int surface_height_c;
 	unsigned int viewport_width;
 	unsigned int viewport_height;
 	unsigned int viewport_y_y;
@@ -277,6 +283,7 @@ struct _vcs_dpi_display_output_params_st {
 	int output_type;
 	int output_format;
 	int dsc_slices;
+	int max_audio_sample_rate;
 	struct writeback_st wb;
 };
 
@@ -322,7 +329,7 @@ struct _vcs_dpi_display_pipe_dest_params_st {
 	double pixel_rate_mhz;
 	unsigned char synchronized_vblank_all_planes;
 	unsigned char otg_inst;
-	unsigned char odm_combine;
+	unsigned int odm_combine;
 	unsigned char use_maximum_vstartup;
 	unsigned int vtotal_max;
 	unsigned int vtotal_min;
@@ -401,6 +408,7 @@ struct _vcs_dpi_display_rq_misc_params_st {
 struct _vcs_dpi_display_rq_params_st {
 	unsigned char yuv420;
 	unsigned char yuv420_10bpc;
+	unsigned char rgbe_alpha;
 	display_rq_misc_params_st misc;
 	display_rq_sizing_params_st sizing;
 	display_rq_dlg_params_st dlg;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index 7f9a5621922f..b3c96d9b472f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #include "display_mode_lib.h"
 #include "display_mode_vba.h"
@@ -222,13 +221,17 @@ static void fetch_socbb_params(struct display_mode_lib *mode_lib)
 	mode_lib->vba.SRExitTime = soc->sr_exit_time_us;
 	mode_lib->vba.SREnterPlusExitTime = soc->sr_enter_plus_exit_time_us;
 	mode_lib->vba.DRAMClockChangeLatency = soc->dram_clock_change_latency_us;
+	mode_lib->vba.DummyPStateCheck = soc->dram_clock_change_latency_us == soc->dummy_pstate_latency_us;
+	mode_lib->vba.DRAMClockChangeSupportsVActive = !soc->disable_dram_clock_change_vactive_support ||
+			mode_lib->vba.DummyPStateCheck;
+
 	mode_lib->vba.Downspreading = soc->downspread_percent;
 	mode_lib->vba.DRAMChannelWidth = soc->dram_channel_width_bytes;   // new!
 	mode_lib->vba.FabricDatapathToDCNDataReturn = soc->fabric_datapath_to_dcn_data_return_bytes; // new!
 	mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading = soc->dcn_downspread_percent;   // new
 	mode_lib->vba.DISPCLKDPPCLKVCOSpeed = soc->dispclk_dppclk_vco_speed_mhz;   // new
 	mode_lib->vba.VMMPageSize = soc->vmm_page_size_bytes;
-	mode_lib->vba.GPUVMMinPageSize = soc->vmm_page_size_bytes / 1024;
+	mode_lib->vba.GPUVMMinPageSize = soc->gpuvm_min_page_size_bytes / 1024;
 	mode_lib->vba.HostVMMinPageSize = soc->hostvm_min_page_size_bytes / 1024;
 	// Set the voltage scaling clocks as the defaults. Most of these will
 	// be set to different values by the test
@@ -261,7 +264,10 @@ static void fetch_socbb_params(struct display_mode_lib *mode_lib)
 		mode_lib->vba.DRAMSpeedPerState[i] = soc->clock_limits[i].dram_speed_mts;
 		//mode_lib->vba.DRAMSpeedPerState[i] = soc->clock_limits[i].dram_speed_mhz;
 		mode_lib->vba.MaxDispclk[i] = soc->clock_limits[i].dispclk_mhz;
+		mode_lib->vba.DTBCLKPerState[i] = soc->clock_limits[i].dtbclk_mhz;
 	}
+	mode_lib->vba.MinVoltageLevel = 0;
+	mode_lib->vba.MaxVoltageLevel = mode_lib->vba.soc.num_states;
 
 	mode_lib->vba.DoUrgentLatencyAdjustment =
 		soc->do_urgent_latency_adjustment;
@@ -303,8 +309,6 @@ static void fetch_ip_params(struct display_mode_lib *mode_lib)
 
 	mode_lib->vba.WritebackInterfaceBufferSize = ip->writeback_interface_buffer_size_kbytes;
 	mode_lib->vba.WritebackLineBufferSize = ip->writeback_line_buffer_buffer_size;
-	mode_lib->vba.MinVoltageLevel = 0;
-	mode_lib->vba.MaxVoltageLevel = 5;
 
 	mode_lib->vba.WritebackChromaLineBufferWidth =
 			ip->writeback_chroma_line_buffer_width_pixels;
@@ -420,8 +424,8 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 						ip->dcc_supported : src->dcc && ip->dcc_supported;
 		mode_lib->vba.DCCRate[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate;
 		/* TODO: Needs to be set based on src->dcc_rate_luma/chroma */
-		mode_lib->vba.DCCRateLuma[mode_lib->vba.NumberOfActivePlanes] = 0;
-		mode_lib->vba.DCCRateChroma[mode_lib->vba.NumberOfActivePlanes] = 0;
+		mode_lib->vba.DCCRateLuma[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate;
+		mode_lib->vba.DCCRateChroma[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate_chroma;
 
 		mode_lib->vba.SourcePixelFormat[mode_lib->vba.NumberOfActivePlanes] =
 				(enum source_format_class) (src->source_format);
@@ -433,8 +437,6 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 				dst->recout_width; // TODO: or should this be full_recout_width???...maybe only when in hsplit mode?
 		mode_lib->vba.ODMCombineEnabled[mode_lib->vba.NumberOfActivePlanes] =
 				dst->odm_combine;
-		mode_lib->vba.ODMCombineTypeEnabled[mode_lib->vba.NumberOfActivePlanes] =
-				dst->odm_combine;
 		mode_lib->vba.OutputFormat[mode_lib->vba.NumberOfActivePlanes] =
 				(enum output_format_class) (dout->output_format);
 		mode_lib->vba.OutputBpp[mode_lib->vba.NumberOfActivePlanes] =
@@ -451,7 +453,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 				dout->dp_lanes;
 		/* TODO: Needs to be set based on dout->audio.audio_sample_rate_khz/sample_layout */
 		mode_lib->vba.AudioSampleRate[mode_lib->vba.NumberOfActivePlanes] =
-			44.1 * 1000;
+			dout->max_audio_sample_rate;
 		mode_lib->vba.AudioSampleLayout[mode_lib->vba.NumberOfActivePlanes] =
 			1;
 		mode_lib->vba.DRAMClockChangeLatencyOverride = 0.0;
@@ -587,6 +589,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 			for (k = j + 1; k < mode_lib->vba.cache_num_pipes; ++k) {
 				display_pipe_source_params_st *src_k = &pipes[k].pipe.src;
 				display_pipe_dest_params_st *dst_k = &pipes[k].pipe.dest;
+				display_output_params_st *dout_k = &pipes[j].dout;
 
 				if (src_k->is_hsplit && !visited[k]
 						&& src->hsplit_grp == src_k->hsplit_grp) {
@@ -597,12 +600,18 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 							== dm_horz) {
 						mode_lib->vba.ViewportWidth[mode_lib->vba.NumberOfActivePlanes] +=
 								src_k->viewport_width;
+						mode_lib->vba.ViewportWidthChroma[mode_lib->vba.NumberOfActivePlanes] +=
+								src_k->viewport_width;
 						mode_lib->vba.ScalerRecoutWidth[mode_lib->vba.NumberOfActivePlanes] +=
 								dst_k->recout_width;
 					} else {
 						mode_lib->vba.ViewportHeight[mode_lib->vba.NumberOfActivePlanes] +=
 								src_k->viewport_height;
+						mode_lib->vba.ViewportHeightChroma[mode_lib->vba.NumberOfActivePlanes] +=
+								src_k->viewport_height;
 					}
+					mode_lib->vba.NumberOfDSCSlices[mode_lib->vba.NumberOfActivePlanes] +=
+							dout_k->dsc_slices;
 
 					visited[k] = true;
 				}
@@ -808,7 +817,9 @@ void ModeSupportAndSystemConfiguration(struct display_mode_lib *mode_lib)
 	unsigned int total_pipes = 0;
 
 	mode_lib->vba.VoltageLevel = mode_lib->vba.cache_pipes[0].clks_cfg.voltage;
-	mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel];
+	mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb];
+	if (mode_lib->vba.ReturnBW == 0)
+		mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel][0];
 	mode_lib->vba.FabricAndDRAMBandwidth = mode_lib->vba.FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel];
 
 	fetch_socbb_params(mode_lib);
@@ -858,4 +869,3 @@ double CalculateWriteBackDISPCLK(
 	return CalculateWriteBackDISPCLK;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index 1540ffbe3979..e7a44df676ca 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #ifndef __DML2_DISPLAY_MODE_VBA_H__
 #define __DML2_DISPLAY_MODE_VBA_H__
@@ -155,7 +154,10 @@ struct vba_vars_st {
 	double UrgentLatencySupportUsChroma;
 	unsigned int DSCFormatFactor;
 
+	bool DummyPStateCheck;
+	bool DRAMClockChangeSupportsVActive;
 	bool PrefetchModeSupported;
+	bool PrefetchAndImmediateFlipSupported;
 	enum self_refresh_affinity AllowDRAMSelfRefreshOrDRAMClockChangeInVblank; // Mode Support only
 	double XFCRemoteSurfaceFlipDelay;
 	double TInitXFill;
@@ -317,8 +319,7 @@ struct vba_vars_st {
 	unsigned int DynamicMetadataTransmittedBytes[DC__NUM_DPP__MAX];
 	double DCCRate[DC__NUM_DPP__MAX];
 	double AverageDCCCompressionRate;
-	bool ODMCombineEnabled[DC__NUM_DPP__MAX];
-	enum odm_combine_mode ODMCombineTypeEnabled[DC__NUM_DPP__MAX];
+	enum odm_combine_mode ODMCombineEnabled[DC__NUM_DPP__MAX];
 	double OutputBpp[DC__NUM_DPP__MAX];
 	bool DSCEnabled[DC__NUM_DPP__MAX];
 	unsigned int DSCInputBitPerComponent[DC__NUM_DPP__MAX];
@@ -346,6 +347,7 @@ struct vba_vars_st {
 	unsigned int EffectiveLBLatencyHidingSourceLinesChroma;
 	double BandwidthAvailableForImmediateFlip;
 	unsigned int PrefetchMode[DC__VOLTAGE_STATES + 1][2];
+	unsigned int PrefetchModePerState[DC__VOLTAGE_STATES + 1][2];
 	unsigned int MinPrefetchMode;
 	unsigned int MaxPrefetchMode;
 	bool AnyLinesForVMOrRowTooLarge;
@@ -395,6 +397,7 @@ struct vba_vars_st {
 	bool WritebackLumaAndChromaScalingSupported;
 	bool Cursor64BppSupport;
 	double DCFCLKPerState[DC__VOLTAGE_STATES + 1];
+	double DCFCLKState[DC__VOLTAGE_STATES + 1][2];
 	double FabricClockPerState[DC__VOLTAGE_STATES + 1];
 	double SOCCLKPerState[DC__VOLTAGE_STATES + 1];
 	double PHYCLKPerState[DC__VOLTAGE_STATES + 1];
@@ -443,7 +446,7 @@ struct vba_vars_st {
 	double OutputLinkDPLanes[DC__NUM_DPP__MAX];
 	double ForcedOutputLinkBPP[DC__NUM_DPP__MAX]; // Mode Support only
 	double ImmediateFlipBW[DC__NUM_DPP__MAX];
-	double MaxMaxVStartup;
+	double MaxMaxVStartup[DC__VOLTAGE_STATES + 1][2];
 
 	double WritebackLumaVExtra;
 	double WritebackChromaVExtra;
@@ -470,7 +473,7 @@ struct vba_vars_st {
 	double RoundedUpMaxSwathSizeBytesC;
 	double EffectiveDETLBLinesLuma;
 	double EffectiveDETLBLinesChroma;
-	double ProjectedDCFCLKDeepSleep;
+	double ProjectedDCFCLKDeepSleep[DC__VOLTAGE_STATES + 1][2];
 	double PDEAndMetaPTEBytesPerFrameY;
 	double PDEAndMetaPTEBytesPerFrameC;
 	unsigned int MetaRowBytesY;
@@ -488,12 +491,11 @@ struct vba_vars_st {
 	double FractionOfUrgentBandwidthImmediateFlip; // Mode Support debugging output
 
 	/* ms locals */
-	double IdealSDPPortBandwidthPerState[DC__VOLTAGE_STATES + 1];
+	double IdealSDPPortBandwidthPerState[DC__VOLTAGE_STATES + 1][2];
 	unsigned int NoOfDPP[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	int NoOfDPPThisState[DC__NUM_DPP__MAX];
-	bool ODMCombineEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
-	enum odm_combine_mode ODMCombineTypeEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
-	unsigned int SwathWidthYThisState[DC__NUM_DPP__MAX];
+	enum odm_combine_mode ODMCombineEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
+	double SwathWidthYThisState[DC__NUM_DPP__MAX];
 	unsigned int SwathHeightCPerState[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	unsigned int SwathHeightYThisState[DC__NUM_DPP__MAX];
 	unsigned int SwathHeightCThisState[DC__NUM_DPP__MAX];
@@ -505,7 +507,7 @@ struct vba_vars_st {
 	double RequiredDPPCLKThisState[DC__NUM_DPP__MAX];
 	bool PTEBufferSizeNotExceededY[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	bool PTEBufferSizeNotExceededC[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
-	bool BandwidthWithoutPrefetchSupported[DC__VOLTAGE_STATES + 1];
+	bool BandwidthWithoutPrefetchSupported[DC__VOLTAGE_STATES + 1][2];
 	bool PrefetchSupported[DC__VOLTAGE_STATES + 1][2];
 	bool VRatioInPrefetchSupported[DC__VOLTAGE_STATES + 1][2];
 	double RequiredDISPCLK[DC__VOLTAGE_STATES + 1][2];
@@ -514,22 +516,22 @@ struct vba_vars_st {
 	unsigned int TotalNumberOfActiveDPP[DC__VOLTAGE_STATES + 1][2];
 	unsigned int TotalNumberOfDCCActiveDPP[DC__VOLTAGE_STATES + 1][2];
 	bool ModeSupport[DC__VOLTAGE_STATES + 1][2];
-	double ReturnBWPerState[DC__VOLTAGE_STATES + 1];
+	double ReturnBWPerState[DC__VOLTAGE_STATES + 1][2];
 	bool DIOSupport[DC__VOLTAGE_STATES + 1];
 	bool NotEnoughDSCUnits[DC__VOLTAGE_STATES + 1];
 	bool DSCCLKRequiredMoreThanSupported[DC__VOLTAGE_STATES + 1];
 	bool DTBCLKRequiredMoreThanSupported[DC__VOLTAGE_STATES + 1];
 	double UrgentRoundTripAndOutOfOrderLatencyPerState[DC__VOLTAGE_STATES + 1];
-	bool ROBSupport[DC__VOLTAGE_STATES + 1];
+	bool ROBSupport[DC__VOLTAGE_STATES + 1][2];
 	bool PTEBufferSizeNotExceeded[DC__VOLTAGE_STATES + 1][2];
-	bool TotalVerticalActiveBandwidthSupport[DC__VOLTAGE_STATES + 1];
-	double MaxTotalVerticalActiveAvailableBandwidth[DC__VOLTAGE_STATES + 1];
+	bool TotalVerticalActiveBandwidthSupport[DC__VOLTAGE_STATES + 1][2];
+	double MaxTotalVerticalActiveAvailableBandwidth[DC__VOLTAGE_STATES + 1][2];
 	double PrefetchBW[DC__NUM_DPP__MAX];
-	double PDEAndMetaPTEBytesPerFrame[DC__NUM_DPP__MAX];
-	double MetaRowBytes[DC__NUM_DPP__MAX];
-	double DPTEBytesPerRow[DC__NUM_DPP__MAX];
-	double PrefetchLinesY[DC__NUM_DPP__MAX];
-	double PrefetchLinesC[DC__NUM_DPP__MAX];
+	double PDEAndMetaPTEBytesPerFrame[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double MetaRowBytes[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double DPTEBytesPerRow[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double PrefetchLinesY[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double PrefetchLinesC[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	unsigned int MaxNumSwY[DC__NUM_DPP__MAX];
 	unsigned int MaxNumSwC[DC__NUM_DPP__MAX];
 	double PrefillY[DC__NUM_DPP__MAX];
@@ -538,7 +540,7 @@ struct vba_vars_st {
 	double LinesForMetaPTE[DC__NUM_DPP__MAX];
 	double LinesForMetaAndDPTERow[DC__NUM_DPP__MAX];
 	double MinDPPCLKUsingSingleDPP[DC__NUM_DPP__MAX];
-	unsigned int SwathWidthYSingleDPP[DC__NUM_DPP__MAX];
+	double SwathWidthYSingleDPP[DC__NUM_DPP__MAX];
 	double BytePerPixelInDETY[DC__NUM_DPP__MAX];
 	double BytePerPixelInDETC[DC__NUM_DPP__MAX];
 	bool RequiresDSC[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
@@ -546,7 +548,7 @@ struct vba_vars_st {
 	double RequiresFEC[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
 	double OutputBppPerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
 	double DSCDelayPerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
-	bool ViewportSizeSupport[DC__VOLTAGE_STATES + 1];
+	bool ViewportSizeSupport[DC__VOLTAGE_STATES + 1][2];
 	unsigned int Read256BlockHeightY[DC__NUM_DPP__MAX];
 	unsigned int Read256BlockWidthY[DC__NUM_DPP__MAX];
 	unsigned int Read256BlockHeightC[DC__NUM_DPP__MAX];
@@ -561,7 +563,7 @@ struct vba_vars_st {
 	double WriteBandwidth[DC__NUM_DPP__MAX];
 	double PSCL_FACTOR[DC__NUM_DPP__MAX];
 	double PSCL_FACTOR_CHROMA[DC__NUM_DPP__MAX];
-	double MaximumVStartup[DC__NUM_DPP__MAX];
+	double MaximumVStartup[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	unsigned int MacroTileWidthY[DC__NUM_DPP__MAX];
 	unsigned int MacroTileWidthC[DC__NUM_DPP__MAX];
 	double AlignedDCCMetaPitch[DC__NUM_DPP__MAX];
@@ -578,7 +580,7 @@ struct vba_vars_st {
 	bool ImmediateFlipSupportedForState[DC__VOLTAGE_STATES + 1][2];
 	double WritebackDelay[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
 	unsigned int vm_group_bytes[DC__NUM_DPP__MAX];
-	long dpte_group_bytes[DC__NUM_DPP__MAX];
+	unsigned int dpte_group_bytes[DC__NUM_DPP__MAX];
 	unsigned int dpte_row_height[DC__NUM_DPP__MAX];
 	unsigned int meta_req_height[DC__NUM_DPP__MAX];
 	unsigned int meta_req_width[DC__NUM_DPP__MAX];
@@ -604,14 +606,14 @@ struct vba_vars_st {
 	double UrgentBurstFactorChroma[DC__NUM_DPP__MAX];
 	double UrgentBurstFactorChromaPre[DC__NUM_DPP__MAX];
 
+
 	bool           MPCCombine[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	double         SwathWidthCSingleDPP[DC__NUM_DPP__MAX];
 	double         MaximumSwathWidthInLineBufferLuma;
 	double         MaximumSwathWidthInLineBufferChroma;
 	double         MaximumSwathWidthLuma[DC__NUM_DPP__MAX];
 	double         MaximumSwathWidthChroma[DC__NUM_DPP__MAX];
-	bool odm_combine_dummy[DC__NUM_DPP__MAX];
-	enum odm_combine_mode odm_combine_mode_dummy[DC__NUM_DPP__MAX];
+	enum odm_combine_mode odm_combine_dummy[DC__NUM_DPP__MAX];
 	double         dummy1[DC__NUM_DPP__MAX];
 	double         dummy2[DC__NUM_DPP__MAX];
 	double         dummy3[DC__NUM_DPP__MAX];
@@ -621,9 +623,9 @@ struct vba_vars_st {
 	double         dummy7[DC__NUM_DPP__MAX];
 	double         dummy8[DC__NUM_DPP__MAX];
 	unsigned int        dummyinteger1ms[DC__NUM_DPP__MAX];
-	unsigned int        dummyinteger2ms[DC__NUM_DPP__MAX];
+	double        dummyinteger2ms[DC__NUM_DPP__MAX];
 	unsigned int        dummyinteger3[DC__NUM_DPP__MAX];
-	unsigned int        dummyinteger4;
+	unsigned int        dummyinteger4[DC__NUM_DPP__MAX];
 	unsigned int        dummyinteger5;
 	unsigned int        dummyinteger6;
 	unsigned int        dummyinteger7;
@@ -636,7 +638,6 @@ struct vba_vars_st {
 	unsigned int        dummyintegerarr2[DC__NUM_DPP__MAX];
 	unsigned int        dummyintegerarr3[DC__NUM_DPP__MAX];
 	unsigned int        dummyintegerarr4[DC__NUM_DPP__MAX];
-	long                dummylongarr1[DC__NUM_DPP__MAX];
 	bool           dummysinglestring;
 	bool           SingleDPPViewportSizeSupportPerPlane[DC__NUM_DPP__MAX];
 	double         PlaneRequiredDISPCLKWithODMCombine2To1;
@@ -644,20 +645,19 @@ struct vba_vars_st {
 	unsigned int   TotalNumberOfSingleDPPPlanes[DC__VOLTAGE_STATES + 1][2];
 	bool           LinkDSCEnable;
 	bool           ODMCombine4To1SupportCheckOK[DC__VOLTAGE_STATES + 1];
-	bool ODMCombineEnableThisState[DC__NUM_DPP__MAX];
-	enum odm_combine_mode ODMCombineEnableTypeThisState[DC__NUM_DPP__MAX];
-	unsigned int   SwathWidthCThisState[DC__NUM_DPP__MAX];
+	enum odm_combine_mode ODMCombineEnableThisState[DC__NUM_DPP__MAX];
+	double   SwathWidthCThisState[DC__NUM_DPP__MAX];
 	bool           ViewportSizeSupportPerPlane[DC__NUM_DPP__MAX];
 	double         AlignedDCCMetaPitchY[DC__NUM_DPP__MAX];
 	double         AlignedDCCMetaPitchC[DC__NUM_DPP__MAX];
 
 	unsigned int NotEnoughUrgentLatencyHiding;
 	unsigned int NotEnoughUrgentLatencyHidingPre;
-	long PTEBufferSizeInRequestsForLuma;
-	long PTEBufferSizeInRequestsForChroma;
+	int PTEBufferSizeInRequestsForLuma;
+	int PTEBufferSizeInRequestsForChroma;
 
 	// Missing from VBA
-	long dpte_group_bytes_chroma;
+	int dpte_group_bytes_chroma;
 	unsigned int vm_group_bytes_chroma;
 	double dst_x_after_scaler;
 	double dst_y_after_scaler;
@@ -682,8 +682,8 @@ struct vba_vars_st {
 	double MinTTUVBlank[DC__NUM_DPP__MAX];
 	double BytePerPixelDETY[DC__NUM_DPP__MAX];
 	double BytePerPixelDETC[DC__NUM_DPP__MAX];
-	unsigned int SwathWidthY[DC__NUM_DPP__MAX];
-	unsigned int SwathWidthSingleDPPY[DC__NUM_DPP__MAX];
+	double SwathWidthY[DC__NUM_DPP__MAX];
+	double SwathWidthSingleDPPY[DC__NUM_DPP__MAX];
 	double CursorRequestDeliveryTime[DC__NUM_DPP__MAX];
 	double CursorRequestDeliveryTimePrefetch[DC__NUM_DPP__MAX];
 	double ReadBandwidthPlaneLuma[DC__NUM_DPP__MAX];
@@ -759,8 +759,8 @@ struct vba_vars_st {
 	double LinesInDETY[DC__NUM_DPP__MAX];
 	double LinesInDETYRoundedDownToSwath[DC__NUM_DPP__MAX];
 
-	unsigned int SwathWidthSingleDPPC[DC__NUM_DPP__MAX];
-	unsigned int SwathWidthC[DC__NUM_DPP__MAX];
+	double SwathWidthSingleDPPC[DC__NUM_DPP__MAX];
+	double SwathWidthC[DC__NUM_DPP__MAX];
 	unsigned int BytePerPixelY[DC__NUM_DPP__MAX];
 	unsigned int BytePerPixelC[DC__NUM_DPP__MAX];
 	long dummyinteger1;
@@ -778,6 +778,7 @@ struct vba_vars_st {
 	unsigned int DCCCMaxCompressedBlock[DC__NUM_DPP__MAX];
 	unsigned int DCCCIndependent64ByteBlock[DC__NUM_DPP__MAX];
 	double VStartupMargin;
+	bool NotEnoughTimeForDynamicMetadata;
 
 	/* Missing from VBA */
 	unsigned int MaximumMaxVStartupLines;
@@ -813,7 +814,7 @@ struct vba_vars_st {
 	unsigned int ViewportHeightChroma[DC__NUM_DPP__MAX];
 	double HRatioChroma[DC__NUM_DPP__MAX];
 	double VRatioChroma[DC__NUM_DPP__MAX];
-	long WritebackSourceWidth[DC__NUM_DPP__MAX];
+	int WritebackSourceWidth[DC__NUM_DPP__MAX];
 
 	bool ModeIsSupported;
 	bool ODMCombine4To1Supported;
@@ -849,6 +850,58 @@ struct vba_vars_st {
 	unsigned int MaxNumHDMIFRLOutputs;
 	int    AudioSampleRate[DC__NUM_DPP__MAX];
 	int    AudioSampleLayout[DC__NUM_DPP__MAX];
+
+	int PercentMarginOverMinimumRequiredDCFCLK;
+	bool DynamicMetadataSupported[DC__VOLTAGE_STATES + 1][2];
+	enum immediate_flip_requirement ImmediateFlipRequirement;
+	double DETBufferSizeYThisState[DC__NUM_DPP__MAX];
+	double DETBufferSizeCThisState[DC__NUM_DPP__MAX];
+	bool NoUrgentLatencyHiding[DC__NUM_DPP__MAX];
+	bool NoUrgentLatencyHidingPre[DC__NUM_DPP__MAX];
+	int swath_width_luma_ub_this_state[DC__NUM_DPP__MAX];
+	int swath_width_chroma_ub_this_state[DC__NUM_DPP__MAX];
+	double UrgLatency[DC__VOLTAGE_STATES + 1];
+	double VActiveCursorBandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double VActivePixelBandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	bool NoTimeForPrefetch[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	bool NoTimeForDynamicMetadata[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double dpte_row_bandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double meta_row_bandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double DETBufferSizeYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double DETBufferSizeCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	int swath_width_luma_ub_all_states[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	int swath_width_chroma_ub_all_states[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	bool NotUrgentLatencyHiding[DC__VOLTAGE_STATES + 1][2];
+	unsigned int SwathHeightYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	unsigned int SwathHeightCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	unsigned int SwathWidthYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	unsigned int SwathWidthCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double TotalDPTERowBandwidth[DC__VOLTAGE_STATES + 1][2];
+	double TotalMetaRowBandwidth[DC__VOLTAGE_STATES + 1][2];
+	double TotalVActiveCursorBandwidth[DC__VOLTAGE_STATES + 1][2];
+	double TotalVActivePixelBandwidth[DC__VOLTAGE_STATES + 1][2];
+	bool UseMinimumRequiredDCFCLK;
+	double WritebackDelayTime[DC__NUM_DPP__MAX];
+	unsigned int DCCYIndependentBlock[DC__NUM_DPP__MAX];
+	unsigned int DCCCIndependentBlock[DC__NUM_DPP__MAX];
+	unsigned int dummyinteger15;
+	unsigned int dummyinteger16;
+	unsigned int dummyinteger17;
+	unsigned int dummyinteger18;
+	unsigned int dummyinteger19;
+	unsigned int dummyinteger20;
+	unsigned int dummyinteger21;
+	unsigned int dummyinteger22;
+	unsigned int dummyinteger23;
+	unsigned int dummyinteger24;
+	unsigned int dummyinteger25;
+	unsigned int dummyinteger26;
+	unsigned int dummyinteger27;
+	unsigned int dummyinteger28;
+	unsigned int dummyinteger29;
+	bool dummystring[DC__NUM_DPP__MAX];
+	double BPP;
+	enum odm_combine_policy ODMCombinePolicy;
 };
 
 bool CalculateMinAndMaxPrefetchMode(
@@ -870,4 +923,3 @@ double CalculateWriteBackDISPCLK(
 		unsigned int WritebackChromaLineBufferWidth);
 
 #endif /* _DML2_DISPLAY_MODE_VBA_H_ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
index b953b02a1512..723af0b2dda0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
@@ -24,7 +24,7 @@
  */
 
 #include "dml_common_defs.h"
-#include "../calcs/dcn_calc_math.h"
+#include "dcn_calc_math.h"
 
 #include "dml_inline_defs.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
index eca140da13d8..ded71ea82413 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
@@ -27,7 +27,7 @@
 #define __DML_INLINE_DEFS_H__
 
 #include "dml_common_defs.h"
-#include "../calcs/dcn_calc_math.h"
+#include "dcn_calc_math.h"
 #include "dml_logger.h"
 
 static inline double dml_min(double a, double b)
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index 641ffb7cfaed..3f66868df171 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -2,7 +2,13 @@
 #
 # Makefile for the 'dsc' sub-component of DAL.
 
+ifdef CONFIG_X86
 dsc_ccflags := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+dsc_ccflags := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -10,6 +16,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -18,6 +25,7 @@ dsc_ccflags += -mpreferred-stack-boundary=4
 else
 dsc_ccflags += -msse2
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc_dpi.o := $(dsc_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index e60f760585e4..8b78fcbfe746 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -22,30 +22,16 @@
  * Author: AMD
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dc_hw_types.h"
 #include "dsc.h"
 #include <drm/drm_dp_helper.h>
-
-struct dc_dsc_policy {
-	bool use_min_slices_h;
-	int max_slices_h; // Maximum available if 0
-	int min_sice_height; // Must not be less than 8
-	int max_target_bpp;
-	int min_target_bpp; // Minimum target bits per pixel
-};
-
-const struct dc_dsc_policy dsc_policy = {
-	.use_min_slices_h = true, // DSC Policy: Use minimum number of slices that fits the pixel clock
-	.max_slices_h = 0, // DSC Policy: Use max available slices (in our case 4 for or 8, depending on the mode)
-	.min_sice_height = 108, // DSC Policy: Use slice height recommended by VESA DSC Spreadsheet user guide
-	.max_target_bpp = 16,
-	.min_target_bpp = 8,
-};
-
+#include "dc.h"
 
 /* This module's internal functions */
 
+/* default DSC policy target bitrate limit is 16bpp */
+static uint32_t dsc_policy_max_target_bpp_limit = 16;
+
 static uint32_t dc_dsc_bandwidth_in_kbps_from_timing(
 	const struct dc_crtc_timing *timing)
 {
@@ -237,8 +223,11 @@ static void get_dsc_enc_caps(
 	// This is a static HW query, so we can use any DSC
 
 	memset(dsc_enc_caps, 0, sizeof(struct dsc_enc_caps));
-	if (dsc)
+	if (dsc) {
 		dsc->funcs->dsc_get_enc_caps(dsc_enc_caps, pixel_clock_100Hz);
+		if (dsc->ctx->dc->debug.native422_support)
+			dsc_enc_caps->color_formats.bits.YCBCR_NATIVE_422 = 1;
+	}
 }
 
 /* Returns 'false' if no intersection was found for at least one capablity.
@@ -578,9 +567,11 @@ static bool setup_dsc_config(
 	bool is_dsc_possible = false;
 	int pic_height;
 	int slice_height;
+	struct dc_dsc_policy policy;
 
 	memset(dsc_cfg, 0, sizeof(struct dc_dsc_config));
 
+	dc_dsc_get_policy_for_timing(timing, &policy);
 	pic_width = timing->h_addressable + timing->h_border_left + timing->h_border_right;
 	pic_height = timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
 
@@ -596,7 +587,12 @@ static bool setup_dsc_config(
 		goto done;
 
 	if (target_bandwidth_kbps > 0) {
-		is_dsc_possible = decide_dsc_target_bpp_x16(&dsc_policy, &dsc_common_caps, target_bandwidth_kbps, timing, &target_bpp);
+		is_dsc_possible = decide_dsc_target_bpp_x16(
+				&policy,
+				&dsc_common_caps,
+				target_bandwidth_kbps,
+				timing,
+				&target_bpp);
 		dsc_cfg->bits_per_pixel = target_bpp;
 	}
 	if (!is_dsc_possible)
@@ -698,20 +694,20 @@ static bool setup_dsc_config(
 	if (!is_dsc_possible)
 		goto done;
 
-	if (dsc_policy.use_min_slices_h) {
+	if (policy.use_min_slices_h) {
 		if (min_slices_h > 0)
 			num_slices_h = min_slices_h;
 		else if (max_slices_h > 0) { // Fall back to max slices if min slices is not working out
-			if (dsc_policy.max_slices_h)
-				num_slices_h = min(dsc_policy.max_slices_h, max_slices_h);
+			if (policy.max_slices_h)
+				num_slices_h = min(policy.max_slices_h, max_slices_h);
 			else
 				num_slices_h = max_slices_h;
 		} else
 			is_dsc_possible = false;
 	} else {
 		if (max_slices_h > 0) {
-			if (dsc_policy.max_slices_h)
-				num_slices_h = min(dsc_policy.max_slices_h, max_slices_h);
+			if (policy.max_slices_h)
+				num_slices_h = min(policy.max_slices_h, max_slices_h);
 			else
 				num_slices_h = max_slices_h;
 		} else if (min_slices_h > 0) // Fall back to min slices if max slices is not possible
@@ -733,7 +729,7 @@ static bool setup_dsc_config(
 	// Slice height (i.e. number of slices per column): start with policy and pick the first one that height is divisible by.
 	// For 4:2:0 make sure the slice height is divisible by 2 as well.
 	if (min_slice_height_override == 0)
-		slice_height = min(dsc_policy.min_sice_height, pic_height);
+		slice_height = min(policy.min_slice_height, pic_height);
 	else
 		slice_height = min(min_slice_height_override, pic_height);
 
@@ -764,7 +760,7 @@ done:
 	return is_dsc_possible;
 }
 
-bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data, const uint8_t *dpcd_dsc_ext_data, struct dsc_dec_dpcd_caps *dsc_sink_caps)
+bool dc_dsc_parse_dsc_dpcd(const struct dc *dc, const uint8_t *dpcd_dsc_basic_data, const uint8_t *dpcd_dsc_ext_data, struct dsc_dec_dpcd_caps *dsc_sink_caps)
 {
 	if (!dpcd_dsc_basic_data)
 		return false;
@@ -817,6 +813,23 @@ bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data, const uint8_t *dp
 	if (!dsc_bpp_increment_div_from_dpcd(dpcd_dsc_basic_data[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT], &dsc_sink_caps->bpp_increment_div))
 		return false;
 
+	if (dc->debug.dsc_bpp_increment_div) {
+		/* dsc_bpp_increment_div should onl be 1, 2, 4, 8 or 16, but rather than rejecting invalid values,
+		 * we'll accept all and get it into range. This also makes the above check against 0 redundant,
+		 * but that one stresses out the override will be only used if it's not 0.
+		 */
+		if (dc->debug.dsc_bpp_increment_div >= 1)
+			dsc_sink_caps->bpp_increment_div = 1;
+		if (dc->debug.dsc_bpp_increment_div >= 2)
+			dsc_sink_caps->bpp_increment_div = 2;
+		if (dc->debug.dsc_bpp_increment_div >= 4)
+			dsc_sink_caps->bpp_increment_div = 4;
+		if (dc->debug.dsc_bpp_increment_div >= 8)
+			dsc_sink_caps->bpp_increment_div = 8;
+		if (dc->debug.dsc_bpp_increment_div >= 16)
+			dsc_sink_caps->bpp_increment_div = 16;
+	}
+
 	/* Extended caps */
 	if (dpcd_dsc_ext_data == NULL) { // Extended DPCD DSC data can be null, e.g. because it doesn't apply to SST
 		dsc_sink_caps->branch_overall_throughput_0_mps = 0;
@@ -903,4 +916,67 @@ bool dc_dsc_compute_config(
 			timing, dsc_min_slice_height_override, dsc_cfg);
 	return is_dsc_possible;
 }
-#endif /* CONFIG_DRM_AMD_DC_DSC_SUPPORT */
+
+void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, struct dc_dsc_policy *policy)
+{
+	uint32_t bpc = 0;
+
+	policy->min_target_bpp = 0;
+	policy->max_target_bpp = 0;
+
+	/* DSC Policy: Use minimum number of slices that fits the pixel clock */
+	policy->use_min_slices_h = true;
+
+	/* DSC Policy: Use max available slices
+	 * (in our case 4 for or 8, depending on the mode)
+	 */
+	policy->max_slices_h = 0;
+
+	/* DSC Policy: Use slice height recommended
+	 * by VESA DSC Spreadsheet user guide
+	 */
+	policy->min_slice_height = 108;
+
+	/* DSC Policy: follow DP specs with an internal upper limit to 16 bpp
+	 * for better interoperability
+	 */
+	switch (timing->display_color_depth) {
+	case COLOR_DEPTH_888:
+		bpc = 8;
+		break;
+	case COLOR_DEPTH_101010:
+		bpc = 10;
+		break;
+	case COLOR_DEPTH_121212:
+		bpc = 12;
+		break;
+	default:
+		return;
+	}
+	switch (timing->pixel_encoding) {
+	case PIXEL_ENCODING_RGB:
+	case PIXEL_ENCODING_YCBCR444:
+	case PIXEL_ENCODING_YCBCR422: /* assume no YCbCr422 native support */
+		/* DP specs limits to 8 */
+		policy->min_target_bpp = 8;
+		/* DP specs limits to 3 x bpc */
+		policy->max_target_bpp = 3 * bpc;
+		break;
+	case PIXEL_ENCODING_YCBCR420:
+		/* DP specs limits to 6 */
+		policy->min_target_bpp = 6;
+		/* DP specs limits to 1.5 x bpc assume bpc is an even number */
+		policy->max_target_bpp = bpc * 3 / 2;
+		break;
+	default:
+		return;
+	}
+	/* internal upper limit, default 16 bpp */
+	if (policy->max_target_bpp > dsc_policy_max_target_bpp_limit)
+		policy->max_target_bpp = dsc_policy_max_target_bpp_limit;
+}
+
+void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit)
+{
+	dsc_policy_max_target_bpp_limit = limit;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dscc_types.h b/drivers/gpu/drm/amd/display/dc/dsc/dscc_types.h
index 020ad8f685ea..9f70e87b3ecb 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dscc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dscc_types.h
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
@@ -51,4 +50,3 @@ int dscc_compute_dsc_parameters(const struct drm_dsc_config *pps, struct dsc_par
 
 #endif
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h b/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h
index f66d006eac5d..e5fac9f4181d 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h
+++ b/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
@@ -703,4 +702,3 @@ const qp_table   qp_table_422_8bpc_max = {
 	{  16, { 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2, 3, 4} }
 };
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
index 76c4b12d6824..03ae15946c6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
@@ -252,4 +251,3 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 	rc->rc_buf_thresh[13] = 8064;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
index f1d6e793bc61..b6b1f09c2009 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
@@ -82,4 +81,3 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 
 #endif
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
index 73172fd0b529..1f6e63b71456 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 /*
  * Copyright 2012-17 Advanced Micro Devices, Inc.
  *
@@ -144,4 +143,3 @@ int dscc_compute_dsc_parameters(const struct drm_dsc_config *pps, struct dsc_par
 	return ret;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/Makefile b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
index b3062275711e..202baa210cc8 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
@@ -61,26 +61,25 @@ AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCE120)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 GPIO_DCN10 = hw_translate_dcn10.o hw_factory_dcn10.o
 
 AMD_DAL_GPIO_DCN10 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn10/,$(GPIO_DCN10))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCN10)
-endif
 
 ###############################################################################
 # DCN 2
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
 GPIO_DCN20 = hw_translate_dcn20.o hw_factory_dcn20.o
 
 AMD_DAL_GPIO_DCN20 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn20/,$(GPIO_DCN20))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCN20)
-endif
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
+###############################################################################
+# DCN 21
+###############################################################################
 GPIO_DCN21 = hw_translate_dcn21.o hw_factory_dcn21.o
 
 AMD_DAL_GPIO_DCN21 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn21/,$(GPIO_DCN21))
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
index 43a440385b43..83f798cb8b21 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dm_services.h"
 #include "include/gpio_types.h"
 #include "../hw_factory.h"
@@ -110,6 +109,12 @@ static const struct ddc_registers ddc_data_regs_dcn[] = {
 	ddc_data_regs_dcn2(4),
 	ddc_data_regs_dcn2(5),
 	ddc_data_regs_dcn2(6),
+	{
+			DDC_GPIO_VGA_REG_LIST(DATA),
+			.ddc_setup = 0,
+			.phy_aux_cntl = 0,
+			.dc_gpio_aux_ctrl_5 = 0
+	}
 };
 
 static const struct ddc_registers ddc_clk_regs_dcn[] = {
@@ -119,6 +124,12 @@ static const struct ddc_registers ddc_clk_regs_dcn[] = {
 	ddc_clk_regs_dcn2(4),
 	ddc_clk_regs_dcn2(5),
 	ddc_clk_regs_dcn2(6),
+	{
+			DDC_GPIO_VGA_REG_LIST(CLK),
+			.ddc_setup = 0,
+			.phy_aux_cntl = 0,
+			.dc_gpio_aux_ctrl_5 = 0
+	}
 };
 
 static const struct ddc_sh_mask ddc_shift[] = {
@@ -246,4 +257,3 @@ void dal_hw_factory_dcn20_init(struct hw_factory *factory)
 	factory->funcs = &funcs;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.h b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.h
index 43a4ce7aa3bf..0fd9b315bd7a 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #ifndef __DAL_HW_FACTORY_DCN20_H__
 #define __DAL_HW_FACTORY_DCN20_H__
 
@@ -30,4 +29,3 @@
 void dal_hw_factory_dcn20_init(struct hw_factory *factory);
 
 #endif /* __DAL_HW_FACTORY_DCN20_H__ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.c
index 915e896e0e91..52ba62b3b5e4 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.c
@@ -26,7 +26,6 @@
 /*
  * Pre-requisites: headers required by header of this unit
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "hw_translate_dcn20.h"
 
 #include "dm_services.h"
@@ -379,4 +378,3 @@ void dal_hw_translate_dcn20_init(struct hw_translate *tr)
 	tr->funcs = &funcs;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.h b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.h
index 01f52c7bed86..5f7a35530e26 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #ifndef __DAL_HW_TRANSLATE_DCN20_H__
 #define __DAL_HW_TRANSLATE_DCN20_H__
 
@@ -32,4 +31,3 @@ struct hw_translate;
 void dal_hw_translate_dcn20_init(struct hw_translate *tr);
 
 #endif /* __DAL_HW_TRANSLATE_DCN20_H__ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
index 8572678f8d4f..907c5911eb9e 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dm_services.h"
 #include "include/gpio_types.h"
 #include "../hw_factory.h"
@@ -239,4 +238,3 @@ void dal_hw_factory_dcn21_init(struct hw_factory *factory)
 	factory->funcs = &funcs;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.h b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.h
index 2443f9e7afbf..4949e0c7fa06 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #ifndef __DAL_HW_FACTORY_DCN21_H__
 #define __DAL_HW_FACTORY_DCN21_H__
 
@@ -30,4 +29,3 @@
 void dal_hw_factory_dcn21_init(struct hw_factory *factory);
 
 #endif /* __DAL_HW_FACTORY_DCN20_H__ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
index fbb58fb8c318..291966efe63d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
@@ -26,7 +26,6 @@
 /*
  * Pre-requisites: headers required by header of this unit
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "hw_translate_dcn21.h"
 
 #include "dm_services.h"
@@ -382,4 +381,3 @@ void dal_hw_translate_dcn21_init(struct hw_translate *tr)
 	tr->funcs = &funcs;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.h b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.h
index 2bfaac24c574..9462b0a65200 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #ifndef __DAL_HW_TRANSLATE_DCN21_H__
 #define __DAL_HW_TRANSLATE_DCN21_H__
 
@@ -32,4 +31,3 @@ struct hw_translate;
 void dal_hw_translate_dcn21_init(struct hw_translate *tr);
 
 #endif /* __DAL_HW_TRANSLATE_DCN21_H__ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
index f91e85b04956..308a543178a5 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
@@ -48,13 +48,11 @@
 	DDC_GPIO_REG_LIST(cd,id),\
 	.ddc_setup = REG(DC_I2C_DDC ## id ## _SETUP)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	#define DDC_REG_LIST_DCN2(cd, id) \
 	DDC_GPIO_REG_LIST(cd, id),\
 	.ddc_setup = REG(DC_I2C_DDC ## id ## _SETUP),\
 	.phy_aux_cntl = REG(PHY_AUX_CNTL), \
 	.dc_gpio_aux_ctrl_5 = REG(DC_GPIO_AUX_CTRL_5)
-#endif
 
 #define DDC_GPIO_VGA_REG_LIST_ENTRY(type,cd)\
 	.type ## _reg =   REG(DC_GPIO_DDCVGA_ ## type),\
@@ -90,13 +88,11 @@
 	DDC_GPIO_I2C_REG_LIST(cd),\
 	.ddc_setup = 0
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define DDC_I2C_REG_LIST_DCN2(cd) \
 	DDC_GPIO_I2C_REG_LIST(cd),\
 	.ddc_setup = 0,\
 	.phy_aux_cntl = REG(PHY_AUX_CNTL), \
 	.dc_gpio_aux_ctrl_5 = REG(DC_GPIO_AUX_CTRL_5)
-#endif
 #define DDC_MASK_SH_LIST_COMMON(mask_sh) \
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE, mask_sh),\
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_EDID_DETECT_ENABLE, mask_sh),\
@@ -110,22 +106,18 @@
 		SF_DDC(DC_GPIO_I2CPAD_MASK, DC_GPIO_SDA_PD_DIS, mask_sh),\
 		SF_DDC(DC_GPIO_I2CPAD_MASK, DC_GPIO_SCL_PD_DIS, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define DDC_MASK_SH_LIST_DCN2(mask_sh, cd) \
 	{DDC_MASK_SH_LIST_COMMON(mask_sh),\
 	0,\
 	0,\
 	(PHY_AUX_CNTL__AUX## cd ##_PAD_RXSEL## mask_sh),\
 	(DC_GPIO_AUX_CTRL_5__DDC_PAD## cd ##_I2CMODE## mask_sh)}
-#endif
 
 struct ddc_registers {
 	struct gpio_registers gpio;
 	uint32_t ddc_setup;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t phy_aux_cntl;
 	uint32_t dc_gpio_aux_ctrl_5;
-#endif
 };
 
 struct ddc_sh_mask {
@@ -140,11 +132,9 @@ struct ddc_sh_mask {
 	/* i2cpad_mask */
 	uint32_t DC_GPIO_SDA_PD_DIS;
 	uint32_t DC_GPIO_SCL_PD_DIS;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	//phy_aux_cntl
 	uint32_t AUX_PAD_RXSEL;
 	uint32_t DDC_PAD_I2CMODE;
-#endif
 };
 
 
@@ -180,7 +170,6 @@ struct ddc_sh_mask {
 {\
 	DDC_I2C_REG_LIST(SCL)\
 }
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define ddc_data_regs_dcn2(id) \
 {\
 	DDC_REG_LIST_DCN2(DATA, id)\
@@ -200,7 +189,6 @@ struct ddc_sh_mask {
 {\
 	DDC_REG_LIST_DCN2(SCL)\
 }
-#endif
 
 
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_GPIO_DDC_REGS_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
index 1c12961f6472..1ae153eab31d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
@@ -48,18 +48,18 @@
 
 struct gpio;
 
-static void destruct(
+static void dal_hw_ddc_destruct(
 	struct hw_ddc *pin)
 {
 	dal_hw_gpio_destruct(&pin->base);
 }
 
-static void destroy(
+static void dal_hw_ddc_destroy(
 	struct hw_gpio_pin **ptr)
 {
 	struct hw_ddc *pin = HW_DDC_FROM_BASE(*ptr);
 
-	destruct(pin);
+	dal_hw_ddc_destruct(pin);
 
 	kfree(pin);
 
@@ -150,7 +150,6 @@ static enum gpio_result set_config(
 					AUX_PAD1_MODE, 0);
 		}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (ddc->regs->dc_gpio_aux_ctrl_5 != 0) {
 				REG_UPDATE(dc_gpio_aux_ctrl_5, DDC_PAD_I2CMODE, 1);
 		}
@@ -158,7 +157,6 @@ static enum gpio_result set_config(
 		if (ddc->regs->phy_aux_cntl != 0) {
 				REG_UPDATE(phy_aux_cntl, AUX_PAD_RXSEL, 1);
 		}
-#endif
 		return GPIO_RESULT_OK;
 	case GPIO_DDC_CONFIG_TYPE_MODE_AUX:
 		/* set the AUX pad mode */
@@ -166,12 +164,10 @@ static enum gpio_result set_config(
 			REG_SET(gpio.MASK_reg, regval,
 					AUX_PAD1_MODE, 1);
 		}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (ddc->regs->dc_gpio_aux_ctrl_5 != 0) {
 			REG_UPDATE(dc_gpio_aux_ctrl_5,
 					DDC_PAD_I2CMODE, 0);
 		}
-#endif
 
 		return GPIO_RESULT_OK;
 	case GPIO_DDC_CONFIG_TYPE_POLL_FOR_CONNECT:
@@ -211,7 +207,7 @@ static enum gpio_result set_config(
 }
 
 static const struct hw_gpio_pin_funcs funcs = {
-	.destroy = destroy,
+	.destroy = dal_hw_ddc_destroy,
 	.open = dal_hw_gpio_open,
 	.get_value = dal_hw_gpio_get_value,
 	.set_value = dal_hw_gpio_set_value,
@@ -220,7 +216,7 @@ static const struct hw_gpio_pin_funcs funcs = {
 	.close = dal_hw_gpio_close,
 };
 
-static void construct(
+static void dal_hw_ddc_construct(
 	struct hw_ddc *ddc,
 	enum gpio_id id,
 	uint32_t en,
@@ -247,7 +243,7 @@ void dal_hw_ddc_init(
 		return;
 	}
 
-	construct(*hw_ddc, id, en, ctx);
+	dal_hw_ddc_construct(*hw_ddc, id, en, ctx);
 }
 
 struct hw_gpio_pin *dal_hw_ddc_get_pin(struct gpio *gpio)
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
index fa9f1d055ec8..d2d36d48caaa 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
@@ -45,15 +45,11 @@
 #include "dce80/hw_factory_dce80.h"
 #include "dce110/hw_factory_dce110.h"
 #include "dce120/hw_factory_dce120.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "dcn10/hw_factory_dcn10.h"
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dcn20/hw_factory_dcn20.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #include "dcn21/hw_factory_dcn21.h"
-#endif
 
 #include "diagnostics/hw_factory_diag.h"
 
@@ -90,19 +86,15 @@ bool dal_hw_factory_init(
 	case DCE_VERSION_12_1:
 		dal_hw_factory_dce120_init(factory);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case DCN_VERSION_1_0:
 	case DCN_VERSION_1_01:
 		dal_hw_factory_dcn10_init(factory);
 		return true;
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case DCN_VERSION_2_0:
 		dal_hw_factory_dcn20_init(factory);
 		return true;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case DCN_VERSION_2_1:
 		dal_hw_factory_dcn21_init(factory);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_generic.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_generic.c
index 69b899741f6d..f9e847e6555d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_generic.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_generic.c
@@ -46,22 +46,13 @@
 
 struct gpio;
 
-static void dal_hw_generic_construct(
-	struct hw_generic *pin,
-	enum gpio_id id,
-	uint32_t en,
-	struct dc_context *ctx)
-{
-	dal_hw_gpio_construct(&pin->base, id, en, ctx);
-}
-
 static void dal_hw_generic_destruct(
 	struct hw_generic *pin)
 {
 	dal_hw_gpio_destruct(&pin->base);
 }
 
-static void destroy(
+static void dal_hw_generic_destroy(
 	struct hw_gpio_pin **ptr)
 {
 	struct hw_generic *generic = HW_GENERIC_FROM_BASE(*ptr);
@@ -90,7 +81,7 @@ static enum gpio_result set_config(
 }
 
 static const struct hw_gpio_pin_funcs funcs = {
-	.destroy = destroy,
+	.destroy = dal_hw_generic_destroy,
 	.open = dal_hw_gpio_open,
 	.get_value = dal_hw_gpio_get_value,
 	.set_value = dal_hw_gpio_set_value,
@@ -99,14 +90,14 @@ static const struct hw_gpio_pin_funcs funcs = {
 	.close = dal_hw_gpio_close,
 };
 
-static void construct(
-	struct hw_generic *generic,
+static void dal_hw_generic_construct(
+	struct hw_generic *pin,
 	enum gpio_id id,
 	uint32_t en,
 	struct dc_context *ctx)
 {
-	dal_hw_generic_construct(generic, id, en, ctx);
-	generic->base.base.funcs = &funcs;
+	dal_hw_gpio_construct(&pin->base, id, en, ctx);
+	pin->base.base.funcs = &funcs;
 }
 
 void dal_hw_generic_init(
@@ -126,7 +117,7 @@ void dal_hw_generic_init(
 		return;
 	}
 
-	construct(*hw_generic, id, en, ctx);
+	dal_hw_generic_construct(*hw_generic, id, en, ctx);
 }
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_hpd.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_hpd.c
index 00c9bcf660a3..692f29de7797 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_hpd.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_hpd.c
@@ -46,34 +46,18 @@
 
 struct gpio;
 
-static void dal_hw_hpd_construct(
-	struct hw_hpd *pin,
-	enum gpio_id id,
-	uint32_t en,
-	struct dc_context *ctx)
-{
-	dal_hw_gpio_construct(&pin->base, id, en, ctx);
-}
-
 static void dal_hw_hpd_destruct(
 	struct hw_hpd *pin)
 {
 	dal_hw_gpio_destruct(&pin->base);
 }
 
-
-static void destruct(
-	struct hw_hpd *hpd)
-{
-	dal_hw_hpd_destruct(hpd);
-}
-
-static void destroy(
+static void dal_hw_hpd_destroy(
 	struct hw_gpio_pin **ptr)
 {
 	struct hw_hpd *hpd = HW_HPD_FROM_BASE(*ptr);
 
-	destruct(hpd);
+	dal_hw_hpd_destruct(hpd);
 
 	kfree(hpd);
 
@@ -120,7 +104,7 @@ static enum gpio_result set_config(
 }
 
 static const struct hw_gpio_pin_funcs funcs = {
-	.destroy = destroy,
+	.destroy = dal_hw_hpd_destroy,
 	.open = dal_hw_gpio_open,
 	.get_value = get_value,
 	.set_value = dal_hw_gpio_set_value,
@@ -129,14 +113,14 @@ static const struct hw_gpio_pin_funcs funcs = {
 	.close = dal_hw_gpio_close,
 };
 
-static void construct(
-	struct hw_hpd *hpd,
+static void dal_hw_hpd_construct(
+	struct hw_hpd *pin,
 	enum gpio_id id,
 	uint32_t en,
 	struct dc_context *ctx)
 {
-	dal_hw_hpd_construct(hpd, id, en, ctx);
-	hpd->base.base.funcs = &funcs;
+	dal_hw_gpio_construct(&pin->base, id, en, ctx);
+	pin->base.base.funcs = &funcs;
 }
 
 void dal_hw_hpd_init(
@@ -156,7 +140,7 @@ void dal_hw_hpd_init(
 		return;
 	}
 
-	construct(*hw_hpd, id, en, ctx);
+	dal_hw_hpd_construct(*hw_hpd, id, en, ctx);
 }
 
 struct hw_gpio_pin *dal_hw_hpd_get_pin(struct gpio *gpio)
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
index f2046f55d6a8..5d396657a1ee 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
@@ -43,15 +43,11 @@
 #include "dce80/hw_translate_dce80.h"
 #include "dce110/hw_translate_dce110.h"
 #include "dce120/hw_translate_dce120.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "dcn10/hw_translate_dcn10.h"
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dcn20/hw_translate_dcn20.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #include "dcn21/hw_translate_dcn21.h"
-#endif
 
 #include "diagnostics/hw_translate_diag.h"
 
@@ -85,19 +81,15 @@ bool dal_hw_translate_init(
 	case DCE_VERSION_12_1:
 		dal_hw_translate_dce120_init(translate);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case DCN_VERSION_1_0:
 	case DCN_VERSION_1_01:
 		dal_hw_translate_dcn10_init(translate);
 		return true;
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case DCN_VERSION_2_0:
 		dal_hw_translate_dcn20_init(translate);
 		return true;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case DCN_VERSION_2_1:
 		dal_hw_translate_dcn21_init(translate);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_status.h b/drivers/gpu/drm/amd/display/dc/inc/core_status.h
index fd39e2abe2ed..4ead89dd7c41 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_status.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_status.h
@@ -43,10 +43,8 @@ enum dc_status {
 	DC_FAIL_BANDWIDTH_VALIDATE = 13, /* BW and Watermark validation */
 	DC_FAIL_SCALING = 14,
 	DC_FAIL_DP_LINK_TRAINING = 15,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	DC_FAIL_DSC_VALIDATE = 16,
 	DC_NO_DSC_RESOURCE = 17,
-#endif
 	DC_FAIL_UNSUPPORTED_1 = 18,
 	DC_FAIL_CLK_EXCEED_MAX = 21,
 	DC_FAIL_CLK_BELOW_MIN = 22, /*THIS IS MIN PER IP*/
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index a831079607cd..f285b76888fb 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -33,13 +33,11 @@
 #include "dc_bios_types.h"
 #include "mem_input.h"
 #include "hubp.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "mpc.h"
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dwb.h"
 #include "mcif_wb.h"
-#endif
 
 #define MAX_CLOCK_SOURCES 7
 
@@ -89,9 +87,7 @@ void core_link_set_avmute(struct pipe_ctx *pipe_ctx, bool enable);
 struct resource_pool;
 struct dc_state;
 struct resource_context;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 struct clk_bw_params;
-#endif
 
 struct resource_funcs {
 	void (*destroy)(struct resource_pool **pool);
@@ -105,7 +101,7 @@ struct resource_funcs {
 
 	int (*populate_dml_pipes)(
 		struct dc *dc,
-		struct resource_context *res_ctx,
+		struct dc_state *context,
 		display_e2e_pipe_params_st *pipes);
 
 	enum dc_status (*validate_global)(
@@ -135,7 +131,6 @@ struct resource_funcs {
 			struct resource_context *res_ctx,
 			const struct resource_pool *pool,
 			struct dc_stream_state *stream);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*populate_dml_writeback_from_context)(
 			struct dc *dc,
 			struct resource_context *res_ctx,
@@ -146,12 +141,9 @@ struct resource_funcs {
 			struct dc_state *context,
 			display_e2e_pipe_params_st *pipes,
 			int pipe_cnt);
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	void (*update_bw_bounding_box)(
 			struct dc *dc,
 			struct clk_bw_params *bw_params);
-#endif
 
 };
 
@@ -180,7 +172,6 @@ struct resource_pool {
 	struct dce_i2c_sw *sw_i2cs[MAX_PIPES];
 	bool i2c_hw_buffer_in_use;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dwbc *dwbc[MAX_DWB_PIPES];
 	struct mcif_wb *mcif_wb[MAX_DWB_PIPES];
 	struct {
@@ -188,11 +179,8 @@ struct resource_pool {
 		unsigned int gsl_1:1;
 		unsigned int gsl_2:1;
 	} gsl_groups;
-#endif
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct display_stream_compressor *dscs[MAX_PIPES];
-#endif
 
 	unsigned int pipe_count;
 	unsigned int underlay_pipe_index;
@@ -206,9 +194,7 @@ struct resource_pool {
 	unsigned int timing_generator_count;
 	unsigned int mpcc_count;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	unsigned int writeback_pipe_count;
-#endif
 	/*
 	 * reserved clock source for DP
 	 */
@@ -226,9 +212,12 @@ struct resource_pool {
 
 	struct abm *abm;
 	struct dmcu *dmcu;
+	struct dmub_psr *psr;
 
 	const struct resource_funcs *funcs;
 	const struct resource_caps *res_cap;
+
+	struct ddc_service *oem_device;
 };
 
 struct dcn_fe_bandwidth {
@@ -238,9 +227,7 @@ struct dcn_fe_bandwidth {
 
 struct stream_resource {
 	struct output_pixel_processor *opp;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct display_stream_compressor *dsc;
-#endif
 	struct timing_generator *tg;
 	struct stream_encoder *stream_enc;
 	struct audio *audio;
@@ -249,12 +236,10 @@ struct stream_resource {
 	struct encoder_info_frame encoder_info_frame;
 
 	struct abm *abm;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* There are only (num_pipes+1)/2 groups. 0 means unassigned,
 	 * otherwise it's using group number 'gsl_group-1'
 	 */
 	uint8_t gsl_group;
-#endif
 };
 
 struct plane_resource {
@@ -306,17 +291,15 @@ struct pipe_ctx {
 	struct pipe_ctx *next_odm_pipe;
 	struct pipe_ctx *prev_odm_pipe;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	struct _vcs_dpi_display_dlg_regs_st dlg_regs;
 	struct _vcs_dpi_display_ttu_regs_st ttu_regs;
 	struct _vcs_dpi_display_rq_regs_st rq_regs;
 	struct _vcs_dpi_display_pipe_dest_params_st pipe_dlg_param;
 #endif
 	union pipe_update_flags update_flags;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct dwbc *dwbc;
 	struct mcif_wb *mcif_wb;
-#endif
 };
 
 struct resource_context {
@@ -325,9 +308,7 @@ struct resource_context {
 	bool is_audio_acquired[MAX_PIPES];
 	uint8_t clock_source_ref_count[MAX_CLOCK_SOURCES];
 	uint8_t dp_clock_source_ref_count;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	bool is_dsc_acquired[MAX_PIPES];
-#endif
 };
 
 struct dce_bw_output {
@@ -347,18 +328,14 @@ struct dce_bw_output {
 	int blackout_recovery_time_us;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dcn_bw_writeback {
 	struct mcif_arb_params mcif_wb_arb[MAX_DWB_PIPES];
 };
-#endif
 
 struct dcn_bw_output {
 	struct dc_clocks clk;
 	struct dcn_watermark_set watermarks;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dcn_bw_writeback bw_writeback;
-#endif
 };
 
 union bw_output {
@@ -392,7 +369,7 @@ struct dc_state {
 
 	/* Note: these are big structures, do *not* put on stack! */
 	struct dm_pp_display_configuration pp_display_cfg;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	struct dcn_bw_internal_vars dcn_bw_vars;
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 14716ba35662..de2d160114db 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -105,7 +105,7 @@ int dc_link_aux_transfer_raw(struct ddc_service *ddc,
 bool dc_link_aux_transfer_with_retries(struct ddc_service *ddc,
 		struct aux_payload *payload);
 
-enum dc_status dc_link_aux_configure_timeout(struct ddc_service *ddc,
+uint32_t dc_link_aux_configure_timeout(struct ddc_service *ddc,
 		uint32_t timeout);
 
 void dal_ddc_service_write_scdc_data(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
index 045138dbdccb..8b1f0ce6c2a7 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
@@ -28,8 +28,8 @@
 
 #define LINK_TRAINING_ATTEMPTS 4
 #define LINK_TRAINING_RETRY_DELAY 50 /* ms */
-#define LINK_AUX_DEFAULT_EXTENDED_TIMEOUT_PERIOD 32000 /*us*/
-#define LINK_AUX_DEFAULT_TIMEOUT_PERIOD 400 /*us*/
+#define LINK_AUX_DEFAULT_EXTENDED_TIMEOUT_PERIOD 3200 /*us*/
+#define LINK_AUX_DEFAULT_TIMEOUT_PERIOD 552 /*us*/
 
 struct dc_link;
 struct dc_stream_state;
@@ -57,10 +57,11 @@ void decide_link_settings(
 	struct dc_link_settings *link_setting);
 
 bool perform_link_training_with_retries(
-	struct dc_link *link,
 	const struct dc_link_settings *link_setting,
 	bool skip_video_pattern,
-	int attempts);
+	int attempts,
+	struct pipe_ctx *pipe_ctx,
+	enum signal_type signal);
 
 bool is_mst_supported(struct dc_link *link);
 
@@ -75,13 +76,13 @@ void dp_enable_mst_on_sink(struct dc_link *link, bool enable);
 enum dp_panel_mode dp_get_panel_mode(struct dc_link *link);
 void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+bool dp_overwrite_extended_receiver_cap(struct dc_link *link);
+
 void dp_set_fec_ready(struct dc_link *link, bool ready);
 void dp_set_fec_enable(struct dc_link *link, bool enable);
 bool dp_set_dsc_enable(struct pipe_ctx *pipe_ctx, bool enable);
 bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable);
 void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable);
 bool dp_update_dsc_config(struct pipe_ctx *pipe_ctx);
-#endif
 
 #endif /* __DC_LINK_DP_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calc_math.h
index 45a07eeffbb6..45a07eeffbb6 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calc_math.h
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index 026e6a2a2c44..ac530c057ddd 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -31,7 +31,6 @@
 #define DCN_MINIMUM_DISPCLK_Khz 100000
 #define DCN_MINIMUM_DPPCLK_Khz 100000
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 /* Constants */
 #define DDR4_DRAM_WIDTH   64
 #define WM_A 0
@@ -39,12 +38,10 @@
 #define WM_C 2
 #define WM_D 3
 #define WM_SET_COUNT 4
-#endif
 
 #define DCN_MINIMUM_DISPCLK_Khz 100000
 #define DCN_MINIMUM_DPPCLK_Khz 100000
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 /* Will these bw structures be ASIC specific? */
 
 #define MAX_NUM_DPM_LVL		8
@@ -154,7 +151,6 @@ struct clk_bw_params {
 	struct clk_limit_table clk_table;
 	struct wm_table wm_table;
 };
-#endif
 /* Public interfaces */
 
 struct clk_states {
@@ -195,9 +191,8 @@ struct clk_mgr {
 	bool psr_allow_active_cache;
 	int dprefclk_khz; // Used by program pixel clock in clock source funcs, need to figureout where this goes
 	int dentist_vco_freq_khz;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
+	struct clk_state_registers_and_bypass boot_snapshot;
 	struct clk_bw_params *bw_params;
-#endif
 };
 
 /* forward declarations */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
index a17a77192690..862952c0286a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
@@ -96,12 +96,10 @@ enum dentist_divider_range {
 	.MP1_SMN_C2PMSG_83 = mmMP1_SMN_C2PMSG_83, \
 	.MP1_SMN_C2PMSG_67 = mmMP1_SMN_C2PMSG_67
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define CLK_REG_LIST_NV10() \
 	SR(DENTIST_DISPCLK_CNTL), \
 	CLK_SRI(CLK3_CLK_PLL_REQ, CLK3, 0), \
 	CLK_SRI(CLK3_CLK2_DFS_CNTL, CLK3, 0)
-#endif
 
 #define CLK_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
@@ -120,7 +118,6 @@ enum dentist_divider_range {
 	CLK_SF(MP1_SMN_C2PMSG_83, CONTENT, mask_sh),\
 	CLK_SF(MP1_SMN_C2PMSG_91, CONTENT, mask_sh),
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define CLK_COMMON_MASK_SH_LIST_DCN20_BASE(mask_sh) \
 	CLK_COMMON_MASK_SH_LIST_DCN_COMMON_BASE(mask_sh),\
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, mask_sh),\
@@ -130,7 +127,6 @@ enum dentist_divider_range {
 	CLK_COMMON_MASK_SH_LIST_DCN20_BASE(mask_sh),\
 	CLK_SF(CLK3_0_CLK3_CLK_PLL_REQ, FbMult_int, mask_sh),\
 	CLK_SF(CLK3_0_CLK3_CLK_PLL_REQ, FbMult_frac, mask_sh)
-#endif
 
 #define CLK_REG_FIELD_LIST(type) \
 	type DPREFCLK_SRC_SEL; \
@@ -143,30 +139,24 @@ enum dentist_divider_range {
  ****************** Clock Manager Private Structures ***********************************
  ***************************************************************************************
  */
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define CLK20_REG_FIELD_LIST(type) \
 	type DENTIST_DPPCLK_WDIVIDER; \
 	type DENTIST_DPPCLK_CHG_DONE; \
 	type FbMult_int; \
 	type FbMult_frac;
-#endif
 
 #define VBIOS_SMU_REG_FIELD_LIST(type) \
 	type CONTENT;
 
 struct clk_mgr_shift {
 	CLK_REG_FIELD_LIST(uint8_t)
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	CLK20_REG_FIELD_LIST(uint8_t)
-#endif
 	VBIOS_SMU_REG_FIELD_LIST(uint32_t)
 };
 
 struct clk_mgr_mask {
 	CLK_REG_FIELD_LIST(uint32_t)
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	CLK20_REG_FIELD_LIST(uint32_t)
-#endif
 	VBIOS_SMU_REG_FIELD_LIST(uint32_t)
 };
 
@@ -174,10 +164,8 @@ struct clk_mgr_registers {
 	uint32_t DPREFCLK_CNTL;
 	uint32_t DENTIST_DISPCLK_CNTL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	uint32_t CLK3_CLK2_DFS_CNTL;
 	uint32_t CLK3_CLK_PLL_REQ;
-#endif
 
 	uint32_t MP1_SMN_C2PMSG_67;
 	uint32_t MP1_SMN_C2PMSG_83;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
index c81a17aeaa25..c0dc1d0f5cae 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
@@ -52,7 +52,6 @@ struct dcn_hubbub_wm {
 	struct dcn_hubbub_wm_set sets[4];
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 enum dcn_hubbub_page_table_depth {
 	DCN_PAGE_TABLE_DEPTH_1_LEVEL,
 	DCN_PAGE_TABLE_DEPTH_2_LEVEL,
@@ -101,13 +100,11 @@ struct hubbub_addr_config {
 	} default_addrs;
 };
 
-#endif
 struct hubbub_funcs {
 	void (*update_dchub)(
 			struct hubbub *hubbub,
 			struct dchub_init_data *dh_data);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	int (*init_dchub_sys_ctx)(
 			struct hubbub *hubbub,
 			struct dcn_hubbub_phys_addr_config *pa_config);
@@ -116,7 +113,6 @@ struct hubbub_funcs {
 			struct dcn_hubbub_virt_addr_config *va_config,
 			int vmid);
 
-#endif
 	bool (*get_dcc_compression_cap)(struct hubbub *hubbub,
 			const struct dc_dcc_surface_param *input,
 			struct dc_surface_dcc_cap *output);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
index c68f0ce346c7..5315f1f86b21 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
@@ -52,6 +52,8 @@ struct dmcu {
 	enum dmcu_state dmcu_state;
 	struct dmcu_version dmcu_version;
 	unsigned int cached_wait_loop_number;
+	uint32_t psp_version;
+	bool auto_load_dmcu;
 };
 
 struct dmcu_funcs {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 474c7194a9f8..45ef390ae052 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -36,14 +36,10 @@ struct dpp {
 	struct dpp_caps *caps;
 	struct pwl_params regamma_params;
 	struct pwl_params degamma_params;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dpp_cursor_attributes cur_attr;
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct pwl_params shaper_params;
 	bool cm_bypass_mode;
-#endif
 };
 
 struct dpp_input_csc_matrix {
@@ -51,12 +47,31 @@ struct dpp_input_csc_matrix {
 	uint16_t regval[12];
 };
 
+static const struct dpp_input_csc_matrix dpp_input_csc_matrix[] = {
+	{COLOR_SPACE_SRGB,
+		{0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
+	{COLOR_SPACE_SRGB_LIMITED,
+		{0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
+	{COLOR_SPACE_YCBCR601,
+		{0x2cdd, 0x2000, 0, 0xe991, 0xe926, 0x2000, 0xf4fd, 0x10ef,
+						0, 0x2000, 0x38b4, 0xe3a6} },
+	{COLOR_SPACE_YCBCR601_LIMITED,
+		{0x3353, 0x2568, 0, 0xe400, 0xe5dc, 0x2568, 0xf367, 0x1108,
+						0, 0x2568, 0x40de, 0xdd3a} },
+	{COLOR_SPACE_YCBCR709,
+		{0x3265, 0x2000, 0, 0xe6ce, 0xf105, 0x2000, 0xfa01, 0xa7d, 0,
+						0x2000, 0x3b61, 0xe24f} },
+
+	{COLOR_SPACE_YCBCR709_LIMITED,
+		{0x39a6, 0x2568, 0, 0xe0d6, 0xeedd, 0x2568, 0xf925, 0x9a8, 0,
+						0x2568, 0x43ee, 0xdbb2} }
+};
+
 struct dpp_grph_csc_adjustment {
 	struct fixed31_32 temperature_matrix[CSC_TEMPERATURE_MATRIX_SIZE];
 	enum graphics_gamut_adjust_type gamut_adjust_type;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 struct cnv_color_keyer_params {
 	int color_keyer_en;
 	int color_keyer_mode;
@@ -82,7 +97,6 @@ struct cnv_alpha_2bit_lut {
 	int lut2;
 	int lut3;
 };
-#endif
 
 struct dcn_dpp_state {
 	uint32_t is_enabled;
@@ -190,12 +204,8 @@ struct dpp_funcs {
 			enum surface_pixel_format format,
 			enum expansion_mode mode,
 			struct dc_csc_transform input_csc_color_matrix,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 			enum dc_color_space input_color_space,
 			struct cnv_alpha_2bit_lut *alpha_2bit_lut);
-#else
-			enum dc_color_space input_color_space);
-#endif
 
 	void (*dpp_full_bypass)(struct dpp *dpp_base);
 
@@ -224,7 +234,6 @@ struct dpp_funcs {
 			bool dppclk_div,
 			bool enable);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool (*dpp_program_blnd_lut)(
 			struct dpp *dpp,
 			const struct pwl_params *params);
@@ -237,7 +246,6 @@ struct dpp_funcs {
 	void (*dpp_cnv_set_alpha_keyer)(
 			struct dpp *dpp_base,
 			struct cnv_color_keyer_params *color_keyer);
-#endif
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
index c6ff3d78b435..c59740084ebc 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #ifndef __DAL_DSC_H__
 #define __DAL_DSC_H__
 
@@ -98,4 +97,3 @@ struct dsc_funcs {
 };
 
 #endif
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h
index ff1a07b35c85..459f95f52486 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h
@@ -51,20 +51,15 @@ enum dwb_source {
 	dwb_src_otg3,		/* for DCN1.x/DCN2.x */
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 /* DCN1.x, DCN2.x support 2 pipes */
-#else
-/* DCN1.x supports 2 pipes */
-#endif
 enum dwb_pipe {
 	dwb_pipe0 = 0,
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	dwb_pipe1,
 #endif
 	dwb_pipe_max_num,
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 enum dwb_frame_capture_enable {
 	DWB_FRAME_CAPTURE_DISABLE = 0,
 	DWB_FRAME_CAPTURE_ENABLE = 1,
@@ -77,9 +72,7 @@ enum wbscl_coef_filter_type_sel {
 	WBSCL_COEF_CHROMA_HORZ_FILTER = 3
 };
 
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dwb_warmup_params {
 	bool	warmup_en;	/* false: normal mode, true: enable pattern generator */
 	bool	warmup_mode;	/* false: 420, true: 444 */
@@ -88,7 +81,6 @@ struct dwb_warmup_params {
 	int	warmup_width;	/* Pattern width (pixels) */
 	int	warmup_height;	/* Pattern height (lines) */
 };
-#endif
 
 struct dwb_caps {
 	enum dce_version hw_version;	/* DCN engine version. */
@@ -121,7 +113,8 @@ struct dwbc {
 	int wb_src_plane_inst;/*hubp, mpcc, inst*/
 	bool update_privacymask;
 	uint32_t mask_id;
-
+        int otg_inst;
+        bool mvc_cfg;
 };
 
 struct dwbc_funcs {
@@ -150,13 +143,11 @@ struct dwbc_funcs {
 		struct dwbc *dwbc,
 		bool is_new_content);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 	void (*set_warmup)(
 		struct dwbc *dwbc,
 		struct dwb_warmup_params *warmup_params);
 
-#endif
 
 	bool (*get_dwb_status)(
 		struct dwbc *dwbc);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 809b62b51a43..2cb8466e657b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -38,9 +38,7 @@ enum cursor_pitch {
 };
 
 enum cursor_lines_per_chunk {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	CURSOR_LINE_PER_CHUNK_1 = 0, /* new for DCN2 */
-#endif
 	CURSOR_LINE_PER_CHUNK_2 = 1,
 	CURSOR_LINE_PER_CHUNK_4,
 	CURSOR_LINE_PER_CHUNK_8,
@@ -65,6 +63,26 @@ struct hubp {
 	bool power_gated;
 };
 
+struct surface_flip_registers {
+	uint32_t DCSURF_SURFACE_CONTROL;
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS;
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C;
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_C;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C;
+	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS;
+	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS;
+	bool tmz_surface;
+	bool immediate;
+	uint8_t vmid;
+	bool grph_stereo;
+};
+
 struct hubp_funcs {
 	void (*hubp_setup)(
 			struct hubp *hubp,
@@ -86,6 +104,9 @@ struct hubp_funcs {
 			const struct rect *viewport,
 			const struct rect *viewport_c);
 
+	void (*apply_PLAT_54186_wa)(struct hubp *hubp,
+			const struct dc_plane_address *address);
+
 	bool (*hubp_program_surface_flip_and_addr)(
 		struct hubp *hubp,
 		const struct dc_plane_address *address,
@@ -139,7 +160,6 @@ struct hubp_funcs {
 	unsigned int (*hubp_get_underflow_status)(struct hubp *hubp);
 	void (*hubp_init)(struct hubp *hubp);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*dmdata_set_attributes)(
 			struct hubp *hubp,
 			const struct dc_dmdata_attributes *attr);
@@ -159,7 +179,13 @@ struct hubp_funcs {
 	void (*hubp_set_flip_control_surface_gsl)(
 		struct hubp *hubp,
 		bool enable);
-#endif
+
+	void (*validate_dml_output)(
+			struct hubp *hubp,
+			struct dc_context *ctx,
+			struct _vcs_dpi_display_rq_regs_st *dml_rq_regs,
+			struct _vcs_dpi_display_dlg_regs_st *dml_dlg_attr,
+			struct _vcs_dpi_display_ttu_regs_st *dml_ttu_attr);
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
index f82365e2d03c..75d419081e76 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
@@ -36,9 +36,7 @@
 
 #define MAX_AUDIOS 7
 #define MAX_PIPES 6
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define MAX_DWB_PIPES	1
-#endif
 
 struct gamma_curve {
 	uint32_t offset;
@@ -81,7 +79,6 @@ struct pwl_result_data {
 	uint32_t delta_blue_reg;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_rgb {
 	uint32_t red;
 	uint32_t green;
@@ -110,7 +107,6 @@ struct tetrahedral_params {
 	bool use_12bits;
 
 };
-#endif
 
 /* arr_curve_points - regamma regions/segments specification
  * arr_points - beginning and end point specified separately (only one on DCE)
@@ -195,13 +191,11 @@ enum opp_regamma {
 	OPP_REGAMMA_USER
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 enum optc_dsc_mode {
 	OPTC_DSC_DISABLED = 0,
 	OPTC_DSC_ENABLED_444 = 1, /* 'RGB 444' or 'Simple YCbCr 4:2:2' (4:2:2 upsampled to 4:4:4) */
 	OPTC_DSC_ENABLED_NATIVE_SUBSAMPLED = 2 /* Native 4:2:2 or 4:2:0 */
 };
-#endif
 
 struct dc_bias_and_scale {
 	uint16_t scale_red;
@@ -224,12 +218,8 @@ enum test_pattern_mode {
 	TEST_PATTERN_MODE_VERTICALBARS,
 	TEST_PATTERN_MODE_HORIZONTALBARS,
 	TEST_PATTERN_MODE_SINGLERAMP_RGB,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	TEST_PATTERN_MODE_DUALRAMP_RGB,
 	TEST_PATTERN_MODE_XR_BIAS_RGB
-#else
-	TEST_PATTERN_MODE_DUALRAMP_RGB
-#endif
 };
 
 enum test_pattern_color_format {
@@ -255,6 +245,13 @@ enum controller_dp_test_pattern {
 	CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR
 };
 
+enum controller_dp_color_space {
+	CONTROLLER_DP_COLOR_SPACE_RGB,
+	CONTROLLER_DP_COLOR_SPACE_YCBCR601,
+	CONTROLLER_DP_COLOR_SPACE_YCBCR709,
+	CONTROLLER_DP_COLOR_SPACE_UDEFINED
+};
+
 enum dc_lut_mode {
 	LUT_BYPASS,
 	LUT_RAM_A,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
index b21909216fb6..fb748f082c56 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
@@ -113,26 +113,21 @@ struct link_encoder {
 	struct encoder_feature_support features;
 	enum transmitter transmitter;
 	enum hpd_source_id hpd_source;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	bool usbc_combo_phy;
-#endif
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct link_enc_state {
 
 		uint32_t dphy_fec_en;
 		uint32_t dphy_fec_ready_shadow;
 		uint32_t dphy_fec_active_status;
+		uint32_t dp_link_training_complete;
 
 };
-#endif
 
 struct link_encoder_funcs {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	void (*read_state)(
 			struct link_encoder *enc, struct link_enc_state *s);
-#endif
 	bool (*validate_output_with_stream)(
 		struct link_encoder *enc, const struct dc_stream_state *stream);
 	void (*hw_init)(struct link_encoder *enc);
@@ -174,7 +169,6 @@ struct link_encoder_funcs {
 	unsigned int (*get_dig_frontend)(struct link_encoder *enc);
 	void (*destroy)(struct link_encoder **enc);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*fec_set_enable)(struct link_encoder *enc,
 		bool enable);
 
@@ -182,7 +176,6 @@ struct link_encoder_funcs {
 		bool ready);
 
 	bool (*fec_is_active)(struct link_encoder *enc);
-#endif
 	bool (*is_in_alt_mode) (struct link_encoder *enc);
 
 	void (*get_max_link_cap)(struct link_encoder *enc,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
index 67b610d6d91f..2e2310f1901a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
@@ -40,11 +40,9 @@ struct cstate_pstate_watermarks_st {
 struct dcn_watermarks {
 	uint32_t pte_meta_urgent_ns;
 	uint32_t urgent_ns;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	uint32_t frac_urg_bw_nom;
 	uint32_t frac_urg_bw_flip;
 	int32_t urgent_latency_ns;
-#endif
 	struct cstate_pstate_watermarks_st cstate_pstate;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 58826be81395..094afc4c8173 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -31,9 +31,7 @@
 #define MAX_MPCC 6
 #define MAX_OPP 6
 
-#if   defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define MAX_DWB		1
-#endif
 
 enum mpc_output_csc_mode {
 	MPC_OUTPUT_CSC_DISABLE = 0,
@@ -66,14 +64,12 @@ struct mpcc_blnd_cfg {
 	int global_alpha;
 	bool overlap_only;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* MPCC top/bottom gain settings */
 	int bottom_gain_mode;
 	int background_color_bpc;
 	int top_gain;
 	int bottom_inside_gain;
 	int bottom_outside_gain;
-#endif
 };
 
 struct mpcc_sm_cfg {
@@ -90,7 +86,6 @@ struct mpcc_sm_cfg {
 	int force_next_field_polarity;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct mpc_denorm_clamp {
 	int clamp_max_r_cr;
 	int clamp_min_r_cr;
@@ -99,7 +94,6 @@ struct mpc_denorm_clamp {
 	int clamp_max_b_cb;
 	int clamp_min_b_cb;
 };
-#endif
 
 /*
  * MPCC connection and blending configuration for a single MPCC instance.
@@ -126,10 +120,8 @@ struct mpc {
 	struct dc_context *ctx;
 
 	struct mpcc mpcc_array[MAX_MPCC];
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct pwl_params blender_params;
 	bool cm_bypass_mode;
-#endif
 };
 
 struct mpcc_state {
@@ -230,7 +222,6 @@ struct mpc_funcs {
 		struct mpc *mpc,
 		struct mpc_tree *tree);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*set_denorm)(struct mpc *mpc,
 			int opp_id,
 			enum dc_color_depth output_depth);
@@ -258,7 +249,6 @@ struct mpc_funcs {
 			struct mpc *mpc,
 			int mpcc_id,
 			bool power_on);
-#endif
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
index 18def2b6fafe..7575564b2265 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
@@ -263,9 +263,7 @@ struct oppbuf_params {
 	enum oppbuf_display_segmentation mso_segmentation;
 	uint32_t mso_overlap_pixel_num;
 	uint32_t pixel_repetition;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t num_segment_padded_pixels;
-#endif
 };
 
 struct opp_funcs {
@@ -305,10 +303,10 @@ struct opp_funcs {
 			struct output_pixel_processor *opp,
 			bool enable);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*opp_set_disp_pattern_generator)(
 			struct output_pixel_processor *opp,
 			enum controller_dp_test_pattern test_pattern,
+			enum controller_dp_color_space color_space,
 			enum dc_color_depth color_depth,
 			const struct tg_color *solid_color,
 			int width,
@@ -324,7 +322,6 @@ struct opp_funcs {
 	void (*opp_program_left_edge_extra_pixel)(
 			struct output_pixel_processor *opp,
 			bool count);
-#endif
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
index 6305e388612a..351b387ad606 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
@@ -65,13 +65,11 @@ struct audio_clock_info {
 	uint32_t cts_48khz;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 enum dynamic_metadata_mode {
 	dmdata_dp,
 	dmdata_hdmi,
 	dmdata_dolby_vision
 };
-#endif
 
 struct encoder_info_frame {
 	/* auxiliary video information */
@@ -90,9 +88,7 @@ struct encoder_info_frame {
 struct encoder_unblank_param {
 	struct dc_link_settings link_settings;
 	struct dc_crtc_timing timing;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	int opp_cnt;
-#endif
 };
 
 struct encoder_set_dp_phy_pattern_param {
@@ -109,7 +105,6 @@ struct stream_encoder {
 	enum engine_id id;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct enc_state {
 	uint32_t dsc_mode;  // DISABLED  0; 1 or 2 indicate enabled state.
 	uint32_t dsc_slice_width;
@@ -119,13 +114,13 @@ struct enc_state {
 	uint32_t sec_gsp_pps_enable;
 	uint32_t sec_stream_enable;
 };
-#endif
 
 struct stream_encoder_funcs {
 	void (*dp_set_stream_attribute)(
 		struct stream_encoder *enc,
 		struct dc_crtc_timing *crtc_timing,
 		enum dc_color_space output_color_space,
+		bool use_vsc_sdp_for_colorimetry,
 		uint32_t enable_sdp_splitting);
 
 	void (*hdmi_set_stream_attribute)(
@@ -219,8 +214,6 @@ struct stream_encoder_funcs {
 		enum dc_pixel_encoding *encoding,
 		enum dc_color_depth *depth);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	void (*enc_read_state)(struct stream_encoder *enc, struct enc_state *s);
 
 	void (*dp_set_dsc_config)(
@@ -232,7 +225,6 @@ struct stream_encoder_funcs {
 	void (*dp_set_dsc_pps_info_packet)(struct stream_encoder *enc,
 				bool enable,
 				uint8_t *dsc_packed_pps);
-#endif
 
 	void (*set_dynamic_metadata)(struct stream_encoder *enc,
 			bool enable,
@@ -242,7 +234,6 @@ struct stream_encoder_funcs {
 	void (*dp_set_odm_combine)(
 		struct stream_encoder *enc,
 		bool odm_combine);
-#endif
 };
 
 #endif /* STREAM_ENCODER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index 27c73caf74ee..e5e7d94026fc 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -195,10 +195,8 @@ struct timing_generator_funcs {
 	void (*lock)(struct timing_generator *tg);
 	void (*lock_doublebuffer_disable)(struct timing_generator *tg);
 	void (*lock_doublebuffer_enable)(struct timing_generator *tg);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void(*triplebuffer_unlock)(struct timing_generator *tg);
 	void(*triplebuffer_lock)(struct timing_generator *tg);
-#endif
 	void (*enable_reset_trigger)(struct timing_generator *tg,
 				     int source_tg_inst);
 	void (*enable_crtc_reset)(struct timing_generator *tg,
@@ -210,7 +208,8 @@ struct timing_generator_funcs {
 					bool enable, const struct dc_crtc_timing *timing);
 	void (*set_drr)(struct timing_generator *tg, const struct drr_params *params);
 	void (*set_static_screen_control)(struct timing_generator *tg,
-							uint32_t value);
+						uint32_t event_triggers,
+						uint32_t num_frames);
 	void (*set_test_pattern)(
 		struct timing_generator *tg,
 		enum controller_dp_test_pattern test_pattern,
@@ -235,7 +234,6 @@ struct timing_generator_funcs {
 	bool (*is_optc_underflow_occurred)(struct timing_generator *tg);
 	void (*clear_optc_underflow)(struct timing_generator *tg);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*set_dwb_source)(struct timing_generator *optc,
 		uint32_t dwb_pipe_inst);
 
@@ -243,7 +241,6 @@ struct timing_generator_funcs {
 			uint32_t *num_of_input_segments,
 			uint32_t *seg0_src_sel,
 			uint32_t *seg1_src_sel);
-#endif
 
 	/**
 	 * Configure CRCs for the given timing generator. Return false if TG is
@@ -267,13 +264,10 @@ struct timing_generator_funcs {
 	void (*set_vtg_params)(struct timing_generator *optc,
 			const struct dc_crtc_timing *dc_crtc_timing);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	void (*set_dsc_config)(struct timing_generator *optc,
 			       enum optc_dsc_mode dsc_mode,
 			       uint32_t dsc_bytes_per_pixel,
 			       uint32_t dsc_slice_width);
-#endif
 	void (*set_odm_bypass)(struct timing_generator *optc, const struct dc_crtc_timing *dc_crtc_timing);
 	void (*set_odm_combine)(struct timing_generator *optc, int *opp_id, int opp_cnt,
 			struct dc_crtc_timing *timing);
@@ -281,7 +275,6 @@ struct timing_generator_funcs {
 	void (*set_gsl_source_select)(struct timing_generator *optc,
 			int group_idx,
 			uint32_t gsl_ready_signal);
-#endif
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index d39c1e11def5..209118f9f193 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -32,326 +32,160 @@
 #include "inc/hw/link_encoder.h"
 #include "core_status.h"
 
-enum pipe_gating_control {
-	PIPE_GATING_CONTROL_DISABLE = 0,
-	PIPE_GATING_CONTROL_ENABLE,
-	PIPE_GATING_CONTROL_INIT
-};
-
 enum vline_select {
 	VLINE0,
 	VLINE1
 };
 
-struct dce_hwseq_wa {
-	bool blnd_crtc_trigger;
-	bool DEGVIDCN10_253;
-	bool false_optc_underflow;
-	bool DEGVIDCN10_254;
-	bool DEGVIDCN21;
-};
-
-struct hwseq_wa_state {
-	bool DEGVIDCN10_253_applied;
-};
-
-struct dce_hwseq {
-	struct dc_context *ctx;
-	const struct dce_hwseq_registers *regs;
-	const struct dce_hwseq_shift *shifts;
-	const struct dce_hwseq_mask *masks;
-	struct dce_hwseq_wa wa;
-	struct hwseq_wa_state wa_state;
-};
-
 struct pipe_ctx;
 struct dc_state;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_stream_status;
 struct dc_writeback_info;
-#endif
 struct dchub_init_data;
-struct dc_static_screen_events;
+struct dc_static_screen_params;
 struct resource_pool;
-struct resource_context;
-struct stream_resource;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 struct dc_phy_addr_space_config;
 struct dc_virtual_addr_space_config;
-#endif
-struct hubp;
 struct dpp;
+struct dce_hwseq;
 
 struct hw_sequencer_funcs {
+	/* Embedded Display Related */
+	void (*edp_power_control)(struct dc_link *link, bool enable);
+	void (*edp_wait_for_hpd_ready)(struct dc_link *link, bool power_up);
 
-	void (*disable_stream_gating)(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-	void (*enable_stream_gating)(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
+	/* Pipe Programming Related */
 	void (*init_hw)(struct dc *dc);
-
-	void (*init_pipes)(struct dc *dc, struct dc_state *context);
-
-	enum dc_status (*apply_ctx_to_hw)(
-			struct dc *dc, struct dc_state *context);
-
-	void (*reset_hw_ctx_wrap)(
-			struct dc *dc, struct dc_state *context);
-
-	void (*apply_ctx_for_surface)(
-			struct dc *dc,
+	void (*enable_accelerated_mode)(struct dc *dc,
+			struct dc_state *context);
+	enum dc_status (*apply_ctx_to_hw)(struct dc *dc,
+			struct dc_state *context);
+	void (*disable_plane)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*apply_ctx_for_surface)(struct dc *dc,
 			const struct dc_stream_state *stream,
-			int num_planes,
+			int num_planes, struct dc_state *context);
+	void (*program_front_end_for_ctx)(struct dc *dc,
 			struct dc_state *context);
-
-	void (*program_gamut_remap)(
+	void (*update_plane_addr)(const struct dc *dc,
 			struct pipe_ctx *pipe_ctx);
-
-	void (*program_output_csc)(struct dc *dc,
-			struct pipe_ctx *pipe_ctx,
-			enum dc_color_space colorspace,
-			uint16_t *matrix,
-			int opp_id);
-
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	void (*program_front_end_for_ctx)(
-			struct dc *dc,
-			struct dc_state *context);
-	void (*program_triplebuffer)(
-		const struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		bool enableTripleBuffer);
-	void (*set_flip_control_gsl)(
-		struct pipe_ctx *pipe_ctx,
-		bool flip_immediate);
-#endif
-
-	void (*update_plane_addr)(
-		const struct dc *dc,
-		struct pipe_ctx *pipe_ctx);
-
-	void (*plane_atomic_disconnect)(
-		struct dc *dc,
-		struct pipe_ctx *pipe_ctx);
-
-	void (*update_dchub)(
-		struct dce_hwseq *hws,
-		struct dchub_init_data *dh_data);
-
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
-	int (*init_sys_ctx)(
-			struct dce_hwseq *hws,
-			struct dc *dc,
-			struct dc_phy_addr_space_config *pa_config);
-	void (*init_vm_ctx)(
-			struct dce_hwseq *hws,
-			struct dc *dc,
-			struct dc_virtual_addr_space_config *va_config,
-			int vmid);
-#endif
-	void (*update_mpcc)(
-		struct dc *dc,
-		struct pipe_ctx *pipe_ctx);
-
-	void (*update_pending_status)(
+	void (*update_dchub)(struct dce_hwseq *hws,
+			struct dchub_init_data *dh_data);
+	void (*wait_for_mpcc_disconnect)(struct dc *dc,
+			struct resource_pool *res_pool,
 			struct pipe_ctx *pipe_ctx);
-
-	bool (*set_input_transfer_func)(
-				struct pipe_ctx *pipe_ctx,
-				const struct dc_plane_state *plane_state);
-
-	bool (*set_output_transfer_func)(
-				struct pipe_ctx *pipe_ctx,
-				const struct dc_stream_state *stream);
-
-	void (*power_down)(struct dc *dc);
-
-	void (*enable_accelerated_mode)(struct dc *dc, struct dc_state *context);
-
-	void (*enable_timing_synchronization)(
-			struct dc *dc,
-			int group_index,
-			int group_size,
-			struct pipe_ctx *grouped_pipes[]);
-
-	void (*enable_per_frame_crtc_position_reset)(
-			struct dc *dc,
-			int group_size,
+	void (*program_triplebuffer)(const struct dc *dc,
+		struct pipe_ctx *pipe_ctx, bool enableTripleBuffer);
+	void (*update_pending_status)(struct pipe_ctx *pipe_ctx);
+
+	/* Pipe Lock Related */
+	void (*pipe_control_lock_global)(struct dc *dc,
+			struct pipe_ctx *pipe, bool lock);
+	void (*pipe_control_lock)(struct dc *dc,
+			struct pipe_ctx *pipe, bool lock);
+	void (*set_flip_control_gsl)(struct pipe_ctx *pipe_ctx,
+			bool flip_immediate);
+
+	/* Timing Related */
+	void (*get_position)(struct pipe_ctx **pipe_ctx, int num_pipes,
+			struct crtc_position *position);
+	int (*get_vupdate_offset_from_vsync)(struct pipe_ctx *pipe_ctx);
+	void (*enable_per_frame_crtc_position_reset)(struct dc *dc,
+			int group_size, struct pipe_ctx *grouped_pipes[]);
+	void (*enable_timing_synchronization)(struct dc *dc,
+			int group_index, int group_size,
 			struct pipe_ctx *grouped_pipes[]);
+	void (*setup_periodic_interrupt)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			enum vline_select vline);
+	void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes,
+			unsigned int vmin, unsigned int vmax,
+			unsigned int vmid, unsigned int vmid_frame_number);
+	void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx,
+			int num_pipes,
+			const struct dc_static_screen_params *events);
 
-	void (*enable_display_pipe_clock_gating)(
-					struct dc_context *ctx,
-					bool clock_gating);
-
-	bool (*enable_display_power_gating)(
-					struct dc *dc,
-					uint8_t controller_id,
-					struct dc_bios *dcb,
-					enum pipe_gating_control power_gating);
-
-	void (*disable_plane)(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-	void (*update_info_frame)(struct pipe_ctx *pipe_ctx);
-
-	void (*send_immediate_sdp_message)(
-				struct pipe_ctx *pipe_ctx,
-				const uint8_t *custom_sdp_message,
-				unsigned int sdp_message_size);
-
+	/* Stream Related */
 	void (*enable_stream)(struct pipe_ctx *pipe_ctx);
-
 	void (*disable_stream)(struct pipe_ctx *pipe_ctx);
-
+	void (*blank_stream)(struct pipe_ctx *pipe_ctx);
 	void (*unblank_stream)(struct pipe_ctx *pipe_ctx,
 			struct dc_link_settings *link_settings);
 
-	void (*blank_stream)(struct pipe_ctx *pipe_ctx);
-
-	void (*enable_audio_stream)(struct pipe_ctx *pipe_ctx);
+	/* Bandwidth Related */
+	void (*prepare_bandwidth)(struct dc *dc, struct dc_state *context);
+	bool (*update_bandwidth)(struct dc *dc, struct dc_state *context);
+	void (*optimize_bandwidth)(struct dc *dc, struct dc_state *context);
 
-	void (*disable_audio_stream)(struct pipe_ctx *pipe_ctx);
-
-	void (*pipe_control_lock)(
-				struct dc *dc,
-				struct pipe_ctx *pipe,
-				bool lock);
-
-	void (*pipe_control_lock_global)(
-				struct dc *dc,
-				struct pipe_ctx *pipe,
-				bool lock);
-	void (*blank_pixel_data)(
-			struct dc *dc,
+	/* Infopacket Related */
+	void (*set_avmute)(struct pipe_ctx *pipe_ctx, bool enable);
+	void (*send_immediate_sdp_message)(
 			struct pipe_ctx *pipe_ctx,
-			bool blank);
-
-	void (*prepare_bandwidth)(
-			struct dc *dc,
-			struct dc_state *context);
-	void (*optimize_bandwidth)(
-			struct dc *dc,
-			struct dc_state *context);
-
-	void (*exit_optimized_pwr_state)(
-			const struct dc *dc,
-			struct dc_state *context);
-	void (*optimize_pwr_state)(
-			const struct dc *dc,
-			struct dc_state *context);
-
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	bool (*update_bandwidth)(
-			struct dc *dc,
-			struct dc_state *context);
+			const uint8_t *custom_sdp_message,
+			unsigned int sdp_message_size);
+	void (*update_info_frame)(struct pipe_ctx *pipe_ctx);
+	void (*set_dmdata_attributes)(struct pipe_ctx *pipe);
 	void (*program_dmdata_engine)(struct pipe_ctx *pipe_ctx);
 	bool (*dmdata_status_done)(struct pipe_ctx *pipe_ctx);
-#endif
-
-	void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes,
-			unsigned int vmin, unsigned int vmax,
-			unsigned int vmid, unsigned int vmid_frame_number);
-
-	void (*get_position)(struct pipe_ctx **pipe_ctx, int num_pipes,
-			struct crtc_position *position);
-
-	void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx,
-			int num_pipes, const struct dc_static_screen_events *events);
-
-	enum dc_status (*enable_stream_timing)(
-			struct pipe_ctx *pipe_ctx,
-			struct dc_state *context,
-			struct dc *dc);
-
-	void (*setup_stereo)(
-			struct pipe_ctx *pipe_ctx,
-			struct dc *dc);
-
-	void (*set_avmute)(struct pipe_ctx *pipe_ctx, bool enable);
-
-	void (*log_hw_state)(struct dc *dc,
-		struct dc_log_buffer_ctx *log_ctx);
-	void (*get_hw_state)(struct dc *dc, char *pBuf, unsigned int bufSize, unsigned int mask);
-	void (*clear_status_bits)(struct dc *dc, unsigned int mask);
-
-	void (*wait_for_mpcc_disconnect)(struct dc *dc,
-			struct resource_pool *res_pool,
-			struct pipe_ctx *pipe_ctx);
-
-	void (*edp_power_control)(
-			struct dc_link *link,
-			bool enable);
-	void (*edp_backlight_control)(
-			struct dc_link *link,
-			bool enable);
-	void (*edp_wait_for_hpd_ready)(struct dc_link *link, bool power_up);
 
+	/* Cursor Related */
 	void (*set_cursor_position)(struct pipe_ctx *pipe);
 	void (*set_cursor_attribute)(struct pipe_ctx *pipe);
 	void (*set_cursor_sdr_white_level)(struct pipe_ctx *pipe);
 
-	void (*setup_periodic_interrupt)(struct pipe_ctx *pipe_ctx, enum vline_select vline);
-	void (*setup_vupdate_interrupt)(struct pipe_ctx *pipe_ctx);
-	bool (*did_underflow_occur)(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-	void (*init_blank)(struct dc *dc, struct timing_generator *tg);
-	void (*disable_vga)(struct dce_hwseq *hws);
-	void (*bios_golden_init)(struct dc *dc);
-	void (*plane_atomic_power_down)(struct dc *dc,
-			struct dpp *dpp,
-			struct hubp *hubp);
-
-	void (*plane_atomic_disable)(
-			struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-	void (*enable_power_gating_plane)(
-		struct dce_hwseq *hws,
-		bool enable);
-
-	void (*dpp_pg_control)(
-			struct dce_hwseq *hws,
-			unsigned int dpp_inst,
-			bool power_on);
-
-	void (*hubp_pg_control)(
-			struct dce_hwseq *hws,
-			unsigned int hubp_inst,
-			bool power_on);
-
-	void (*dsc_pg_control)(
-			struct dce_hwseq *hws,
-			unsigned int dsc_inst,
-			bool power_on);
-
+	/* Colour Related */
+	void (*program_gamut_remap)(struct pipe_ctx *pipe_ctx);
+	void (*program_output_csc)(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			enum dc_color_space colorspace,
+			uint16_t *matrix, int opp_id);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	void (*update_odm)(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx);
-	void (*program_all_writeback_pipes_in_tree)(
+	/* VM Related */
+	int (*init_sys_ctx)(struct dce_hwseq *hws,
 			struct dc *dc,
-			const struct dc_stream_state *stream,
-			struct dc_state *context);
+			struct dc_phy_addr_space_config *pa_config);
+	void (*init_vm_ctx)(struct dce_hwseq *hws,
+			struct dc *dc,
+			struct dc_virtual_addr_space_config *va_config,
+			int vmid);
+
+	/* Writeback Related */
 	void (*update_writeback)(struct dc *dc,
-			const struct dc_stream_status *stream_status,
 			struct dc_writeback_info *wb_info,
 			struct dc_state *context);
 	void (*enable_writeback)(struct dc *dc,
-			const struct dc_stream_status *stream_status,
 			struct dc_writeback_info *wb_info,
 			struct dc_state *context);
 	void (*disable_writeback)(struct dc *dc,
 			unsigned int dwb_pipe_inst);
-#endif
-	enum dc_status (*set_clock)(struct dc *dc,
-			enum dc_clock_type clock_type,
-			uint32_t clk_khz,
-			uint32_t stepping);
 
-	void (*get_clock)(struct dc *dc,
+	bool (*mmhubbub_warmup)(struct dc *dc,
+			unsigned int num_dwb,
+			struct dc_writeback_info *wb_info);
+
+	/* Clock Related */
+	enum dc_status (*set_clock)(struct dc *dc,
 			enum dc_clock_type clock_type,
+			uint32_t clk_khz, uint32_t stepping);
+	void (*get_clock)(struct dc *dc, enum dc_clock_type clock_type,
 			struct dc_clock_config *clock_cfg);
+	void (*optimize_pwr_state)(const struct dc *dc,
+			struct dc_state *context);
+	void (*exit_optimized_pwr_state)(const struct dc *dc,
+			struct dc_state *context);
+
+	/* Audio Related */
+	void (*enable_audio_stream)(struct pipe_ctx *pipe_ctx);
+	void (*disable_audio_stream)(struct pipe_ctx *pipe_ctx);
+
+	/* Stereo 3D Related */
+	void (*setup_stereo)(struct pipe_ctx *pipe_ctx, struct dc *dc);
+
+	/* HW State Logging Related */
+	void (*log_hw_state)(struct dc *dc, struct dc_log_buffer_ctx *log_ctx);
+	void (*get_hw_state)(struct dc *dc, char *pBuf,
+			unsigned int bufSize, unsigned int mask);
+	void (*clear_status_bits)(struct dc *dc, unsigned int mask);
+
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
-	bool (*s0i3_golden_init_wa)(struct dc *dc);
-#endif
 };
 
 void color_space_to_black_color(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
new file mode 100644
index 000000000000..ecf566378ccd
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
@@ -0,0 +1,156 @@
+/*
+ * Copyright 2015 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_HW_SEQUENCER_PRIVATE_H__
+#define __DC_HW_SEQUENCER_PRIVATE_H__
+
+#include "dc_types.h"
+
+enum pipe_gating_control {
+	PIPE_GATING_CONTROL_DISABLE = 0,
+	PIPE_GATING_CONTROL_ENABLE,
+	PIPE_GATING_CONTROL_INIT
+};
+
+struct dce_hwseq_wa {
+	bool blnd_crtc_trigger;
+	bool DEGVIDCN10_253;
+	bool false_optc_underflow;
+	bool DEGVIDCN10_254;
+	bool DEGVIDCN21;
+};
+
+struct hwseq_wa_state {
+	bool DEGVIDCN10_253_applied;
+};
+
+struct pipe_ctx;
+struct dc_state;
+struct dc_stream_status;
+struct dc_writeback_info;
+struct dchub_init_data;
+struct dc_static_screen_params;
+struct resource_pool;
+struct resource_context;
+struct stream_resource;
+struct dc_phy_addr_space_config;
+struct dc_virtual_addr_space_config;
+struct hubp;
+struct dpp;
+struct dce_hwseq;
+struct timing_generator;
+struct tg_color;
+struct output_pixel_processor;
+
+struct hwseq_private_funcs {
+
+	void (*disable_stream_gating)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*enable_stream_gating)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*init_pipes)(struct dc *dc, struct dc_state *context);
+	void (*reset_hw_ctx_wrap)(struct dc *dc, struct dc_state *context);
+	void (*update_plane_addr)(const struct dc *dc,
+			struct pipe_ctx *pipe_ctx);
+	void (*plane_atomic_disconnect)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx);
+	void (*update_mpcc)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	bool (*set_input_transfer_func)(struct dc *dc,
+				struct pipe_ctx *pipe_ctx,
+				const struct dc_plane_state *plane_state);
+	bool (*set_output_transfer_func)(struct dc *dc,
+				struct pipe_ctx *pipe_ctx,
+				const struct dc_stream_state *stream);
+	void (*power_down)(struct dc *dc);
+	void (*enable_display_pipe_clock_gating)(struct dc_context *ctx,
+					bool clock_gating);
+	bool (*enable_display_power_gating)(struct dc *dc,
+					uint8_t controller_id,
+					struct dc_bios *dcb,
+					enum pipe_gating_control power_gating);
+	void (*blank_pixel_data)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			bool blank);
+	enum dc_status (*enable_stream_timing)(
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context,
+			struct dc *dc);
+	void (*edp_backlight_control)(struct dc_link *link,
+			bool enable);
+	void (*setup_vupdate_interrupt)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx);
+	bool (*did_underflow_occur)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*init_blank)(struct dc *dc, struct timing_generator *tg);
+	void (*disable_vga)(struct dce_hwseq *hws);
+	void (*bios_golden_init)(struct dc *dc);
+	void (*plane_atomic_power_down)(struct dc *dc,
+			struct dpp *dpp,
+			struct hubp *hubp);
+	void (*plane_atomic_disable)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*enable_power_gating_plane)(struct dce_hwseq *hws,
+		bool enable);
+	void (*dpp_pg_control)(struct dce_hwseq *hws,
+			unsigned int dpp_inst,
+			bool power_on);
+	void (*hubp_pg_control)(struct dce_hwseq *hws,
+			unsigned int hubp_inst,
+			bool power_on);
+	void (*dsc_pg_control)(struct dce_hwseq *hws,
+			unsigned int dsc_inst,
+			bool power_on);
+	void (*update_odm)(struct dc *dc, struct dc_state *context,
+			struct pipe_ctx *pipe_ctx);
+	void (*program_all_writeback_pipes_in_tree)(struct dc *dc,
+			const struct dc_stream_state *stream,
+			struct dc_state *context);
+	bool (*s0i3_golden_init_wa)(struct dc *dc);
+	void (*get_surface_visual_confirm_color)(
+			const struct pipe_ctx *pipe_ctx,
+			struct tg_color *color);
+	void (*get_hdr_visual_confirm_color)(struct pipe_ctx *pipe_ctx,
+			struct tg_color *color);
+	void (*set_hdr_multiplier)(struct pipe_ctx *pipe_ctx);
+	void (*verify_allow_pstate_change_high)(struct dc *dc);
+	void (*program_pipe)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context);
+	bool (*wait_for_blank_complete)(struct output_pixel_processor *opp);
+	void (*dccg_init)(struct dce_hwseq *hws);
+	bool (*set_blend_lut)(struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state);
+	bool (*set_shaper_3dlut)(struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state);
+};
+
+struct dce_hwseq {
+	struct dc_context *ctx;
+	const struct dce_hwseq_registers *regs;
+	const struct dce_hwseq_shift *shifts;
+	const struct dce_hwseq_mask *masks;
+	struct dce_hwseq_wa wa;
+	struct hwseq_wa_state wa_state;
+	struct hwseq_private_funcs funcs;
+
+};
+
+#endif /* __DC_HW_SEQUENCER_PRIVATE_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h b/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h
index 4eff5d38a2f9..9af7ee5bc8ee 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h
@@ -60,11 +60,13 @@ void dp_disable_link_phy_mst(struct dc_link *link, enum signal_type signal);
 
 bool dp_set_hw_training_pattern(
 	struct dc_link *link,
-	enum dc_dp_training_pattern pattern);
+	enum dc_dp_training_pattern pattern,
+	uint32_t offset);
 
 void dp_set_hw_lane_settings(
 	struct dc_link *link,
-	const struct link_training_settings *link_settings);
+	const struct link_training_settings *link_settings,
+	uint32_t offset);
 
 void dp_set_hw_test_pattern(
 	struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
index 8503d9cc4763..2470405e996b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
@@ -458,7 +458,14 @@ uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr,
 #define IX_REG_READ(index_reg_name, data_reg_name, index) \
 		generic_read_indirect_reg(CTX, REG(index_reg_name), REG(data_reg_name), IND_REG(index))
 
+#define IX_REG_GET_N(index_reg_name, data_reg_name, index, n, ...) \
+		generic_indirect_reg_get(CTX, REG(index_reg_name), REG(data_reg_name), \
+				IND_REG(index), \
+				n, __VA_ARGS__)
 
+#define IX_REG_GET(index_reg_name, data_reg_name, index, field, val) \
+		IX_REG_GET_N(index_reg_name, data_reg_name, index, 1, \
+				FN(data_reg_name, field), val)
 
 #define IX_REG_UPDATE_N(index_reg_name, data_reg_name, index, n, ...)	\
 		generic_indirect_reg_update_ex(CTX, \
@@ -479,10 +486,35 @@ uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
 		uint32_t addr_index, uint32_t addr_data,
 		uint32_t index);
 
+uint32_t generic_indirect_reg_get(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		...);
+
 uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr_index, uint32_t addr_data,
 		uint32_t index, uint32_t reg_val, int n,
 		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
 		...);
 
+/* register offload macros
+ *
+ * instead of MMIO to register directly, in some cases we want
+ * to gather register sequence and execute the register sequence
+ * from another thread so we optimize time required for lengthy ops
+ */
+
+/* start gathering register sequence */
+#define REG_SEQ_START() \
+	reg_sequence_start_gather(CTX)
+
+/* start execution of register sequence gathered since REG_SEQ_START */
+#define REG_SEQ_SUBMIT() \
+	reg_sequence_start_execute(CTX)
+
+/* wait for the last REG_SEQ_SUBMIT to finish */
+#define REG_SEQ_WAIT_DONE() \
+	reg_sequence_wait_done(CTX)
+
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_REG_HELPER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index bef224bf803e..5ae8ada154ef 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -46,12 +46,8 @@ struct resource_caps {
 	int num_pll;
 	int num_dwb;
 	int num_ddc;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	int num_vmid;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	int num_dsc;
-#endif
-#endif
 };
 
 struct resource_straps {
@@ -181,4 +177,6 @@ void update_audio_usage(
 
 unsigned int resource_pixel_format_to_bpp(enum surface_pixel_format format);
 
+void get_audio_check(struct audio_info *aud_modes,
+	struct audio_check *aud_chk);
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/irq/Makefile b/drivers/gpu/drm/amd/display/dc/irq/Makefile
index ea75420fc876..0f682ac53bb2 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/irq/Makefile
@@ -60,27 +60,23 @@ AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCE12)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 IRQ_DCN1 = irq_service_dcn10.o
 
 AMD_DAL_IRQ_DCN1 = $(addprefix $(AMDDALPATH)/dc/irq/dcn10/,$(IRQ_DCN1))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCN1)
-endif
 ###############################################################################
 # DCN 20
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
 IRQ_DCN2 = irq_service_dcn20.o
 
 AMD_DAL_IRQ_DCN2 = $(addprefix $(AMDDALPATH)/dc/irq/dcn20/,$(IRQ_DCN2))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCN2)
-endif
 ###############################################################################
 # DCN 21
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 IRQ_DCN21 = irq_service_dcn21.o
 
 AMD_DAL_IRQ_DCN21= $(addprefix $(AMDDALPATH)/dc/irq/dcn21/,$(IRQ_DCN21))
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c
index 1a581c464345..378cc11aa047 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c
@@ -204,7 +204,7 @@ bool dce110_vblank_set(struct irq_service *irq_service,
 		       bool enable)
 {
 	struct dc_context *dc_ctx = irq_service->ctx;
-	struct dc *core_dc = irq_service->ctx->dc;
+	struct dc *dc = irq_service->ctx->dc;
 	enum dc_irq_source dal_irq_src =
 			dc_interrupt_to_irq_source(irq_service->ctx->dc,
 						   info->src_id,
@@ -212,7 +212,7 @@ bool dce110_vblank_set(struct irq_service *irq_service,
 	uint8_t pipe_offset = dal_irq_src - IRQ_TYPE_VBLANK;
 
 	struct timing_generator *tg =
-			core_dc->current_state->res_ctx.pipe_ctx[pipe_offset].stream_res.tg;
+			dc->current_state->res_ctx.pipe_ctx[pipe_offset].stream_res.tg;
 
 	if (enable) {
 		if (!tg || !tg->funcs->arm_vert_intr(tg, 2)) {
@@ -403,7 +403,7 @@ static const struct irq_service_funcs irq_service_funcs_dce110 = {
 		.to_dal_irq_source = to_dal_irq_source_dce110
 };
 
-static void construct(struct irq_service *irq_service,
+static void dce110_irq_construct(struct irq_service *irq_service,
 		      struct irq_service_init_data *init_data)
 {
 	dal_irq_service_construct(irq_service, init_data);
@@ -421,6 +421,6 @@ dal_irq_service_dce110_create(struct irq_service_init_data *init_data)
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dce110_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c b/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
index 15380336cb51..2fe4703395f3 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
@@ -273,7 +273,7 @@ static const struct irq_service_funcs irq_service_funcs_dce120 = {
 		.to_dal_irq_source = to_dal_irq_source_dce110
 };
 
-static void construct(
+static void dce120_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -292,6 +292,6 @@ struct irq_service *dal_irq_service_dce120_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dce120_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce80/irq_service_dce80.c b/drivers/gpu/drm/amd/display/dc/irq/dce80/irq_service_dce80.c
index 281fee8ad1e5..17e426b80a00 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dce80/irq_service_dce80.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce80/irq_service_dce80.c
@@ -283,7 +283,7 @@ static const struct irq_service_funcs irq_service_funcs_dce80 = {
 		.to_dal_irq_source = to_dal_irq_source_dce110
 };
 
-static void construct(
+static void dce80_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -302,7 +302,7 @@ struct irq_service *dal_irq_service_dce80_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dce80_irq_construct(irq_service, init_data);
 	return irq_service;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c b/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
index cc8e7dedccce..f956b3bde680 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
@@ -355,7 +355,7 @@ static const struct irq_service_funcs irq_service_funcs_dcn10 = {
 		.to_dal_irq_source = to_dal_irq_source_dcn10
 };
 
-static void construct(
+static void dcn10_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -374,6 +374,6 @@ struct irq_service *dal_irq_service_dcn10_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dcn10_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
index 5db29bf582d3..2a1fea501f8c 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
@@ -359,7 +359,7 @@ static const struct irq_service_funcs irq_service_funcs_dcn20 = {
 		.to_dal_irq_source = to_dal_irq_source_dcn20
 };
 
-static void construct(
+static void dcn20_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -378,6 +378,6 @@ struct irq_service *dal_irq_service_dcn20_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dcn20_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
index cbe7818529bb..1b971265418b 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
@@ -350,7 +350,7 @@ static const struct irq_service_funcs irq_service_funcs_dcn21 = {
 		.to_dal_irq_source = to_dal_irq_source_dcn21
 };
 
-static void construct(
+static void dcn21_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -369,6 +369,6 @@ struct irq_service *dal_irq_service_dcn21_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dcn21_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index 0878550a8178..33053b9fe6bd 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -38,7 +38,7 @@
 #include "dce120/irq_service_dce120.h"
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "dcn10/irq_service_dcn10.h"
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 30ec80ac6fc8..c34eba19860a 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -1,5 +1,6 @@
 /*
  * Copyright 2012-16 Advanced Micro Devices, Inc.
+ * Copyright 2019 Raptor Engineering, LLC
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -29,6 +30,7 @@
 #include <linux/kgdb.h>
 #include <linux/kref.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 
 #include <asm/byteorder.h>
 
@@ -48,8 +50,39 @@
 
 #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+#if defined(CONFIG_X86)
 #include <asm/fpu/api.h>
+#define DC_FP_START() kernel_fpu_begin()
+#define DC_FP_END() kernel_fpu_end()
+#elif defined(CONFIG_PPC64)
+#include <asm/switch_to.h>
+#include <asm/cputable.h>
+#define DC_FP_START() { \
+	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
+		preempt_disable(); \
+		enable_kernel_vsx(); \
+	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
+		preempt_disable(); \
+		enable_kernel_altivec(); \
+	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
+		preempt_disable(); \
+		enable_kernel_fp(); \
+	} \
+}
+#define DC_FP_END() { \
+	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
+		disable_kernel_vsx(); \
+		preempt_enable(); \
+	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
+		disable_kernel_altivec(); \
+		preempt_enable(); \
+	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
+		disable_kernel_fp(); \
+		preempt_enable(); \
+	} \
+}
+#endif
 #endif
 
 /*
diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
index ff664bdb1482..b8040da94b9d 100644
--- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
@@ -32,6 +32,7 @@ static void virtual_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting) {}
 
 static void virtual_stream_encoder_hdmi_set_stream_attribute(
@@ -81,22 +82,14 @@ static void virtual_stream_encoder_reset_hdmi_stream_attribute(
 		struct stream_encoder *enc)
 {}
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 static void virtual_enc_dp_set_odm_combine(
 	struct stream_encoder *enc,
 	bool odm_combine)
 {}
-#endif
-#endif
 
 static const struct stream_encoder_funcs virtual_str_enc_funcs = {
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.dp_set_odm_combine =
 		virtual_enc_dp_set_odm_combine,
-#endif
-#endif
 	.dp_set_stream_attribute =
 		virtual_stream_encoder_dp_set_stream_attribute,
 	.hdmi_set_stream_attribute =
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
new file mode 100644
index 000000000000..cd9532b4f14d
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -0,0 +1,289 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_CMD_H_
+#define _DMUB_CMD_H_
+
+#include "dmub_types.h"
+#include "dmub_cmd_dal.h"
+#include "dmub_cmd_vbios.h"
+#include "atomfirmware.h"
+
+#define DMUB_RB_CMD_SIZE 64
+#define DMUB_RB_MAX_ENTRY 128
+#define DMUB_RB_SIZE (DMUB_RB_CMD_SIZE * DMUB_RB_MAX_ENTRY)
+#define REG_SET_MASK 0xFFFF
+
+
+/*
+ * Command IDs should be treated as stable ABI.
+ * Do not reuse or modify IDs.
+ */
+
+enum dmub_cmd_type {
+	DMUB_CMD__NULL = 0,
+	DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE = 1,
+	DMUB_CMD__REG_SEQ_FIELD_UPDATE_SEQ = 2,
+	DMUB_CMD__REG_SEQ_BURST_WRITE = 3,
+	DMUB_CMD__REG_REG_WAIT = 4,
+	DMUB_CMD__PLAT_54186_WA = 5,
+	DMUB_CMD__PSR = 64,
+	DMUB_CMD__VBIOS = 128,
+};
+
+#pragma pack(push, 1)
+
+struct dmub_cmd_header {
+	unsigned int type : 8;
+	unsigned int sub_type : 8;
+	unsigned int reserved0 : 8;
+	unsigned int payload_bytes : 6;  /* up to 60 bytes */
+	unsigned int reserved1 : 2;
+};
+
+/*
+ * Read modify write
+ *
+ * 60 payload bytes can hold up to 5 sets of read modify writes,
+ * each take 3 dwords.
+ *
+ * number of sequences = header.payload_bytes / sizeof(struct dmub_cmd_read_modify_write_sequence)
+ *
+ * modify_mask = 0xffff'ffff means all fields are going to be updated.  in this case
+ * command parser will skip the read and we can use modify_mask = 0xffff'ffff as reg write
+ */
+struct dmub_cmd_read_modify_write_sequence {
+	uint32_t addr;
+	uint32_t modify_mask;
+	uint32_t modify_value;
+};
+
+#define DMUB_READ_MODIFY_WRITE_SEQ__MAX		5
+struct dmub_rb_cmd_read_modify_write {
+	struct dmub_cmd_header header;  // type = DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE
+	struct dmub_cmd_read_modify_write_sequence seq[DMUB_READ_MODIFY_WRITE_SEQ__MAX];
+};
+
+/*
+ * Update a register with specified masks and values sequeunce
+ *
+ * 60 payload bytes can hold address + up to 7 sets of mask/value combo, each take 2 dword
+ *
+ * number of field update sequence = (header.payload_bytes - sizeof(addr)) / sizeof(struct read_modify_write_sequence)
+ *
+ *
+ * USE CASE:
+ *   1. auto-increment register where additional read would update pointer and produce wrong result
+ *   2. toggle a bit without read in the middle
+ */
+
+struct dmub_cmd_reg_field_update_sequence {
+	uint32_t modify_mask;  // 0xffff'ffff to skip initial read
+	uint32_t modify_value;
+};
+
+#define DMUB_REG_FIELD_UPDATE_SEQ__MAX		7
+
+struct dmub_rb_cmd_reg_field_update_sequence {
+	struct dmub_cmd_header header;
+	uint32_t addr;
+	struct dmub_cmd_reg_field_update_sequence seq[DMUB_REG_FIELD_UPDATE_SEQ__MAX];
+};
+
+
+/*
+ * Burst write
+ *
+ * support use case such as writing out LUTs.
+ *
+ * 60 payload bytes can hold up to 14 values to write to given address
+ *
+ * number of payload = header.payload_bytes / sizeof(struct read_modify_write_sequence)
+ */
+#define DMUB_BURST_WRITE_VALUES__MAX  14
+struct dmub_rb_cmd_burst_write {
+	struct dmub_cmd_header header;  // type = DMUB_CMD__REG_SEQ_BURST_WRITE
+	uint32_t addr;
+	uint32_t write_values[DMUB_BURST_WRITE_VALUES__MAX];
+};
+
+
+struct dmub_rb_cmd_common {
+	struct dmub_cmd_header header;
+	uint8_t cmd_buffer[DMUB_RB_CMD_SIZE - sizeof(struct dmub_cmd_header)];
+};
+
+struct dmub_cmd_reg_wait_data {
+	uint32_t addr;
+	uint32_t mask;
+	uint32_t condition_field_value;
+	uint32_t time_out_us;
+};
+
+struct dmub_rb_cmd_reg_wait {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_reg_wait_data reg_wait;
+};
+
+#ifndef PHYSICAL_ADDRESS_LOC
+#define PHYSICAL_ADDRESS_LOC union large_integer
+#endif
+
+struct dmub_cmd_PLAT_54186_wa {
+	uint32_t DCSURF_SURFACE_CONTROL;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C;
+	struct {
+		uint8_t hubp_inst : 4;
+		uint8_t tmz_surface : 1;
+		uint8_t immediate :1;
+		uint8_t vmid : 4;
+		uint8_t grph_stereo : 1;
+		uint32_t reserved : 21;
+	} flip_params;
+	uint32_t reserved[9];
+};
+
+struct dmub_rb_cmd_PLAT_54186_wa {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_PLAT_54186_wa flip;
+};
+
+struct dmub_cmd_digx_encoder_control_data {
+	union dig_encoder_control_parameters_v1_5 dig;
+};
+
+struct dmub_rb_cmd_digx_encoder_control {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_digx_encoder_control_data encoder_control;
+};
+
+struct dmub_cmd_set_pixel_clock_data {
+	struct set_pixel_clock_parameter_v1_7 clk;
+};
+
+struct dmub_rb_cmd_set_pixel_clock {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_set_pixel_clock_data pixel_clock;
+};
+
+struct dmub_cmd_enable_disp_power_gating_data {
+	struct enable_disp_power_gating_parameters_v2_1 pwr;
+};
+
+struct dmub_rb_cmd_enable_disp_power_gating {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_enable_disp_power_gating_data power_gating;
+};
+
+struct dmub_cmd_dig1_transmitter_control_data {
+	struct dig_transmitter_control_parameters_v1_6 dig;
+};
+
+struct dmub_rb_cmd_dig1_transmitter_control {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_dig1_transmitter_control_data transmitter_control;
+};
+
+struct dmub_rb_cmd_dpphy_init {
+	struct dmub_cmd_header header;
+	uint8_t reserved[60];
+};
+
+struct dmub_cmd_psr_copy_settings_data {
+	uint16_t psr_level;
+	uint8_t hubp_inst;
+	uint8_t dpp_inst;
+	uint8_t mpcc_inst;
+	uint8_t opp_inst;
+	uint8_t otg_inst;
+	uint8_t digfe_inst;
+	uint8_t digbe_inst;
+	uint8_t dpphy_inst;
+	uint8_t aux_inst;
+	uint8_t hyst_frames;
+	uint8_t hyst_lines;
+	uint8_t phy_num;
+	uint8_t phy_type;
+	uint8_t aux_repeat;
+	uint8_t smu_optimizations_en;
+	uint8_t skip_wait_for_pll_lock;
+	uint8_t frame_delay;
+	uint8_t smu_phy_id;
+	uint8_t num_of_controllers;
+	uint8_t link_rate;
+	uint8_t frame_cap_ind;
+};
+
+struct dmub_rb_cmd_psr_copy_settings {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_psr_copy_settings_data psr_copy_settings_data;
+};
+
+struct dmub_cmd_psr_set_level_data {
+	uint16_t psr_level;
+};
+
+struct dmub_rb_cmd_psr_set_level {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_psr_set_level_data psr_set_level_data;
+};
+
+struct dmub_rb_cmd_psr_enable {
+	struct dmub_cmd_header header;
+};
+
+struct dmub_cmd_psr_setup_data {
+	enum psr_version version; // PSR version 1 or 2
+};
+
+struct dmub_rb_cmd_psr_setup {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_psr_setup_data psr_setup_data;
+};
+
+union dmub_rb_cmd {
+	struct dmub_rb_cmd_read_modify_write read_modify_write;
+	struct dmub_rb_cmd_reg_field_update_sequence reg_field_update_seq;
+	struct dmub_rb_cmd_burst_write burst_write;
+	struct dmub_rb_cmd_reg_wait reg_wait;
+	struct dmub_rb_cmd_common cmd_common;
+	struct dmub_rb_cmd_digx_encoder_control digx_encoder_control;
+	struct dmub_rb_cmd_set_pixel_clock set_pixel_clock;
+	struct dmub_rb_cmd_enable_disp_power_gating enable_disp_power_gating;
+	struct dmub_rb_cmd_dpphy_init dpphy_init;
+	struct dmub_rb_cmd_dig1_transmitter_control dig1_transmitter_control;
+	struct dmub_rb_cmd_psr_enable psr_enable;
+	struct dmub_rb_cmd_psr_copy_settings psr_copy_settings;
+	struct dmub_rb_cmd_psr_set_level psr_set_level;
+	struct dmub_rb_cmd_PLAT_54186_wa PLAT_54186_wa;
+	struct dmub_rb_cmd_psr_setup psr_setup;
+};
+
+#pragma pack(pop)
+
+#endif /* _DMUB_CMD_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h
new file mode 100644
index 000000000000..7b69eb37f762
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_CMD_DAL_H_
+#define _DMUB_CMD_DAL_H_
+
+/*
+ * Command IDs should be treated as stable ABI.
+ * Do not reuse or modify IDs.
+ */
+
+enum dmub_cmd_psr_type {
+	DMUB_CMD__PSR_SETUP		= 0,
+	DMUB_CMD__PSR_COPY_SETTINGS	= 1,
+	DMUB_CMD__PSR_ENABLE		= 2,
+	DMUB_CMD__PSR_DISABLE		= 3,
+	DMUB_CMD__PSR_SET_LEVEL		= 4,
+};
+
+enum psr_version {
+	PSR_VERSION_1			= 0x10, // PSR Version 1
+	PSR_VERSION_2			= 0x20, // PSR Version 2, includes selective update
+	PSR_VERSION_2_Y_COORD		= 0x21, // PSR Version 2, includes Y-coordinate support for SU
+};
+
+#endif /* _DMUB_CMD_DAL_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_vbios.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_vbios.h
new file mode 100644
index 000000000000..b6deb8e2590f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_vbios.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_CMD_VBIOS_H_
+#define _DMUB_CMD_VBIOS_H_
+
+/*
+ * Command IDs should be treated as stable ABI.
+ * Do not reuse or modify IDs.
+ */
+
+enum dmub_cmd_vbios_type {
+	DMUB_CMD__VBIOS_DIGX_ENCODER_CONTROL = 0,
+	DMUB_CMD__VBIOS_DIG1_TRANSMITTER_CONTROL = 1,
+	DMUB_CMD__VBIOS_SET_PIXEL_CLOCK = 2,
+	DMUB_CMD__VBIOS_ENABLE_DISP_POWER_GATING = 3,
+};
+
+#endif /* _DMUB_CMD_VBIOS_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h
new file mode 100644
index 000000000000..242ec257998c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+#ifndef _DMUB_META_H_
+#define _DMUB_META_H_
+
+#include "dmub_types.h"
+
+#pragma pack(push, 1)
+
+/* Magic value for identifying dmub_fw_meta_info */
+#define DMUB_FW_META_MAGIC 0x444D5542
+
+/* Offset from the end of the file to the dmub_fw_meta_info */
+#define DMUB_FW_META_OFFSET 0x24
+
+/**
+ * struct dmub_fw_meta_info - metadata associated with fw binary
+ *
+ * NOTE: This should be considered a stable API. Fields should
+ *       not be repurposed or reordered. New fields should be
+ *       added instead to extend the structure.
+ *
+ * @magic_value: magic value identifying DMUB firmware meta info
+ * @fw_region_size: size of the firmware state region
+ * @trace_buffer_size: size of the tracebuffer region
+ */
+struct dmub_fw_meta_info {
+	uint32_t magic_value;
+	uint32_t fw_region_size;
+	uint32_t trace_buffer_size;
+};
+
+/* Ensure that the structure remains 64 bytes. */
+union dmub_fw_meta {
+	struct dmub_fw_meta_info info;
+	uint8_t reserved[64];
+};
+
+#pragma pack(pop)
+
+#endif /* _DMUB_META_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h
new file mode 100644
index 000000000000..df875fdd2ab0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h
@@ -0,0 +1,154 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_RB_H_
+#define _DMUB_RB_H_
+
+#include "dmub_types.h"
+#include "dmub_cmd.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+struct dmub_cmd_header;
+
+struct dmub_rb_init_params {
+	void *ctx;
+	void *base_address;
+	uint32_t capacity;
+};
+
+struct dmub_rb {
+	void *base_address;
+	uint32_t data_count;
+	uint32_t rptr;
+	uint32_t wrpt;
+	uint32_t capacity;
+
+	void *ctx;
+	void *dmub;
+};
+
+
+static inline bool dmub_rb_empty(struct dmub_rb *rb)
+{
+	return (rb->wrpt == rb->rptr);
+}
+
+static inline bool dmub_rb_full(struct dmub_rb *rb)
+{
+	uint32_t data_count;
+
+	if (rb->wrpt >= rb->rptr)
+		data_count = rb->wrpt - rb->rptr;
+	else
+		data_count = rb->capacity - (rb->rptr - rb->wrpt);
+
+	return (data_count == (rb->capacity - DMUB_RB_CMD_SIZE));
+}
+
+static inline bool dmub_rb_push_front(struct dmub_rb *rb,
+				      const struct dmub_cmd_header *cmd)
+{
+	uint64_t volatile *dst = (uint64_t volatile *)(rb->base_address) + rb->wrpt / sizeof(uint64_t);
+	const uint64_t *src = (const uint64_t *)cmd;
+	int i;
+
+	if (dmub_rb_full(rb))
+		return false;
+
+	// copying data
+	for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
+		*dst++ = *src++;
+
+	rb->wrpt += DMUB_RB_CMD_SIZE;
+
+	if (rb->wrpt >= rb->capacity)
+		rb->wrpt %= rb->capacity;
+
+	return true;
+}
+
+static inline bool dmub_rb_front(struct dmub_rb *rb,
+				 struct dmub_cmd_header *cmd)
+{
+	uint8_t *rd_ptr = (uint8_t *)rb->base_address + rb->rptr;
+
+	if (dmub_rb_empty(rb))
+		return false;
+
+	dmub_memcpy(cmd, rd_ptr, DMUB_RB_CMD_SIZE);
+
+	return true;
+}
+
+static inline bool dmub_rb_pop_front(struct dmub_rb *rb)
+{
+	if (dmub_rb_empty(rb))
+		return false;
+
+	rb->rptr += DMUB_RB_CMD_SIZE;
+
+	if (rb->rptr >= rb->capacity)
+		rb->rptr %= rb->capacity;
+
+	return true;
+}
+
+static inline void dmub_rb_flush_pending(const struct dmub_rb *rb)
+{
+	uint32_t rptr = rb->rptr;
+	uint32_t wptr = rb->wrpt;
+
+	while (rptr != wptr) {
+		uint64_t volatile *data = (uint64_t volatile *)rb->base_address + rptr / sizeof(uint64_t);
+		//uint64_t volatile *p = (uint64_t volatile *)data;
+		uint64_t temp;
+		int i;
+
+		for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
+			temp = *data++;
+
+		rptr += DMUB_RB_CMD_SIZE;
+		if (rptr >= rb->capacity)
+			rptr %= rb->capacity;
+	}
+}
+
+static inline void dmub_rb_init(struct dmub_rb *rb,
+				struct dmub_rb_init_params *init_params)
+{
+	rb->base_address = init_params->base_address;
+	rb->capacity = init_params->capacity;
+	rb->rptr = 0;
+	rb->wrpt = 0;
+}
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _DMUB_RB_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h
new file mode 100644
index 000000000000..8e23a7017588
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h
@@ -0,0 +1,506 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_SRV_H_
+#define _DMUB_SRV_H_
+
+/**
+ * DOC: DMUB interface and operation
+ *
+ * DMUB is the interface to the display DMCUB microcontroller on DCN hardware.
+ * It delegates hardware initialization and command submission to the
+ * microcontroller. DMUB is the shortname for DMCUB.
+ *
+ * This interface is not thread-safe. Ensure that all access to the interface
+ * is properly synchronized by the caller.
+ *
+ * Initialization and usage of the DMUB service should be done in the
+ * steps given below:
+ *
+ * 1. dmub_srv_create()
+ * 2. dmub_srv_has_hw_support()
+ * 3. dmub_srv_calc_region_info()
+ * 4. dmub_srv_hw_init()
+ *
+ * The call to dmub_srv_create() is required to use the server.
+ *
+ * The calls to dmub_srv_has_hw_support() and dmub_srv_calc_region_info()
+ * are helpers to query cache window size and allocate framebuffer(s)
+ * for the cache windows.
+ *
+ * The call to dmub_srv_hw_init() programs the DMCUB registers to prepare
+ * for command submission. Commands can be queued via dmub_srv_cmd_queue()
+ * and executed via dmub_srv_cmd_execute().
+ *
+ * If the queue is full the dmub_srv_wait_for_idle() call can be used to
+ * wait until the queue has been cleared.
+ *
+ * Destroying the DMUB service can be done by calling dmub_srv_destroy().
+ * This does not clear DMUB hardware state, only software state.
+ *
+ * The interface is intended to be standalone and should not depend on any
+ * other component within DAL.
+ */
+
+#include "dmub_types.h"
+#include "dmub_cmd.h"
+#include "dmub_rb.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* Forward declarations */
+struct dmub_srv;
+struct dmub_cmd_header;
+struct dmub_srv_common_regs;
+
+/* enum dmub_status - return code for dmcub functions */
+enum dmub_status {
+	DMUB_STATUS_OK = 0,
+	DMUB_STATUS_NO_CTX,
+	DMUB_STATUS_QUEUE_FULL,
+	DMUB_STATUS_TIMEOUT,
+	DMUB_STATUS_INVALID,
+};
+
+/* enum dmub_asic - dmub asic identifier */
+enum dmub_asic {
+	DMUB_ASIC_NONE = 0,
+	DMUB_ASIC_DCN20,
+	DMUB_ASIC_DCN21,
+	DMUB_ASIC_MAX,
+};
+
+/* enum dmub_window_id - dmub window identifier */
+enum dmub_window_id {
+	DMUB_WINDOW_0_INST_CONST = 0,
+	DMUB_WINDOW_1_STACK,
+	DMUB_WINDOW_2_BSS_DATA,
+	DMUB_WINDOW_3_VBIOS,
+	DMUB_WINDOW_4_MAILBOX,
+	DMUB_WINDOW_5_TRACEBUFF,
+	DMUB_WINDOW_6_FW_STATE,
+	DMUB_WINDOW_7_RESERVED,
+	DMUB_WINDOW_TOTAL,
+};
+
+/**
+ * struct dmub_region - dmub hw memory region
+ * @base: base address for region, must be 256 byte aligned
+ * @top: top address for region
+ */
+struct dmub_region {
+	uint32_t base;
+	uint32_t top;
+};
+
+/**
+ * struct dmub_window - dmub hw cache window
+ * @off: offset to the fb memory in gpu address space
+ * @r: region in uc address space for cache window
+ */
+struct dmub_window {
+	union dmub_addr offset;
+	struct dmub_region region;
+};
+
+/**
+ * struct dmub_fb - defines a dmub framebuffer memory region
+ * @cpu_addr: cpu virtual address for the region, NULL if invalid
+ * @gpu_addr: gpu virtual address for the region, NULL if invalid
+ * @size: size of the region in bytes, zero if invalid
+ */
+struct dmub_fb {
+	void *cpu_addr;
+	uint64_t gpu_addr;
+	uint32_t size;
+};
+
+/**
+ * struct dmub_srv_region_params - params used for calculating dmub regions
+ * @inst_const_size: size of the fw inst const section
+ * @bss_data_size: size of the fw bss data section
+ * @vbios_size: size of the vbios data
+ * @fw_bss_data: raw firmware bss data section
+ */
+struct dmub_srv_region_params {
+	uint32_t inst_const_size;
+	uint32_t bss_data_size;
+	uint32_t vbios_size;
+	const uint8_t *fw_bss_data;
+};
+
+/**
+ * struct dmub_srv_region_info - output region info from the dmub service
+ * @fb_size: required minimum fb size for all regions, aligned to 4096 bytes
+ * @num_regions: number of regions used by the dmub service
+ * @regions: region info
+ *
+ * The regions are aligned such that they can be all placed within the
+ * same framebuffer but they can also be placed into different framebuffers.
+ *
+ * The size of each region can be calculated by the caller:
+ * size = reg.top - reg.base
+ *
+ * Care must be taken when performing custom allocations to ensure that each
+ * region base address is 256 byte aligned.
+ */
+struct dmub_srv_region_info {
+	uint32_t fb_size;
+	uint8_t num_regions;
+	struct dmub_region regions[DMUB_WINDOW_TOTAL];
+};
+
+/**
+ * struct dmub_srv_fb_params - parameters used for driver fb setup
+ * @region_info: region info calculated by dmub service
+ * @cpu_addr: base cpu address for the framebuffer
+ * @gpu_addr: base gpu virtual address for the framebuffer
+ */
+struct dmub_srv_fb_params {
+	const struct dmub_srv_region_info *region_info;
+	void *cpu_addr;
+	uint64_t gpu_addr;
+};
+
+/**
+ * struct dmub_srv_fb_info - output fb info from the dmub service
+ * @num_fbs: number of required dmub framebuffers
+ * @fbs: fb data for each region
+ *
+ * Output from the dmub service helper that can be used by the
+ * driver to prepare dmub_fb that can be passed into the dmub
+ * hw init service.
+ *
+ * Assumes that all regions are within the same framebuffer
+ * and have been setup according to the region_info generated
+ * by the dmub service.
+ */
+struct dmub_srv_fb_info {
+	uint8_t num_fb;
+	struct dmub_fb fb[DMUB_WINDOW_TOTAL];
+};
+
+/**
+ * struct dmub_srv_base_funcs - Driver specific base callbacks
+ */
+struct dmub_srv_base_funcs {
+	/**
+	 * @reg_read:
+	 *
+	 * Hook for reading a register.
+	 *
+	 * Return: The 32-bit register value from the given address.
+	 */
+	uint32_t (*reg_read)(void *ctx, uint32_t address);
+
+	/**
+	 * @reg_write:
+	 *
+	 * Hook for writing a value to the register specified by address.
+	 */
+	void (*reg_write)(void *ctx, uint32_t address, uint32_t value);
+};
+
+/**
+ * struct dmub_srv_hw_funcs - hardware sequencer funcs for dmub
+ */
+struct dmub_srv_hw_funcs {
+	/* private: internal use only */
+
+	void (*reset)(struct dmub_srv *dmub);
+
+	void (*reset_release)(struct dmub_srv *dmub);
+
+	void (*backdoor_load)(struct dmub_srv *dmub,
+			      const struct dmub_window *cw0,
+			      const struct dmub_window *cw1);
+
+	void (*setup_windows)(struct dmub_srv *dmub,
+			      const struct dmub_window *cw2,
+			      const struct dmub_window *cw3,
+			      const struct dmub_window *cw4,
+			      const struct dmub_window *cw5,
+			      const struct dmub_window *cw6);
+
+	void (*setup_mailbox)(struct dmub_srv *dmub,
+			      const struct dmub_region *inbox1);
+
+	uint32_t (*get_inbox1_rptr)(struct dmub_srv *dmub);
+
+	void (*set_inbox1_wptr)(struct dmub_srv *dmub, uint32_t wptr_offset);
+
+	bool (*is_supported)(struct dmub_srv *dmub);
+
+	bool (*is_hw_init)(struct dmub_srv *dmub);
+
+	bool (*is_phy_init)(struct dmub_srv *dmub);
+
+	bool (*is_auto_load_done)(struct dmub_srv *dmub);
+};
+
+/**
+ * struct dmub_srv_create_params - params for dmub service creation
+ * @base_funcs: driver supplied base routines
+ * @hw_funcs: optional overrides for hw funcs
+ * @user_ctx: context data for callback funcs
+ * @asic: driver supplied asic
+ * @is_virtual: false for hw support only
+ */
+struct dmub_srv_create_params {
+	struct dmub_srv_base_funcs funcs;
+	struct dmub_srv_hw_funcs *hw_funcs;
+	void *user_ctx;
+	enum dmub_asic asic;
+	bool is_virtual;
+};
+
+/*
+ * struct dmub_srv_hw_params - params for dmub hardware initialization
+ * @fb: framebuffer info for each region
+ * @fb_base: base of the framebuffer aperture
+ * @fb_offset: offset of the framebuffer aperture
+ * @psp_version: psp version to pass for DMCU init
+ * @load_inst_const: true if DMUB should load inst const fw
+ */
+struct dmub_srv_hw_params {
+	struct dmub_fb *fb[DMUB_WINDOW_TOTAL];
+	uint64_t fb_base;
+	uint64_t fb_offset;
+	uint32_t psp_version;
+	bool load_inst_const;
+};
+
+/**
+ * struct dmub_srv - software state for dmcub
+ * @asic: dmub asic identifier
+ * @user_ctx: user provided context for the dmub_srv
+ * @is_virtual: false if hardware support only
+ * @fw_state: dmub firmware state pointer
+ */
+struct dmub_srv {
+	enum dmub_asic asic;
+	void *user_ctx;
+	bool is_virtual;
+	volatile const struct dmub_fw_state *fw_state;
+
+	/* private: internal use only */
+	const struct dmub_srv_common_regs *regs;
+
+	struct dmub_srv_base_funcs funcs;
+	struct dmub_srv_hw_funcs hw_funcs;
+	struct dmub_rb inbox1_rb;
+
+	bool sw_init;
+	bool hw_init;
+
+	uint64_t fb_base;
+	uint64_t fb_offset;
+	uint32_t psp_version;
+};
+
+/**
+ * dmub_srv_create() - creates the DMUB service.
+ * @dmub: the dmub service
+ * @params: creation parameters for the service
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_create(struct dmub_srv *dmub,
+				 const struct dmub_srv_create_params *params);
+
+/**
+ * dmub_srv_destroy() - destroys the DMUB service.
+ * @dmub: the dmub service
+ */
+void dmub_srv_destroy(struct dmub_srv *dmub);
+
+/**
+ * dmub_srv_calc_region_info() - retreives region info from the dmub service
+ * @dmub: the dmub service
+ * @params: parameters used to calculate region locations
+ * @info_out: the output region info from dmub
+ *
+ * Calculates the base and top address for all relevant dmub regions
+ * using the parameters given (if any).
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status
+dmub_srv_calc_region_info(struct dmub_srv *dmub,
+			  const struct dmub_srv_region_params *params,
+			  struct dmub_srv_region_info *out);
+
+/**
+ * dmub_srv_calc_region_info() - retreives fb info from the dmub service
+ * @dmub: the dmub service
+ * @params: parameters used to calculate fb locations
+ * @info_out: the output fb info from dmub
+ *
+ * Calculates the base and top address for all relevant dmub regions
+ * using the parameters given (if any).
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
+				       const struct dmub_srv_fb_params *params,
+				       struct dmub_srv_fb_info *out);
+
+/**
+ * dmub_srv_has_hw_support() - returns hw support state for dmcub
+ * @dmub: the dmub service
+ * @is_supported: hw support state
+ *
+ * Queries the hardware for DMCUB support and returns the result.
+ *
+ * Can be called before dmub_srv_hw_init().
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_has_hw_support(struct dmub_srv *dmub,
+					 bool *is_supported);
+
+/**
+ * dmub_srv_is_hw_init() - returns hardware init state
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_is_hw_init(struct dmub_srv *dmub, bool *is_hw_init);
+
+/**
+ * dmub_srv_hw_init() - initializes the underlying DMUB hardware
+ * @dmub: the dmub service
+ * @params: params for hardware initialization
+ *
+ * Resets the DMUB hardware and performs backdoor loading of the
+ * required cache regions based on the input framebuffer regions.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_NO_CTX - dmcub context not initialized
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub,
+				  const struct dmub_srv_hw_params *params);
+
+/**
+ * dmub_srv_cmd_queue() - queues a command to the DMUB
+ * @dmub: the dmub service
+ * @cmd: the command to queue
+ *
+ * Queues a command to the DMUB service but does not begin execution
+ * immediately.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_QUEUE_FULL - no remaining room in queue
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub,
+				    const struct dmub_cmd_header *cmd);
+
+/**
+ * dmub_srv_cmd_execute() - Executes a queued sequence to the dmub
+ * @dmub: the dmub service
+ *
+ * Begins execution of queued commands on the dmub.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_cmd_execute(struct dmub_srv *dmub);
+
+/**
+ * dmub_srv_wait_for_auto_load() - Waits for firmware auto load to complete
+ * @dmub: the dmub service
+ * @timeout_us: the maximum number of microseconds to wait
+ *
+ * Waits until firmware has been autoloaded by the DMCUB. The maximum
+ * wait time is given in microseconds to prevent spinning forever.
+ *
+ * On ASICs without firmware autoload support this function will return
+ * immediately.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_TIMEOUT - wait for phy init timed out
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_wait_for_auto_load(struct dmub_srv *dmub,
+					     uint32_t timeout_us);
+
+/**
+ * dmub_srv_wait_for_phy_init() - Waits for DMUB PHY init to complete
+ * @dmub: the dmub service
+ * @timeout_us: the maximum number of microseconds to wait
+ *
+ * Waits until the PHY has been initialized by the DMUB. The maximum
+ * wait time is given in microseconds to prevent spinning forever.
+ *
+ * On ASICs without PHY init support this function will return
+ * immediately.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_TIMEOUT - wait for phy init timed out
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_wait_for_phy_init(struct dmub_srv *dmub,
+					    uint32_t timeout_us);
+
+/**
+ * dmub_srv_wait_for_idle() - Waits for the DMUB to be idle
+ * @dmub: the dmub service
+ * @timeout_us: the maximum number of microseconds to wait
+ *
+ * Waits until the DMUB buffer is empty and all commands have
+ * finished processing. The maximum wait time is given in
+ * microseconds to prevent spinning forever.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_TIMEOUT - wait for buffer to flush timed out
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_wait_for_idle(struct dmub_srv *dmub,
+					uint32_t timeout_us);
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _DMUB_SRV_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_trace_buffer.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_trace_buffer.h
new file mode 100644
index 000000000000..6b3ee42db350
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_trace_buffer.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+#ifndef _DMUB_TRACE_BUFFER_H_
+#define _DMUB_TRACE_BUFFER_H_
+
+#include "dmub_types.h"
+
+#define LOAD_DMCU_FW	1
+#define LOAD_PHY_FW	2
+
+
+enum dmucb_trace_code {
+	DMCUB__UNKNOWN,
+	DMCUB__MAIN_BEGIN,
+	DMCUB__PHY_INIT_BEGIN,
+	DMCUB__PHY_FW_SRAM_LOAD_BEGIN,
+	DMCUB__PHY_FW_SRAM_LOAD_END,
+	DMCUB__PHY_INIT_POLL_DONE,
+	DMCUB__PHY_INIT_END,
+	DMCUB__DMCU_ERAM_LOAD_BEGIN,
+	DMCUB__DMCU_ERAM_LOAD_END,
+	DMCUB__DMCU_ISR_LOAD_BEGIN,
+	DMCUB__DMCU_ISR_LOAD_END,
+	DMCUB__MAIN_IDLE,
+	DMCUB__PERF_TRACE,
+	DMCUB__PG_DONE,
+};
+
+struct dmcub_trace_buf_entry {
+	enum dmucb_trace_code trace_code;
+	uint32_t tick_count;
+	uint32_t param0;
+	uint32_t param1;
+};
+
+#define TRACE_BUF_SIZE (1024) //1 kB
+#define PERF_TRACE_MAX_ENTRY ((TRACE_BUF_SIZE - 8)/sizeof(struct dmcub_trace_buf_entry))
+
+
+struct dmcub_trace_buf {
+	uint32_t entry_count;
+	uint32_t clk_freq;
+	struct dmcub_trace_buf_entry entries[PERF_TRACE_MAX_ENTRY];
+};
+
+
+#endif /* _DMUB_TRACE_BUFFER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_types.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_types.h
new file mode 100644
index 000000000000..41d524b0db2f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_types.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_TYPES_H_
+#define _DMUB_TYPES_H_
+
+/* Basic type definitions. */
+#include <asm/byteorder.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <stdarg.h>
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#ifndef dmub_memcpy
+#define dmub_memcpy(dest, source, bytes) memcpy((dest), (source), (bytes))
+#endif
+
+#ifndef dmub_memset
+#define dmub_memset(dest, val, bytes) memset((dest), (val), (bytes))
+#endif
+
+#ifndef dmub_udelay
+#define dmub_udelay(microseconds) udelay(microseconds)
+#endif
+
+union dmub_addr {
+	struct {
+		uint32_t low_part;
+		uint32_t high_part;
+	} u;
+	uint64_t quad_part;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _DMUB_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/Makefile b/drivers/gpu/drm/amd/display/dmub/src/Makefile
new file mode 100644
index 000000000000..e08dfeea24b0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/Makefile
@@ -0,0 +1,27 @@
+#
+# Copyright 2019 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+
+DMUB = dmub_srv.o dmub_reg.o dmub_dcn20.o dmub_dcn21.o
+
+AMD_DAL_DMUB = $(addprefix $(AMDDALPATH)/dmub/src/,$(DMUB))
+
+AMD_DISPLAY_FILES += $(AMD_DAL_DMUB)
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c
new file mode 100644
index 000000000000..cd51c6138894
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "../inc/dmub_srv.h"
+#include "dmub_reg.h"
+#include "dmub_dcn20.h"
+
+#include "dcn/dcn_2_0_0_offset.h"
+#include "dcn/dcn_2_0_0_sh_mask.h"
+#include "soc15_hw_ip.h"
+#include "vega10_ip_offset.h"
+
+#define BASE_INNER(seg) DCN_BASE__INST0_SEG##seg
+#define CTX dmub
+#define REGS dmub->regs
+
+/* Registers. */
+
+const struct dmub_srv_common_regs dmub_srv_dcn20_regs = {
+#define DMUB_SR(reg) REG_OFFSET(reg),
+	{ DMUB_COMMON_REGS() },
+#undef DMUB_SR
+
+#define DMUB_SF(reg, field) FD_MASK(reg, field),
+	{ DMUB_COMMON_FIELDS() },
+#undef DMUB_SF
+
+#define DMUB_SF(reg, field) FD_SHIFT(reg, field),
+	{ DMUB_COMMON_FIELDS() },
+#undef DMUB_SF
+};
+
+/* Shared functions. */
+
+static inline void dmub_dcn20_translate_addr(const union dmub_addr *addr_in,
+					     uint64_t fb_base,
+					     uint64_t fb_offset,
+					     union dmub_addr *addr_out)
+{
+	addr_out->quad_part = addr_in->quad_part - fb_base + fb_offset;
+}
+
+void dmub_dcn20_reset(struct dmub_srv *dmub)
+{
+	REG_UPDATE(DMCUB_CNTL, DMCUB_SOFT_RESET, 1);
+	REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0);
+	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
+}
+
+void dmub_dcn20_reset_release(struct dmub_srv *dmub)
+{
+	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 0);
+	REG_WRITE(DMCUB_SCRATCH15, dmub->psp_version & 0x001100FF);
+	REG_UPDATE_2(DMCUB_CNTL, DMCUB_ENABLE, 1, DMCUB_TRACEPORT_EN, 1);
+	REG_UPDATE(DMCUB_CNTL, DMCUB_SOFT_RESET, 0);
+}
+
+void dmub_dcn20_backdoor_load(struct dmub_srv *dmub,
+			      const struct dmub_window *cw0,
+			      const struct dmub_window *cw1)
+{
+	union dmub_addr offset;
+	uint64_t fb_base = dmub->fb_base, fb_offset = dmub->fb_offset;
+
+	REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1);
+	REG_UPDATE_2(DMCUB_MEM_CNTL, DMCUB_MEM_READ_SPACE, 0x3,
+		     DMCUB_MEM_WRITE_SPACE, 0x3);
+
+	dmub_dcn20_translate_addr(&cw0->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW0_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW0_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW0_BASE_ADDRESS, cw0->region.base);
+	REG_SET_2(DMCUB_REGION3_CW0_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW0_TOP_ADDRESS, cw0->region.top,
+		  DMCUB_REGION3_CW0_ENABLE, 1);
+
+	dmub_dcn20_translate_addr(&cw1->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW1_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW1_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW1_BASE_ADDRESS, cw1->region.base);
+	REG_SET_2(DMCUB_REGION3_CW1_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top,
+		  DMCUB_REGION3_CW1_ENABLE, 1);
+
+	REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID,
+		     0x20);
+}
+
+void dmub_dcn20_setup_windows(struct dmub_srv *dmub,
+			      const struct dmub_window *cw2,
+			      const struct dmub_window *cw3,
+			      const struct dmub_window *cw4,
+			      const struct dmub_window *cw5,
+			      const struct dmub_window *cw6)
+{
+	union dmub_addr offset;
+	uint64_t fb_base = dmub->fb_base, fb_offset = dmub->fb_offset;
+
+	dmub_dcn20_translate_addr(&cw2->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW2_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW2_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW2_BASE_ADDRESS, cw2->region.base);
+	REG_SET_2(DMCUB_REGION3_CW2_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW2_TOP_ADDRESS, cw2->region.top,
+		  DMCUB_REGION3_CW2_ENABLE, 1);
+
+	dmub_dcn20_translate_addr(&cw3->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW3_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW3_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW3_BASE_ADDRESS, cw3->region.base);
+	REG_SET_2(DMCUB_REGION3_CW3_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW3_TOP_ADDRESS, cw3->region.top,
+		  DMCUB_REGION3_CW3_ENABLE, 1);
+
+	/* TODO: Move this to CW4. */
+	dmub_dcn20_translate_addr(&cw4->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION4_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION4_OFFSET_HIGH, offset.u.high_part);
+	REG_SET_2(DMCUB_REGION4_TOP_ADDRESS, 0, DMCUB_REGION4_TOP_ADDRESS,
+		  cw4->region.top - cw4->region.base - 1, DMCUB_REGION4_ENABLE,
+		  1);
+
+	dmub_dcn20_translate_addr(&cw5->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW5_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW5_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW5_BASE_ADDRESS, cw5->region.base);
+	REG_SET_2(DMCUB_REGION3_CW5_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW5_TOP_ADDRESS, cw5->region.top,
+		  DMCUB_REGION3_CW5_ENABLE, 1);
+
+	dmub_dcn20_translate_addr(&cw6->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW6_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW6_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW6_BASE_ADDRESS, cw6->region.base);
+	REG_SET_2(DMCUB_REGION3_CW6_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW6_TOP_ADDRESS, cw6->region.top,
+		  DMCUB_REGION3_CW6_ENABLE, 1);
+}
+
+void dmub_dcn20_setup_mailbox(struct dmub_srv *dmub,
+			      const struct dmub_region *inbox1)
+{
+	/* TODO: Use CW4 instead of region 4. */
+
+	REG_WRITE(DMCUB_INBOX1_BASE_ADDRESS, 0x80000000);
+	REG_WRITE(DMCUB_INBOX1_SIZE, inbox1->top - inbox1->base);
+	REG_WRITE(DMCUB_INBOX1_RPTR, 0);
+	REG_WRITE(DMCUB_INBOX1_WPTR, 0);
+}
+
+uint32_t dmub_dcn20_get_inbox1_rptr(struct dmub_srv *dmub)
+{
+	return REG_READ(DMCUB_INBOX1_RPTR);
+}
+
+void dmub_dcn20_set_inbox1_wptr(struct dmub_srv *dmub, uint32_t wptr_offset)
+{
+	REG_WRITE(DMCUB_INBOX1_WPTR, wptr_offset);
+}
+
+bool dmub_dcn20_is_hw_init(struct dmub_srv *dmub)
+{
+	return REG_READ(DMCUB_REGION3_CW2_BASE_ADDRESS) != 0;
+}
+
+bool dmub_dcn20_is_supported(struct dmub_srv *dmub)
+{
+	uint32_t supported = 0;
+
+	REG_GET(CC_DC_PIPE_DIS, DC_DMCUB_ENABLE, &supported);
+
+	return supported;
+}
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h
new file mode 100644
index 000000000000..53bfd4da69ad
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h
@@ -0,0 +1,182 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_DCN20_H_
+#define _DMUB_DCN20_H_
+
+#include "../inc/dmub_types.h"
+
+struct dmub_srv;
+
+/* DCN20 register definitions. */
+
+#define DMUB_COMMON_REGS() \
+	DMUB_SR(DMCUB_CNTL) \
+	DMUB_SR(DMCUB_MEM_CNTL) \
+	DMUB_SR(DMCUB_SEC_CNTL) \
+	DMUB_SR(DMCUB_INBOX1_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_INBOX1_SIZE) \
+	DMUB_SR(DMCUB_INBOX1_RPTR) \
+	DMUB_SR(DMCUB_INBOX1_WPTR) \
+	DMUB_SR(DMCUB_REGION3_CW0_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW1_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW2_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW3_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW4_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW5_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW6_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW7_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW0_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW1_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW2_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW3_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW4_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW5_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW6_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW7_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW0_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW1_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW2_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW3_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW4_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW5_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW6_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW7_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW0_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW1_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW2_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW3_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW4_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW5_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW6_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW7_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION4_OFFSET) \
+	DMUB_SR(DMCUB_REGION4_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION4_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_SCRATCH0) \
+	DMUB_SR(DMCUB_SCRATCH1) \
+	DMUB_SR(DMCUB_SCRATCH2) \
+	DMUB_SR(DMCUB_SCRATCH3) \
+	DMUB_SR(DMCUB_SCRATCH4) \
+	DMUB_SR(DMCUB_SCRATCH5) \
+	DMUB_SR(DMCUB_SCRATCH6) \
+	DMUB_SR(DMCUB_SCRATCH7) \
+	DMUB_SR(DMCUB_SCRATCH8) \
+	DMUB_SR(DMCUB_SCRATCH9) \
+	DMUB_SR(DMCUB_SCRATCH10) \
+	DMUB_SR(DMCUB_SCRATCH11) \
+	DMUB_SR(DMCUB_SCRATCH12) \
+	DMUB_SR(DMCUB_SCRATCH13) \
+	DMUB_SR(DMCUB_SCRATCH14) \
+	DMUB_SR(DMCUB_SCRATCH15) \
+	DMUB_SR(CC_DC_PIPE_DIS) \
+	DMUB_SR(MMHUBBUB_SOFT_RESET)
+
+#define DMUB_COMMON_FIELDS() \
+	DMUB_SF(DMCUB_CNTL, DMCUB_ENABLE) \
+	DMUB_SF(DMCUB_CNTL, DMCUB_SOFT_RESET) \
+	DMUB_SF(DMCUB_CNTL, DMCUB_TRACEPORT_EN) \
+	DMUB_SF(DMCUB_MEM_CNTL, DMCUB_MEM_READ_SPACE) \
+	DMUB_SF(DMCUB_MEM_CNTL, DMCUB_MEM_WRITE_SPACE) \
+	DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET) \
+	DMUB_SF(DMCUB_SEC_CNTL, DMCUB_MEM_UNIT_ID) \
+	DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW2_TOP_ADDRESS, DMCUB_REGION3_CW2_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW2_TOP_ADDRESS, DMCUB_REGION3_CW2_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW3_TOP_ADDRESS, DMCUB_REGION3_CW3_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW3_TOP_ADDRESS, DMCUB_REGION3_CW3_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW4_TOP_ADDRESS, DMCUB_REGION3_CW4_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW4_TOP_ADDRESS, DMCUB_REGION3_CW4_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW5_TOP_ADDRESS, DMCUB_REGION3_CW5_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW5_TOP_ADDRESS, DMCUB_REGION3_CW5_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW7_TOP_ADDRESS, DMCUB_REGION3_CW7_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW7_TOP_ADDRESS, DMCUB_REGION3_CW7_ENABLE) \
+	DMUB_SF(DMCUB_REGION4_TOP_ADDRESS, DMCUB_REGION4_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION4_TOP_ADDRESS, DMCUB_REGION4_ENABLE) \
+	DMUB_SF(CC_DC_PIPE_DIS, DC_DMCUB_ENABLE) \
+	DMUB_SF(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET)
+
+struct dmub_srv_common_reg_offset {
+#define DMUB_SR(reg) uint32_t reg;
+	DMUB_COMMON_REGS()
+#undef DMUB_SR
+};
+
+struct dmub_srv_common_reg_shift {
+#define DMUB_SF(reg, field) uint8_t reg##__##field;
+	DMUB_COMMON_FIELDS()
+#undef DMUB_SF
+};
+
+struct dmub_srv_common_reg_mask {
+#define DMUB_SF(reg, field) uint32_t reg##__##field;
+	DMUB_COMMON_FIELDS()
+#undef DMUB_SF
+};
+
+struct dmub_srv_common_regs {
+	const struct dmub_srv_common_reg_offset offset;
+	const struct dmub_srv_common_reg_mask mask;
+	const struct dmub_srv_common_reg_shift shift;
+};
+
+extern const struct dmub_srv_common_regs dmub_srv_dcn20_regs;
+
+/* Hardware functions. */
+
+void dmub_dcn20_init(struct dmub_srv *dmub);
+
+void dmub_dcn20_reset(struct dmub_srv *dmub);
+
+void dmub_dcn20_reset_release(struct dmub_srv *dmub);
+
+void dmub_dcn20_backdoor_load(struct dmub_srv *dmub,
+			      const struct dmub_window *cw0,
+			      const struct dmub_window *cw1);
+
+void dmub_dcn20_setup_windows(struct dmub_srv *dmub,
+			      const struct dmub_window *cw2,
+			      const struct dmub_window *cw3,
+			      const struct dmub_window *cw4,
+			      const struct dmub_window *cw5,
+			      const struct dmub_window *cw6);
+
+void dmub_dcn20_setup_mailbox(struct dmub_srv *dmub,
+			      const struct dmub_region *inbox1);
+
+uint32_t dmub_dcn20_get_inbox1_rptr(struct dmub_srv *dmub);
+
+void dmub_dcn20_set_inbox1_wptr(struct dmub_srv *dmub, uint32_t wptr_offset);
+
+bool dmub_dcn20_is_hw_init(struct dmub_srv *dmub);
+
+bool dmub_dcn20_is_supported(struct dmub_srv *dmub);
+
+#endif /* _DMUB_DCN20_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c
new file mode 100644
index 000000000000..5bed9fcd6b5c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "../inc/dmub_srv.h"
+#include "dmub_reg.h"
+#include "dmub_dcn21.h"
+
+#include "dcn/dcn_2_1_0_offset.h"
+#include "dcn/dcn_2_1_0_sh_mask.h"
+#include "renoir_ip_offset.h"
+
+#define BASE_INNER(seg) DMU_BASE__INST0_SEG##seg
+#define CTX dmub
+#define REGS dmub->regs
+
+/* Registers. */
+
+const struct dmub_srv_common_regs dmub_srv_dcn21_regs = {
+#define DMUB_SR(reg) REG_OFFSET(reg),
+	{ DMUB_COMMON_REGS() },
+#undef DMUB_SR
+
+#define DMUB_SF(reg, field) FD_MASK(reg, field),
+	{ DMUB_COMMON_FIELDS() },
+#undef DMUB_SF
+
+#define DMUB_SF(reg, field) FD_SHIFT(reg, field),
+	{ DMUB_COMMON_FIELDS() },
+#undef DMUB_SF
+};
+
+/* Shared functions. */
+
+bool dmub_dcn21_is_auto_load_done(struct dmub_srv *dmub)
+{
+	return (REG_READ(DMCUB_SCRATCH0) == 3);
+}
+
+bool dmub_dcn21_is_phy_init(struct dmub_srv *dmub)
+{
+	return REG_READ(DMCUB_SCRATCH10) == 0;
+}
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h
new file mode 100644
index 000000000000..2bbea237137b
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_DCN21_H_
+#define _DMUB_DCN21_H_
+
+#include "dmub_dcn20.h"
+
+/* Registers. */
+
+extern const struct dmub_srv_common_regs dmub_srv_dcn21_regs;
+
+/* Hardware functions. */
+
+bool dmub_dcn21_is_auto_load_done(struct dmub_srv *dmub);
+
+bool dmub_dcn21_is_phy_init(struct dmub_srv *dmub);
+
+#endif /* _DMUB_DCN21_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.c
new file mode 100644
index 000000000000..4094eca212f0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dmub_reg.h"
+#include "../inc/dmub_srv.h"
+
+struct dmub_reg_value_masks {
+	uint32_t value;
+	uint32_t mask;
+};
+
+static inline void
+set_reg_field_value_masks(struct dmub_reg_value_masks *field_value_mask,
+			  uint32_t value, uint32_t mask, uint8_t shift)
+{
+	field_value_mask->value =
+		(field_value_mask->value & ~mask) | (mask & (value << shift));
+	field_value_mask->mask = field_value_mask->mask | mask;
+}
+
+static void set_reg_field_values(struct dmub_reg_value_masks *field_value_mask,
+				 uint32_t addr, int n, uint8_t shift1,
+				 uint32_t mask1, uint32_t field_value1,
+				 va_list ap)
+{
+	uint32_t shift, mask, field_value;
+	int i = 1;
+
+	/* gather all bits value/mask getting updated in this register */
+	set_reg_field_value_masks(field_value_mask, field_value1, mask1,
+				  shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t);
+
+		set_reg_field_value_masks(field_value_mask, field_value, mask,
+					  shift);
+		i++;
+	}
+}
+
+static inline uint32_t get_reg_field_value_ex(uint32_t reg_value, uint32_t mask,
+					      uint8_t shift)
+{
+	return (mask & reg_value) >> shift;
+}
+
+void dmub_reg_update(struct dmub_srv *srv, uint32_t addr, int n, uint8_t shift1,
+		     uint32_t mask1, uint32_t field_value1, ...)
+{
+	struct dmub_reg_value_masks field_value_mask = { 0 };
+	uint32_t reg_val;
+	va_list ap;
+
+	va_start(ap, field_value1);
+	set_reg_field_values(&field_value_mask, addr, n, shift1, mask1,
+			     field_value1, ap);
+	va_end(ap);
+
+	reg_val = srv->funcs.reg_read(srv->user_ctx, addr);
+	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+	srv->funcs.reg_write(srv->user_ctx, addr, reg_val);
+}
+
+void dmub_reg_set(struct dmub_srv *srv, uint32_t addr, uint32_t reg_val, int n,
+		  uint8_t shift1, uint32_t mask1, uint32_t field_value1, ...)
+{
+	struct dmub_reg_value_masks field_value_mask = { 0 };
+	va_list ap;
+
+	va_start(ap, field_value1);
+	set_reg_field_values(&field_value_mask, addr, n, shift1, mask1,
+			     field_value1, ap);
+	va_end(ap);
+
+	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+	srv->funcs.reg_write(srv->user_ctx, addr, reg_val);
+}
+
+void dmub_reg_get(struct dmub_srv *srv, uint32_t addr, uint8_t shift,
+		  uint32_t mask, uint32_t *field_value)
+{
+	uint32_t reg_val = srv->funcs.reg_read(srv->user_ctx, addr);
+	*field_value = get_reg_field_value_ex(reg_val, mask, shift);
+}
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h
new file mode 100644
index 000000000000..c1f4030929a4
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_REG_H_
+#define _DMUB_REG_H_
+
+#include "../inc/dmub_types.h"
+
+struct dmub_srv;
+
+/* Register offset and field lookup. */
+
+#define BASE(seg) BASE_INNER(seg)
+
+#define REG_OFFSET(reg_name) (BASE(mm##reg_name##_BASE_IDX) + mm##reg_name)
+
+#define FD_SHIFT(reg_name, field) reg_name##__##field##__SHIFT
+
+#define FD_MASK(reg_name, field) reg_name##__##field##_MASK
+
+#define REG(reg) (REGS)->offset.reg
+
+#define FD(reg_field) (REGS)->shift.reg_field, (REGS)->mask.reg_field
+
+#define FN(reg_name, field) FD(reg_name##__##field)
+
+/* Register reads and writes. */
+
+#define REG_READ(reg) ((CTX)->funcs.reg_read((CTX)->user_ctx, REG(reg)))
+
+#define REG_WRITE(reg, val) \
+	((CTX)->funcs.reg_write((CTX)->user_ctx, REG(reg), (val)))
+
+/* Register field setting. */
+
+#define REG_SET_N(reg_name, n, initial_val, ...) \
+	dmub_reg_set(CTX, REG(reg_name), initial_val, n, __VA_ARGS__)
+
+#define REG_SET(reg_name, initial_val, field, val) \
+		REG_SET_N(reg_name, 1, initial_val, \
+				FN(reg_name, field), val)
+
+#define REG_SET_2(reg, init_value, f1, v1, f2, v2) \
+		REG_SET_N(reg, 2, init_value, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2)
+
+#define REG_SET_3(reg, init_value, f1, v1, f2, v2, f3, v3) \
+		REG_SET_N(reg, 3, init_value, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2, \
+				FN(reg, f3), v3)
+
+#define REG_SET_4(reg, init_value, f1, v1, f2, v2, f3, v3, f4, v4) \
+		REG_SET_N(reg, 4, init_value, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2, \
+				FN(reg, f3), v3, \
+				FN(reg, f4), v4)
+
+/* Register field updating. */
+
+#define REG_UPDATE_N(reg_name, n, ...)\
+		dmub_reg_update(CTX, REG(reg_name), n, __VA_ARGS__)
+
+#define REG_UPDATE(reg_name, field, val)	\
+		REG_UPDATE_N(reg_name, 1, \
+				FN(reg_name, field), val)
+
+#define REG_UPDATE_2(reg, f1, v1, f2, v2)	\
+		REG_UPDATE_N(reg, 2,\
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+#define REG_UPDATE_3(reg, f1, v1, f2, v2, f3, v3) \
+		REG_UPDATE_N(reg, 3, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2, \
+				FN(reg, f3), v3)
+
+#define REG_UPDATE_4(reg, f1, v1, f2, v2, f3, v3, f4, v4) \
+		REG_UPDATE_N(reg, 4, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2, \
+				FN(reg, f3), v3, \
+				FN(reg, f4), v4)
+
+/* Register field getting. */
+
+#define REG_GET(reg_name, field, val) \
+	dmub_reg_get(CTX, REG(reg_name), FN(reg_name, field), val)
+
+void dmub_reg_set(struct dmub_srv *srv, uint32_t addr, uint32_t reg_val, int n,
+		  uint8_t shift1, uint32_t mask1, uint32_t field_value1, ...);
+
+void dmub_reg_update(struct dmub_srv *srv, uint32_t addr, int n, uint8_t shift1,
+		     uint32_t mask1, uint32_t field_value1, ...);
+
+void dmub_reg_get(struct dmub_srv *srv, uint32_t addr, uint8_t shift,
+		  uint32_t mask, uint32_t *field_value);
+
+#endif /* _DMUB_REG_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
new file mode 100644
index 000000000000..dee676335d73
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -0,0 +1,505 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "../inc/dmub_srv.h"
+#include "dmub_dcn20.h"
+#include "dmub_dcn21.h"
+#include "dmub_fw_meta.h"
+#include "os_types.h"
+/*
+ * Note: the DMUB service is standalone. No additional headers should be
+ * added below or above this line unless they reside within the DMUB
+ * folder.
+ */
+
+/* Alignment for framebuffer memory. */
+#define DMUB_FB_ALIGNMENT (1024 * 1024)
+
+/* Stack size. */
+#define DMUB_STACK_SIZE (128 * 1024)
+
+/* Context size. */
+#define DMUB_CONTEXT_SIZE (512 * 1024)
+
+/* Mailbox size */
+#define DMUB_MAILBOX_SIZE (DMUB_RB_SIZE)
+
+/* Default state size if meta is absent. */
+#define DMUB_FW_STATE_SIZE (1024)
+
+/* Default tracebuffer size if meta is absent. */
+#define DMUB_TRACE_BUFFER_SIZE (1024)
+
+/* Number of windows in use. */
+#define DMUB_NUM_WINDOWS (DMUB_WINDOW_6_FW_STATE + 1)
+/* Base addresses. */
+
+#define DMUB_CW0_BASE (0x60000000)
+#define DMUB_CW1_BASE (0x61000000)
+#define DMUB_CW3_BASE (0x63000000)
+#define DMUB_CW5_BASE (0x65000000)
+#define DMUB_CW6_BASE (0x66000000)
+
+static inline uint32_t dmub_align(uint32_t val, uint32_t factor)
+{
+	return (val + factor - 1) / factor * factor;
+}
+
+static void dmub_flush_buffer_mem(const struct dmub_fb *fb)
+{
+	const uint8_t *base = (const uint8_t *)fb->cpu_addr;
+	uint8_t buf[64];
+	uint32_t pos, end;
+
+	/**
+	 * Read 64-byte chunks since we don't want to store a
+	 * large temporary buffer for this purpose.
+	 */
+	end = fb->size / sizeof(buf) * sizeof(buf);
+
+	for (pos = 0; pos < end; pos += sizeof(buf))
+		dmub_memcpy(buf, base + pos, sizeof(buf));
+
+	/* Read anything leftover into the buffer. */
+	if (end < fb->size)
+		dmub_memcpy(buf, base + pos, fb->size - end);
+}
+
+static const struct dmub_fw_meta_info *
+dmub_get_fw_meta_info(const uint8_t *fw_bss_data, uint32_t fw_bss_data_size)
+{
+	const union dmub_fw_meta *meta;
+
+	if (fw_bss_data == NULL)
+		return NULL;
+
+	if (fw_bss_data_size < sizeof(union dmub_fw_meta) + DMUB_FW_META_OFFSET)
+		return NULL;
+
+	meta = (const union dmub_fw_meta *)(fw_bss_data + fw_bss_data_size -
+					    DMUB_FW_META_OFFSET -
+					    sizeof(union dmub_fw_meta));
+
+	if (meta->info.magic_value != DMUB_FW_META_MAGIC)
+		return NULL;
+
+	return &meta->info;
+}
+
+static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic)
+{
+	struct dmub_srv_hw_funcs *funcs = &dmub->hw_funcs;
+
+	switch (asic) {
+	case DMUB_ASIC_DCN20:
+	case DMUB_ASIC_DCN21:
+		dmub->regs = &dmub_srv_dcn20_regs;
+
+		funcs->reset = dmub_dcn20_reset;
+		funcs->reset_release = dmub_dcn20_reset_release;
+		funcs->backdoor_load = dmub_dcn20_backdoor_load;
+		funcs->setup_windows = dmub_dcn20_setup_windows;
+		funcs->setup_mailbox = dmub_dcn20_setup_mailbox;
+		funcs->get_inbox1_rptr = dmub_dcn20_get_inbox1_rptr;
+		funcs->set_inbox1_wptr = dmub_dcn20_set_inbox1_wptr;
+		funcs->is_supported = dmub_dcn20_is_supported;
+		funcs->is_hw_init = dmub_dcn20_is_hw_init;
+
+		if (asic == DMUB_ASIC_DCN21) {
+			dmub->regs = &dmub_srv_dcn21_regs;
+
+			funcs->is_auto_load_done = dmub_dcn21_is_auto_load_done;
+			funcs->is_phy_init = dmub_dcn21_is_phy_init;
+		}
+		break;
+
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+enum dmub_status dmub_srv_create(struct dmub_srv *dmub,
+				 const struct dmub_srv_create_params *params)
+{
+	enum dmub_status status = DMUB_STATUS_OK;
+
+	dmub_memset(dmub, 0, sizeof(*dmub));
+
+	dmub->funcs = params->funcs;
+	dmub->user_ctx = params->user_ctx;
+	dmub->asic = params->asic;
+	dmub->is_virtual = params->is_virtual;
+
+	/* Setup asic dependent hardware funcs. */
+	if (!dmub_srv_hw_setup(dmub, params->asic)) {
+		status = DMUB_STATUS_INVALID;
+		goto cleanup;
+	}
+
+	/* Override (some) hardware funcs based on user params. */
+	if (params->hw_funcs) {
+		if (params->hw_funcs->get_inbox1_rptr)
+			dmub->hw_funcs.get_inbox1_rptr =
+				params->hw_funcs->get_inbox1_rptr;
+
+		if (params->hw_funcs->set_inbox1_wptr)
+			dmub->hw_funcs.set_inbox1_wptr =
+				params->hw_funcs->set_inbox1_wptr;
+
+		if (params->hw_funcs->is_supported)
+			dmub->hw_funcs.is_supported =
+				params->hw_funcs->is_supported;
+	}
+
+	/* Sanity checks for required hw func pointers. */
+	if (!dmub->hw_funcs.get_inbox1_rptr ||
+	    !dmub->hw_funcs.set_inbox1_wptr) {
+		status = DMUB_STATUS_INVALID;
+		goto cleanup;
+	}
+
+cleanup:
+	if (status == DMUB_STATUS_OK)
+		dmub->sw_init = true;
+	else
+		dmub_srv_destroy(dmub);
+
+	return status;
+}
+
+void dmub_srv_destroy(struct dmub_srv *dmub)
+{
+	dmub_memset(dmub, 0, sizeof(*dmub));
+}
+
+enum dmub_status
+dmub_srv_calc_region_info(struct dmub_srv *dmub,
+			  const struct dmub_srv_region_params *params,
+			  struct dmub_srv_region_info *out)
+{
+	struct dmub_region *inst = &out->regions[DMUB_WINDOW_0_INST_CONST];
+	struct dmub_region *stack = &out->regions[DMUB_WINDOW_1_STACK];
+	struct dmub_region *data = &out->regions[DMUB_WINDOW_2_BSS_DATA];
+	struct dmub_region *bios = &out->regions[DMUB_WINDOW_3_VBIOS];
+	struct dmub_region *mail = &out->regions[DMUB_WINDOW_4_MAILBOX];
+	struct dmub_region *trace_buff = &out->regions[DMUB_WINDOW_5_TRACEBUFF];
+	struct dmub_region *fw_state = &out->regions[DMUB_WINDOW_6_FW_STATE];
+	const struct dmub_fw_meta_info *fw_info;
+	uint32_t fw_state_size = DMUB_FW_STATE_SIZE;
+	uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	memset(out, 0, sizeof(*out));
+
+	out->num_regions = DMUB_NUM_WINDOWS;
+
+	inst->base = 0x0;
+	inst->top = inst->base + params->inst_const_size;
+
+	data->base = dmub_align(inst->top, 256);
+	data->top = data->base + params->bss_data_size;
+
+	/*
+	 * All cache windows below should be aligned to the size
+	 * of the DMCUB cache line, 64 bytes.
+	 */
+
+	stack->base = dmub_align(data->top, 256);
+	stack->top = stack->base + DMUB_STACK_SIZE + DMUB_CONTEXT_SIZE;
+
+	bios->base = dmub_align(stack->top, 256);
+	bios->top = bios->base + params->vbios_size;
+
+	mail->base = dmub_align(bios->top, 256);
+	mail->top = mail->base + DMUB_MAILBOX_SIZE;
+
+	fw_info = dmub_get_fw_meta_info(params->fw_bss_data,
+					params->bss_data_size);
+
+	if (fw_info) {
+		fw_state_size = fw_info->fw_region_size;
+		trace_buffer_size = fw_info->trace_buffer_size;
+	}
+
+	trace_buff->base = dmub_align(mail->top, 256);
+	trace_buff->top = trace_buff->base + dmub_align(trace_buffer_size, 64);
+
+	fw_state->base = dmub_align(trace_buff->top, 256);
+	fw_state->top = fw_state->base + dmub_align(fw_state_size, 64);
+
+	out->fb_size = dmub_align(fw_state->top, 4096);
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
+				       const struct dmub_srv_fb_params *params,
+				       struct dmub_srv_fb_info *out)
+{
+	uint8_t *cpu_base;
+	uint64_t gpu_base;
+	uint32_t i;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	memset(out, 0, sizeof(*out));
+
+	if (params->region_info->num_regions != DMUB_NUM_WINDOWS)
+		return DMUB_STATUS_INVALID;
+
+	cpu_base = (uint8_t *)params->cpu_addr;
+	gpu_base = params->gpu_addr;
+
+	for (i = 0; i < DMUB_NUM_WINDOWS; ++i) {
+		const struct dmub_region *reg =
+			&params->region_info->regions[i];
+
+		out->fb[i].cpu_addr = cpu_base + reg->base;
+		out->fb[i].gpu_addr = gpu_base + reg->base;
+		out->fb[i].size = reg->top - reg->base;
+	}
+
+	out->num_fb = DMUB_NUM_WINDOWS;
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_has_hw_support(struct dmub_srv *dmub,
+					 bool *is_supported)
+{
+	*is_supported = false;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (dmub->hw_funcs.is_supported)
+		*is_supported = dmub->hw_funcs.is_supported(dmub);
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_is_hw_init(struct dmub_srv *dmub, bool *is_hw_init)
+{
+	*is_hw_init = false;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (dmub->hw_funcs.is_hw_init)
+		*is_hw_init = dmub->hw_funcs.is_hw_init(dmub);
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub,
+				  const struct dmub_srv_hw_params *params)
+{
+	struct dmub_fb *inst_fb = params->fb[DMUB_WINDOW_0_INST_CONST];
+	struct dmub_fb *stack_fb = params->fb[DMUB_WINDOW_1_STACK];
+	struct dmub_fb *data_fb = params->fb[DMUB_WINDOW_2_BSS_DATA];
+	struct dmub_fb *bios_fb = params->fb[DMUB_WINDOW_3_VBIOS];
+	struct dmub_fb *mail_fb = params->fb[DMUB_WINDOW_4_MAILBOX];
+	struct dmub_fb *tracebuff_fb = params->fb[DMUB_WINDOW_5_TRACEBUFF];
+	struct dmub_fb *fw_state_fb = params->fb[DMUB_WINDOW_6_FW_STATE];
+
+	struct dmub_rb_init_params rb_params;
+	struct dmub_window cw0, cw1, cw2, cw3, cw4, cw5, cw6;
+	struct dmub_region inbox1;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	dmub->fb_base = params->fb_base;
+	dmub->fb_offset = params->fb_offset;
+	dmub->psp_version = params->psp_version;
+
+	if (inst_fb && data_fb) {
+		cw0.offset.quad_part = inst_fb->gpu_addr;
+		cw0.region.base = DMUB_CW0_BASE;
+		cw0.region.top = cw0.region.base + inst_fb->size - 1;
+
+		cw1.offset.quad_part = stack_fb->gpu_addr;
+		cw1.region.base = DMUB_CW1_BASE;
+		cw1.region.top = cw1.region.base + stack_fb->size - 1;
+
+		/**
+		 * Read back all the instruction memory so we don't hang the
+		 * DMCUB when backdoor loading if the write from x86 hasn't been
+		 * flushed yet. This only occurs in backdoor loading.
+		 */
+		dmub_flush_buffer_mem(inst_fb);
+
+		if (params->load_inst_const && dmub->hw_funcs.backdoor_load)
+			dmub->hw_funcs.backdoor_load(dmub, &cw0, &cw1);
+	}
+
+	if (dmub->hw_funcs.reset)
+		dmub->hw_funcs.reset(dmub);
+
+	if (inst_fb && data_fb && bios_fb && mail_fb && tracebuff_fb &&
+	    fw_state_fb) {
+		cw2.offset.quad_part = data_fb->gpu_addr;
+		cw2.region.base = DMUB_CW0_BASE + inst_fb->size;
+		cw2.region.top = cw2.region.base + data_fb->size;
+
+		cw3.offset.quad_part = bios_fb->gpu_addr;
+		cw3.region.base = DMUB_CW3_BASE;
+		cw3.region.top = cw3.region.base + bios_fb->size;
+
+		cw4.offset.quad_part = mail_fb->gpu_addr;
+		cw4.region.base = cw3.region.top + 1;
+		cw4.region.top = cw4.region.base + mail_fb->size;
+
+		inbox1.base = cw4.region.base;
+		inbox1.top = cw4.region.top;
+
+		cw5.offset.quad_part = tracebuff_fb->gpu_addr;
+		cw5.region.base = DMUB_CW5_BASE;
+		cw5.region.top = cw5.region.base + tracebuff_fb->size;
+
+		cw6.offset.quad_part = fw_state_fb->gpu_addr;
+		cw6.region.base = DMUB_CW6_BASE;
+		cw6.region.top = cw6.region.base + fw_state_fb->size;
+
+		dmub->fw_state = fw_state_fb->cpu_addr;
+
+		if (dmub->hw_funcs.setup_windows)
+			dmub->hw_funcs.setup_windows(dmub, &cw2, &cw3, &cw4,
+						     &cw5, &cw6);
+
+		if (dmub->hw_funcs.setup_mailbox)
+			dmub->hw_funcs.setup_mailbox(dmub, &inbox1);
+	}
+
+	if (mail_fb) {
+		dmub_memset(&rb_params, 0, sizeof(rb_params));
+		rb_params.ctx = dmub;
+		rb_params.base_address = mail_fb->cpu_addr;
+		rb_params.capacity = DMUB_RB_SIZE;
+
+		dmub_rb_init(&dmub->inbox1_rb, &rb_params);
+	}
+
+	if (dmub->hw_funcs.reset_release)
+		dmub->hw_funcs.reset_release(dmub);
+
+	dmub->hw_init = true;
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub,
+				    const struct dmub_cmd_header *cmd)
+{
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (dmub_rb_push_front(&dmub->inbox1_rb, cmd))
+		return DMUB_STATUS_OK;
+
+	return DMUB_STATUS_QUEUE_FULL;
+}
+
+enum dmub_status dmub_srv_cmd_execute(struct dmub_srv *dmub)
+{
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	/**
+	 * Read back all the queued commands to ensure that they've
+	 * been flushed to framebuffer memory. Otherwise DMCUB might
+	 * read back stale, fully invalid or partially invalid data.
+	 */
+	dmub_rb_flush_pending(&dmub->inbox1_rb);
+
+	dmub->hw_funcs.set_inbox1_wptr(dmub, dmub->inbox1_rb.wrpt);
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_wait_for_auto_load(struct dmub_srv *dmub,
+					     uint32_t timeout_us)
+{
+	uint32_t i;
+
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (!dmub->hw_funcs.is_auto_load_done)
+		return DMUB_STATUS_OK;
+
+	for (i = 0; i <= timeout_us; i += 100) {
+		if (dmub->hw_funcs.is_auto_load_done(dmub))
+			return DMUB_STATUS_OK;
+
+		udelay(100);
+	}
+
+	return DMUB_STATUS_TIMEOUT;
+}
+
+enum dmub_status dmub_srv_wait_for_phy_init(struct dmub_srv *dmub,
+					    uint32_t timeout_us)
+{
+	uint32_t i = 0;
+
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (!dmub->hw_funcs.is_phy_init)
+		return DMUB_STATUS_OK;
+
+	for (i = 0; i <= timeout_us; i += 10) {
+		if (dmub->hw_funcs.is_phy_init(dmub))
+			return DMUB_STATUS_OK;
+
+		udelay(10);
+	}
+
+	return DMUB_STATUS_TIMEOUT;
+}
+
+enum dmub_status dmub_srv_wait_for_idle(struct dmub_srv *dmub,
+					uint32_t timeout_us)
+{
+	uint32_t i;
+
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	for (i = 0; i <= timeout_us; ++i) {
+		dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub);
+		if (dmub_rb_empty(&dmub->inbox1_rb))
+			return DMUB_STATUS_OK;
+
+		udelay(1);
+	}
+
+	return DMUB_STATUS_TIMEOUT;
+}
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 1be6c44fd32f..a2903985b9e8 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -134,23 +134,34 @@
 #define PICASSO_A0 0x41
 /* DCN1_01 */
 #define RAVEN2_A0 0x81
+#define RAVEN2_15D8_REV_94 0x94
+#define RAVEN2_15D8_REV_95 0x95
+#define RAVEN2_15D8_REV_E3 0xE3
+#define RAVEN2_15D8_REV_E4 0xE4
+#define RAVEN2_15D8_REV_E9 0xE9
+#define RAVEN2_15D8_REV_EA 0xEA
+#define RAVEN2_15D8_REV_EB 0xEB
 #define RAVEN1_F0 0xF0
 #define RAVEN_UNKNOWN 0xFF
-
-#define PICASSO_15D8_REV_E3 0xE3
-#define PICASSO_15D8_REV_E4 0xE4
-
+#ifndef ASICREV_IS_RAVEN
 #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN)
-#define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
-#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < PICASSO_15D8_REV_E3))
-#define ASICREV_IS_DALI(eChipRev) ((eChipRev >= PICASSO_15D8_REV_E3) && (eChipRev < RAVEN1_F0))
+#endif
 
+#define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
+#ifndef ASICREV_IS_RAVEN2
+#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < RAVEN1_F0))
+#endif
 #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN))
-
+#define ASICREV_IS_DALI(eChipRev) ((eChipRev == RAVEN2_15D8_REV_E3) \
+		|| (eChipRev == RAVEN2_15D8_REV_E4))
+#define ASICREV_IS_POLLOCK(eChipRev) (eChipRev == RAVEN2_15D8_REV_94 \
+		|| eChipRev == RAVEN2_15D8_REV_95 \
+			|| eChipRev == RAVEN2_15D8_REV_E9 \
+				|| eChipRev == RAVEN2_15D8_REV_EA \
+					|| eChipRev == RAVEN2_15D8_REV_EB)
 
 #define FAMILY_RV 142 /* DCN 1*/
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 #define FAMILY_NV 143 /* DCN 2*/
 
@@ -164,12 +175,9 @@ enum {
 #define ASICREV_IS_NAVI10_P(eChipRev)        (eChipRev < NV_NAVI12_P_A0)
 #define ASICREV_IS_NAVI12_P(eChipRev)        ((eChipRev >= NV_NAVI12_P_A0) && (eChipRev < NV_NAVI14_M_A0))
 #define ASICREV_IS_NAVI14_M(eChipRev)        ((eChipRev >= NV_NAVI14_M_A0) && (eChipRev < NV_UNKNOWN))
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define RENOIR_A0 0x91
 #define DEVICE_ID_RENOIR_1636 0x1636   // Renoir
 #define ASICREV_IS_RENOIR(eChipRev) ((eChipRev >= RENOIR_A0) && (eChipRev < 0xFF))
-#endif
 
 /*
  * ASIC chip ID
diff --git a/drivers/gpu/drm/amd/display/include/dal_types.h b/drivers/gpu/drm/amd/display/include/dal_types.h
index fcc42372b6cf..0b6859189ca7 100644
--- a/drivers/gpu/drm/amd/display/include/dal_types.h
+++ b/drivers/gpu/drm/amd/display/include/dal_types.h
@@ -46,12 +46,8 @@ enum dce_version {
 	DCE_VERSION_MAX,
 	DCN_VERSION_1_0,
 	DCN_VERSION_1_01,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	DCN_VERSION_2_0,
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	DCN_VERSION_2_1,
-#endif
 	DCN_VERSION_MAX
 };
 
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
index f312834fef50..d51de94e4bc3 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
@@ -178,7 +178,8 @@ struct dc_firmware_info {
 	uint32_t default_engine_clk; /* in KHz */
 	uint32_t dp_phy_ref_clk; /* in KHz - DCE12 only */
 	uint32_t i2c_engine_ref_clk; /* in KHz - DCE12 only */
-
+	bool oem_i2c_present;
+	uint8_t oem_i2c_obj_id;
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/include/link_service_types.h b/drivers/gpu/drm/amd/display/include/link_service_types.h
index 876b0b3e1a9c..4869d4562e4d 100644
--- a/drivers/gpu/drm/amd/display/include/link_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/link_service_types.h
@@ -123,6 +123,13 @@ enum dp_test_pattern {
 	DP_TEST_PATTERN_UNSUPPORTED
 };
 
+enum dp_test_pattern_color_space {
+	DP_TEST_PATTERN_COLOR_SPACE_RGB,
+	DP_TEST_PATTERN_COLOR_SPACE_YCBCR601,
+	DP_TEST_PATTERN_COLOR_SPACE_YCBCR709,
+	DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED
+};
+
 enum dp_panel_mode {
 	/* not required */
 	DP_PANEL_MODE_DEFAULT,
diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h
index 2b219cdb13ad..89a709267019 100644
--- a/drivers/gpu/drm/amd/display/include/logger_types.h
+++ b/drivers/gpu/drm/amd/display/include/logger_types.h
@@ -66,12 +66,8 @@
 #define DC_LOG_GAMMA(...) pr_debug("[GAMMA]:"__VA_ARGS__)
 #define DC_LOG_ALL_GAMMA(...) pr_debug("[GAMMA]:"__VA_ARGS__)
 #define DC_LOG_ALL_TF_CHANNELS(...) pr_debug("[GAMMA]:"__VA_ARGS__)
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define DC_LOG_DSC(...) DRM_DEBUG_KMS(__VA_ARGS__)
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN3_0) || defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define DC_LOG_DWB(...) DRM_DEBUG_KMS(__VA_ARGS__)
-#endif
 
 struct dal_logger;
 
@@ -116,9 +112,7 @@ enum dc_log_type {
 	LOG_PERF_TRACE,
 	LOG_DISPLAYSTATS,
 	LOG_HDMI_RETIMER_REDRIVER,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	LOG_DSC,
-#endif
 	LOG_DWB,
 	LOG_GAMMA_DEBUG,
 	LOG_MAX_HW_POINTS,
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 1de4805cb8c7..1b278c42809a 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -154,6 +154,7 @@ static void compute_de_pq(struct fixed31_32 in_x, struct fixed31_32 *out_y)
 
 	struct fixed31_32 l_pow_m1;
 	struct fixed31_32 base, div;
+	struct fixed31_32 base2;
 
 
 	if (dc_fixpt_lt(in_x, dc_fixpt_zero))
@@ -163,13 +164,15 @@ static void compute_de_pq(struct fixed31_32 in_x, struct fixed31_32 *out_y)
 			dc_fixpt_div(dc_fixpt_one, m2));
 	base = dc_fixpt_sub(l_pow_m1, c1);
 
-	if (dc_fixpt_lt(base, dc_fixpt_zero))
-		base = dc_fixpt_zero;
-
 	div = dc_fixpt_sub(c2, dc_fixpt_mul(c3, l_pow_m1));
 
-	*out_y = dc_fixpt_pow(dc_fixpt_div(base, div),
-			dc_fixpt_div(dc_fixpt_one, m1));
+	base2 = dc_fixpt_div(base, div);
+	//avoid complex numbers
+	if (dc_fixpt_lt(base2, dc_fixpt_zero))
+		base2 = dc_fixpt_sub(dc_fixpt_zero, base2);
+
+
+	*out_y = dc_fixpt_pow(base2, dc_fixpt_div(dc_fixpt_one, m1));
 
 }
 
@@ -361,8 +364,10 @@ static struct fixed31_32 translate_from_linear_space(
 			scratch_2 = dc_fixpt_mul(gamma_of_2,
 					pow_buffer[pow_buffer_ptr%16]);
 
-		pow_buffer[pow_buffer_ptr%16] = scratch_2;
-		pow_buffer_ptr++;
+		if (pow_buffer_ptr != -1) {
+			pow_buffer[pow_buffer_ptr%16] = scratch_2;
+			pow_buffer_ptr++;
+		}
 
 		scratch_1 = dc_fixpt_mul(scratch_1, scratch_2);
 		scratch_1 = dc_fixpt_sub(scratch_1, args->a2);
@@ -937,7 +942,6 @@ static bool build_freesync_hdr(struct pwl_float_data_ex *rgb_regamma,
 	struct fixed31_32 max_display;
 	struct fixed31_32 min_display;
 	struct fixed31_32 max_content;
-	struct fixed31_32 min_content;
 	struct fixed31_32 clip = dc_fixpt_one;
 	struct fixed31_32 output;
 	bool use_eetf = false;
@@ -951,7 +955,6 @@ static bool build_freesync_hdr(struct pwl_float_data_ex *rgb_regamma,
 	max_display = dc_fixpt_from_int(fs_params->max_display);
 	min_display = dc_fixpt_from_fraction(fs_params->min_display, 10000);
 	max_content = dc_fixpt_from_int(fs_params->max_content);
-	min_content = dc_fixpt_from_fraction(fs_params->min_content, 10000);
 	sdr_white_level = dc_fixpt_from_int(fs_params->sdr_white_level);
 
 	if (fs_params->min_display > 1000) // cap at 0.1 at the bottom
@@ -2000,10 +2003,28 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf,
 	tf_pts->x_point_at_y1_green = 1;
 	tf_pts->x_point_at_y1_blue = 1;
 
-	map_regamma_hw_to_x_user(ramp, coeff, rgb_user,
-			coordinates_x, axis_x, curve,
-			MAX_HW_POINTS, tf_pts,
-			mapUserRamp && ramp && ramp->type == GAMMA_RGB_256);
+	if (input_tf->tf == TRANSFER_FUNCTION_PQ) {
+		/* just copy current rgb_regamma into  tf_pts */
+		struct pwl_float_data_ex *curvePt = curve;
+		int i = 0;
+
+		while (i <= MAX_HW_POINTS) {
+			tf_pts->red[i]   = curvePt->r;
+			tf_pts->green[i] = curvePt->g;
+			tf_pts->blue[i]  = curvePt->b;
+			++curvePt;
+			++i;
+		}
+	} else {
+		//clamps to 0-1
+		map_regamma_hw_to_x_user(ramp, coeff, rgb_user,
+				coordinates_x, axis_x, curve,
+				MAX_HW_POINTS, tf_pts,
+				mapUserRamp && ramp && ramp->type == GAMMA_RGB_256);
+	}
+
+
+
 	if (ramp->type == GAMMA_CUSTOM)
 		apply_lut_1d(ramp, MAX_HW_POINTS, tf_pts);
 
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index 5437b50e9f90..6e5ecefe7d9d 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -37,8 +37,8 @@
 #define STATIC_SCREEN_RAMP_DELTA_REFRESH_RATE_PER_FRAME ((1000 / 60) * 65)
 /* Number of elements in the render times cache array */
 #define RENDER_TIMES_MAX_COUNT 10
-/* Threshold to exit BTR (to avoid frequent enter-exits at the lower limit) */
-#define BTR_EXIT_MARGIN 2000
+/* Threshold to exit/exit BTR (to avoid frequent enter-exits at the lower limit) */
+#define BTR_MAX_MARGIN 2500
 /* Threshold to change BTR multiplier (to avoid frequent changes) */
 #define BTR_DRIFT_MARGIN 2000
 /*Threshold to exit fixed refresh rate*/
@@ -122,7 +122,7 @@ static unsigned int calc_v_total_from_refresh(
 		const struct dc_stream_state *stream,
 		unsigned int refresh_in_uhz)
 {
-	unsigned int v_total = stream->timing.v_total;
+	unsigned int v_total;
 	unsigned int frame_duration_in_ns;
 
 	frame_duration_in_ns =
@@ -254,24 +254,22 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 	unsigned int delta_from_mid_point_in_us_1 = 0xFFFFFFFF;
 	unsigned int delta_from_mid_point_in_us_2 = 0xFFFFFFFF;
 	unsigned int frames_to_insert = 0;
-	unsigned int min_frame_duration_in_ns = 0;
-	unsigned int max_render_time_in_us = in_out_vrr->max_duration_in_us;
 	unsigned int delta_from_mid_point_delta_in_us;
-
-	min_frame_duration_in_ns = ((unsigned int) (div64_u64(
-		(1000000000ULL * 1000000),
-		in_out_vrr->max_refresh_in_uhz)));
+	unsigned int max_render_time_in_us =
+			in_out_vrr->max_duration_in_us - in_out_vrr->btr.margin_in_us;
 
 	/* Program BTR */
-	if (last_render_time_in_us + BTR_EXIT_MARGIN < max_render_time_in_us) {
+	if ((last_render_time_in_us + in_out_vrr->btr.margin_in_us / 2) < max_render_time_in_us) {
 		/* Exit Below the Range */
 		if (in_out_vrr->btr.btr_active) {
 			in_out_vrr->btr.frame_counter = 0;
 			in_out_vrr->btr.btr_active = false;
 		}
-	} else if (last_render_time_in_us > max_render_time_in_us) {
+	} else if (last_render_time_in_us > (max_render_time_in_us + in_out_vrr->btr.margin_in_us / 2)) {
 		/* Enter Below the Range */
-		in_out_vrr->btr.btr_active = true;
+		if (!in_out_vrr->btr.btr_active) {
+			in_out_vrr->btr.btr_active = true;
+		}
 	}
 
 	/* BTR set to "not active" so disengage */
@@ -327,7 +325,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		/* Choose number of frames to insert based on how close it
 		 * can get to the mid point of the variable range.
 		 */
-		if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) {
+		if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us &&
+				(delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 ||
+						mid_point_frames_floor < 2)) {
 			frames_to_insert = mid_point_frames_ceil;
 			delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 -
 					delta_from_mid_point_in_us_1;
@@ -343,7 +343,7 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		if (in_out_vrr->btr.frames_to_insert != 0 &&
 				delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) {
 			if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) <
-					in_out_vrr->max_duration_in_us) &&
+					max_render_time_in_us) &&
 				((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) >
 					in_out_vrr->min_duration_in_us))
 				frames_to_insert = in_out_vrr->btr.frames_to_insert;
@@ -796,6 +796,11 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 		refresh_range = in_out_vrr->max_refresh_in_uhz -
 				in_out_vrr->min_refresh_in_uhz;
 
+		in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us -
+				2 * in_out_vrr->min_duration_in_us;
+		if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN)
+			in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN;
+
 		in_out_vrr->supported = true;
 	}
 
@@ -811,6 +816,9 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 	in_out_vrr->btr.inserted_duration_in_us = 0;
 	in_out_vrr->btr.frames_to_insert = 0;
 	in_out_vrr->btr.frame_counter = 0;
+	in_out_vrr->fixed.fixed_active = false;
+	in_out_vrr->fixed.target_refresh_in_uhz = 0;
+
 	in_out_vrr->btr.mid_point_in_us =
 				(in_out_vrr->min_duration_in_us +
 				 in_out_vrr->max_duration_in_us) / 2;
@@ -826,6 +834,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 		in_out_vrr->adjust.v_total_max = stream->timing.v_total;
 	} else if (in_out_vrr->state == VRR_STATE_ACTIVE_VARIABLE &&
 			refresh_range >= MIN_REFRESH_RANGE_IN_US) {
+
 		in_out_vrr->adjust.v_total_min =
 			calc_v_total_from_refresh(stream,
 				in_out_vrr->max_refresh_in_uhz);
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/Makefile b/drivers/gpu/drm/amd/display/modules/hdcp/Makefile
index 1c3c6d47973a..904424da01b5 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/Makefile
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/Makefile
@@ -24,7 +24,8 @@
 #
 
 HDCP = hdcp_ddc.o hdcp_log.o hdcp_psp.o hdcp.o \
-		hdcp1_execution.o hdcp1_transition.o
+		hdcp1_execution.o hdcp1_transition.o \
+		hdcp2_execution.o hdcp2_transition.o
 
 AMD_DAL_HDCP = $(addprefix $(AMDDALPATH)/modules/hdcp/,$(HDCP))
 #$(info ************  DAL-HDCP_MAKEFILE ************)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
index d7ac445dec6f..8aa528e874c4 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
@@ -37,24 +37,52 @@ static void push_error_status(struct mod_hdcp *hdcp,
 		HDCP_ERROR_TRACE(hdcp, status);
 	}
 
-	hdcp->connection.hdcp1_retry_count++;
+	if (is_hdcp1(hdcp)) {
+		hdcp->connection.hdcp1_retry_count++;
+	} else if (is_hdcp2(hdcp)) {
+		hdcp->connection.hdcp2_retry_count++;
+	}
 }
 
 static uint8_t is_cp_desired_hdcp1(struct mod_hdcp *hdcp)
 {
-	int i, display_enabled = 0;
+	int i, is_auth_needed = 0;
 
-	/* if all displays on the link are disabled, hdcp is not desired */
+	/* if all displays on the link don't need authentication,
+	 * hdcp is not desired
+	 */
 	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
 		if (hdcp->connection.displays[i].state != MOD_HDCP_DISPLAY_INACTIVE &&
 				!hdcp->connection.displays[i].adjust.disable) {
-			display_enabled = 1;
+			is_auth_needed = 1;
 			break;
 		}
 	}
 
 	return (hdcp->connection.hdcp1_retry_count < MAX_NUM_OF_ATTEMPTS) &&
-			display_enabled && !hdcp->connection.link.adjust.hdcp1.disable;
+			is_auth_needed &&
+			!hdcp->connection.link.adjust.hdcp1.disable;
+}
+
+static uint8_t is_cp_desired_hdcp2(struct mod_hdcp *hdcp)
+{
+	int i, is_auth_needed = 0;
+
+	/* if all displays on the link don't need authentication,
+	 * hdcp is not desired
+	 */
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
+		if (hdcp->connection.displays[i].state != MOD_HDCP_DISPLAY_INACTIVE &&
+				!hdcp->connection.displays[i].adjust.disable) {
+			is_auth_needed = 1;
+			break;
+		}
+	}
+
+	return (hdcp->connection.hdcp2_retry_count < MAX_NUM_OF_ATTEMPTS) &&
+			is_auth_needed &&
+			!hdcp->connection.link.adjust.hdcp2.disable &&
+			!hdcp->connection.is_hdcp2_revoked;
 }
 
 static enum mod_hdcp_status execution(struct mod_hdcp *hdcp,
@@ -82,6 +110,11 @@ static enum mod_hdcp_status execution(struct mod_hdcp *hdcp,
 	} else if (is_in_hdcp1_dp_states(hdcp)) {
 		status = mod_hdcp_hdcp1_dp_execution(hdcp,
 				event_ctx, &input->hdcp1);
+	} else if (is_in_hdcp2_states(hdcp)) {
+		status = mod_hdcp_hdcp2_execution(hdcp, event_ctx, &input->hdcp2);
+	} else if (is_in_hdcp2_dp_states(hdcp)) {
+		status = mod_hdcp_hdcp2_dp_execution(hdcp,
+				event_ctx, &input->hdcp2);
 	}
 out:
 	return status;
@@ -99,7 +132,10 @@ static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
 
 	if (is_in_initialized_state(hdcp)) {
 		if (is_dp_hdcp(hdcp))
-			if (is_cp_desired_hdcp1(hdcp)) {
+			if (is_cp_desired_hdcp2(hdcp)) {
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, D2_A0_DETERMINE_RX_HDCP_CAPABLE);
+			} else if (is_cp_desired_hdcp1(hdcp)) {
 				callback_in_ms(0, output);
 				set_state_id(hdcp, output, D1_A0_DETERMINE_RX_HDCP_CAPABLE);
 			} else {
@@ -107,7 +143,10 @@ static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
 				set_state_id(hdcp, output, HDCP_CP_NOT_DESIRED);
 			}
 		else if (is_hdmi_dvi_sl_hdcp(hdcp))
-			if (is_cp_desired_hdcp1(hdcp)) {
+			if (is_cp_desired_hdcp2(hdcp)) {
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, H2_A0_KNOWN_HDCP2_CAPABLE_RX);
+			} else if (is_cp_desired_hdcp1(hdcp)) {
 				callback_in_ms(0, output);
 				set_state_id(hdcp, output, H1_A0_WAIT_FOR_ACTIVE_RX);
 			} else {
@@ -126,6 +165,12 @@ static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
 	} else if (is_in_hdcp1_dp_states(hdcp)) {
 		status = mod_hdcp_hdcp1_dp_transition(hdcp,
 				event_ctx, &input->hdcp1, output);
+	} else if (is_in_hdcp2_states(hdcp)) {
+		status = mod_hdcp_hdcp2_transition(hdcp,
+				event_ctx, &input->hdcp2, output);
+	} else if (is_in_hdcp2_dp_states(hdcp)) {
+		status = mod_hdcp_hdcp2_dp_transition(hdcp,
+				event_ctx, &input->hdcp2, output);
 	} else {
 		status = MOD_HDCP_STATUS_INVALID_STATE;
 	}
@@ -139,9 +184,13 @@ static enum mod_hdcp_status reset_authentication(struct mod_hdcp *hdcp,
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	if (is_hdcp1(hdcp)) {
-		if (hdcp->auth.trans_input.hdcp1.create_session != UNKNOWN)
+		if (hdcp->auth.trans_input.hdcp1.create_session != UNKNOWN) {
+			/* TODO - update psp to unify create session failure
+			 * recovery between hdcp1 and 2.
+			 */
 			mod_hdcp_hdcp1_destroy_session(hdcp);
 
+		}
 		if (hdcp->auth.trans_input.hdcp1.add_topology == PASS) {
 			status = mod_hdcp_remove_display_topology(hdcp);
 			if (status != MOD_HDCP_STATUS_SUCCESS) {
@@ -154,6 +203,27 @@ static enum mod_hdcp_status reset_authentication(struct mod_hdcp *hdcp,
 		memset(&hdcp->auth, 0, sizeof(struct mod_hdcp_authentication));
 		memset(&hdcp->state, 0, sizeof(struct mod_hdcp_state));
 		set_state_id(hdcp, output, HDCP_INITIALIZED);
+	} else if (is_hdcp2(hdcp)) {
+		if (hdcp->auth.trans_input.hdcp2.create_session == PASS) {
+			status = mod_hdcp_hdcp2_destroy_session(hdcp);
+			if (status != MOD_HDCP_STATUS_SUCCESS) {
+				output->callback_needed = 0;
+				output->watchdog_timer_needed = 0;
+				goto out;
+			}
+		}
+		if (hdcp->auth.trans_input.hdcp2.add_topology == PASS) {
+			status = mod_hdcp_remove_display_topology(hdcp);
+			if (status != MOD_HDCP_STATUS_SUCCESS) {
+				output->callback_needed = 0;
+				output->watchdog_timer_needed = 0;
+				goto out;
+			}
+		}
+		HDCP_TOP_RESET_AUTH_TRACE(hdcp);
+		memset(&hdcp->auth, 0, sizeof(struct mod_hdcp_authentication));
+		memset(&hdcp->state, 0, sizeof(struct mod_hdcp_state));
+		set_state_id(hdcp, output, HDCP_INITIALIZED);
 	} else if (is_in_cp_not_desired_state(hdcp)) {
 		status = mod_hdcp_remove_display_topology(hdcp);
 		if (status != MOD_HDCP_STATUS_SUCCESS) {
@@ -347,7 +417,20 @@ enum mod_hdcp_status mod_hdcp_query_display(struct mod_hdcp *hdcp,
 	query->trace = &hdcp->connection.trace;
 	query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
 
-	mod_hdcp_hdcp1_get_link_encryption_status(hdcp, &query->encryption_status);
+	if (is_display_encryption_enabled(display)) {
+		if (is_hdcp1(hdcp)) {
+			query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON;
+		} else if (is_hdcp2(hdcp)) {
+			if (query->link->adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0)
+				query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON;
+			else if (query->link->adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_1)
+				query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON;
+			else
+				query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_ON;
+		}
+	} else {
+		query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+	}
 
 out:
 	return status;
@@ -420,7 +503,7 @@ enum mod_hdcp_operation_mode mod_hdcp_signal_type_to_operation_mode(
 		break;
 	default:
 		break;
-	};
+	}
 
 	return mode;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
index 5664bc0b5bd0..f98d3d9ecb6d 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
@@ -29,32 +29,8 @@
 #include "mod_hdcp.h"
 #include "hdcp_log.h"
 
-#define BCAPS_READY_MASK				0x20
-#define BCAPS_REPEATER_MASK				0x40
-#define BSTATUS_DEVICE_COUNT_MASK			0X007F
-#define BSTATUS_MAX_DEVS_EXCEEDED_MASK			0x0080
-#define BSTATUS_MAX_CASCADE_EXCEEDED_MASK		0x0800
-#define BCAPS_HDCP_CAPABLE_MASK_DP			0x01
-#define BCAPS_REPEATER_MASK_DP				0x02
-#define BSTATUS_READY_MASK_DP				0x01
-#define BSTATUS_R0_P_AVAILABLE_MASK_DP			0x02
-#define BSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP		0x04
-#define BSTATUS_REAUTH_REQUEST_MASK_DP			0x08
-#define BINFO_DEVICE_COUNT_MASK_DP			0X007F
-#define BINFO_MAX_DEVS_EXCEEDED_MASK_DP			0x0080
-#define BINFO_MAX_CASCADE_EXCEEDED_MASK_DP		0x0800
-
-#define RXSTATUS_MSG_SIZE_MASK				0x03FF
-#define RXSTATUS_READY_MASK				0x0400
-#define RXSTATUS_REAUTH_REQUEST_MASK			0x0800
-#define RXIDLIST_DEVICE_COUNT_LOWER_MASK		0xf0
-#define RXIDLIST_DEVICE_COUNT_UPPER_MASK		0x01
-#define RXCAPS_BYTE0_HDCP_CAPABLE_MASK_DP		0x02
-#define RXSTATUS_READY_MASK_DP				0x0001
-#define RXSTATUS_H_P_AVAILABLE_MASK_DP			0x0002
-#define RXSTATUS_PAIRING_AVAILABLE_MASK_DP		0x0004
-#define RXSTATUS_REAUTH_REQUEST_MASK_DP			0x0008
-#define RXSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP		0x0010
+#include <drm/drm_hdcp.h>
+#include <drm/drm_dp_helper.h>
 
 enum mod_hdcp_trans_input_result {
 	UNKNOWN = 0,
@@ -92,8 +68,52 @@ struct mod_hdcp_transition_input_hdcp1 {
 	uint8_t stream_encryption_dp;
 };
 
+struct mod_hdcp_transition_input_hdcp2 {
+	uint8_t hdcp2version_read;
+	uint8_t hdcp2_capable_check;
+	uint8_t add_topology;
+	uint8_t create_session;
+	uint8_t ake_init_prepare;
+	uint8_t ake_init_write;
+	uint8_t rxstatus_read;
+	uint8_t ake_cert_available;
+	uint8_t ake_cert_read;
+	uint8_t ake_cert_validation;
+	uint8_t stored_km_write;
+	uint8_t no_stored_km_write;
+	uint8_t h_prime_available;
+	uint8_t h_prime_read;
+	uint8_t pairing_available;
+	uint8_t pairing_info_read;
+	uint8_t h_prime_validation;
+	uint8_t lc_init_prepare;
+	uint8_t lc_init_write;
+	uint8_t l_prime_available_poll;
+	uint8_t l_prime_read;
+	uint8_t l_prime_validation;
+	uint8_t eks_prepare;
+	uint8_t eks_write;
+	uint8_t enable_encryption;
+	uint8_t reauth_request_check;
+	uint8_t rx_id_list_read;
+	uint8_t device_count_check;
+	uint8_t rx_id_list_validation;
+	uint8_t repeater_auth_ack_write;
+	uint8_t prepare_stream_manage;
+	uint8_t stream_manage_write;
+	uint8_t stream_ready_available;
+	uint8_t stream_ready_read;
+	uint8_t stream_ready_validation;
+
+	uint8_t rx_caps_read_dp;
+	uint8_t content_stream_type_write;
+	uint8_t link_integrity_check_dp;
+	uint8_t stream_encryption_dp;
+};
+
 union mod_hdcp_transition_input {
 	struct mod_hdcp_transition_input_hdcp1 hdcp1;
+	struct mod_hdcp_transition_input_hdcp2 hdcp2;
 };
 
 struct mod_hdcp_message_hdcp1 {
@@ -111,8 +131,33 @@ struct mod_hdcp_message_hdcp1 {
 	uint16_t	binfo_dp;
 };
 
+struct mod_hdcp_message_hdcp2 {
+	uint8_t		hdcp2version_hdmi;
+	uint8_t		rxcaps_dp[3];
+	uint8_t		rxstatus[2];
+
+	uint8_t		ake_init[12];
+	uint8_t		ake_cert[534];
+	uint8_t		ake_no_stored_km[129];
+	uint8_t		ake_stored_km[33];
+	uint8_t		ake_h_prime[33];
+	uint8_t		ake_pairing_info[17];
+	uint8_t		lc_init[9];
+	uint8_t		lc_l_prime[33];
+	uint8_t		ske_eks[25];
+	uint8_t		rx_id_list[177]; // 22 + 5 * 31
+	uint16_t	rx_id_list_size;
+	uint8_t		repeater_auth_ack[17];
+	uint8_t		repeater_auth_stream_manage[68]; // 6 + 2 * 31
+	uint16_t	stream_manage_size;
+	uint8_t		repeater_auth_stream_ready[33];
+	uint8_t		rxstatus_dp;
+	uint8_t		content_stream_type_dp[2];
+};
+
 union mod_hdcp_message {
 	struct mod_hdcp_message_hdcp1 hdcp1;
+	struct mod_hdcp_message_hdcp2 hdcp2;
 };
 
 struct mod_hdcp_auth_counters {
@@ -125,8 +170,10 @@ struct mod_hdcp_connection {
 	struct mod_hdcp_display displays[MAX_NUM_OF_DISPLAYS];
 	uint8_t is_repeater;
 	uint8_t is_km_stored;
+	uint8_t is_hdcp2_revoked;
 	struct mod_hdcp_trace trace;
 	uint8_t hdcp1_retry_count;
+	uint8_t hdcp2_retry_count;
 };
 
 /* contains values per authentication cycle */
@@ -194,6 +241,50 @@ enum mod_hdcp_hdcp1_dp_state_id {
 	HDCP1_DP_STATE_END = D1_A7_READ_KSV_LIST,
 };
 
+enum mod_hdcp_hdcp2_state_id {
+	HDCP2_STATE_START = HDCP1_DP_STATE_END,
+	H2_A0_KNOWN_HDCP2_CAPABLE_RX,
+	H2_A1_SEND_AKE_INIT,
+	H2_A1_VALIDATE_AKE_CERT,
+	H2_A1_SEND_NO_STORED_KM,
+	H2_A1_READ_H_PRIME,
+	H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME,
+	H2_A1_SEND_STORED_KM,
+	H2_A1_VALIDATE_H_PRIME,
+	H2_A2_LOCALITY_CHECK,
+	H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER,
+	H2_ENABLE_ENCRYPTION,
+	H2_A5_AUTHENTICATED,
+	H2_A6_WAIT_FOR_RX_ID_LIST,
+	H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK,
+	H2_A9_SEND_STREAM_MANAGEMENT,
+	H2_A9_VALIDATE_STREAM_READY,
+	HDCP2_STATE_END = H2_A9_VALIDATE_STREAM_READY,
+};
+
+enum mod_hdcp_hdcp2_dp_state_id {
+	HDCP2_DP_STATE_START = HDCP2_STATE_END,
+	D2_A0_DETERMINE_RX_HDCP_CAPABLE,
+	D2_A1_SEND_AKE_INIT,
+	D2_A1_VALIDATE_AKE_CERT,
+	D2_A1_SEND_NO_STORED_KM,
+	D2_A1_READ_H_PRIME,
+	D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME,
+	D2_A1_SEND_STORED_KM,
+	D2_A1_VALIDATE_H_PRIME,
+	D2_A2_LOCALITY_CHECK,
+	D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER,
+	D2_SEND_CONTENT_STREAM_TYPE,
+	D2_ENABLE_ENCRYPTION,
+	D2_A5_AUTHENTICATED,
+	D2_A6_WAIT_FOR_RX_ID_LIST,
+	D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK,
+	D2_A9_SEND_STREAM_MANAGEMENT,
+	D2_A9_VALIDATE_STREAM_READY,
+	HDCP2_DP_STATE_END = D2_A9_VALIDATE_STREAM_READY,
+	HDCP_STATE_END = HDCP2_DP_STATE_END,
+};
+
 /* hdcp1 executions and transitions */
 typedef enum mod_hdcp_status (*mod_hdcp_action)(struct mod_hdcp *hdcp);
 uint8_t mod_hdcp_execute_and_set(
@@ -214,6 +305,22 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp,
 	struct mod_hdcp_transition_input_hdcp1 *input,
 	struct mod_hdcp_output *output);
 
+/* hdcp2 executions and transitions */
+enum mod_hdcp_status mod_hdcp_hdcp2_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input);
+enum mod_hdcp_status mod_hdcp_hdcp2_dp_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input);
+enum mod_hdcp_status mod_hdcp_hdcp2_transition(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input,
+	struct mod_hdcp_output *output);
+enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input,
+	struct mod_hdcp_output *output);
+
 /* log functions */
 void mod_hdcp_dump_binary_message(uint8_t *msg, uint32_t msg_size,
 		uint8_t *buf, uint32_t buf_size);
@@ -234,6 +341,25 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_dp_stream_encryption(
 enum mod_hdcp_status mod_hdcp_hdcp1_link_maintenance(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_hdcp1_get_link_encryption_status(struct mod_hdcp *hdcp,
 							       enum mod_hdcp_encryption_status *encryption_status);
+enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_destroy_session(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_ake_init(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_ake_cert(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_h_prime(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_lc_init(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_l_prime(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_eks(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_enable_encryption(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_rx_id_list(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_enable_dp_stream_encryption(
+		struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_stream_management(
+		struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_stream_ready(
+		struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_get_link_encryption_status(struct mod_hdcp *hdcp,
+							       enum mod_hdcp_encryption_status *encryption_status);
+
 /* ddc functions */
 enum mod_hdcp_status mod_hdcp_read_bksv(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_read_bcaps(struct mod_hdcp *hdcp);
@@ -245,6 +371,7 @@ enum mod_hdcp_status mod_hdcp_read_binfo(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_aksv(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_ainfo(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_an(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_hdcp2version(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_read_rxcaps(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_read_rxstatus(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_read_ake_cert(struct mod_hdcp *hdcp);
@@ -308,11 +435,28 @@ static inline uint8_t is_in_hdcp1_dp_states(struct mod_hdcp *hdcp)
 			current_state(hdcp) <= HDCP1_DP_STATE_END);
 }
 
+static inline uint8_t is_in_hdcp2_states(struct mod_hdcp *hdcp)
+{
+	return (current_state(hdcp) > HDCP2_STATE_START &&
+			current_state(hdcp) <= HDCP2_STATE_END);
+}
+
+static inline uint8_t is_in_hdcp2_dp_states(struct mod_hdcp *hdcp)
+{
+	return (current_state(hdcp) > HDCP2_DP_STATE_START &&
+			current_state(hdcp) <= HDCP2_DP_STATE_END);
+}
+
 static inline uint8_t is_hdcp1(struct mod_hdcp *hdcp)
 {
 	return (is_in_hdcp1_states(hdcp) || is_in_hdcp1_dp_states(hdcp));
 }
 
+static inline uint8_t is_hdcp2(struct mod_hdcp *hdcp)
+{
+	return (is_in_hdcp2_states(hdcp) || is_in_hdcp2_dp_states(hdcp));
+}
+
 static inline uint8_t is_in_cp_not_desired_state(struct mod_hdcp *hdcp)
 {
 	return current_state(hdcp) == HDCP_CP_NOT_DESIRED;
@@ -437,6 +581,7 @@ static inline struct mod_hdcp_display *get_empty_display_container(
 static inline void reset_retry_counts(struct mod_hdcp *hdcp)
 {
 	hdcp->connection.hdcp1_retry_count = 0;
+	hdcp->connection.hdcp2_retry_count = 0;
 }
 
 #endif /* HDCP_H_ */
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
index 3db4a7da414f..04845e43df15 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
@@ -27,9 +27,11 @@
 
 static inline enum mod_hdcp_status validate_bksv(struct mod_hdcp *hdcp)
 {
-	uint64_t n = *(uint64_t *)hdcp->auth.msg.hdcp1.bksv;
+	uint64_t n = 0;
 	uint8_t count = 0;
 
+	memcpy(&n, hdcp->auth.msg.hdcp1.bksv, sizeof(uint64_t));
+
 	while (n) {
 		count++;
 		n &= (n - 1);
@@ -41,17 +43,17 @@ static inline enum mod_hdcp_status validate_bksv(struct mod_hdcp *hdcp)
 static inline enum mod_hdcp_status check_ksv_ready(struct mod_hdcp *hdcp)
 {
 	if (is_dp_hdcp(hdcp))
-		return (hdcp->auth.msg.hdcp1.bstatus & BSTATUS_READY_MASK_DP) ?
+		return (hdcp->auth.msg.hdcp1.bstatus & DP_BSTATUS_READY) ?
 				MOD_HDCP_STATUS_SUCCESS :
 				MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY;
-	return (hdcp->auth.msg.hdcp1.bcaps & BCAPS_READY_MASK) ?
+	return (hdcp->auth.msg.hdcp1.bcaps & DRM_HDCP_DDC_BCAPS_KSV_FIFO_READY) ?
 			MOD_HDCP_STATUS_SUCCESS :
 			MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY;
 }
 
 static inline enum mod_hdcp_status check_hdcp_capable_dp(struct mod_hdcp *hdcp)
 {
-	return (hdcp->auth.msg.hdcp1.bcaps & BCAPS_HDCP_CAPABLE_MASK_DP) ?
+	return (hdcp->auth.msg.hdcp1.bcaps & DP_BCAPS_HDCP_CAPABLE) ?
 			MOD_HDCP_STATUS_SUCCESS :
 			MOD_HDCP_STATUS_HDCP1_NOT_CAPABLE;
 }
@@ -61,7 +63,7 @@ static inline enum mod_hdcp_status check_r0p_available_dp(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status;
 	if (is_dp_hdcp(hdcp)) {
 		status = (hdcp->auth.msg.hdcp1.bstatus &
-				BSTATUS_R0_P_AVAILABLE_MASK_DP) ?
+				DP_BSTATUS_R0_PRIME_READY) ?
 			MOD_HDCP_STATUS_SUCCESS :
 			MOD_HDCP_STATUS_HDCP1_R0_PRIME_PENDING;
 	} else {
@@ -74,7 +76,7 @@ static inline enum mod_hdcp_status check_link_integrity_dp(
 		struct mod_hdcp *hdcp)
 {
 	return (hdcp->auth.msg.hdcp1.bstatus &
-			BSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP) ?
+			DP_BSTATUS_LINK_FAILURE) ?
 			MOD_HDCP_STATUS_HDCP1_LINK_INTEGRITY_FAILURE :
 			MOD_HDCP_STATUS_SUCCESS;
 }
@@ -82,7 +84,7 @@ static inline enum mod_hdcp_status check_link_integrity_dp(
 static inline enum mod_hdcp_status check_no_reauthentication_request_dp(
 		struct mod_hdcp *hdcp)
 {
-	return (hdcp->auth.msg.hdcp1.bstatus & BSTATUS_REAUTH_REQUEST_MASK_DP) ?
+	return (hdcp->auth.msg.hdcp1.bstatus & DP_BSTATUS_REAUTH_REQ) ?
 			MOD_HDCP_STATUS_HDCP1_REAUTH_REQUEST_ISSUED :
 			MOD_HDCP_STATUS_SUCCESS;
 }
@@ -92,15 +94,13 @@ static inline enum mod_hdcp_status check_no_max_cascade(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status;
 
 	if (is_dp_hdcp(hdcp))
-		status = (hdcp->auth.msg.hdcp1.binfo_dp &
-				BINFO_MAX_CASCADE_EXCEEDED_MASK_DP) ?
-			MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE :
-			MOD_HDCP_STATUS_SUCCESS;
+		status = DRM_HDCP_MAX_CASCADE_EXCEEDED(hdcp->auth.msg.hdcp1.binfo_dp >> 8)
+				 ? MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE
+				 : MOD_HDCP_STATUS_SUCCESS;
 	else
-		status = (hdcp->auth.msg.hdcp1.bstatus &
-				BSTATUS_MAX_CASCADE_EXCEEDED_MASK) ?
-				MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE :
-				MOD_HDCP_STATUS_SUCCESS;
+		status = DRM_HDCP_MAX_CASCADE_EXCEEDED(hdcp->auth.msg.hdcp1.bstatus >> 8)
+				 ? MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE
+				 : MOD_HDCP_STATUS_SUCCESS;
 	return status;
 }
 
@@ -109,13 +109,11 @@ static inline enum mod_hdcp_status check_no_max_devs(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status;
 
 	if (is_dp_hdcp(hdcp))
-		status = (hdcp->auth.msg.hdcp1.binfo_dp &
-				BINFO_MAX_DEVS_EXCEEDED_MASK_DP) ?
+		status = DRM_HDCP_MAX_DEVICE_EXCEEDED(hdcp->auth.msg.hdcp1.binfo_dp) ?
 				MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE :
 				MOD_HDCP_STATUS_SUCCESS;
 	else
-		status = (hdcp->auth.msg.hdcp1.bstatus &
-				BSTATUS_MAX_DEVS_EXCEEDED_MASK) ?
+		status = DRM_HDCP_MAX_DEVICE_EXCEEDED(hdcp->auth.msg.hdcp1.bstatus) ?
 				MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE :
 				MOD_HDCP_STATUS_SUCCESS;
 	return status;
@@ -124,8 +122,8 @@ static inline enum mod_hdcp_status check_no_max_devs(struct mod_hdcp *hdcp)
 static inline uint8_t get_device_count(struct mod_hdcp *hdcp)
 {
 	return is_dp_hdcp(hdcp) ?
-			(hdcp->auth.msg.hdcp1.binfo_dp & BINFO_DEVICE_COUNT_MASK_DP) :
-			(hdcp->auth.msg.hdcp1.bstatus & BSTATUS_DEVICE_COUNT_MASK);
+			DRM_HDCP_NUM_DOWNSTREAM(hdcp->auth.msg.hdcp1.binfo_dp) :
+			DRM_HDCP_NUM_DOWNSTREAM(hdcp->auth.msg.hdcp1.bstatus);
 }
 
 static inline enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
index 136b8011ff3f..21ebc62bb9d9 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
@@ -67,11 +67,19 @@ enum mod_hdcp_status mod_hdcp_hdcp1_transition(struct mod_hdcp *hdcp,
 		break;
 	case H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER:
 		if (input->bcaps_read != PASS ||
-				input->r0p_read != PASS ||
-				input->rx_validation != PASS ||
-				(!conn->is_repeater && input->encryption != PASS)) {
+				input->r0p_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->rx_validation != PASS) {
 			/* 1A-06: consider invalid r0' a failure */
 			/* 1A-08: consider bksv listed in SRM a failure */
+			/*
+			 * some slow RX will fail rx validation when it is
+			 * not ready. give it more time to react before retry.
+			 */
+			fail_and_restart_in_ms(1000, &status, output);
+			break;
+		} else if (!conn->is_repeater && input->encryption != PASS) {
 			fail_and_restart_in_ms(0, &status, output);
 			break;
 		}
@@ -212,7 +220,11 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp,
 				 * after 3 attempts.
 				 * 1A-08: consider bksv listed in SRM a failure
 				 */
-				fail_and_restart_in_ms(0, &status, output);
+				/*
+				 * some slow RX will fail rx validation when it is
+				 * not ready. give it more time to react before retry.
+				 */
+				fail_and_restart_in_ms(1000, &status, output);
 			}
 			break;
 		} else if ((!conn->is_repeater && input->encryption != PASS) ||
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
new file mode 100644
index 000000000000..f730b94ac3c0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
@@ -0,0 +1,886 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <linux/delay.h>
+
+#include "hdcp.h"
+
+static inline enum mod_hdcp_status check_receiver_id_list_ready(struct mod_hdcp *hdcp)
+{
+	uint8_t is_ready = 0;
+
+	if (is_dp_hdcp(hdcp))
+		is_ready = HDCP_2_2_DP_RXSTATUS_READY(hdcp->auth.msg.hdcp2.rxstatus_dp) ? 1 : 0;
+	else
+		is_ready = (HDCP_2_2_HDMI_RXSTATUS_READY(hdcp->auth.msg.hdcp2.rxstatus[0]) &&
+				(HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+						hdcp->auth.msg.hdcp2.rxstatus[0])) ? 1 : 0;
+	return is_ready ? MOD_HDCP_STATUS_SUCCESS :
+			MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY;
+}
+
+static inline enum mod_hdcp_status check_hdcp2_capable(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = (hdcp->auth.msg.hdcp2.rxcaps_dp[2] & HDCP_2_2_RX_CAPS_VERSION_VAL) &&
+				HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[0]) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE;
+	else
+		status = (hdcp->auth.msg.hdcp2.hdcp2version_hdmi & HDCP_2_2_HDMI_SUPPORT_MASK) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE;
+	return status;
+}
+
+static inline enum mod_hdcp_status check_reauthentication_request(
+		struct mod_hdcp *hdcp)
+{
+	uint8_t ret = 0;
+
+	if (is_dp_hdcp(hdcp))
+		ret = HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(hdcp->auth.msg.hdcp2.rxstatus_dp) ?
+				MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST :
+				MOD_HDCP_STATUS_SUCCESS;
+	else
+		ret = HDCP_2_2_HDMI_RXSTATUS_REAUTH_REQ(hdcp->auth.msg.hdcp2.rxstatus[0]) ?
+				MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST :
+				MOD_HDCP_STATUS_SUCCESS;
+	return ret;
+}
+
+static inline enum mod_hdcp_status check_link_integrity_failure_dp(
+		struct mod_hdcp *hdcp)
+{
+	return HDCP_2_2_DP_RXSTATUS_LINK_FAILED(hdcp->auth.msg.hdcp2.rxstatus_dp) ?
+			MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE :
+			MOD_HDCP_STATUS_SUCCESS;
+}
+
+static enum mod_hdcp_status check_ake_cert_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint16_t size;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = MOD_HDCP_STATUS_SUCCESS;
+	} else {
+		status = mod_hdcp_read_rxstatus(hdcp);
+		if (status == MOD_HDCP_STATUS_SUCCESS) {
+			size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+			       hdcp->auth.msg.hdcp2.rxstatus[0];
+			status = (size == sizeof(hdcp->auth.msg.hdcp2.ake_cert)) ?
+					MOD_HDCP_STATUS_SUCCESS :
+					MOD_HDCP_STATUS_HDCP2_AKE_CERT_PENDING;
+		}
+	}
+	return status;
+}
+
+static enum mod_hdcp_status check_h_prime_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint8_t size;
+
+	status = mod_hdcp_read_rxstatus(hdcp);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = HDCP_2_2_DP_RXSTATUS_H_PRIME(hdcp->auth.msg.hdcp2.rxstatus_dp) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING;
+	} else {
+		size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+		       hdcp->auth.msg.hdcp2.rxstatus[0];
+		status = (size == sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status check_pairing_info_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint8_t size;
+
+	status = mod_hdcp_read_rxstatus(hdcp);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = HDCP_2_2_DP_RXSTATUS_PAIRING(hdcp->auth.msg.hdcp2.rxstatus_dp) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING;
+	} else {
+		size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+		       hdcp->auth.msg.hdcp2.rxstatus[0];
+		status = (size == sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info)) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status poll_l_prime_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint8_t size;
+	uint16_t max_wait = 20; // units of ms
+	uint16_t num_polls = 5;
+	uint16_t wait_time = max_wait / num_polls;
+
+	if (is_dp_hdcp(hdcp))
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	else
+		for (; num_polls; num_polls--) {
+			msleep(wait_time);
+
+			status = mod_hdcp_read_rxstatus(hdcp);
+			if (status != MOD_HDCP_STATUS_SUCCESS)
+				break;
+
+			size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+			       hdcp->auth.msg.hdcp2.rxstatus[0];
+			status = (size == sizeof(hdcp->auth.msg.hdcp2.lc_l_prime)) ?
+					MOD_HDCP_STATUS_SUCCESS :
+					MOD_HDCP_STATUS_HDCP2_L_PRIME_PENDING;
+			if (status == MOD_HDCP_STATUS_SUCCESS)
+				break;
+		}
+	return status;
+}
+
+static enum mod_hdcp_status check_stream_ready_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint8_t size;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	} else {
+		status = mod_hdcp_read_rxstatus(hdcp);
+		if (status != MOD_HDCP_STATUS_SUCCESS)
+			goto out;
+		size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+		       hdcp->auth.msg.hdcp2.rxstatus[0];
+		status = (size == sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready)) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING;
+	}
+out:
+	return status;
+}
+
+static inline uint8_t get_device_count(struct mod_hdcp *hdcp)
+{
+	return HDCP_2_2_DEV_COUNT_LO(hdcp->auth.msg.hdcp2.rx_id_list[2]) +
+			(HDCP_2_2_DEV_COUNT_HI(hdcp->auth.msg.hdcp2.rx_id_list[1]) << 4);
+}
+
+static enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp)
+{
+	/* device count must be greater than or equal to tracked hdcp displays */
+	return (get_device_count(hdcp) < get_added_display_count(hdcp)) ?
+			MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE :
+			MOD_HDCP_STATUS_SUCCESS;
+}
+
+static uint8_t process_rxstatus(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input,
+		enum mod_hdcp_status *status)
+{
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_rxstatus,
+			&input->rxstatus_read, status,
+			hdcp, "rxstatus_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_reauthentication_request,
+			&input->reauth_request_check, status,
+			hdcp, "reauth_request_check"))
+		goto out;
+	if (is_dp_hdcp(hdcp)) {
+		if (!mod_hdcp_execute_and_set(check_link_integrity_failure_dp,
+				&input->link_integrity_check_dp, status,
+				hdcp, "link_integrity_check_dp"))
+			goto out;
+	}
+	if (hdcp->connection.is_repeater)
+		if (check_receiver_id_list_ready(hdcp) ==
+				MOD_HDCP_STATUS_SUCCESS) {
+			HDCP_INPUT_PASS_TRACE(hdcp, "rx_id_list_ready");
+			event_ctx->rx_id_list_ready = 1;
+			if (is_dp_hdcp(hdcp))
+				hdcp->auth.msg.hdcp2.rx_id_list_size =
+						sizeof(hdcp->auth.msg.hdcp2.rx_id_list);
+			else
+				hdcp->auth.msg.hdcp2.rx_id_list_size =
+					HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+					hdcp->auth.msg.hdcp2.rxstatus[0];
+		}
+out:
+	return (*status == MOD_HDCP_STATUS_SUCCESS);
+}
+
+static enum mod_hdcp_status known_hdcp2_capable_rx(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_hdcp2version,
+			&input->hdcp2version_read, &status,
+			hdcp, "hdcp2version_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_hdcp2_capable,
+			&input->hdcp2_capable_check, &status,
+			hdcp, "hdcp2_capable"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_ake_init(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (!mod_hdcp_execute_and_set(mod_hdcp_add_display_topology,
+			&input->add_topology, &status,
+			hdcp, "add_topology"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_create_session,
+			&input->create_session, &status,
+			hdcp, "create_session"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_prepare_ake_init,
+			&input->ake_init_prepare, &status,
+			hdcp, "ake_init_prepare"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_ake_init,
+			&input->ake_init_write, &status,
+			hdcp, "ake_init_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status validate_ake_cert(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (is_hdmi_dvi_sl_hdcp(hdcp))
+		if (!mod_hdcp_execute_and_set(check_ake_cert_available,
+				&input->ake_cert_available, &status,
+				hdcp, "ake_cert_available"))
+			goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_ake_cert,
+			&input->ake_cert_read, &status,
+			hdcp, "ake_cert_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_ake_cert,
+			&input->ake_cert_validation, &status,
+			hdcp, "ake_cert_validation"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_no_stored_km(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_no_stored_km,
+			&input->no_stored_km_write, &status,
+			hdcp, "no_stored_km_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status read_h_prime(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(check_h_prime_available,
+			&input->h_prime_available, &status,
+			hdcp, "h_prime_available"))
+		goto out;
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_h_prime,
+			&input->h_prime_read, &status,
+			hdcp, "h_prime_read"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status read_pairing_info_and_validate_h_prime(
+		struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(check_pairing_info_available,
+			&input->pairing_available, &status,
+			hdcp, "pairing_available"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_pairing_info,
+			&input->pairing_info_read, &status,
+			hdcp, "pairing_info_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_h_prime,
+			&input->h_prime_validation, &status,
+			hdcp, "h_prime_validation"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_stored_km(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_stored_km,
+			&input->stored_km_write, &status,
+			hdcp, "stored_km_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status validate_h_prime(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(check_h_prime_available,
+			&input->h_prime_available, &status,
+			hdcp, "h_prime_available"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_h_prime,
+			&input->h_prime_read, &status,
+			hdcp, "h_prime_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_h_prime,
+			&input->h_prime_validation, &status,
+			hdcp, "h_prime_validation"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status locality_check(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_prepare_lc_init,
+			&input->lc_init_prepare, &status,
+			hdcp, "lc_init_prepare"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_lc_init,
+			&input->lc_init_write, &status,
+			 hdcp, "lc_init_write"))
+		goto out;
+	if (is_dp_hdcp(hdcp))
+		msleep(16);
+	else
+		if (!mod_hdcp_execute_and_set(poll_l_prime_available,
+				&input->l_prime_available_poll, &status,
+				hdcp, "l_prime_available_poll"))
+			goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_l_prime,
+			&input->l_prime_read, &status,
+			hdcp, "l_prime_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_l_prime,
+			&input->l_prime_validation, &status,
+			hdcp, "l_prime_validation"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status exchange_ks_and_test_for_repeater(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_prepare_eks,
+			&input->eks_prepare, &status,
+			hdcp, "eks_prepare"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_eks,
+			&input->eks_write, &status,
+			hdcp, "eks_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status enable_encryption(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (event_ctx->event == MOD_HDCP_EVENT_CPIRQ) {
+		process_rxstatus(hdcp, event_ctx, input, &status);
+		goto out;
+	}
+
+	if (is_hdmi_dvi_sl_hdcp(hdcp)) {
+		if (!process_rxstatus(hdcp, event_ctx, input, &status))
+			goto out;
+		if (event_ctx->rx_id_list_ready)
+			goto out;
+	}
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_enable_encryption,
+			&input->enable_encryption, &status,
+			hdcp, "enable_encryption"))
+		goto out;
+	if (is_dp_mst_hdcp(hdcp)) {
+		if (!mod_hdcp_execute_and_set(
+				mod_hdcp_hdcp2_enable_dp_stream_encryption,
+				&input->stream_encryption_dp, &status,
+				hdcp, "stream_encryption_dp"))
+			goto out;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status authenticated(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!process_rxstatus(hdcp, event_ctx, input, &status))
+		goto out;
+	if (event_ctx->rx_id_list_ready)
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status wait_for_rx_id_list(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!process_rxstatus(hdcp, event_ctx, input, &status))
+		goto out;
+	if (!event_ctx->rx_id_list_ready) {
+		status = MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY;
+		goto out;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status verify_rx_id_list_and_send_ack(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (event_ctx->event == MOD_HDCP_EVENT_CPIRQ) {
+		process_rxstatus(hdcp, event_ctx, input, &status);
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_rx_id_list,
+			&input->rx_id_list_read,
+			&status, hdcp, "receiver_id_list_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_device_count,
+			&input->device_count_check,
+			&status, hdcp, "device_count_check"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_rx_id_list,
+			&input->rx_id_list_validation,
+			&status, hdcp, "rx_id_list_validation"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_repeater_auth_ack,
+			&input->repeater_auth_ack_write,
+			&status, hdcp, "repeater_auth_ack_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_stream_management(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (event_ctx->event == MOD_HDCP_EVENT_CPIRQ) {
+		process_rxstatus(hdcp, event_ctx, input, &status);
+		goto out;
+	}
+
+	if (is_hdmi_dvi_sl_hdcp(hdcp)) {
+		if (!process_rxstatus(hdcp, event_ctx, input, &status))
+			goto out;
+		if (event_ctx->rx_id_list_ready)
+			goto out;
+	}
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_prepare_stream_management,
+			&input->prepare_stream_manage,
+			&status, hdcp, "prepare_stream_manage"))
+		goto out;
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_stream_manage,
+			&input->stream_manage_write,
+			&status, hdcp, "stream_manage_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status validate_stream_ready(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (event_ctx->event == MOD_HDCP_EVENT_CPIRQ) {
+		process_rxstatus(hdcp, event_ctx, input, &status);
+		goto out;
+	}
+
+	if (is_hdmi_dvi_sl_hdcp(hdcp)) {
+		if (!process_rxstatus(hdcp, event_ctx, input, &status))
+			goto out;
+		if (event_ctx->rx_id_list_ready) {
+			goto out;
+		}
+	}
+	if (is_hdmi_dvi_sl_hdcp(hdcp))
+		if (!mod_hdcp_execute_and_set(check_stream_ready_available,
+				&input->stream_ready_available,
+				&status, hdcp, "stream_ready_available"))
+			goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_stream_ready,
+			&input->stream_ready_read,
+			&status, hdcp, "stream_ready_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_stream_ready,
+			&input->stream_ready_validation,
+			&status, hdcp, "stream_ready_validation"))
+		goto out;
+
+out:
+	return status;
+}
+
+static enum mod_hdcp_status determine_rx_hdcp_capable_dp(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_rxcaps,
+			&input->rx_caps_read_dp,
+			&status, hdcp, "rx_caps_read_dp"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_hdcp2_capable,
+			&input->hdcp2_capable_check, &status,
+			hdcp, "hdcp2_capable_check"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_content_stream_type_dp(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!process_rxstatus(hdcp, event_ctx, input, &status))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_content_type,
+			&input->content_stream_type_write, &status,
+			hdcp, "content_stream_type_write"))
+		goto out;
+out:
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	switch (current_state(hdcp)) {
+	case H2_A0_KNOWN_HDCP2_CAPABLE_RX:
+		status = known_hdcp2_capable_rx(hdcp, event_ctx, input);
+		break;
+	case H2_A1_SEND_AKE_INIT:
+		status = send_ake_init(hdcp, event_ctx, input);
+		break;
+	case H2_A1_VALIDATE_AKE_CERT:
+		status = validate_ake_cert(hdcp, event_ctx, input);
+		break;
+	case H2_A1_SEND_NO_STORED_KM:
+		status = send_no_stored_km(hdcp, event_ctx, input);
+		break;
+	case H2_A1_READ_H_PRIME:
+		status = read_h_prime(hdcp, event_ctx, input);
+		break;
+	case H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		status = read_pairing_info_and_validate_h_prime(hdcp,
+				event_ctx, input);
+		break;
+	case H2_A1_SEND_STORED_KM:
+		status = send_stored_km(hdcp, event_ctx, input);
+		break;
+	case H2_A1_VALIDATE_H_PRIME:
+		status = validate_h_prime(hdcp, event_ctx, input);
+		break;
+	case H2_A2_LOCALITY_CHECK:
+		status = locality_check(hdcp, event_ctx, input);
+		break;
+	case H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		status = exchange_ks_and_test_for_repeater(hdcp, event_ctx, input);
+		break;
+	case H2_ENABLE_ENCRYPTION:
+		status = enable_encryption(hdcp, event_ctx, input);
+		break;
+	case H2_A5_AUTHENTICATED:
+		status = authenticated(hdcp, event_ctx, input);
+		break;
+	case H2_A6_WAIT_FOR_RX_ID_LIST:
+		status = wait_for_rx_id_list(hdcp, event_ctx, input);
+		break;
+	case H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		status = verify_rx_id_list_and_send_ack(hdcp, event_ctx, input);
+		break;
+	case H2_A9_SEND_STREAM_MANAGEMENT:
+		status = send_stream_management(hdcp, event_ctx, input);
+		break;
+	case H2_A9_VALIDATE_STREAM_READY:
+		status = validate_stream_ready(hdcp, event_ctx, input);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		break;
+	}
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_dp_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	switch (current_state(hdcp)) {
+	case D2_A0_DETERMINE_RX_HDCP_CAPABLE:
+		status = determine_rx_hdcp_capable_dp(hdcp, event_ctx, input);
+		break;
+	case D2_A1_SEND_AKE_INIT:
+		status = send_ake_init(hdcp, event_ctx, input);
+		break;
+	case D2_A1_VALIDATE_AKE_CERT:
+		status = validate_ake_cert(hdcp, event_ctx, input);
+		break;
+	case D2_A1_SEND_NO_STORED_KM:
+		status = send_no_stored_km(hdcp, event_ctx, input);
+		break;
+	case D2_A1_READ_H_PRIME:
+		status = read_h_prime(hdcp, event_ctx, input);
+		break;
+	case D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		status = read_pairing_info_and_validate_h_prime(hdcp,
+				event_ctx, input);
+		break;
+	case D2_A1_SEND_STORED_KM:
+		status = send_stored_km(hdcp, event_ctx, input);
+		break;
+	case D2_A1_VALIDATE_H_PRIME:
+		status = validate_h_prime(hdcp, event_ctx, input);
+		break;
+	case D2_A2_LOCALITY_CHECK:
+		status = locality_check(hdcp, event_ctx, input);
+		break;
+	case D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		status = exchange_ks_and_test_for_repeater(hdcp,
+				event_ctx, input);
+		break;
+	case D2_SEND_CONTENT_STREAM_TYPE:
+		status = send_content_stream_type_dp(hdcp, event_ctx, input);
+		break;
+	case D2_ENABLE_ENCRYPTION:
+		status = enable_encryption(hdcp, event_ctx, input);
+		break;
+	case D2_A5_AUTHENTICATED:
+		status = authenticated(hdcp, event_ctx, input);
+		break;
+	case D2_A6_WAIT_FOR_RX_ID_LIST:
+		status = wait_for_rx_id_list(hdcp, event_ctx, input);
+		break;
+	case D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		status = verify_rx_id_list_and_send_ack(hdcp, event_ctx, input);
+		break;
+	case D2_A9_SEND_STREAM_MANAGEMENT:
+		status = send_stream_management(hdcp, event_ctx, input);
+		break;
+	case D2_A9_VALIDATE_STREAM_READY:
+		status = validate_stream_ready(hdcp, event_ctx, input);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		break;
+	}
+
+	return status;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c
new file mode 100644
index 000000000000..8cae3e3aacd5
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c
@@ -0,0 +1,679 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "hdcp.h"
+
+enum mod_hdcp_status mod_hdcp_hdcp2_transition(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_connection *conn = &hdcp->connection;
+	struct mod_hdcp_link_adjustment *adjust = &hdcp->connection.link.adjust;
+
+	switch (current_state(hdcp)) {
+	case H2_A0_KNOWN_HDCP2_CAPABLE_RX:
+		if (input->hdcp2version_read != PASS ||
+				input->hdcp2_capable_check != PASS) {
+			adjust->hdcp2.disable = 1;
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, HDCP_INITIALIZED);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A1_SEND_AKE_INIT);
+		}
+		break;
+	case H2_A1_SEND_AKE_INIT:
+		if (input->add_topology != PASS ||
+				input->create_session != PASS ||
+				input->ake_init_prepare != PASS) {
+			/* out of sync with psp state */
+			adjust->hdcp2.disable = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->ake_init_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 100, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A1_VALIDATE_AKE_CERT);
+		break;
+	case H2_A1_VALIDATE_AKE_CERT:
+		if (input->ake_cert_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1A-08: consider ake timeout a failure */
+				/* some hdmi receivers are not ready for HDCP
+				 * immediately after video becomes active,
+				 * delay 1s before retry on first HDCP message
+				 * timeout.
+				 */
+				fail_and_restart_in_ms(1000, &status, output);
+			} else {
+				/* continue ake cert polling*/
+				callback_in_ms(10, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->ake_cert_read != PASS ||
+				input->ake_cert_validation != PASS) {
+			/*
+			 * 1A-09: consider invalid ake cert a failure
+			 * 1A-10: consider receiver id listed in SRM a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_km_stored &&
+				!adjust->hdcp2.force_no_stored_km) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A1_SEND_STORED_KM);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A1_SEND_NO_STORED_KM);
+		}
+		break;
+	case H2_A1_SEND_NO_STORED_KM:
+		if (input->no_stored_km_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (adjust->hdcp2.increase_h_prime_timeout)
+			set_watchdog_in_ms(hdcp, 2000, output);
+		else
+			set_watchdog_in_ms(hdcp, 1000, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A1_READ_H_PRIME);
+		break;
+	case H2_A1_READ_H_PRIME:
+		if (input->h_prime_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1A-11-3: consider h' timeout a failure */
+				fail_and_restart_in_ms(1000, &status, output);
+			} else {
+				/* continue h' polling */
+				callback_in_ms(100, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->h_prime_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 200, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME);
+		break;
+	case H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		if (input->pairing_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1A-12: consider pairing info timeout
+				 * a failure
+				 */
+				fail_and_restart_in_ms(0, &status, output);
+			} else {
+				/* continue pairing info polling */
+				callback_in_ms(20, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->pairing_info_read != PASS ||
+				input->h_prime_validation != PASS) {
+			/* 1A-11-1: consider invalid h' a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A2_LOCALITY_CHECK);
+		break;
+	case H2_A1_SEND_STORED_KM:
+		if (input->stored_km_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 200, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A1_VALIDATE_H_PRIME);
+		break;
+	case H2_A1_VALIDATE_H_PRIME:
+		if (input->h_prime_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1A-11-2: consider h' timeout a failure */
+				fail_and_restart_in_ms(1000, &status, output);
+			} else {
+				/* continue h' polling */
+				callback_in_ms(20, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->h_prime_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->h_prime_validation != PASS) {
+			/* 1A-11-1: consider invalid h' a failure */
+			adjust->hdcp2.force_no_stored_km = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A2_LOCALITY_CHECK);
+		break;
+	case H2_A2_LOCALITY_CHECK:
+		if (hdcp->state.stay_count > 10 ||
+				input->lc_init_prepare != PASS ||
+				input->lc_init_write != PASS ||
+				input->l_prime_available_poll != PASS ||
+				input->l_prime_read != PASS) {
+			/*
+			 * 1A-05: consider disconnection after LC init a failure
+			 * 1A-13-1: consider invalid l' a failure
+			 * 1A-13-2: consider l' timeout a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->l_prime_validation != PASS) {
+			callback_in_ms(0, output);
+			increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER);
+		break;
+	case H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		if (input->eks_prepare != PASS ||
+				input->eks_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_repeater) {
+			set_watchdog_in_ms(hdcp, 3000, output);
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A6_WAIT_FOR_RX_ID_LIST);
+		} else {
+			/* some CTS equipment requires a delay GREATER than
+			 * 200 ms, so delay 210 ms instead of 200 ms
+			 */
+			callback_in_ms(210, output);
+			set_state_id(hdcp, output, H2_ENABLE_ENCRYPTION);
+		}
+		break;
+	case H2_ENABLE_ENCRYPTION:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			/*
+			 * 1A-07: restart hdcp on REAUTH_REQ
+			 * 1B-08: restart hdcp on REAUTH_REQ
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->enable_encryption != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A5_AUTHENTICATED);
+		HDCP_FULL_DDC_TRACE(hdcp);
+		break;
+	case H2_A5_AUTHENTICATED:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		}
+		callback_in_ms(500, output);
+		increment_stay_counter(hdcp);
+		break;
+	case H2_A6_WAIT_FOR_RX_ID_LIST:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (!event_ctx->rx_id_list_ready) {
+			if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1B-02: consider rx id list timeout a failure */
+				/* some CTS equipment's actual timeout
+				 * measurement is slightly greater than 3000 ms.
+				 * Delay 100 ms to ensure it is fully timeout
+				 * before re-authentication.
+				 */
+				fail_and_restart_in_ms(100, &status, output);
+			} else {
+				callback_in_ms(300, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+		break;
+	case H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->rx_id_list_read != PASS ||
+				input->device_count_check != PASS ||
+				input->rx_id_list_validation != PASS ||
+				input->repeater_auth_ack_write != PASS) {
+			/* 1B-03: consider invalid v' a failure
+			 * 1B-04: consider MAX_DEVS_EXCEEDED a failure
+			 * 1B-05: consider MAX_CASCADE_EXCEEDED a failure
+			 * 1B-06: consider invalid seq_num_V a failure
+			 * 1B-09: consider seq_num_V rollover a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A9_SEND_STREAM_MANAGEMENT);
+		break;
+	case H2_A9_SEND_STREAM_MANAGEMENT:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->prepare_stream_manage != PASS ||
+				input->stream_manage_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 100, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A9_VALIDATE_STREAM_READY);
+		break;
+	case H2_A9_VALIDATE_STREAM_READY:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->stream_ready_available != PASS) {
+			if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1B-10-2: restart content stream management on
+				 * stream ready timeout
+				 */
+				hdcp->auth.count.stream_management_retry_count++;
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, H2_A9_SEND_STREAM_MANAGEMENT);
+			} else {
+				callback_in_ms(10, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->stream_ready_read != PASS ||
+				input->stream_ready_validation != PASS) {
+			/*
+			 * 1B-10-1: restart content stream management
+			 * on invalid M'
+			 */
+			if (hdcp->auth.count.stream_management_retry_count > 10) {
+				fail_and_restart_in_ms(0, &status, output);
+			} else {
+				hdcp->auth.count.stream_management_retry_count++;
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, H2_A9_SEND_STREAM_MANAGEMENT);
+			}
+			break;
+		}
+		callback_in_ms(200, output);
+		set_state_id(hdcp, output, H2_ENABLE_ENCRYPTION);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		fail_and_restart_in_ms(0, &status, output);
+		break;
+	}
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_connection *conn = &hdcp->connection;
+	struct mod_hdcp_link_adjustment *adjust = &hdcp->connection.link.adjust;
+
+	switch (current_state(hdcp)) {
+	case D2_A0_DETERMINE_RX_HDCP_CAPABLE:
+		if (input->rx_caps_read_dp != PASS ||
+				input->hdcp2_capable_check != PASS) {
+			adjust->hdcp2.disable = 1;
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, HDCP_INITIALIZED);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A1_SEND_AKE_INIT);
+		}
+		break;
+	case D2_A1_SEND_AKE_INIT:
+		if (input->add_topology != PASS ||
+				input->create_session != PASS ||
+				input->ake_init_prepare != PASS) {
+			/* out of sync with psp state */
+			adjust->hdcp2.disable = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->ake_init_write != PASS) {
+			/* possibly display not ready */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(100, output);
+		set_state_id(hdcp, output, D2_A1_VALIDATE_AKE_CERT);
+		break;
+	case D2_A1_VALIDATE_AKE_CERT:
+		if (input->ake_cert_read != PASS ||
+				input->ake_cert_validation != PASS) {
+			/*
+			 * 1A-08: consider invalid ake cert a failure
+			 * 1A-09: consider receiver id listed in SRM a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_km_stored &&
+				!adjust->hdcp2.force_no_stored_km) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A1_SEND_STORED_KM);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A1_SEND_NO_STORED_KM);
+		}
+		break;
+	case D2_A1_SEND_NO_STORED_KM:
+		if (input->no_stored_km_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (adjust->hdcp2.increase_h_prime_timeout)
+			set_watchdog_in_ms(hdcp, 2000, output);
+		else
+			set_watchdog_in_ms(hdcp, 1000, output);
+		set_state_id(hdcp, output, D2_A1_READ_H_PRIME);
+		break;
+	case D2_A1_READ_H_PRIME:
+		if (input->h_prime_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				/* 1A-10-3: consider h' timeout a failure */
+				fail_and_restart_in_ms(1000, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		} else if (input->h_prime_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 200, output);
+		set_state_id(hdcp, output, D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME);
+		break;
+	case D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		if (input->pairing_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				/*
+				 * 1A-11: consider pairing info timeout
+				 * a failure
+				 */
+				fail_and_restart_in_ms(0, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		} else if (input->pairing_info_read != PASS ||
+				input->h_prime_validation != PASS) {
+			/* 1A-10-1: consider invalid h' a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A2_LOCALITY_CHECK);
+		break;
+	case D2_A1_SEND_STORED_KM:
+		if (input->stored_km_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 200, output);
+		set_state_id(hdcp, output, D2_A1_VALIDATE_H_PRIME);
+		break;
+	case D2_A1_VALIDATE_H_PRIME:
+		if (input->h_prime_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				/* 1A-10-2: consider h' timeout a failure */
+				fail_and_restart_in_ms(1000, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		} else if (input->h_prime_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->h_prime_validation != PASS) {
+			/* 1A-10-1: consider invalid h' a failure */
+			adjust->hdcp2.force_no_stored_km = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A2_LOCALITY_CHECK);
+		break;
+	case D2_A2_LOCALITY_CHECK:
+		if (hdcp->state.stay_count > 10 ||
+				input->lc_init_prepare != PASS ||
+				input->lc_init_write != PASS ||
+				input->l_prime_read != PASS) {
+			/* 1A-12: consider invalid l' a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->l_prime_validation != PASS) {
+			callback_in_ms(0, output);
+			increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER);
+		break;
+	case D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		if (input->eks_prepare != PASS ||
+				input->eks_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_repeater) {
+			set_watchdog_in_ms(hdcp, 3000, output);
+			set_state_id(hdcp, output, D2_A6_WAIT_FOR_RX_ID_LIST);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_SEND_CONTENT_STREAM_TYPE);
+		}
+		break;
+	case D2_SEND_CONTENT_STREAM_TYPE:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS ||
+				input->content_stream_type_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(210, output);
+		set_state_id(hdcp, output, D2_ENABLE_ENCRYPTION);
+		break;
+	case D2_ENABLE_ENCRYPTION:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS) {
+			/*
+			 * 1A-07: restart hdcp on REAUTH_REQ
+			 * 1B-08: restart hdcp on REAUTH_REQ
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->enable_encryption != PASS ||
+				(is_dp_mst_hdcp(hdcp) && input->stream_encryption_dp != PASS)) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_state_id(hdcp, output, D2_A5_AUTHENTICATED);
+		HDCP_FULL_DDC_TRACE(hdcp);
+		break;
+	case D2_A5_AUTHENTICATED:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->link_integrity_check_dp != PASS) {
+			if (hdcp->connection.hdcp2_retry_count >= 1)
+				adjust->hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		}
+		increment_stay_counter(hdcp);
+		break;
+	case D2_A6_WAIT_FOR_RX_ID_LIST:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (!event_ctx->rx_id_list_ready) {
+			if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				/* 1B-02: consider rx id list timeout a failure */
+				fail_and_restart_in_ms(0, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+		break;
+	case D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS ||
+				input->rx_id_list_read != PASS ||
+				input->device_count_check != PASS ||
+				input->rx_id_list_validation != PASS ||
+				input->repeater_auth_ack_write != PASS) {
+			/*
+			 * 1B-03: consider invalid v' a failure
+			 * 1B-04: consider MAX_DEVS_EXCEEDED a failure
+			 * 1B-05: consider MAX_CASCADE_EXCEEDED a failure
+			 * 1B-06: consider invalid seq_num_V a failure
+			 * 1B-09: consider seq_num_V rollover a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A9_SEND_STREAM_MANAGEMENT);
+		break;
+	case D2_A9_SEND_STREAM_MANAGEMENT:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->prepare_stream_manage != PASS ||
+				input->stream_manage_write != PASS) {
+			if (event_ctx->event == MOD_HDCP_EVENT_CALLBACK)
+				fail_and_restart_in_ms(0, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(100, output);
+		set_state_id(hdcp, output, D2_A9_VALIDATE_STREAM_READY);
+		break;
+	case D2_A9_VALIDATE_STREAM_READY:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->stream_ready_read != PASS ||
+				input->stream_ready_validation != PASS) {
+			/*
+			 * 1B-10-1: restart content stream management
+			 * on invalid M'
+			 * 1B-10-2: consider stream ready timeout a failure
+			 */
+			if (hdcp->auth.count.stream_management_retry_count > 10) {
+				fail_and_restart_in_ms(0, &status, output);
+			} else if (event_ctx->event == MOD_HDCP_EVENT_CALLBACK) {
+				hdcp->auth.count.stream_management_retry_count++;
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, D2_A9_SEND_STREAM_MANAGEMENT);
+			} else {
+				increment_stay_counter(hdcp);
+			}
+			break;
+		}
+		callback_in_ms(200, output);
+		set_state_id(hdcp, output, D2_ENABLE_ENCRYPTION);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		fail_and_restart_in_ms(0, &status, output);
+		break;
+	}
+	return status;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
index e7baae059b85..ff9d54812e62 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
@@ -51,6 +51,26 @@ enum mod_hdcp_ddc_message_id {
 	MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO,
 	MOD_HDCP_MESSAGE_ID_READ_BINFO,
 
+	/* HDCP 2.2 */
+
+	MOD_HDCP_MESSAGE_ID_HDCP2VERSION,
+	MOD_HDCP_MESSAGE_ID_RX_CAPS,
+	MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT,
+	MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT,
+	MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM,
+	MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM,
+	MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME,
+	MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO,
+	MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT,
+	MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME,
+	MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS,
+	MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST,
+	MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK,
+	MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE,
+	MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY,
+	MOD_HDCP_MESSAGE_ID_READ_RXSTATUS,
+	MOD_HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE,
+
 	MOD_HDCP_MESSAGE_ID_MAX
 };
 
@@ -70,6 +90,22 @@ static const uint8_t hdcp_i2c_offsets[] = {
 	[MOD_HDCP_MESSAGE_ID_READ_BSTATUS] = 0x41,
 	[MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO] = 0x43,
 	[MOD_HDCP_MESSAGE_ID_READ_BINFO] = 0xFF,
+	[MOD_HDCP_MESSAGE_ID_HDCP2VERSION] = 0x50,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_READ_RXSTATUS] = 0x70,
+	[MOD_HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE] = 0x0
 };
 
 static const uint32_t hdcp_dpcd_addrs[] = {
@@ -88,6 +124,22 @@ static const uint32_t hdcp_dpcd_addrs[] = {
 	[MOD_HDCP_MESSAGE_ID_READ_BSTATUS] = 0x68029,
 	[MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO] = 0x6802c,
 	[MOD_HDCP_MESSAGE_ID_READ_BINFO] = 0x6802a,
+	[MOD_HDCP_MESSAGE_ID_RX_CAPS] = 0x6921d,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT] = 0x69000,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT] = 0x6900b,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM] = 0x69220,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM] = 0x692a0,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME] = 0x692c0,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO] = 0x692e0,
+	[MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT] = 0x692f0,
+	[MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME] = 0x692f8,
+	[MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS] = 0x69318,
+	[MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST] = 0x69330,
+	[MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK] = 0x693e0,
+	[MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE] = 0x693f0,
+	[MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY] = 0x69473,
+	[MOD_HDCP_MESSAGE_ID_READ_RXSTATUS] = 0x69493,
+	[MOD_HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE] = 0x69494
 };
 
 static enum mod_hdcp_status read(struct mod_hdcp *hdcp,
@@ -303,3 +355,277 @@ enum mod_hdcp_status mod_hdcp_write_an(struct mod_hdcp *hdcp)
 			hdcp->auth.msg.hdcp1.an,
 			sizeof(hdcp->auth.msg.hdcp1.an));
 }
+
+enum mod_hdcp_status mod_hdcp_read_hdcp2version(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	else
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_HDCP2VERSION,
+				&hdcp->auth.msg.hdcp2.hdcp2version_hdmi,
+				sizeof(hdcp->auth.msg.hdcp2.hdcp2version_hdmi));
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_rxcaps(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (!is_dp_hdcp(hdcp))
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	else
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_RX_CAPS,
+				hdcp->auth.msg.hdcp2.rxcaps_dp,
+				sizeof(hdcp->auth.msg.hdcp2.rxcaps_dp));
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_rxstatus(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_RXSTATUS,
+				&hdcp->auth.msg.hdcp2.rxstatus_dp,
+				1);
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_RXSTATUS,
+					(uint8_t *)&hdcp->auth.msg.hdcp2.rxstatus,
+					sizeof(hdcp->auth.msg.hdcp2.rxstatus));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_ake_cert(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.ake_cert[0] = 3;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT,
+				hdcp->auth.msg.hdcp2.ake_cert+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_cert)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT,
+					hdcp->auth.msg.hdcp2.ake_cert,
+					sizeof(hdcp->auth.msg.hdcp2.ake_cert));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_h_prime(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.ake_h_prime[0] = 7;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME,
+				hdcp->auth.msg.hdcp2.ake_h_prime+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME,
+				hdcp->auth.msg.hdcp2.ake_h_prime,
+				sizeof(hdcp->auth.msg.hdcp2.ake_h_prime));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_pairing_info(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.ake_pairing_info[0] = 8;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO,
+				hdcp->auth.msg.hdcp2.ake_pairing_info+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO,
+				hdcp->auth.msg.hdcp2.ake_pairing_info,
+				sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_l_prime(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.lc_l_prime[0] = 10;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME,
+				hdcp->auth.msg.hdcp2.lc_l_prime+1,
+				sizeof(hdcp->auth.msg.hdcp2.lc_l_prime)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME,
+				hdcp->auth.msg.hdcp2.lc_l_prime,
+				sizeof(hdcp->auth.msg.hdcp2.lc_l_prime));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_rx_id_list(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.rx_id_list[0] = 12;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST,
+				hdcp->auth.msg.hdcp2.rx_id_list+1,
+				sizeof(hdcp->auth.msg.hdcp2.rx_id_list)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST,
+				hdcp->auth.msg.hdcp2.rx_id_list,
+				hdcp->auth.msg.hdcp2.rx_id_list_size);
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_stream_ready(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.repeater_auth_stream_ready[0] = 17;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY,
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_ready+1,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY,
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_ready,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_ake_init(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT,
+				hdcp->auth.msg.hdcp2.ake_init+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_init)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT,
+					hdcp->auth.msg.hdcp2.ake_init,
+					sizeof(hdcp->auth.msg.hdcp2.ake_init));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_no_stored_km(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM,
+				hdcp->auth.msg.hdcp2.ake_no_stored_km+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM,
+			hdcp->auth.msg.hdcp2.ake_no_stored_km,
+			sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_stored_km(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM,
+				hdcp->auth.msg.hdcp2.ake_stored_km+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_stored_km)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM,
+				hdcp->auth.msg.hdcp2.ake_stored_km,
+				sizeof(hdcp->auth.msg.hdcp2.ake_stored_km));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_lc_init(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT,
+				hdcp->auth.msg.hdcp2.lc_init+1,
+				sizeof(hdcp->auth.msg.hdcp2.lc_init)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT,
+				hdcp->auth.msg.hdcp2.lc_init,
+				sizeof(hdcp->auth.msg.hdcp2.lc_init));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_eks(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp,
+				MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS,
+				hdcp->auth.msg.hdcp2.ske_eks+1,
+				sizeof(hdcp->auth.msg.hdcp2.ske_eks)-1);
+	else
+		status = write(hdcp,
+			MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS,
+			hdcp->auth.msg.hdcp2.ske_eks,
+			sizeof(hdcp->auth.msg.hdcp2.ske_eks));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_repeater_auth_ack(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK,
+				hdcp->auth.msg.hdcp2.repeater_auth_ack+1,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK,
+				hdcp->auth.msg.hdcp2.repeater_auth_ack,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_stream_manage(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp,
+				MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE,
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_manage+1,
+				hdcp->auth.msg.hdcp2.stream_manage_size-1);
+	else
+		status = write(hdcp,
+				MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE,
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_manage,
+				hdcp->auth.msg.hdcp2.stream_manage_size);
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_content_type(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE,
+				hdcp->auth.msg.hdcp2.content_stream_type_dp+1,
+				sizeof(hdcp->auth.msg.hdcp2.content_stream_type_dp)-1);
+	else
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	return status;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
index 3982ced5f969..724ebcee9a19 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
@@ -116,6 +116,58 @@ char *mod_hdcp_status_to_str(int32_t status)
 		return "MOD_HDCP_STATUS_DDC_FAILURE";
 	case MOD_HDCP_STATUS_INVALID_OPERATION:
 		return "MOD_HDCP_STATUS_INVALID_OPERATION";
+	case MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE:
+		return "MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE";
+	case MOD_HDCP_STATUS_HDCP2_CREATE_SESSION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_CREATE_SESSION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_DESTROY_SESSION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_DESTROY_SESSION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_PREP_AKE_INIT_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_PREP_AKE_INIT_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_AKE_CERT_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_AKE_CERT_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_AKE_CERT_REVOKED:
+		return "MOD_HDCP_STATUS_HDCP2_AKE_CERT_REVOKED";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_L_PRIME_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_L_PRIME_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_PREP_EKS_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_PREP_EKS_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_REVOKED:
+		return "MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_REVOKED";
+	case MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY:
+		return "MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY";
+	case MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION:
+		return "MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION";
+	case MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_PREPARE_STREAM_MANAGEMENT_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_PREPARE_STREAM_MANAGEMENT_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST:
+		return "MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST";
+	case MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE";
 	default:
 		return "MOD_HDCP_STATUS_UNKNOWN";
 	}
@@ -156,6 +208,72 @@ char *mod_hdcp_state_id_to_str(int32_t id)
 		return "D1_A6_WAIT_FOR_READY";
 	case D1_A7_READ_KSV_LIST:
 		return "D1_A7_READ_KSV_LIST";
+	case H2_A0_KNOWN_HDCP2_CAPABLE_RX:
+		return "H2_A0_KNOWN_HDCP2_CAPABLE_RX";
+	case H2_A1_SEND_AKE_INIT:
+		return "H2_A1_SEND_AKE_INIT";
+	case H2_A1_VALIDATE_AKE_CERT:
+		return "H2_A1_VALIDATE_AKE_CERT";
+	case H2_A1_SEND_NO_STORED_KM:
+		return "H2_A1_SEND_NO_STORED_KM";
+	case H2_A1_READ_H_PRIME:
+		return "H2_A1_READ_H_PRIME";
+	case H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		return "H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME";
+	case H2_A1_SEND_STORED_KM:
+		return "H2_A1_SEND_STORED_KM";
+	case H2_A1_VALIDATE_H_PRIME:
+		return "H2_A1_VALIDATE_H_PRIME";
+	case H2_A2_LOCALITY_CHECK:
+		return "H2_A2_LOCALITY_CHECK";
+	case H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		return "H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER";
+	case H2_ENABLE_ENCRYPTION:
+		return "H2_ENABLE_ENCRYPTION";
+	case H2_A5_AUTHENTICATED:
+		return "H2_A5_AUTHENTICATED";
+	case H2_A6_WAIT_FOR_RX_ID_LIST:
+		return "H2_A6_WAIT_FOR_RX_ID_LIST";
+	case H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		return "H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK";
+	case H2_A9_SEND_STREAM_MANAGEMENT:
+		return "H2_A9_SEND_STREAM_MANAGEMENT";
+	case H2_A9_VALIDATE_STREAM_READY:
+		return "H2_A9_VALIDATE_STREAM_READY";
+	case D2_A0_DETERMINE_RX_HDCP_CAPABLE:
+		return "D2_A0_DETERMINE_RX_HDCP_CAPABLE";
+	case D2_A1_SEND_AKE_INIT:
+		return "D2_A1_SEND_AKE_INIT";
+	case D2_A1_VALIDATE_AKE_CERT:
+		return "D2_A1_VALIDATE_AKE_CERT";
+	case D2_A1_SEND_NO_STORED_KM:
+		return "D2_A1_SEND_NO_STORED_KM";
+	case D2_A1_READ_H_PRIME:
+		return "D2_A1_READ_H_PRIME";
+	case D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		return "D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME";
+	case D2_A1_SEND_STORED_KM:
+		return "D2_A1_SEND_STORED_KM";
+	case D2_A1_VALIDATE_H_PRIME:
+		return "D2_A1_VALIDATE_H_PRIME";
+	case D2_A2_LOCALITY_CHECK:
+		return "D2_A2_LOCALITY_CHECK";
+	case D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		return "D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER";
+	case D2_SEND_CONTENT_STREAM_TYPE:
+		return "D2_SEND_CONTENT_STREAM_TYPE";
+	case D2_ENABLE_ENCRYPTION:
+		return "D2_ENABLE_ENCRYPTION";
+	case D2_A5_AUTHENTICATED:
+		return "D2_A5_AUTHENTICATED";
+	case D2_A6_WAIT_FOR_RX_ID_LIST:
+		return "D2_A6_WAIT_FOR_RX_ID_LIST";
+	case D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		return "D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK";
+	case D2_A9_SEND_STREAM_MANAGEMENT:
+		return "D2_A9_SEND_STREAM_MANAGEMENT";
+	case D2_A9_VALIDATE_STREAM_READY:
+		return "D2_A9_VALIDATE_STREAM_READY";
 	default:
 		return "UNKNOWN_STATE_ID";
 	};
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
index 2fd0e0a893ef..ff91373ebada 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
@@ -27,7 +27,7 @@
 #define MOD_HDCP_LOG_H_
 
 #ifdef CONFIG_DRM_AMD_DC_HDCP
-#define HDCP_LOG_ERR(hdcp, ...) DRM_ERROR(__VA_ARGS__)
+#define HDCP_LOG_ERR(hdcp, ...) DRM_WARN(__VA_ARGS__)
 #define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__)
@@ -37,7 +37,7 @@
 /* default logs */
 #define HDCP_ERROR_TRACE(hdcp, status) \
 		HDCP_LOG_ERR(hdcp, \
-			"[Link %d] ERROR %s IN STATE %s", \
+			"[Link %d] WARNING %s IN STATE %s", \
 			hdcp->config.index, \
 			mod_hdcp_status_to_str(status), \
 			mod_hdcp_state_id_to_str(hdcp->state.id))
@@ -45,6 +45,10 @@
 		HDCP_LOG_VER(hdcp, \
 			"[Link %d] HDCP 1.4 enabled on display %d", \
 			hdcp->config.index, displayIndex)
+#define HDCP_HDCP2_ENABLED_TRACE(hdcp, displayIndex) \
+		HDCP_LOG_VER(hdcp, \
+			"[Link %d] HDCP 2.2 enabled on display %d", \
+			hdcp->config.index, displayIndex)
 /* state machine logs */
 #define HDCP_REMOVE_DISPLAY_TRACE(hdcp, displayIndex) \
 		HDCP_LOG_FSM(hdcp, \
@@ -93,26 +97,73 @@
 				hdcp->buf); \
 } while (0)
 #define HDCP_FULL_DDC_TRACE(hdcp) do { \
-	HDCP_DDC_READ_TRACE(hdcp, "BKSV", hdcp->auth.msg.hdcp1.bksv, \
-			sizeof(hdcp->auth.msg.hdcp1.bksv)); \
-	HDCP_DDC_READ_TRACE(hdcp, "BCAPS", &hdcp->auth.msg.hdcp1.bcaps, \
-			sizeof(hdcp->auth.msg.hdcp1.bcaps)); \
-	HDCP_DDC_WRITE_TRACE(hdcp, "AN", hdcp->auth.msg.hdcp1.an, \
-			sizeof(hdcp->auth.msg.hdcp1.an)); \
-	HDCP_DDC_WRITE_TRACE(hdcp, "AKSV", hdcp->auth.msg.hdcp1.aksv, \
-			sizeof(hdcp->auth.msg.hdcp1.aksv)); \
-	HDCP_DDC_WRITE_TRACE(hdcp, "AINFO", &hdcp->auth.msg.hdcp1.ainfo, \
-			sizeof(hdcp->auth.msg.hdcp1.ainfo)); \
-	HDCP_DDC_READ_TRACE(hdcp, "RI' / R0'", \
-			(uint8_t *)&hdcp->auth.msg.hdcp1.r0p, \
-			sizeof(hdcp->auth.msg.hdcp1.r0p)); \
-	HDCP_DDC_READ_TRACE(hdcp, "BINFO", \
-			(uint8_t *)&hdcp->auth.msg.hdcp1.binfo_dp, \
-			sizeof(hdcp->auth.msg.hdcp1.binfo_dp)); \
-	HDCP_DDC_READ_TRACE(hdcp, "KSVLIST", hdcp->auth.msg.hdcp1.ksvlist, \
-			hdcp->auth.msg.hdcp1.ksvlist_size); \
-	HDCP_DDC_READ_TRACE(hdcp, "V'", hdcp->auth.msg.hdcp1.vp, \
-			sizeof(hdcp->auth.msg.hdcp1.vp)); \
+	if (is_hdcp1(hdcp)) { \
+		HDCP_DDC_READ_TRACE(hdcp, "BKSV", hdcp->auth.msg.hdcp1.bksv, \
+				sizeof(hdcp->auth.msg.hdcp1.bksv)); \
+		HDCP_DDC_READ_TRACE(hdcp, "BCAPS", &hdcp->auth.msg.hdcp1.bcaps, \
+				sizeof(hdcp->auth.msg.hdcp1.bcaps)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "AN", hdcp->auth.msg.hdcp1.an, \
+				sizeof(hdcp->auth.msg.hdcp1.an)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "AKSV", hdcp->auth.msg.hdcp1.aksv, \
+				sizeof(hdcp->auth.msg.hdcp1.aksv)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "AINFO", &hdcp->auth.msg.hdcp1.ainfo, \
+				sizeof(hdcp->auth.msg.hdcp1.ainfo)); \
+		HDCP_DDC_READ_TRACE(hdcp, "RI' / R0'", \
+				(uint8_t *)&hdcp->auth.msg.hdcp1.r0p, \
+				sizeof(hdcp->auth.msg.hdcp1.r0p)); \
+		HDCP_DDC_READ_TRACE(hdcp, "BINFO", \
+				(uint8_t *)&hdcp->auth.msg.hdcp1.binfo_dp, \
+				sizeof(hdcp->auth.msg.hdcp1.binfo_dp)); \
+		HDCP_DDC_READ_TRACE(hdcp, "KSVLIST", hdcp->auth.msg.hdcp1.ksvlist, \
+				hdcp->auth.msg.hdcp1.ksvlist_size); \
+		HDCP_DDC_READ_TRACE(hdcp, "V'", hdcp->auth.msg.hdcp1.vp, \
+				sizeof(hdcp->auth.msg.hdcp1.vp)); \
+	} else { \
+		HDCP_DDC_READ_TRACE(hdcp, "HDCP2Version", \
+				&hdcp->auth.msg.hdcp2.hdcp2version_hdmi, \
+				sizeof(hdcp->auth.msg.hdcp2.hdcp2version_hdmi)); \
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Caps", hdcp->auth.msg.hdcp2.rxcaps_dp, \
+				sizeof(hdcp->auth.msg.hdcp2.rxcaps_dp)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "AKE Init", hdcp->auth.msg.hdcp2.ake_init, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_init)); \
+		HDCP_DDC_READ_TRACE(hdcp, "AKE Cert", hdcp->auth.msg.hdcp2.ake_cert, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_cert)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Stored KM", \
+				hdcp->auth.msg.hdcp2.ake_stored_km, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_stored_km)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "No Stored KM", \
+				hdcp->auth.msg.hdcp2.ake_no_stored_km, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km)); \
+		HDCP_DDC_READ_TRACE(hdcp, "H'", hdcp->auth.msg.hdcp2.ake_h_prime, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)); \
+		HDCP_DDC_READ_TRACE(hdcp, "Pairing Info", \
+				hdcp->auth.msg.hdcp2.ake_pairing_info, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "LC Init", hdcp->auth.msg.hdcp2.lc_init, \
+				sizeof(hdcp->auth.msg.hdcp2.lc_init)); \
+		HDCP_DDC_READ_TRACE(hdcp, "L'", hdcp->auth.msg.hdcp2.lc_l_prime, \
+				sizeof(hdcp->auth.msg.hdcp2.lc_l_prime)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Exchange KS", hdcp->auth.msg.hdcp2.ske_eks, \
+				sizeof(hdcp->auth.msg.hdcp2.ske_eks)); \
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Status", \
+				(uint8_t *)&hdcp->auth.msg.hdcp2.rxstatus, \
+				sizeof(hdcp->auth.msg.hdcp2.rxstatus)); \
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Id List", \
+				hdcp->auth.msg.hdcp2.rx_id_list, \
+				hdcp->auth.msg.hdcp2.rx_id_list_size); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Rx Id List Ack", \
+				hdcp->auth.msg.hdcp2.repeater_auth_ack, \
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Content Stream Management", \
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_manage, \
+				hdcp->auth.msg.hdcp2.stream_manage_size); \
+		HDCP_DDC_READ_TRACE(hdcp, "Stream Ready", \
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_ready, \
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Content Stream Type", \
+				hdcp->auth.msg.hdcp2.content_stream_type_dp, \
+				sizeof(hdcp->auth.msg.hdcp2.content_stream_type_dp)); \
+	} \
 } while (0)
 #define HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, i) \
 		HDCP_LOG_TOP(hdcp, "[Link %d]\tadd display %d", \
@@ -123,6 +174,9 @@
 #define HDCP_TOP_HDCP1_DESTROY_SESSION_TRACE(hdcp) \
 		HDCP_LOG_TOP(hdcp, "[Link %d]\tdestroy hdcp1 session", \
 				hdcp->config.index)
+#define HDCP_TOP_HDCP2_DESTROY_SESSION_TRACE(hdcp) \
+		HDCP_LOG_TOP(hdcp, "[Link %d]\tdestroy hdcp2 session", \
+				hdcp->config.index)
 #define HDCP_TOP_RESET_AUTH_TRACE(hdcp) \
 		HDCP_LOG_TOP(hdcp, "[Link %d]\treset authentication", hdcp->config.index)
 #define HDCP_TOP_RESET_CONN_TRACE(hdcp) \
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index 646d909bbc37..7911dc157d5a 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -31,6 +31,19 @@
 #include "amdgpu.h"
 #include "hdcp_psp.h"
 
+static void hdcp2_message_init(struct mod_hdcp *hdcp,
+			       struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *in)
+{
+	in->session_handle = hdcp->auth.id;
+	in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->prepare.msg2_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->process.msg1_desc.msg_size = 0;
+	in->process.msg2_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->process.msg2_desc.msg_size = 0;
+	in->process.msg3_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->process.msg3_desc.msg_size = 0;
+}
 enum mod_hdcp_status mod_hdcp_remove_display_topology(struct mod_hdcp *hdcp)
 {
 
@@ -42,7 +55,7 @@ enum mod_hdcp_status mod_hdcp_remove_display_topology(struct mod_hdcp *hdcp)
 	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
 
 	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
-		if (hdcp->connection.displays[i].state == MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED) {
+		if (is_display_added(&(hdcp->connection.displays[i]))) {
 
 			memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory));
 
@@ -96,7 +109,7 @@ enum mod_hdcp_status mod_hdcp_add_display_topology(struct mod_hdcp *hdcp)
 			dtm_cmd->dtm_in_message.topology_update_v2.dig_fe = display->dig_fe;
 			dtm_cmd->dtm_in_message.topology_update_v2.dp_mst_vcid = display->vc_id;
 			dtm_cmd->dtm_in_message.topology_update_v2.max_hdcp_supported_version =
-				TA_DTM_HDCP_VERSION_MAX_SUPPORTED__1_x;
+				TA_DTM_HDCP_VERSION_MAX_SUPPORTED__2_2;
 			dtm_cmd->dtm_status = TA_DTM_STATUS__GENERIC_FAILURE;
 
 			psp_dtm_invoke(psp, dtm_cmd->cmd_id);
@@ -132,10 +145,11 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp)
 
 	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
 
+	hdcp->auth.id = hdcp_cmd->out_msg.hdcp1_create_session.session_handle;
+
 	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
 		return MOD_HDCP_STATUS_HDCP1_CREATE_SESSION_FAILURE;
 
-	hdcp->auth.id = hdcp_cmd->out_msg.hdcp1_create_session.session_handle;
 	hdcp->auth.msg.hdcp1.ainfo = hdcp_cmd->out_msg.hdcp1_create_session.ainfo_primary;
 	memcpy(hdcp->auth.msg.hdcp1.aksv, hdcp_cmd->out_msg.hdcp1_create_session.aksv_primary,
 		sizeof(hdcp->auth.msg.hdcp1.aksv));
@@ -326,3 +340,493 @@ enum mod_hdcp_status mod_hdcp_hdcp1_get_link_encryption_status(struct mod_hdcp *
 	return MOD_HDCP_STATUS_SUCCESS;
 }
 
+enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct mod_hdcp_display *display = get_first_added_display(hdcp);
+
+	if (!psp->hdcp_context.hdcp_initialized) {
+		DRM_ERROR("Failed to create hdcp session, HDCP TA is not initialized");
+		return MOD_HDCP_STATUS_FAILURE;
+	}
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	if (!display)
+		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+
+	hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index;
+
+	if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0)
+		hdcp_cmd->in_msg.hdcp2_create_session_v2.negotiate_content_type =
+			TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__FORCE_TYPE0;
+	else if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_1)
+		hdcp_cmd->in_msg.hdcp2_create_session_v2.negotiate_content_type =
+			TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__FORCE_TYPE1;
+	else if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_MAX)
+		hdcp_cmd->in_msg.hdcp2_create_session_v2.negotiate_content_type =
+			TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__MAX_SUPPORTED;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_CREATE_SESSION_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_CREATE_SESSION_FAILURE;
+
+	hdcp->auth.id = hdcp_cmd->out_msg.hdcp2_create_session_v2.session_handle;
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_destroy_session(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp2_destroy_session.session_handle = hdcp->auth.id;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_DESTROY_SESSION;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_DESTROY_SESSION_FAILURE;
+
+	HDCP_TOP_HDCP2_DESTROY_SESSION_TRACE(hdcp);
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_ake_init(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__AKE_INIT;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_PREP_AKE_INIT_FAILURE;
+
+	memcpy(&hdcp->auth.msg.hdcp2.ake_init[0], &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.ake_init));
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_ake_cert(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__AKE_SEND_CERT;
+	msg_in->process.msg1_desc.msg_size = TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_CERT;
+
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.ake_cert,
+	       sizeof(hdcp->auth.msg.hdcp2.ake_cert));
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__AKE_NO_STORED_KM;
+	msg_in->prepare.msg2_id = TA_HDCP_HDCP2_MSG_ID__AKE_STORED_KM;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE;
+
+	memcpy(hdcp->auth.msg.hdcp2.ake_no_stored_km, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km));
+
+	memcpy(hdcp->auth.msg.hdcp2.ake_stored_km,
+	       &msg_out->prepare.transmitter_message[sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km)],
+	       sizeof(hdcp->auth.msg.hdcp2.ake_stored_km));
+
+	if (msg_out->process.msg1_status == TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS) {
+		hdcp->connection.is_km_stored = msg_out->process.is_km_stored ? 1 : 0;
+		hdcp->connection.is_repeater = msg_out->process.is_repeater ? 1 : 0;
+		return MOD_HDCP_STATUS_SUCCESS;
+	}
+
+	return MOD_HDCP_STATUS_FAILURE;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_h_prime(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__AKE_SEND_H_PRIME;
+	msg_in->process.msg1_desc.msg_size = TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_H_PRIME;
+
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.ake_h_prime,
+	       sizeof(hdcp->auth.msg.hdcp2.ake_h_prime));
+
+	if (!hdcp->connection.is_km_stored) {
+		msg_in->process.msg2_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__AKE_SEND_PAIRING_INFO;
+		msg_in->process.msg2_desc.msg_size = TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_PAIRING_INFO;
+		memcpy(&msg_in->process.receiver_message[sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)],
+		       hdcp->auth.msg.hdcp2.ake_pairing_info, sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info));
+	}
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE;
+
+	if (msg_out->process.msg1_status != TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE;
+	else if (!hdcp->connection.is_km_stored &&
+		 msg_out->process.msg2_status != TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE;
+
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_lc_init(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__LC_INIT;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE;
+
+	memcpy(hdcp->auth.msg.hdcp2.lc_init, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.lc_init));
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_l_prime(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__LC_SEND_L_PRIME;
+	msg_in->process.msg1_desc.msg_size = TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__LC_SEND_L_PRIME;
+
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.lc_l_prime,
+	       sizeof(hdcp->auth.msg.hdcp2.lc_l_prime));
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE;
+
+	if (msg_out->process.msg1_status != TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE;
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_eks(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__SKE_SEND_EKS;
+
+	if (is_dp_hdcp(hdcp))
+		msg_in->prepare.msg2_id = TA_HDCP_HDCP2_MSG_ID__SIGNAL_CONTENT_STREAM_TYPE_DP;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_PREP_EKS_FAILURE;
+
+	memcpy(hdcp->auth.msg.hdcp2.ske_eks, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.ske_eks));
+	msg_out->prepare.msg1_desc.msg_size = sizeof(hdcp->auth.msg.hdcp2.ske_eks);
+
+	if (is_dp_hdcp(hdcp)) {
+		memcpy(hdcp->auth.msg.hdcp2.content_stream_type_dp,
+		       &msg_out->prepare.transmitter_message[sizeof(hdcp->auth.msg.hdcp2.ske_eks)],
+		       sizeof(hdcp->auth.msg.hdcp2.content_stream_type_dp));
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_enable_encryption(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct mod_hdcp_display *display = get_first_added_display(hdcp);
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	if (!display)
+		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+
+	hdcp_cmd->in_msg.hdcp1_enable_encryption.session_handle = hdcp->auth.id;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_SET_ENCRYPTION;
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE;
+
+	if (!is_dp_mst_hdcp(hdcp)) {
+		display->state = MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED;
+		HDCP_HDCP2_ENABLED_TRACE(hdcp, display->index);
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_rx_id_list(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_SEND_RECEIVERID_LIST;
+	msg_in->process.msg1_desc.msg_size = sizeof(hdcp->auth.msg.hdcp2.rx_id_list);
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.rx_id_list,
+	       sizeof(hdcp->auth.msg.hdcp2.rx_id_list));
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_SEND_ACK;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE;
+
+	memcpy(hdcp->auth.msg.hdcp2.repeater_auth_ack, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack));
+
+	if (msg_out->process.msg1_status == TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS) {
+		hdcp->connection.is_km_stored = msg_out->process.is_km_stored ? 1 : 0;
+		hdcp->connection.is_repeater = msg_out->process.is_repeater ? 1 : 0;
+		return MOD_HDCP_STATUS_SUCCESS;
+	}
+
+
+	return MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_enable_dp_stream_encryption(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	uint8_t i;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
+		if (hdcp->connection.displays[i].state != MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED ||
+		    hdcp->connection.displays[i].adjust.disable)
+			continue;
+		hdcp_cmd->in_msg.hdcp2_enable_dp_stream_encryption.display_handle = hdcp->connection.displays[i].index;
+		hdcp_cmd->in_msg.hdcp2_enable_dp_stream_encryption.session_handle = hdcp->auth.id;
+
+		hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_ENABLE_DP_STREAM_ENCRYPTION;
+		psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+		if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+			break;
+
+		hdcp->connection.displays[i].state = MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED;
+		HDCP_HDCP2_ENABLED_TRACE(hdcp, hdcp->connection.displays[i].index);
+	}
+
+	return (hdcp_cmd->hdcp_status == TA_HDCP_STATUS__SUCCESS) ? MOD_HDCP_STATUS_SUCCESS
+								  : MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_stream_management(struct mod_hdcp *hdcp)
+{
+
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_STREAM_MANAGE;
+
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_PREPARE_STREAM_MANAGEMENT_FAILURE;
+
+	hdcp->auth.msg.hdcp2.stream_manage_size = msg_out->prepare.msg1_desc.msg_size;
+
+	memcpy(hdcp->auth.msg.hdcp2.repeater_auth_stream_manage, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_manage));
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_stream_ready(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_STREAM_READY;
+
+	msg_in->process.msg1_desc.msg_size = sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready);
+
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.repeater_auth_stream_ready,
+	       sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready));
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	return (hdcp_cmd->hdcp_status == TA_HDCP_STATUS__SUCCESS) &&
+			       (msg_out->process.msg1_status == TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS)
+		       ? MOD_HDCP_STATUS_SUCCESS
+		       : MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_get_link_encryption_status(struct mod_hdcp *hdcp,
+							       enum mod_hdcp_encryption_status *encryption_status)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp2_get_encryption_status.session_handle = hdcp->auth.id;
+	hdcp_cmd->out_msg.hdcp2_get_encryption_status.protection_level = 0;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_GET_ENCRYPTION_STATUS;
+	*encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_FAILURE;
+
+	if (hdcp_cmd->out_msg.hdcp2_get_encryption_status.protection_level == 1) {
+		if (hdcp_cmd->out_msg.hdcp2_get_encryption_status.hdcp2_type == TA_HDCP2_CONTENT_TYPE__TYPE1)
+			*encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON;
+		else
+			*encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON;
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h
index 986fc07ea9ea..82a5e997d573 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h
@@ -36,6 +36,11 @@ enum bgd_security_hdcp_encryption_level {
 	HDCP_ENCRYPTION_LEVEL__ON
 };
 
+enum bgd_security_hdcp2_content_type {
+	HDCP2_CONTENT_TYPE__INVALID = 0,
+	HDCP2_CONTENT_TYPE__TYPE0,
+	HDCP2_CONTENT_TYPE__TYPE1
+};
 enum ta_dtm_command {
 	TA_DTM_COMMAND__UNUSED_1 = 1,
 	TA_DTM_COMMAND__TOPOLOGY_UPDATE_V2,
@@ -121,8 +126,64 @@ enum ta_hdcp_command {
 	TA_HDCP_COMMAND__HDCP1_ENABLE_ENCRYPTION,
 	TA_HDCP_COMMAND__HDCP1_ENABLE_DP_STREAM_ENCRYPTION,
 	TA_HDCP_COMMAND__HDCP1_GET_ENCRYPTION_STATUS,
+	TA_HDCP_COMMAND__UNUSED_1,
+	TA_HDCP_COMMAND__HDCP2_DESTROY_SESSION,
+	TA_HDCP_COMMAND__UNUSED_2,
+	TA_HDCP_COMMAND__HDCP2_SET_ENCRYPTION,
+	TA_HDCP_COMMAND__HDCP2_GET_ENCRYPTION_STATUS,
+	TA_HDCP_COMMAND__UNUSED_3,
+	TA_HDCP_COMMAND__HDCP2_CREATE_SESSION_V2,
+	TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2,
+	TA_HDCP_COMMAND__HDCP2_ENABLE_DP_STREAM_ENCRYPTION
+};
+
+enum ta_hdcp2_msg_id {
+	TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE = 1,
+	TA_HDCP_HDCP2_MSG_ID__AKE_INIT = 2,
+	TA_HDCP_HDCP2_MSG_ID__AKE_SEND_CERT = 3,
+	TA_HDCP_HDCP2_MSG_ID__AKE_NO_STORED_KM = 4,
+	TA_HDCP_HDCP2_MSG_ID__AKE_STORED_KM = 5,
+	TA_HDCP_HDCP2_MSG_ID__AKE_SEND_RRX = 6,
+	TA_HDCP_HDCP2_MSG_ID__AKE_SEND_H_PRIME = 7,
+	TA_HDCP_HDCP2_MSG_ID__AKE_SEND_PAIRING_INFO = 8,
+	TA_HDCP_HDCP2_MSG_ID__LC_INIT = 9,
+	TA_HDCP_HDCP2_MSG_ID__LC_SEND_L_PRIME = 10,
+	TA_HDCP_HDCP2_MSG_ID__SKE_SEND_EKS = 11,
+	TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_SEND_RECEIVERID_LIST = 12,
+	TA_HDCP_HDCP2_MSG_ID__RTT_READY = 13,
+	TA_HDCP_HDCP2_MSG_ID__RTT_CHALLENGE = 14,
+	TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_SEND_ACK = 15,
+	TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_STREAM_MANAGE = 16,
+	TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_STREAM_READY = 17,
+	TA_HDCP_HDCP2_MSG_ID__RECEIVER_AUTH_STATUS = 18,
+	TA_HDCP_HDCP2_MSG_ID__AKE_TRANSMITTER_INFO = 19,
+	TA_HDCP_HDCP2_MSG_ID__AKE_RECEIVER_INFO = 20,
+	TA_HDCP_HDCP2_MSG_ID__SIGNAL_CONTENT_STREAM_TYPE_DP = 129
 };
 
+enum ta_hdcp2_hdcp2_msg_id_max_size {
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__NULL_MESSAGE = 0,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_INIT = 12,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_CERT = 534,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_NO_STORED_KM = 129,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_STORED_KM = 33,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_RRX = 9,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_H_PRIME = 33,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_PAIRING_INFO = 17,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__LC_INIT = 9,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__LC_SEND_L_PRIME = 33,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__SKE_SEND_EKS = 25,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__REPEATERAUTH_SEND_RECEIVERID_LIST = 181,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__RTT_READY = 1,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__RTT_CHALLENGE = 17,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__REPEATERAUTH_SEND_RACK = 17,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__REPEATERAUTH_STREAM_MANAGE = 13,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__REPEATERAUTH_STREAM_READY = 33,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__RECEIVER_AUTH_STATUS = 4,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_TRANSMITTER_INFO = 6,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_RECEIVER_INFO = 6,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__SIGNAL_CONTENT_STREAM_TYPE_DP = 1
+};
 
 /* HDCP related enumerations */
 /**********************************************************/
@@ -131,6 +192,12 @@ enum ta_hdcp_command {
 #define TA_HDCP__HDCP1_KSV_SIZE 5
 #define TA_HDCP__HDCP1_KSV_LIST_MAX_ENTRIES 127
 #define TA_HDCP__HDCP1_V_PRIME_SIZE 20
+#define TA_HDCP__HDCP2_TX_BUF_MAX_SIZE                                                                                 \
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_NO_STORED_KM + TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_STORED_KM + 6
+
+// 64 bits boundaries
+#define TA_HDCP__HDCP2_RX_BUF_MAX_SIZE                                                                                 \
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_CERT + TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_RECEIVER_INFO + 4
 
 enum ta_hdcp_status {
 	TA_HDCP_STATUS__SUCCESS = 0x00,
@@ -165,9 +232,47 @@ enum ta_hdcp_authentication_status {
 	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_FIRST_PART_COMPLETE = 0x02,
 	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_SECOND_PART_FAILED = 0x03,
 	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_AUTHENTICATED = 0x04,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP22_AUTHENTICATION_PENDING = 0x06,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP22_AUTHENTICATION_FAILED = 0x07,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP22_AUTHENTICATED = 0x08,
 	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_KSV_VALIDATION_FAILED = 0x09
 };
 
+enum ta_hdcp2_msg_authentication_status {
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS = 0,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__KM_NOT_AVAILABLE,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__UNUSED,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID = 100, // everything above does not fail the request
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__NOT_ENOUGH_MEMORY,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__NOT_EXPECTED_MSG,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__SIGNATURE_CERTIFICAT_ERROR,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INCORRECT_HDCP_VERSION,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__UNKNOWN_MESSAGE,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_HMAC,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_TOPOLOGY,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_SEQ_NUM,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_SIZE,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_LENGTH,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__REAUTH_REQUEST
+};
+
+enum ta_hdcp_content_type {
+	TA_HDCP2_CONTENT_TYPE__TYPE0 = 1,
+	TA_HDCP2_CONTENT_TYPE__TYPE1,
+};
+
+enum ta_hdcp_content_type_negotiation_type {
+	TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__FORCE_TYPE0 = 1,
+	TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__FORCE_TYPE1,
+	TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__MAX_SUPPORTED
+};
+
+enum ta_hdcp2_version {
+	TA_HDCP2_VERSION_UNKNOWN = 0,
+	TA_HDCP2_VERSION_2_0 = 20,
+	TA_HDCP2_VERSION_2_1 = 21,
+	TA_HDCP2_VERSION_2_2 = 22
+};
 
 /* input/output structures for HDCP commands */
 /**********************************************************/
@@ -232,6 +337,84 @@ struct ta_hdcp_cmd_hdcp1_get_encryption_status_output {
 	uint32_t protection_level;
 };
 
+struct ta_hdcp_cmd_hdcp2_create_session_input_v2 {
+	uint32_t display_handle;
+	enum ta_hdcp_content_type_negotiation_type negotiate_content_type;
+};
+
+struct ta_hdcp_cmd_hdcp2_create_session_output_v2 {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp2_destroy_session_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp2_authentication_message_v2 {
+	enum ta_hdcp2_msg_id msg_id;
+	uint32_t msg_size;
+};
+
+struct ta_hdcp_cmd_hdcp2_process_authentication_message_input_v2 {
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg1_desc;
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg2_desc;
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg3_desc;
+	uint8_t receiver_message[TA_HDCP__HDCP2_RX_BUF_MAX_SIZE];
+};
+
+struct ta_hdcp_cmd_hdcp2_process_authentication_message_output_v2 {
+	uint32_t hdcp_version;
+	uint32_t is_km_stored;
+	uint32_t is_locality_precompute_support;
+	uint32_t is_repeater;
+	enum ta_hdcp2_msg_authentication_status msg1_status;
+	enum ta_hdcp2_msg_authentication_status msg2_status;
+	enum ta_hdcp2_msg_authentication_status msg3_status;
+};
+
+struct ta_hdcp_cmd_hdcp2_prepare_authentication_message_input_v2 {
+	enum ta_hdcp2_msg_id msg1_id;
+	enum ta_hdcp2_msg_id msg2_id;
+};
+
+struct ta_hdcp_cmd_hdcp2_prepare_authentication_message_output_v2 {
+	enum ta_hdcp2_msg_authentication_status msg1_status;
+	enum ta_hdcp2_msg_authentication_status msg2_status;
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg1_desc;
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg2_desc;
+	uint8_t transmitter_message[TA_HDCP__HDCP2_TX_BUF_MAX_SIZE];
+};
+
+struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 {
+	uint32_t session_handle;
+	struct ta_hdcp_cmd_hdcp2_process_authentication_message_input_v2 process;
+	struct ta_hdcp_cmd_hdcp2_prepare_authentication_message_input_v2 prepare;
+};
+
+struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 {
+	uint32_t authentication_status;
+	struct ta_hdcp_cmd_hdcp2_process_authentication_message_output_v2 process;
+	struct ta_hdcp_cmd_hdcp2_prepare_authentication_message_output_v2 prepare;
+};
+
+struct ta_hdcp_cmd_hdcp2_set_encryption_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp2_get_encryption_status_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp2_get_encryption_status_output {
+	enum ta_hdcp_content_type hdcp2_type;
+	uint32_t protection_level;
+};
+
+struct ta_hdcp_cmd_hdcp2_enable_dp_stream_encryption_input {
+	uint32_t session_handle;
+	uint32_t display_handle;
+};
+
 /**********************************************************/
 /* Common input structure for HDCP callbacks */
 union ta_hdcp_cmd_input {
@@ -242,6 +425,13 @@ union ta_hdcp_cmd_input {
 	struct ta_hdcp_cmd_hdcp1_enable_encryption_input hdcp1_enable_encryption;
 	struct ta_hdcp_cmd_hdcp1_enable_dp_stream_encryption_input hdcp1_enable_dp_stream_encryption;
 	struct ta_hdcp_cmd_hdcp1_get_encryption_status_input hdcp1_get_encryption_status;
+	struct ta_hdcp_cmd_hdcp2_destroy_session_input hdcp2_destroy_session;
+	struct ta_hdcp_cmd_hdcp2_set_encryption_input hdcp2_set_encryption;
+	struct ta_hdcp_cmd_hdcp2_get_encryption_status_input hdcp2_get_encryption_status;
+	struct ta_hdcp_cmd_hdcp2_create_session_input_v2 hdcp2_create_session_v2;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2
+		hdcp2_prepare_process_authentication_message_v2;
+	struct ta_hdcp_cmd_hdcp2_enable_dp_stream_encryption_input hdcp2_enable_dp_stream_encryption;
 };
 
 /* Common output structure for HDCP callbacks */
@@ -250,6 +440,10 @@ union ta_hdcp_cmd_output {
 	struct ta_hdcp_cmd_hdcp1_first_part_authentication_output hdcp1_first_part_authentication;
 	struct ta_hdcp_cmd_hdcp1_second_part_authentication_output hdcp1_second_part_authentication;
 	struct ta_hdcp_cmd_hdcp1_get_encryption_status_output hdcp1_get_encryption_status;
+	struct ta_hdcp_cmd_hdcp2_get_encryption_status_output hdcp2_get_encryption_status;
+	struct ta_hdcp_cmd_hdcp2_create_session_output_v2 hdcp2_create_session_v2;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2
+		hdcp2_prepare_process_authentication_message_v2;
 };
 /**********************************************************/
 
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
index dc187844d10b..dbe7835aabcf 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
@@ -92,6 +92,7 @@ struct mod_vrr_params_btr {
 	uint32_t inserted_duration_in_us;
 	uint32_t frames_to_insert;
 	uint32_t frame_counter;
+	uint32_t margin_in_us;
 };
 
 struct mod_vrr_params_fixed_refresh {
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
index dea21702edff..f2a0e1a064da 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
@@ -77,6 +77,7 @@ enum mod_hdcp_status {
 	MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING,
 	MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_AKE_CERT_REVOKED,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE,
 	MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE,
@@ -86,6 +87,7 @@ enum mod_hdcp_status {
 	MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE,
 	MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_REVOKED,
 	MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION,
 	MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE,
@@ -156,12 +158,18 @@ struct mod_hdcp_link_adjustment_hdcp1 {
 	uint8_t reserved		: 6;
 };
 
+enum mod_hdcp_force_hdcp_type {
+	MOD_HDCP_FORCE_TYPE_MAX = 0,
+	MOD_HDCP_FORCE_TYPE_0,
+	MOD_HDCP_FORCE_TYPE_1
+};
+
 struct mod_hdcp_link_adjustment_hdcp2 {
 	uint8_t disable			: 1;
-	uint8_t disable_type1		: 1;
+	uint8_t force_type		: 2;
 	uint8_t force_no_stored_km	: 1;
 	uint8_t increase_h_prime_timeout: 1;
-	uint8_t reserved		: 4;
+	uint8_t reserved		: 3;
 };
 
 struct mod_hdcp_link_adjustment {
@@ -184,7 +192,8 @@ enum mod_hdcp_encryption_status {
 	MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF = 0,
 	MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON,
 	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON,
-	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON
+	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON,
+	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_ON
 };
 
 /* per link events dm has to notify to hdcp module */
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
index ca8ce3c55337..42cbeffac640 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
@@ -26,6 +26,7 @@
 #ifndef MOD_INFO_PACKET_H_
 #define MOD_INFO_PACKET_H_
 
+#include "dm_services.h"
 #include "mod_shared.h"
 //Forward Declarations
 struct dc_stream_state;
@@ -33,7 +34,8 @@ struct dc_info_packet;
 struct mod_vrr_params;
 
 void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
-		struct dc_info_packet *info_packet);
+		struct dc_info_packet *info_packet,
+		bool *use_vsc_sdp_for_colorimetry);
 
 void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream,
 		struct dc_info_packet *info_packet, int ALLMEnabled, int ALLMValue);
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_shared.h b/drivers/gpu/drm/amd/display/modules/inc/mod_shared.h
index b45f7d65e76a..fe2117904329 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_shared.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_shared.h
@@ -45,7 +45,6 @@ enum vrr_packet_type {
 	PACKET_TYPE_VTEM
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 union lut3d_control_flags {
 	unsigned int raw;
 	struct {
@@ -104,6 +103,5 @@ struct lut3d_settings {
 	enum lut3d_control_gamut_map map2;
 	enum lut3d_control_rotation_mode rotation2;
 };
-#endif
 
 #endif /* MOD_SHARED_H_ */
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index db6b08f6d093..6a8a056424b8 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -30,6 +30,20 @@
 #include "mod_freesync.h"
 #include "dc.h"
 
+enum vsc_packet_revision {
+	vsc_packet_undefined = 0,
+	//01h = VSC SDP supports only 3D stereo.
+	vsc_packet_rev1 = 1,
+	//02h = 3D stereo + PSR.
+	vsc_packet_rev2 = 2,
+	//03h = 3D stereo + PSR2.
+	vsc_packet_rev3 = 3,
+	//04h = 3D stereo + PSR/PSR2 + Y-coordinate.
+	vsc_packet_rev4 = 4,
+	//05h = 3D stereo + PSR/PSR2 + Y-coordinate + Pixel Encoding/Colorimetry Format
+	vsc_packet_rev5 = 5,
+};
+
 #define HDMI_INFOFRAME_TYPE_VENDOR 0x81
 #define HF_VSIF_VERSION 1
 
@@ -116,35 +130,41 @@ enum ColorimetryYCCDP {
 };
 
 void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
-		struct dc_info_packet *info_packet)
+		struct dc_info_packet *info_packet,
+		bool *use_vsc_sdp_for_colorimetry)
 {
-	unsigned int vscPacketRevision = 0;
+	unsigned int vsc_packet_revision = vsc_packet_undefined;
 	unsigned int i;
 	unsigned int pixelEncoding = 0;
 	unsigned int colorimetryFormat = 0;
 	bool stereo3dSupport = false;
 
+	/* Initialize first, later if infopacket is valid determine if VSC SDP
+	 * should be used to signal colorimetry format and pixel encoding.
+	 */
+	*use_vsc_sdp_for_colorimetry = false;
+
 	if (stream->timing.timing_3d_format != TIMING_3D_FORMAT_NONE && stream->view_format != VIEW_3D_FORMAT_NONE) {
-		vscPacketRevision = 1;
+		vsc_packet_revision = vsc_packet_rev1;
 		stereo3dSupport = true;
 	}
 
 	/*VSC packet set to 2 when DP revision >= 1.2*/
 	if (stream->psr_version != 0)
-		vscPacketRevision = 2;
+		vsc_packet_revision = vsc_packet_rev2;
 
 	/* Update to revision 5 for extended colorimetry support for DPCD 1.4+ */
 	if (stream->link->dpcd_caps.dpcd_rev.raw >= 0x14 &&
 			stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED)
-		vscPacketRevision = 5;
+		vsc_packet_revision = vsc_packet_rev5;
 
 	/* VSC packet not needed based on the features
 	 * supported by this DP display
 	 */
-	if (vscPacketRevision == 0)
+	if (vsc_packet_revision == vsc_packet_undefined)
 		return;
 
-	if (vscPacketRevision == 0x2) {
+	if (vsc_packet_revision == vsc_packet_rev2) {
 		/* Secondary-data Packet ID = 0*/
 		info_packet->hb0 = 0x00;
 		/* 07h - Packet Type Value indicating Video
@@ -166,7 +186,7 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 		info_packet->valid = true;
 	}
 
-	if (vscPacketRevision == 0x1) {
+	if (vsc_packet_revision == vsc_packet_rev1) {
 
 		info_packet->hb0 = 0x00;	// Secondary-data Packet ID = 0
 		info_packet->hb1 = 0x07;	// 07h = Packet Type Value indicating Video Stream Configuration packet
@@ -237,7 +257,7 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 	 *   the Pixel Encoding/Colorimetry Format and that a Sink device must ignore MISC1, bit 7, and
 	 *   MISC0, bits 7:1 (MISC1, bit 7. and MISC0, bits 7:1 become "don't care").)
 	 */
-	if (vscPacketRevision == 0x5) {
+	if (vsc_packet_revision == vsc_packet_rev5) {
 		/* Secondary-data Packet ID = 0 */
 		info_packet->hb0 = 0x00;
 		/* 07h - Packet Type Value indicating Video Stream Configuration packet */
@@ -249,6 +269,13 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 
 		info_packet->valid = true;
 
+		/* If we are using VSC SDP revision 05h, use this to signal for
+		 * colorimetry format and pixel encoding. HW should later be
+		 * programmed to set MSA MISC1 bit 6 to indicate ignore
+		 * colorimetry format and pixel encoding in the MSA.
+		 */
+		*use_vsc_sdp_for_colorimetry = true;
+
 		/* Set VSC SDP fields for pixel encoding and colorimetry format from DP 1.3 specs
 		 * Data Bytes DB 18~16
 		 * Bits 3:0 (Colorimetry Format)        |  Bits 7:4 (Pixel Encoding)
@@ -393,7 +420,6 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 		 */
 		info_packet->sb[18] = 0;
 	}
-
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index 4e2f615c3566..e75a4bb94488 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -662,7 +662,11 @@ bool dmcu_load_iram(struct dmcu *dmcu,
 
 	memset(&ram_table, 0, sizeof(ram_table));
 
-	if (dmcu->dmcu_version.abm_version == 0x23) {
+	if (dmcu->dmcu_version.abm_version == 0x24) {
+		fill_iram_v_2_3((struct iram_table_v_2_2 *)ram_table, params);
+		result = dmcu->funcs->load_iram(
+				dmcu, 0, (char *)(&ram_table), IRAM_RESERVE_AREA_START_V2_2);
+	} else if (dmcu->dmcu_version.abm_version == 0x23) {
 		fill_iram_v_2_3((struct iram_table_v_2_2 *)ram_table, params);
 
 		result = dmcu->funcs->load_iram(
@@ -687,3 +691,4 @@ bool dmcu_load_iram(struct dmcu *dmcu,
 
 	return result;
 }
+
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index dc7eb28f0296..d655a76bedc6 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -53,7 +53,8 @@ enum amd_ip_block_type {
 	AMD_IP_BLOCK_TYPE_VCE,
 	AMD_IP_BLOCK_TYPE_ACP,
 	AMD_IP_BLOCK_TYPE_VCN,
-	AMD_IP_BLOCK_TYPE_MES
+	AMD_IP_BLOCK_TYPE_MES,
+	AMD_IP_BLOCK_TYPE_JPEG
 };
 
 enum amd_clockgating_state {
@@ -99,6 +100,7 @@ enum amd_powergating_state {
 #define AMD_CG_SUPPORT_IH_CG			(1 << 27)
 #define AMD_CG_SUPPORT_ATHUB_LS			(1 << 28)
 #define AMD_CG_SUPPORT_ATHUB_MGCG		(1 << 29)
+#define AMD_CG_SUPPORT_JPEG_MGCG		(1 << 30)
 /* PG flags */
 #define AMD_PG_SUPPORT_GFX_PG			(1 << 0)
 #define AMD_PG_SUPPORT_GFX_SMG			(1 << 1)
@@ -117,6 +119,7 @@ enum amd_powergating_state {
 #define AMD_PG_SUPPORT_VCN			(1 << 14)
 #define AMD_PG_SUPPORT_VCN_DPG			(1 << 15)
 #define AMD_PG_SUPPORT_ATHUB			(1 << 16)
+#define AMD_PG_SUPPORT_JPEG			(1 << 17)
 
 enum PP_FEATURE_MASK {
 	PP_SCLK_DPM_MASK = 0x1,
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_offset.h
index cff8f91555d3..e9b2bd84cfed 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_offset.h
@@ -8134,6 +8134,10 @@
 #define mmMPC_OUT5_CSC_C33_C34_B                                                                       0x1604
 #define mmMPC_OUT5_CSC_C33_C34_B_BASE_IDX                                                              2
 
+#define mmMPC_OCSC_TEST_DEBUG_INDEX                                                                    0x163b
+#define mmMPC_OCSC_TEST_DEBUG_INDEX_BASE_IDX                                                           2
+#define mmMPC_OCSC_TEST_DEBUG_DATA_BASE_IDX                                                            2
+#define mmMPC_OCSC_TEST_DEBUG_DATA                                                                     0x163c
 
 // addressBlock: dce_dc_mpc_mpc_dcperfmon_dc_perfmon_dispdec
 // base address: 0x5964
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_sh_mask.h
index 10c83fecd147..dc8ce7aaa0cf 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_sh_mask.h
@@ -28263,7 +28263,14 @@
 #define MPC_OUT5_CSC_C33_C34_B__MPC_OCSC_C34_B__SHIFT                                                         0x10
 #define MPC_OUT5_CSC_C33_C34_B__MPC_OCSC_C33_B_MASK                                                           0x0000FFFFL
 #define MPC_OUT5_CSC_C33_C34_B__MPC_OCSC_C34_B_MASK                                                           0xFFFF0000L
-
+//MPC_OCSC_TEST_DEBUG_INDEX
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_INDEX__SHIFT                                           0x0
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_WRITE_EN__SHIFT                                        0x8
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_INDEX_MASK                                             0x000000FFL
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_WRITE_EN_MASK                                          0x00000100L
+//MPC_OCSC_TEST_DEBUG_DATA
+#define MPC_OCSC_TEST_DEBUG_DATA__MPC_OCSC_TEST_DEBUG_DATA__SHIFT                                             0x0
+#define MPC_OCSC_TEST_DEBUG_DATA__MPC_OCSC_TEST_DEBUG_DATA_MASK                                               0xFFFFFFFFL
 
 // addressBlock: dce_dc_mpc_mpc_dcperfmon_dc_perfmon_dispdec
 //DC_PERFMON17_PERFCOUNTER_CNTL
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
index eddf83ec1c39..7cd0ee61c030 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
@@ -7103,7 +7103,10 @@
 #define mmMPC_OUT3_CSC_C31_C32_B_BASE_IDX                                                              2
 #define mmMPC_OUT3_CSC_C33_C34_B                                                                       0x15ea
 #define mmMPC_OUT3_CSC_C33_C34_B_BASE_IDX                                                              2
-
+#define mmMPC_OCSC_TEST_DEBUG_INDEX                                                                    0x163b
+#define mmMPC_OCSC_TEST_DEBUG_INDEX_BASE_IDX                                                           2
+#define mmMPC_OCSC_TEST_DEBUG_DATA_BASE_IDX                                                            2
+#define mmMPC_OCSC_TEST_DEBUG_DATA                                                                     0x163c
 
 // addressBlock: dce_dc_mpc_mpc_dcperfmon_dc_perfmon_dispdec
 // base address: 0x5964
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_sh_mask.h
index faa0e76e32b4..2f780aefc722 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_sh_mask.h
@@ -56634,5 +56634,13 @@
 #define AZF0INPUTENDPOINT7_AZALIA_F0_CODEC_INPUT_PIN_CONTROL_INFOFRAME__INFOFRAME_BYTE_5_MASK                 0x00FF0000L
 #define AZF0INPUTENDPOINT7_AZALIA_F0_CODEC_INPUT_PIN_CONTROL_INFOFRAME__INFOFRAME_VALID_MASK                  0x80000000L
 
+//MPC_OCSC_TEST_DEBUG_INDEX
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_INDEX__SHIFT                                           0x0
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_WRITE_EN__SHIFT                                        0x8
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_INDEX_MASK                                             0x000000FFL
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_WRITE_EN_MASK                                          0x00000100L
+//MPC_OCSC_TEST_DEBUG_DATA
+#define MPC_OCSC_TEST_DEBUG_DATA__MPC_OCSC_TEST_DEBUG_DATA__SHIFT                                             0x0
+#define MPC_OCSC_TEST_DEBUG_DATA__MPC_OCSC_TEST_DEBUG_DATA_MASK                                               0xFFFFFFFFL
 
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h
index c2bd25589e84..87c84691b5be 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h
@@ -27,6 +27,9 @@
 #define mmDF_PIE_AON0_DfGlobalClkGater									0x00fc
 #define mmDF_PIE_AON0_DfGlobalClkGater_BASE_IDX								0
 
+#define mmDF_CS_UMC_AON0_DfGlobalCtrl									0x00fe
+#define mmDF_CS_UMC_AON0_DfGlobalCtrl_BASE_IDX								0
+
 #define mmDF_CS_UMC_AON0_DramBaseAddress0								0x0044
 #define mmDF_CS_UMC_AON0_DramBaseAddress0_BASE_IDX							0
 
@@ -38,6 +41,14 @@
 #define smnPerfMonCtlHi2					0x01d464UL
 #define smnPerfMonCtlLo3					0x01d470UL
 #define smnPerfMonCtlHi3					0x01d474UL
+#define smnPerfMonCtlLo4					0x01d880UL
+#define smnPerfMonCtlHi4					0x01d884UL
+#define smnPerfMonCtlLo5					0x01d888UL
+#define smnPerfMonCtlHi5					0x01d88cUL
+#define smnPerfMonCtlLo6					0x01d890UL
+#define smnPerfMonCtlHi6					0x01d894UL
+#define smnPerfMonCtlLo7					0x01d898UL
+#define smnPerfMonCtlHi7					0x01d89cUL
 
 #define smnPerfMonCtrLo0					0x01d448UL
 #define smnPerfMonCtrHi0					0x01d44cUL
@@ -47,6 +58,14 @@
 #define smnPerfMonCtrHi2					0x01d46cUL
 #define smnPerfMonCtrLo3					0x01d478UL
 #define smnPerfMonCtrHi3					0x01d47cUL
+#define smnPerfMonCtrLo4					0x01d790UL
+#define smnPerfMonCtrHi4					0x01d794UL
+#define smnPerfMonCtrLo5					0x01d798UL
+#define smnPerfMonCtrHi5					0x01d79cUL
+#define smnPerfMonCtrLo6					0x01d7a0UL
+#define smnPerfMonCtrHi6					0x01d7a4UL
+#define smnPerfMonCtrLo7					0x01d7a8UL
+#define smnPerfMonCtrHi7					0x01d7acUL
 
 #define smnDF_PIE_AON_FabricIndirectConfigAccessAddress3	0x1d05cUL
 #define smnDF_PIE_AON_FabricIndirectConfigAccessDataLo3		0x1d098UL
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h
index 06fac509e987..65e9f756e86e 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h
@@ -33,6 +33,14 @@
 #define DF_PIE_AON0_DfGlobalClkGater__MGCGMode__SHIFT							0x0
 #define DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK							0x0000000FL
 
+/* DF_CS_UMC_AON0_DfGlobalCtrl */
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl64K__SHIFT						0x14
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl2M__SHIFT						0x15
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl1G__SHIFT						0x16
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl64K_MASK						0x00100000L
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl2M_MASK						0x00200000L
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl1G_MASK						0x00400000L
+
 /* DF_CS_AON0_DramBaseAddress0 */
 #define DF_CS_UMC_AON0_DramBaseAddress0__AddrRngVal__SHIFT						0x0
 #define DF_CS_UMC_AON0_DramBaseAddress0__LgcyMmioHoleEn__SHIFT						0x1
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_offset.h
new file mode 100644
index 000000000000..36ae5b7fe88e
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_offset.h
@@ -0,0 +1,647 @@
+/*
+ * Copyright (C) 2019  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) 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 _dpcs_2_0_0_OFFSET_HEADER
+#define _dpcs_2_0_0_OFFSET_HEADER
+
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx0_dispdec
+// base address: 0x0
+#define mmDPCSTX0_DPCSTX_TX_CLOCK_CNTL                                                                 0x2928
+#define mmDPCSTX0_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX0_DPCSTX_TX_CNTL                                                                       0x2929
+#define mmDPCSTX0_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX0_DPCSTX_CBUS_CNTL                                                                     0x292a
+#define mmDPCSTX0_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX0_DPCSTX_INTERRUPT_CNTL                                                                0x292b
+#define mmDPCSTX0_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX0_DPCSTX_PLL_UPDATE_ADDR                                                               0x292c
+#define mmDPCSTX0_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX0_DPCSTX_PLL_UPDATE_DATA                                                               0x292d
+#define mmDPCSTX0_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX0_DPCSTX_DEBUG_CONFIG                                                                  0x292e
+#define mmDPCSTX0_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx0_dispdec
+// base address: 0x0
+#define mmRDPCSTX0_RDPCSTX_CNTL                                                                        0x2930
+#define mmRDPCSTX0_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX0_RDPCSTX_CLOCK_CNTL                                                                  0x2931
+#define mmRDPCSTX0_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_INTERRUPT_CONTROL                                                           0x2932
+#define mmRDPCSTX0_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX0_RDPCSTX_PLL_UPDATE_DATA                                                             0x2933
+#define mmRDPCSTX0_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX0_RDPCS_TX_CR_ADDR                                                                    0x2934
+#define mmRDPCSTX0_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX0_RDPCS_TX_CR_DATA                                                                    0x2935
+#define mmRDPCSTX0_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX0_RDPCS_TX_SRAM_CNTL                                                                  0x2936
+#define mmRDPCSTX0_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_MEM_POWER_CTRL                                                              0x2937
+#define mmRDPCSTX0_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX0_RDPCSTX_MEM_POWER_CTRL2                                                             0x2938
+#define mmRDPCSTX0_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX0_RDPCSTX_SCRATCH                                                                     0x2939
+#define mmRDPCSTX0_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x293c
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX0_RDPCSTX_DEBUG_CONFIG                                                                0x293d
+#define mmRDPCSTX0_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL0                                                                   0x2940
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL1                                                                   0x2941
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL2                                                                   0x2942
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL3                                                                   0x2943
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL4                                                                   0x2944
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL5                                                                   0x2945
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL6                                                                   0x2946
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL7                                                                   0x2947
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL8                                                                   0x2948
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL9                                                                   0x2949
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL10                                                                  0x294a
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL11                                                                  0x294b
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL12                                                                  0x294c
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL13                                                                  0x294d
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL14                                                                  0x294e
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE0                                                                   0x294f
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE1                                                                   0x2950
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE2                                                                   0x2951
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE3                                                                   0x2952
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_RX_LD_VAL                                                               0x2953
+#define mmRDPCSTX0_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2954
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2955
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX0_RDPCSTX_DPALT_CONTROL_REG                                                           0x2956
+#define mmRDPCSTX0_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr0_dispdec
+// base address: 0x0
+#define mmDPCSSYS_CR0_DPCSSYS_CR_ADDR                                                                  0x2934
+#define mmDPCSSYS_CR0_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR0_DPCSSYS_CR_DATA                                                                  0x2935
+#define mmDPCSSYS_CR0_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx1_dispdec
+// base address: 0x360
+#define mmDPCSTX1_DPCSTX_TX_CLOCK_CNTL                                                                 0x2a00
+#define mmDPCSTX1_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX1_DPCSTX_TX_CNTL                                                                       0x2a01
+#define mmDPCSTX1_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX1_DPCSTX_CBUS_CNTL                                                                     0x2a02
+#define mmDPCSTX1_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX1_DPCSTX_INTERRUPT_CNTL                                                                0x2a03
+#define mmDPCSTX1_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX1_DPCSTX_PLL_UPDATE_ADDR                                                               0x2a04
+#define mmDPCSTX1_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX1_DPCSTX_PLL_UPDATE_DATA                                                               0x2a05
+#define mmDPCSTX1_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX1_DPCSTX_DEBUG_CONFIG                                                                  0x2a06
+#define mmDPCSTX1_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx1_dispdec
+// base address: 0x360
+#define mmRDPCSTX1_RDPCSTX_CNTL                                                                        0x2a08
+#define mmRDPCSTX1_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX1_RDPCSTX_CLOCK_CNTL                                                                  0x2a09
+#define mmRDPCSTX1_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_INTERRUPT_CONTROL                                                           0x2a0a
+#define mmRDPCSTX1_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX1_RDPCSTX_PLL_UPDATE_DATA                                                             0x2a0b
+#define mmRDPCSTX1_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX1_RDPCS_TX_CR_ADDR                                                                    0x2a0c
+#define mmRDPCSTX1_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX1_RDPCS_TX_CR_DATA                                                                    0x2a0d
+#define mmRDPCSTX1_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX1_RDPCS_TX_SRAM_CNTL                                                                  0x2a0e
+#define mmRDPCSTX1_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_MEM_POWER_CTRL                                                              0x2a0f
+#define mmRDPCSTX1_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX1_RDPCSTX_MEM_POWER_CTRL2                                                             0x2a10
+#define mmRDPCSTX1_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX1_RDPCSTX_SCRATCH                                                                     0x2a11
+#define mmRDPCSTX1_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2a14
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX1_RDPCSTX_DEBUG_CONFIG                                                                0x2a15
+#define mmRDPCSTX1_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL0                                                                   0x2a18
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL1                                                                   0x2a19
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL2                                                                   0x2a1a
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL3                                                                   0x2a1b
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL4                                                                   0x2a1c
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL5                                                                   0x2a1d
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL6                                                                   0x2a1e
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL7                                                                   0x2a1f
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL8                                                                   0x2a20
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL9                                                                   0x2a21
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL10                                                                  0x2a22
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL11                                                                  0x2a23
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL12                                                                  0x2a24
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL13                                                                  0x2a25
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL14                                                                  0x2a26
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE0                                                                   0x2a27
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE1                                                                   0x2a28
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE2                                                                   0x2a29
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE3                                                                   0x2a2a
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_RX_LD_VAL                                                               0x2a2b
+#define mmRDPCSTX1_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2a2c
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2a2d
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX1_RDPCSTX_DPALT_CONTROL_REG                                                           0x2a2e
+#define mmRDPCSTX1_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr1_dispdec
+// base address: 0x360
+#define mmDPCSSYS_CR1_DPCSSYS_CR_ADDR                                                                  0x2a0c
+#define mmDPCSSYS_CR1_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR1_DPCSSYS_CR_DATA                                                                  0x2a0d
+#define mmDPCSSYS_CR1_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx2_dispdec
+// base address: 0x6c0
+#define mmDPCSTX2_DPCSTX_TX_CLOCK_CNTL                                                                 0x2ad8
+#define mmDPCSTX2_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX2_DPCSTX_TX_CNTL                                                                       0x2ad9
+#define mmDPCSTX2_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX2_DPCSTX_CBUS_CNTL                                                                     0x2ada
+#define mmDPCSTX2_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX2_DPCSTX_INTERRUPT_CNTL                                                                0x2adb
+#define mmDPCSTX2_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX2_DPCSTX_PLL_UPDATE_ADDR                                                               0x2adc
+#define mmDPCSTX2_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX2_DPCSTX_PLL_UPDATE_DATA                                                               0x2add
+#define mmDPCSTX2_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX2_DPCSTX_DEBUG_CONFIG                                                                  0x2ade
+#define mmDPCSTX2_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx2_dispdec
+// base address: 0x6c0
+#define mmRDPCSTX2_RDPCSTX_CNTL                                                                        0x2ae0
+#define mmRDPCSTX2_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX2_RDPCSTX_CLOCK_CNTL                                                                  0x2ae1
+#define mmRDPCSTX2_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_INTERRUPT_CONTROL                                                           0x2ae2
+#define mmRDPCSTX2_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX2_RDPCSTX_PLL_UPDATE_DATA                                                             0x2ae3
+#define mmRDPCSTX2_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX2_RDPCS_TX_CR_ADDR                                                                    0x2ae4
+#define mmRDPCSTX2_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX2_RDPCS_TX_CR_DATA                                                                    0x2ae5
+#define mmRDPCSTX2_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX2_RDPCS_TX_SRAM_CNTL                                                                  0x2ae6
+#define mmRDPCSTX2_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_MEM_POWER_CTRL                                                              0x2ae7
+#define mmRDPCSTX2_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX2_RDPCSTX_MEM_POWER_CTRL2                                                             0x2ae8
+#define mmRDPCSTX2_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX2_RDPCSTX_SCRATCH                                                                     0x2ae9
+#define mmRDPCSTX2_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2aec
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX2_RDPCSTX_DEBUG_CONFIG                                                                0x2aed
+#define mmRDPCSTX2_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL0                                                                   0x2af0
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL1                                                                   0x2af1
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL2                                                                   0x2af2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL3                                                                   0x2af3
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL4                                                                   0x2af4
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL5                                                                   0x2af5
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL6                                                                   0x2af6
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL7                                                                   0x2af7
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL8                                                                   0x2af8
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL9                                                                   0x2af9
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL10                                                                  0x2afa
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL11                                                                  0x2afb
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL12                                                                  0x2afc
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL13                                                                  0x2afd
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL14                                                                  0x2afe
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE0                                                                   0x2aff
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE1                                                                   0x2b00
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE2                                                                   0x2b01
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE3                                                                   0x2b02
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_RX_LD_VAL                                                               0x2b03
+#define mmRDPCSTX2_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2b04
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2b05
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX2_RDPCSTX_DPALT_CONTROL_REG                                                           0x2b06
+#define mmRDPCSTX2_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr2_dispdec
+// base address: 0x6c0
+#define mmDPCSSYS_CR2_DPCSSYS_CR_ADDR                                                                  0x2ae4
+#define mmDPCSSYS_CR2_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR2_DPCSSYS_CR_DATA                                                                  0x2ae5
+#define mmDPCSSYS_CR2_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx3_dispdec
+// base address: 0xa20
+#define mmDPCSTX3_DPCSTX_TX_CLOCK_CNTL                                                                 0x2bb0
+#define mmDPCSTX3_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX3_DPCSTX_TX_CNTL                                                                       0x2bb1
+#define mmDPCSTX3_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX3_DPCSTX_CBUS_CNTL                                                                     0x2bb2
+#define mmDPCSTX3_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX3_DPCSTX_INTERRUPT_CNTL                                                                0x2bb3
+#define mmDPCSTX3_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX3_DPCSTX_PLL_UPDATE_ADDR                                                               0x2bb4
+#define mmDPCSTX3_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX3_DPCSTX_PLL_UPDATE_DATA                                                               0x2bb5
+#define mmDPCSTX3_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX3_DPCSTX_DEBUG_CONFIG                                                                  0x2bb6
+#define mmDPCSTX3_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx3_dispdec
+// base address: 0xa20
+#define mmRDPCSTX3_RDPCSTX_CNTL                                                                        0x2bb8
+#define mmRDPCSTX3_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX3_RDPCSTX_CLOCK_CNTL                                                                  0x2bb9
+#define mmRDPCSTX3_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_INTERRUPT_CONTROL                                                           0x2bba
+#define mmRDPCSTX3_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX3_RDPCSTX_PLL_UPDATE_DATA                                                             0x2bbb
+#define mmRDPCSTX3_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX3_RDPCS_TX_CR_ADDR                                                                    0x2bbc
+#define mmRDPCSTX3_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX3_RDPCS_TX_CR_DATA                                                                    0x2bbd
+#define mmRDPCSTX3_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX3_RDPCS_TX_SRAM_CNTL                                                                  0x2bbe
+#define mmRDPCSTX3_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_MEM_POWER_CTRL                                                              0x2bbf
+#define mmRDPCSTX3_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX3_RDPCSTX_MEM_POWER_CTRL2                                                             0x2bc0
+#define mmRDPCSTX3_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX3_RDPCSTX_SCRATCH                                                                     0x2bc1
+#define mmRDPCSTX3_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2bc4
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX3_RDPCSTX_DEBUG_CONFIG                                                                0x2bc5
+#define mmRDPCSTX3_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL0                                                                   0x2bc8
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL1                                                                   0x2bc9
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL2                                                                   0x2bca
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL3                                                                   0x2bcb
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL4                                                                   0x2bcc
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL5                                                                   0x2bcd
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL6                                                                   0x2bce
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL7                                                                   0x2bcf
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL8                                                                   0x2bd0
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL9                                                                   0x2bd1
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL10                                                                  0x2bd2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL11                                                                  0x2bd3
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL12                                                                  0x2bd4
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL13                                                                  0x2bd5
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL14                                                                  0x2bd6
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE0                                                                   0x2bd7
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE1                                                                   0x2bd8
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE2                                                                   0x2bd9
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE3                                                                   0x2bda
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_RX_LD_VAL                                                               0x2bdb
+#define mmRDPCSTX3_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2bdc
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2bdd
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX3_RDPCSTX_DPALT_CONTROL_REG                                                           0x2bde
+#define mmRDPCSTX3_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr3_dispdec
+// base address: 0xa20
+#define mmDPCSSYS_CR3_DPCSSYS_CR_ADDR                                                                  0x2bbc
+#define mmDPCSSYS_CR3_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR3_DPCSSYS_CR_DATA                                                                  0x2bbd
+#define mmDPCSSYS_CR3_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcsrx_dispdec
+// base address: 0x0
+#define mmDPCSRX_PHY_CNTL                                                                              0x2c76
+#define mmDPCSRX_PHY_CNTL_BASE_IDX                                                                     2
+#define mmDPCSRX_RX_CLOCK_CNTL                                                                         0x2c78
+#define mmDPCSRX_RX_CLOCK_CNTL_BASE_IDX                                                                2
+#define mmDPCSRX_RX_CNTL                                                                               0x2c7a
+#define mmDPCSRX_RX_CNTL_BASE_IDX                                                                      2
+#define mmDPCSRX_CBUS_CNTL                                                                             0x2c7b
+#define mmDPCSRX_CBUS_CNTL_BASE_IDX                                                                    2
+#define mmDPCSRX_REG_ERROR_STATUS                                                                      0x2c7c
+#define mmDPCSRX_REG_ERROR_STATUS_BASE_IDX                                                             2
+#define mmDPCSRX_RX_ERROR_STATUS                                                                       0x2c7d
+#define mmDPCSRX_RX_ERROR_STATUS_BASE_IDX                                                              2
+#define mmDPCSRX_INDEX_MODE_ADDR                                                                       0x2c80
+#define mmDPCSRX_INDEX_MODE_ADDR_BASE_IDX                                                              2
+#define mmDPCSRX_INDEX_MODE_DATA                                                                       0x2c81
+#define mmDPCSRX_INDEX_MODE_DATA_BASE_IDX                                                              2
+#define mmDPCSRX_DEBUG_CONFIG                                                                          0x2c82
+#define mmDPCSRX_DEBUG_CONFIG_BASE_IDX                                                                 2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx4_dispdec
+// base address: 0xd80
+#define mmDPCSTX4_DPCSTX_TX_CLOCK_CNTL                                                                 0x2c88
+#define mmDPCSTX4_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX4_DPCSTX_TX_CNTL                                                                       0x2c89
+#define mmDPCSTX4_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX4_DPCSTX_CBUS_CNTL                                                                     0x2c8a
+#define mmDPCSTX4_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX4_DPCSTX_INTERRUPT_CNTL                                                                0x2c8b
+#define mmDPCSTX4_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX4_DPCSTX_PLL_UPDATE_ADDR                                                               0x2c8c
+#define mmDPCSTX4_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX4_DPCSTX_PLL_UPDATE_DATA                                                               0x2c8d
+#define mmDPCSTX4_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX4_DPCSTX_DEBUG_CONFIG                                                                  0x2c8e
+#define mmDPCSTX4_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx4_dispdec
+// base address: 0xd80
+#define mmRDPCSTX4_RDPCSTX_CNTL                                                                        0x2c90
+#define mmRDPCSTX4_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX4_RDPCSTX_CLOCK_CNTL                                                                  0x2c91
+#define mmRDPCSTX4_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_INTERRUPT_CONTROL                                                           0x2c92
+#define mmRDPCSTX4_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX4_RDPCSTX_PLL_UPDATE_DATA                                                             0x2c93
+#define mmRDPCSTX4_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX4_RDPCS_TX_CR_ADDR                                                                    0x2c94
+#define mmRDPCSTX4_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX4_RDPCS_TX_CR_DATA                                                                    0x2c95
+#define mmRDPCSTX4_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX4_RDPCS_TX_SRAM_CNTL                                                                  0x2c96
+#define mmRDPCSTX4_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_MEM_POWER_CTRL                                                              0x2c97
+#define mmRDPCSTX4_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX4_RDPCSTX_MEM_POWER_CTRL2                                                             0x2c98
+#define mmRDPCSTX4_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX4_RDPCSTX_SCRATCH                                                                     0x2c99
+#define mmRDPCSTX4_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2c9c
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX4_RDPCSTX_DEBUG_CONFIG                                                                0x2c9d
+#define mmRDPCSTX4_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL0                                                                   0x2ca0
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL1                                                                   0x2ca1
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL2                                                                   0x2ca2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL3                                                                   0x2ca3
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL4                                                                   0x2ca4
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL5                                                                   0x2ca5
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL6                                                                   0x2ca6
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL7                                                                   0x2ca7
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL8                                                                   0x2ca8
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL9                                                                   0x2ca9
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL10                                                                  0x2caa
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL11                                                                  0x2cab
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL12                                                                  0x2cac
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL13                                                                  0x2cad
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL14                                                                  0x2cae
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE0                                                                   0x2caf
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE1                                                                   0x2cb0
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE2                                                                   0x2cb1
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE3                                                                   0x2cb2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_RX_LD_VAL                                                               0x2cb3
+#define mmRDPCSTX4_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2cb4
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2cb5
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX4_RDPCSTX_DPALT_CONTROL_REG                                                           0x2cb6
+#define mmRDPCSTX4_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr4_dispdec
+// base address: 0xd80
+#define mmDPCSSYS_CR4_DPCSSYS_CR_ADDR                                                                  0x2c94
+#define mmDPCSSYS_CR4_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR4_DPCSSYS_CR_DATA                                                                  0x2c95
+#define mmDPCSSYS_CR4_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx5_dispdec
+// base address: 0x10e0
+#define mmDPCSTX5_DPCSTX_TX_CLOCK_CNTL                                                                 0x2d60
+#define mmDPCSTX5_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX5_DPCSTX_TX_CNTL                                                                       0x2d61
+#define mmDPCSTX5_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX5_DPCSTX_CBUS_CNTL                                                                     0x2d62
+#define mmDPCSTX5_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX5_DPCSTX_INTERRUPT_CNTL                                                                0x2d63
+#define mmDPCSTX5_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX5_DPCSTX_PLL_UPDATE_ADDR                                                               0x2d64
+#define mmDPCSTX5_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX5_DPCSTX_PLL_UPDATE_DATA                                                               0x2d65
+#define mmDPCSTX5_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX5_DPCSTX_DEBUG_CONFIG                                                                  0x2d66
+#define mmDPCSTX5_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx5_dispdec
+// base address: 0x10e0
+#define mmRDPCSTX5_RDPCSTX_CNTL                                                                        0x2d68
+#define mmRDPCSTX5_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX5_RDPCSTX_CLOCK_CNTL                                                                  0x2d69
+#define mmRDPCSTX5_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_INTERRUPT_CONTROL                                                           0x2d6a
+#define mmRDPCSTX5_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX5_RDPCSTX_PLL_UPDATE_DATA                                                             0x2d6b
+#define mmRDPCSTX5_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX5_RDPCS_TX_CR_ADDR                                                                    0x2d6c
+#define mmRDPCSTX5_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX5_RDPCS_TX_CR_DATA                                                                    0x2d6d
+#define mmRDPCSTX5_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX5_RDPCS_TX_SRAM_CNTL                                                                  0x2d6e
+#define mmRDPCSTX5_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_MEM_POWER_CTRL                                                              0x2d6f
+#define mmRDPCSTX5_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX5_RDPCSTX_MEM_POWER_CTRL2                                                             0x2d70
+#define mmRDPCSTX5_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX5_RDPCSTX_SCRATCH                                                                     0x2d71
+#define mmRDPCSTX5_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2d74
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX5_RDPCSTX_DEBUG_CONFIG                                                                0x2d75
+#define mmRDPCSTX5_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL0                                                                   0x2d78
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL1                                                                   0x2d79
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL2                                                                   0x2d7a
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL3                                                                   0x2d7b
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL4                                                                   0x2d7c
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL5                                                                   0x2d7d
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL6                                                                   0x2d7e
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL7                                                                   0x2d7f
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL8                                                                   0x2d80
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL9                                                                   0x2d81
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL10                                                                  0x2d82
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL11                                                                  0x2d83
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL12                                                                  0x2d84
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL13                                                                  0x2d85
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL14                                                                  0x2d86
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE0                                                                   0x2d87
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE1                                                                   0x2d88
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE2                                                                   0x2d89
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE3                                                                   0x2d8a
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_RX_LD_VAL                                                               0x2d8b
+#define mmRDPCSTX5_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2d8c
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2d8d
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX5_RDPCSTX_DPALT_CONTROL_REG                                                           0x2d8e
+#define mmRDPCSTX5_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr5_dispdec
+// base address: 0x10e0
+#define mmDPCSSYS_CR5_DPCSSYS_CR_ADDR                                                                  0x2d6c
+#define mmDPCSSYS_CR5_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR5_DPCSSYS_CR_DATA                                                                  0x2d6d
+#define mmDPCSSYS_CR5_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_sh_mask.h
new file mode 100644
index 000000000000..25e0569e05c8
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_sh_mask.h
@@ -0,0 +1,3912 @@
+/*
+ * Copyright (C) 2019  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) 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 _dpcs_2_0_0_SH_MASK_HEADER
+#define _dpcs_2_0_0_SH_MASK_HEADER
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx0_dispdec
+//DPCSTX0_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX0_DPCSTX_TX_CNTL
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX0_DPCSTX_CBUS_CNTL
+#define DPCSTX0_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX0_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX0_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX0_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX0_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX0_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX0_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX0_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX0_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX0_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX0_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX0_DPCSTX_DEBUG_CONFIG
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx0_dispdec
+//RDPCSTX0_RDPCSTX_CNTL
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX0_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX0_RDPCS_TX_CR_ADDR
+#define RDPCSTX0_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX0_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX0_RDPCS_TX_CR_DATA
+#define RDPCSTX0_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX0_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX0_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX0_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX0_RDPCSTX_SCRATCH
+#define RDPCSTX0_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX0_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX0_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX0_RDPCSTX_PHY_CNTL2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX0_RDPCSTX_PHY_CNTL3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL5
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX0_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX0_RDPCSTX_PHY_CNTL9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX0_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX0_RDPCSTX_PHY_CNTL11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL12
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX0_RDPCSTX_PHY_CNTL13
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX0_RDPCSTX_PHY_FUSE0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX0_RDPCSTX_PHY_FUSE1
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX0_RDPCSTX_PHY_FUSE2
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX0_RDPCSTX_PHY_FUSE3
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr0_dispdec
+//DPCSSYS_CR0_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR0_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR0_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR0_DPCSSYS_CR_DATA
+#define DPCSSYS_CR0_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR0_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx1_dispdec
+//DPCSTX1_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX1_DPCSTX_TX_CNTL
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX1_DPCSTX_CBUS_CNTL
+#define DPCSTX1_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX1_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX1_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX1_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX1_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX1_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX1_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX1_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX1_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX1_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX1_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX1_DPCSTX_DEBUG_CONFIG
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx1_dispdec
+//RDPCSTX1_RDPCSTX_CNTL
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX1_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX1_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX1_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX1_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX1_RDPCS_TX_CR_ADDR
+#define RDPCSTX1_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX1_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX1_RDPCS_TX_CR_DATA
+#define RDPCSTX1_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX1_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX1_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX1_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX1_RDPCSTX_SCRATCH
+#define RDPCSTX1_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX1_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX1_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX1_RDPCSTX_PHY_CNTL2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX1_RDPCSTX_PHY_CNTL3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL5
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX1_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX1_RDPCSTX_PHY_CNTL9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX1_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX1_RDPCSTX_PHY_CNTL11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL12
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX1_RDPCSTX_PHY_CNTL13
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX1_RDPCSTX_PHY_FUSE0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX1_RDPCSTX_PHY_FUSE1
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX1_RDPCSTX_PHY_FUSE2
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX1_RDPCSTX_PHY_FUSE3
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr1_dispdec
+//DPCSSYS_CR1_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR1_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR1_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR1_DPCSSYS_CR_DATA
+#define DPCSSYS_CR1_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR1_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx2_dispdec
+//DPCSTX2_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX2_DPCSTX_TX_CNTL
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX2_DPCSTX_CBUS_CNTL
+#define DPCSTX2_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX2_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX2_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX2_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX2_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX2_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX2_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX2_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX2_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX2_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX2_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX2_DPCSTX_DEBUG_CONFIG
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx2_dispdec
+//RDPCSTX2_RDPCSTX_CNTL
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX2_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX2_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX2_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX2_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX2_RDPCS_TX_CR_ADDR
+#define RDPCSTX2_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX2_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX2_RDPCS_TX_CR_DATA
+#define RDPCSTX2_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX2_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX2_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX2_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX2_RDPCSTX_SCRATCH
+#define RDPCSTX2_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX2_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX2_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX2_RDPCSTX_PHY_CNTL2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX2_RDPCSTX_PHY_CNTL3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL5
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX2_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX2_RDPCSTX_PHY_CNTL9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX2_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX2_RDPCSTX_PHY_CNTL11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL12
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX2_RDPCSTX_PHY_CNTL13
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX2_RDPCSTX_PHY_FUSE0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX2_RDPCSTX_PHY_FUSE1
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX2_RDPCSTX_PHY_FUSE2
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX2_RDPCSTX_PHY_FUSE3
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr2_dispdec
+//DPCSSYS_CR2_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR2_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR2_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR2_DPCSSYS_CR_DATA
+#define DPCSSYS_CR2_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR2_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx3_dispdec
+//DPCSTX3_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX3_DPCSTX_TX_CNTL
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX3_DPCSTX_CBUS_CNTL
+#define DPCSTX3_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX3_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX3_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX3_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX3_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX3_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX3_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX3_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX3_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX3_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX3_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX3_DPCSTX_DEBUG_CONFIG
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx3_dispdec
+//RDPCSTX3_RDPCSTX_CNTL
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX3_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX3_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX3_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX3_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX3_RDPCS_TX_CR_ADDR
+#define RDPCSTX3_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX3_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX3_RDPCS_TX_CR_DATA
+#define RDPCSTX3_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX3_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX3_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX3_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX3_RDPCSTX_SCRATCH
+#define RDPCSTX3_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX3_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX3_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX3_RDPCSTX_PHY_CNTL2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX3_RDPCSTX_PHY_CNTL3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL5
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX3_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX3_RDPCSTX_PHY_CNTL9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX3_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX3_RDPCSTX_PHY_CNTL11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL12
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX3_RDPCSTX_PHY_CNTL13
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX3_RDPCSTX_PHY_FUSE0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX3_RDPCSTX_PHY_FUSE1
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX3_RDPCSTX_PHY_FUSE2
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX3_RDPCSTX_PHY_FUSE3
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr3_dispdec
+//DPCSSYS_CR3_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR3_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR3_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR3_DPCSSYS_CR_DATA
+#define DPCSSYS_CR3_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR3_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcsrx_dispdec
+//DPCSRX_PHY_CNTL
+#define DPCSRX_PHY_CNTL__DPCS_PHY_RESET__SHIFT                                                                0x0
+#define DPCSRX_PHY_CNTL__DPCS_PHY_RESET_MASK                                                                  0x00000001L
+//DPCSRX_RX_CLOCK_CNTL
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_GATE_DIS__SHIFT                                                  0x0
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_EN__SHIFT                                                        0x1
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_SEL__SHIFT                                                       0x2
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_CLOCK_ON__SHIFT                                                  0x4
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_GATE_DIS__SHIFT                                                 0x10
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_EN__SHIFT                                                       0x11
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_CLOCK_ON__SHIFT                                                 0x12
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_GATE_DIS__SHIFT                                                 0x14
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_EN__SHIFT                                                       0x15
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_CLOCK_ON__SHIFT                                                 0x16
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_GATE_DIS__SHIFT                                                 0x18
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_EN__SHIFT                                                       0x19
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_CLOCK_ON__SHIFT                                                 0x1a
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_GATE_DIS__SHIFT                                                 0x1c
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_EN__SHIFT                                                       0x1d
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_CLOCK_ON__SHIFT                                                 0x1e
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_GATE_DIS_MASK                                                    0x00000001L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_EN_MASK                                                          0x00000002L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_SEL_MASK                                                         0x0000000CL
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_CLOCK_ON_MASK                                                    0x00000010L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_GATE_DIS_MASK                                                   0x00010000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_EN_MASK                                                         0x00020000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_CLOCK_ON_MASK                                                   0x00040000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_GATE_DIS_MASK                                                   0x00100000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_EN_MASK                                                         0x00200000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_CLOCK_ON_MASK                                                   0x00400000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_GATE_DIS_MASK                                                   0x01000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_EN_MASK                                                         0x02000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_CLOCK_ON_MASK                                                   0x04000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_GATE_DIS_MASK                                                   0x10000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_EN_MASK                                                         0x20000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_CLOCK_ON_MASK                                                   0x40000000L
+//DPCSRX_RX_CNTL
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE0_EN__SHIFT                                                               0x0
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE1_EN__SHIFT                                                               0x1
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE2_EN__SHIFT                                                               0x2
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE3_EN__SHIFT                                                               0x3
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_EN__SHIFT                                                                0x4
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_START__SHIFT                                                             0x5
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_RD_START_DELAY__SHIFT                                                    0x8
+#define DPCSRX_RX_CNTL__DPCS_RX_SOFT_RESET__SHIFT                                                             0x1f
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE0_EN_MASK                                                                 0x00000001L
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE1_EN_MASK                                                                 0x00000002L
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE2_EN_MASK                                                                 0x00000004L
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE3_EN_MASK                                                                 0x00000008L
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_EN_MASK                                                                  0x00000010L
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_START_MASK                                                               0x00000020L
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_RD_START_DELAY_MASK                                                      0x00000F00L
+#define DPCSRX_RX_CNTL__DPCS_RX_SOFT_RESET_MASK                                                               0x80000000L
+//DPCSRX_CBUS_CNTL
+#define DPCSRX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                                       0x0
+#define DPCSRX_CBUS_CNTL__DPCS_PHY_MASTER_REQ_DELAY__SHIFT                                                    0x8
+#define DPCSRX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                         0x1f
+#define DPCSRX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                         0x0000000FL
+#define DPCSRX_CBUS_CNTL__DPCS_PHY_MASTER_REQ_DELAY_MASK                                                      0x0000FF00L
+#define DPCSRX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                           0x80000000L
+//DPCSRX_REG_ERROR_STATUS
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_FIFO_OVERFLOW__SHIFT                                                0x0
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_ERROR_CLR__SHIFT                                                    0x1
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                              0x4
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_FIFO_OVERFLOW_MASK                                                  0x00000001L
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_ERROR_CLR_MASK                                                      0x00000002L
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_FIFO_ERROR_MASK_MASK                                                0x00000010L
+//DPCSRX_RX_ERROR_STATUS
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX0_FIFO_ERROR__SHIFT                                                    0x0
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX1_FIFO_ERROR__SHIFT                                                    0x1
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX2_FIFO_ERROR__SHIFT                                                    0x2
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX3_FIFO_ERROR__SHIFT                                                    0x3
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX_ERROR_CLR__SHIFT                                                      0x8
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX_FIFO_ERROR_MASK__SHIFT                                                0xc
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX0_FIFO_ERROR_MASK                                                      0x00000001L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX1_FIFO_ERROR_MASK                                                      0x00000002L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX2_FIFO_ERROR_MASK                                                      0x00000004L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX3_FIFO_ERROR_MASK                                                      0x00000008L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX_ERROR_CLR_MASK                                                        0x00000100L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX_FIFO_ERROR_MASK_MASK                                                  0x00001000L
+//DPCSRX_INDEX_MODE_ADDR
+#define DPCSRX_INDEX_MODE_ADDR__DPCS_INDEX_MODE_ADDR__SHIFT                                                   0x0
+#define DPCSRX_INDEX_MODE_ADDR__DPCS_INDEX_MODE_ADDR_MASK                                                     0x0003FFFFL
+//DPCSRX_INDEX_MODE_DATA
+#define DPCSRX_INDEX_MODE_DATA__DPCS_INDEX_MODE_DATA__SHIFT                                                   0x0
+#define DPCSRX_INDEX_MODE_DATA__DPCS_INDEX_MODE_DATA_MASK                                                     0xFFFFFFFFL
+//DPCSRX_DEBUG_CONFIG
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                               0x0
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                                       0x1
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_RX_SYMCLK_SEL__SHIFT                                                    0x6
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_BLOCK_SEL__SHIFT                                                        0xb
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                         0xe
+#define DPCSRX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                                  0x10
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                                 0x00000001L
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                         0x0000000EL
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_RX_SYMCLK_SEL_MASK                                                      0x000000C0L
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_BLOCK_SEL_MASK                                                          0x00003800L
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                           0x00004000L
+#define DPCSRX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                                    0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx4_dispdec
+//DPCSTX4_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX4_DPCSTX_TX_CNTL
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX4_DPCSTX_CBUS_CNTL
+#define DPCSTX4_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX4_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX4_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX4_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX4_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX4_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX4_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX4_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX4_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX4_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX4_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX4_DPCSTX_DEBUG_CONFIG
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx4_dispdec
+//RDPCSTX4_RDPCSTX_CNTL
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX4_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX4_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX4_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX4_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX4_RDPCS_TX_CR_ADDR
+#define RDPCSTX4_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX4_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX4_RDPCS_TX_CR_DATA
+#define RDPCSTX4_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX4_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX4_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX4_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX4_RDPCSTX_SCRATCH
+#define RDPCSTX4_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX4_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX4_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX4_RDPCSTX_PHY_CNTL2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX4_RDPCSTX_PHY_CNTL3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL5
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX4_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX4_RDPCSTX_PHY_CNTL9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX4_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX4_RDPCSTX_PHY_CNTL11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL12
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX4_RDPCSTX_PHY_CNTL13
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX4_RDPCSTX_PHY_FUSE0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX4_RDPCSTX_PHY_FUSE1
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX4_RDPCSTX_PHY_FUSE2
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX4_RDPCSTX_PHY_FUSE3
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr4_dispdec
+//DPCSSYS_CR4_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR4_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR4_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR4_DPCSSYS_CR_DATA
+#define DPCSSYS_CR4_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR4_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx5_dispdec
+//DPCSTX5_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX5_DPCSTX_TX_CNTL
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX5_DPCSTX_CBUS_CNTL
+#define DPCSTX5_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX5_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX5_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX5_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX5_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX5_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX5_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX5_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX5_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX5_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX5_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX5_DPCSTX_DEBUG_CONFIG
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx5_dispdec
+//RDPCSTX5_RDPCSTX_CNTL
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX5_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX5_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX5_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX5_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX5_RDPCS_TX_CR_ADDR
+#define RDPCSTX5_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX5_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX5_RDPCS_TX_CR_DATA
+#define RDPCSTX5_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX5_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX5_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX5_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX5_RDPCSTX_SCRATCH
+#define RDPCSTX5_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX5_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX5_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX5_RDPCSTX_PHY_CNTL2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX5_RDPCSTX_PHY_CNTL3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL5
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX5_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX5_RDPCSTX_PHY_CNTL9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX5_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX5_RDPCSTX_PHY_CNTL11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL12
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX5_RDPCSTX_PHY_CNTL13
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX5_RDPCSTX_PHY_FUSE0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX5_RDPCSTX_PHY_FUSE1
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX5_RDPCSTX_PHY_FUSE2
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX5_RDPCSTX_PHY_FUSE3
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr5_dispdec
+//DPCSSYS_CR5_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR5_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR5_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR5_DPCSSYS_CR_DATA
+#define DPCSSYS_CR5_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR5_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_2_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_1_0_offset.h
index 945bb6101a9d..945bb6101a9d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_2_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_1_0_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_2_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_1_0_sh_mask.h
index 6e039f2208e1..6e039f2208e1 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_2_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_1_0_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
index 2bfaaa8157d0..d984c916df80 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
@@ -2224,6 +2224,14 @@
 #define mmCOMPUTE_STATIC_THREAD_MGMT_SE2_BASE_IDX                                                      0
 #define mmCOMPUTE_STATIC_THREAD_MGMT_SE3                                                               0x0e1a
 #define mmCOMPUTE_STATIC_THREAD_MGMT_SE3_BASE_IDX                                                      0
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE4                                                               0x0e25
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE4_BASE_IDX                                                      0
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE5                                                               0x0e26
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE5_BASE_IDX                                                      0
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE6                                                               0x0e27
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE6_BASE_IDX                                                      0
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE7                                                               0x0e28
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE7_BASE_IDX                                                      0
 #define mmCOMPUTE_RESTART_X                                                                            0x0e1b
 #define mmCOMPUTE_RESTART_X_BASE_IDX                                                                   0
 #define mmCOMPUTE_RESTART_Y                                                                            0x0e1c
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
index d4c613a85352..c9e3f6d849a8 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
@@ -8739,10 +8739,16 @@
 #define TCP_ADDR_CONFIG__NUM_BANKS__SHIFT                                                                     0x4
 #define TCP_ADDR_CONFIG__COLHI_WIDTH__SHIFT                                                                   0x6
 #define TCP_ADDR_CONFIG__RB_SPLIT_COLHI__SHIFT                                                                0x9
+#define TCP_ADDR_CONFIG__ENABLE64KHASH__SHIFT                                                                 0xb
+#define TCP_ADDR_CONFIG__ENABLE2MHASH__SHIFT                                                                  0xc
+#define TCP_ADDR_CONFIG__ENABLE1GHASH__SHIFT                                                                  0xd
 #define TCP_ADDR_CONFIG__NUM_TCC_BANKS_MASK                                                                   0x0000000FL
 #define TCP_ADDR_CONFIG__NUM_BANKS_MASK                                                                       0x00000030L
 #define TCP_ADDR_CONFIG__COLHI_WIDTH_MASK                                                                     0x000001C0L
 #define TCP_ADDR_CONFIG__RB_SPLIT_COLHI_MASK                                                                  0x00000200L
+#define TCP_ADDR_CONFIG__ENABLE64KHASH_MASK                                                                   0x00000800L
+#define TCP_ADDR_CONFIG__ENABLE2MHASH_MASK                                                                    0x00001000L
+#define TCP_ADDR_CONFIG__ENABLE1GHASH_MASK                                                                    0x00002000L
 //TCP_CREDIT
 #define TCP_CREDIT__LFIFO_CREDIT__SHIFT                                                                       0x0
 #define TCP_CREDIT__REQ_FIFO_CREDIT__SHIFT                                                                    0x10
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
index 352ffae7a7ca..2c3ce243861a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
@@ -1964,4 +1964,20 @@
 #define mmATC_L2_PERFCOUNTER_RSLT_CNTL                                                                 0x084a
 #define mmATC_L2_PERFCOUNTER_RSLT_CNTL_BASE_IDX                                                        0
 
+/* MMEA */
+#define mmMMEA0_EDC_CNT_VG20                                                                           0x0206
+#define mmMMEA0_EDC_CNT_VG20_BASE_IDX                                                                  0
+#define mmMMEA0_EDC_CNT2_VG20                                                                          0x0207
+#define mmMMEA0_EDC_CNT2_VG20_BASE_IDX                                                                 0
+#define mmMMEA1_EDC_CNT_VG20                                                                           0x0346
+#define mmMMEA1_EDC_CNT_VG20_BASE_IDX                                                                  0
+#define mmMMEA1_EDC_CNT2_VG20                                                                          0x0347
+#define mmMMEA1_EDC_CNT2_VG20_BASE_IDX                                                                 0
+
+// addressBlock: mmhub_utcl2_vmsharedpfdec
+// base address: 0x6a040
+#define mmMC_VM_XGMI_LFB_CNTL                                                                          0x0823
+#define mmMC_VM_XGMI_LFB_CNTL_BASE_IDX                                                                 0
+#define mmMC_VM_XGMI_LFB_SIZE                                                                          0x0824
+#define mmMC_VM_XGMI_LFB_SIZE_BASE_IDX                                                                 0
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h
index 34278ef2aa1b..198f5f93ed1a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h
@@ -10124,4 +10124,126 @@
 #define ATC_L2_PERFCOUNTER_RSLT_CNTL__CLEAR_ALL_MASK                                                          0x02000000L
 #define ATC_L2_PERFCOUNTER_RSLT_CNTL__STOP_ALL_ON_SATURATE_MASK                                               0x04000000L
 
+//MMEA0_EDC_CNT
+#define MMEA0_EDC_CNT_VG20__DRAMRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
+#define MMEA0_EDC_CNT_VG20__DRAMRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
+#define MMEA0_EDC_CNT_VG20__DRAMWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
+#define MMEA0_EDC_CNT_VG20__DRAMWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
+#define MMEA0_EDC_CNT_VG20__DRAMWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
+#define MMEA0_EDC_CNT_VG20__DRAMWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
+#define MMEA0_EDC_CNT_VG20__RRET_TAGMEM_SEC_COUNT__SHIFT                                                           0xc
+#define MMEA0_EDC_CNT_VG20__RRET_TAGMEM_DED_COUNT__SHIFT                                                           0xe
+#define MMEA0_EDC_CNT_VG20__WRET_TAGMEM_SEC_COUNT__SHIFT                                                           0x10
+#define MMEA0_EDC_CNT_VG20__WRET_TAGMEM_DED_COUNT__SHIFT                                                           0x12
+#define MMEA0_EDC_CNT_VG20__DRAMRD_PAGEMEM_SED_COUNT__SHIFT                                                        0x14
+#define MMEA0_EDC_CNT_VG20__DRAMWR_PAGEMEM_SED_COUNT__SHIFT                                                        0x16
+#define MMEA0_EDC_CNT_VG20__IORD_CMDMEM_SED_COUNT__SHIFT                                                           0x18
+#define MMEA0_EDC_CNT_VG20__IOWR_CMDMEM_SED_COUNT__SHIFT                                                           0x1a
+#define MMEA0_EDC_CNT_VG20__IOWR_DATAMEM_SED_COUNT__SHIFT                                                          0x1c
+#define MMEA0_EDC_CNT_VG20__DRAMRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
+#define MMEA0_EDC_CNT_VG20__DRAMRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
+#define MMEA0_EDC_CNT_VG20__DRAMWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
+#define MMEA0_EDC_CNT_VG20__DRAMWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
+#define MMEA0_EDC_CNT_VG20__DRAMWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
+#define MMEA0_EDC_CNT_VG20__DRAMWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
+#define MMEA0_EDC_CNT_VG20__RRET_TAGMEM_SEC_COUNT_MASK                                                             0x00003000L
+#define MMEA0_EDC_CNT_VG20__RRET_TAGMEM_DED_COUNT_MASK                                                             0x0000C000L
+#define MMEA0_EDC_CNT_VG20__WRET_TAGMEM_SEC_COUNT_MASK                                                             0x00030000L
+#define MMEA0_EDC_CNT_VG20__WRET_TAGMEM_DED_COUNT_MASK                                                             0x000C0000L
+#define MMEA0_EDC_CNT_VG20__DRAMRD_PAGEMEM_SED_COUNT_MASK                                                          0x00300000L
+#define MMEA0_EDC_CNT_VG20__DRAMWR_PAGEMEM_SED_COUNT_MASK                                                          0x00C00000L
+#define MMEA0_EDC_CNT_VG20__IORD_CMDMEM_SED_COUNT_MASK                                                             0x03000000L
+#define MMEA0_EDC_CNT_VG20__IOWR_CMDMEM_SED_COUNT_MASK                                                             0x0C000000L
+#define MMEA0_EDC_CNT_VG20__IOWR_DATAMEM_SED_COUNT_MASK                                                            0x30000000L
+//MMEA0_EDC_CNT2
+#define MMEA0_EDC_CNT2_VG20__GMIRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
+#define MMEA0_EDC_CNT2_VG20__GMIRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
+#define MMEA0_EDC_CNT2_VG20__GMIWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
+#define MMEA0_EDC_CNT2_VG20__GMIWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
+#define MMEA0_EDC_CNT2_VG20__GMIWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
+#define MMEA0_EDC_CNT2_VG20__GMIWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
+#define MMEA0_EDC_CNT2_VG20__GMIRD_PAGEMEM_SED_COUNT__SHIFT                                                        0xc
+#define MMEA0_EDC_CNT2_VG20__GMIWR_PAGEMEM_SED_COUNT__SHIFT                                                        0xe
+#define MMEA0_EDC_CNT2_VG20__MAM_D0MEM_SED_COUNT__SHIFT                                                            0x10
+#define MMEA0_EDC_CNT2_VG20__MAM_D1MEM_SED_COUNT__SHIFT                                                            0x12
+#define MMEA0_EDC_CNT2_VG20__MAM_D2MEM_SED_COUNT__SHIFT                                                            0x14
+#define MMEA0_EDC_CNT2_VG20__MAM_D3MEM_SED_COUNT__SHIFT                                                            0x16
+#define MMEA0_EDC_CNT2_VG20__GMIRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
+#define MMEA0_EDC_CNT2_VG20__GMIRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
+#define MMEA0_EDC_CNT2_VG20__GMIWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
+#define MMEA0_EDC_CNT2_VG20__GMIWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
+#define MMEA0_EDC_CNT2_VG20__GMIWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
+#define MMEA0_EDC_CNT2_VG20__GMIWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
+#define MMEA0_EDC_CNT2_VG20__GMIRD_PAGEMEM_SED_COUNT_MASK                                                          0x00003000L
+#define MMEA0_EDC_CNT2_VG20__GMIWR_PAGEMEM_SED_COUNT_MASK                                                          0x0000C000L
+#define MMEA0_EDC_CNT2_VG20__MAM_D0MEM_SED_COUNT_MASK                                                              0x00030000L
+#define MMEA0_EDC_CNT2_VG20__MAM_D1MEM_SED_COUNT_MASK                                                              0x000C0000L
+#define MMEA0_EDC_CNT2_VG20__MAM_D2MEM_SED_COUNT_MASK                                                              0x00300000L
+#define MMEA0_EDC_CNT2_VG20__MAM_D3MEM_SED_COUNT_MASK                                                              0x00C00000L
+//MMEA1_EDC_CNT
+#define MMEA1_EDC_CNT_VG20__DRAMRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
+#define MMEA1_EDC_CNT_VG20__DRAMRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
+#define MMEA1_EDC_CNT_VG20__DRAMWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
+#define MMEA1_EDC_CNT_VG20__DRAMWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
+#define MMEA1_EDC_CNT_VG20__DRAMWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
+#define MMEA1_EDC_CNT_VG20__DRAMWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
+#define MMEA1_EDC_CNT_VG20__RRET_TAGMEM_SEC_COUNT__SHIFT                                                           0xc
+#define MMEA1_EDC_CNT_VG20__RRET_TAGMEM_DED_COUNT__SHIFT                                                           0xe
+#define MMEA1_EDC_CNT_VG20__WRET_TAGMEM_SEC_COUNT__SHIFT                                                           0x10
+#define MMEA1_EDC_CNT_VG20__WRET_TAGMEM_DED_COUNT__SHIFT                                                           0x12
+#define MMEA1_EDC_CNT_VG20__DRAMRD_PAGEMEM_SED_COUNT__SHIFT                                                        0x14
+#define MMEA1_EDC_CNT_VG20__DRAMWR_PAGEMEM_SED_COUNT__SHIFT                                                        0x16
+#define MMEA1_EDC_CNT_VG20__IORD_CMDMEM_SED_COUNT__SHIFT                                                           0x18
+#define MMEA1_EDC_CNT_VG20__IOWR_CMDMEM_SED_COUNT__SHIFT                                                           0x1a
+#define MMEA1_EDC_CNT_VG20__IOWR_DATAMEM_SED_COUNT__SHIFT                                                          0x1c
+#define MMEA1_EDC_CNT_VG20__DRAMRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
+#define MMEA1_EDC_CNT_VG20__DRAMRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
+#define MMEA1_EDC_CNT_VG20__DRAMWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
+#define MMEA1_EDC_CNT_VG20__DRAMWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
+#define MMEA1_EDC_CNT_VG20__DRAMWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
+#define MMEA1_EDC_CNT_VG20__DRAMWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
+#define MMEA1_EDC_CNT_VG20__RRET_TAGMEM_SEC_COUNT_MASK                                                             0x00003000L
+#define MMEA1_EDC_CNT_VG20__RRET_TAGMEM_DED_COUNT_MASK                                                             0x0000C000L
+#define MMEA1_EDC_CNT_VG20__WRET_TAGMEM_SEC_COUNT_MASK                                                             0x00030000L
+#define MMEA1_EDC_CNT_VG20__WRET_TAGMEM_DED_COUNT_MASK                                                             0x000C0000L
+#define MMEA1_EDC_CNT_VG20__DRAMRD_PAGEMEM_SED_COUNT_MASK                                                          0x00300000L
+#define MMEA1_EDC_CNT_VG20__DRAMWR_PAGEMEM_SED_COUNT_MASK                                                          0x00C00000L
+#define MMEA1_EDC_CNT_VG20__IORD_CMDMEM_SED_COUNT_MASK                                                             0x03000000L
+#define MMEA1_EDC_CNT_VG20__IOWR_CMDMEM_SED_COUNT_MASK                                                             0x0C000000L
+#define MMEA1_EDC_CNT_VG20__IOWR_DATAMEM_SED_COUNT_MASK                                                            0x30000000L
+//MMEA1_EDC_CNT2
+#define MMEA1_EDC_CNT2_VG20__GMIRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
+#define MMEA1_EDC_CNT2_VG20__GMIRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
+#define MMEA1_EDC_CNT2_VG20__GMIWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
+#define MMEA1_EDC_CNT2_VG20__GMIWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
+#define MMEA1_EDC_CNT2_VG20__GMIWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
+#define MMEA1_EDC_CNT2_VG20__GMIWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
+#define MMEA1_EDC_CNT2_VG20__GMIRD_PAGEMEM_SED_COUNT__SHIFT                                                        0xc
+#define MMEA1_EDC_CNT2_VG20__GMIWR_PAGEMEM_SED_COUNT__SHIFT                                                        0xe
+#define MMEA1_EDC_CNT2_VG20__MAM_D0MEM_SED_COUNT__SHIFT                                                            0x10
+#define MMEA1_EDC_CNT2_VG20__MAM_D1MEM_SED_COUNT__SHIFT                                                            0x12
+#define MMEA1_EDC_CNT2_VG20__MAM_D2MEM_SED_COUNT__SHIFT                                                            0x14
+#define MMEA1_EDC_CNT2_VG20__MAM_D3MEM_SED_COUNT__SHIFT                                                            0x16
+#define MMEA1_EDC_CNT2_VG20__GMIRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
+#define MMEA1_EDC_CNT2_VG20__GMIRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
+#define MMEA1_EDC_CNT2_VG20__GMIWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
+#define MMEA1_EDC_CNT2_VG20__GMIWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
+#define MMEA1_EDC_CNT2_VG20__GMIWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
+#define MMEA1_EDC_CNT2_VG20__GMIWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
+#define MMEA1_EDC_CNT2_VG20__GMIRD_PAGEMEM_SED_COUNT_MASK                                                          0x00003000L
+#define MMEA1_EDC_CNT2_VG20__GMIWR_PAGEMEM_SED_COUNT_MASK                                                          0x0000C000L
+#define MMEA1_EDC_CNT2_VG20__MAM_D0MEM_SED_COUNT_MASK                                                              0x00030000L
+#define MMEA1_EDC_CNT2_VG20__MAM_D1MEM_SED_COUNT_MASK                                                              0x000C0000L
+#define MMEA1_EDC_CNT2_VG20__MAM_D2MEM_SED_COUNT_MASK                                                              0x00300000L
+#define MMEA1_EDC_CNT2_VG20__MAM_D3MEM_SED_COUNT_MASK                                                              0x00C00000L
+
+// addressBlock: mmhub_utcl2_vmsharedpfdec
+//MC_VM_XGMI_LFB_CNTL
+#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION__SHIFT                                                             0x0
+#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION__SHIFT                                                             0x4
+#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION_MASK                                                               0x00000007L
+#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION_MASK                                                               0x00000070L
+//MC_VM_XGMI_LFB_SIZE
+#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE__SHIFT                                                               0x0
+#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE_MASK                                                                 0x0000FFFFL
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_offset.h
deleted file mode 100644
index f2ae3a58949e..000000000000
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_offset.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * Copyright (C) 2018  Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included
- * in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
- * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) 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 _mmhub_9_4_0_OFFSET_HEADER
-#define _mmhub_9_4_0_OFFSET_HEADER
-
-/* MMEA */
-#define mmMMEA0_SDP_ARB_FINAL_VG20                                                                     0x01ee
-#define mmMMEA0_SDP_ARB_FINAL_VG20_BASE_IDX                                                            0
-#define mmMMEA0_EDC_CNT_VG20                                                                           0x0206
-#define mmMMEA0_EDC_CNT_VG20_BASE_IDX                                                                  0
-#define mmMMEA0_EDC_CNT2_VG20                                                                          0x0207
-#define mmMMEA0_EDC_CNT2_VG20_BASE_IDX                                                                 0
-#define mmMMEA0_EDC_MODE_VG20                                                                          0x0210
-#define mmMMEA0_EDC_MODE_VG20_BASE_IDX                                                                 0
-#define mmMMEA0_ERR_STATUS_VG20                                                                        0x0211
-#define mmMMEA0_ERR_STATUS_VG20_BASE_IDX                                                               0
-#define mmMMEA1_SDP_ARB_FINAL_VG20                                                                     0x032e
-#define mmMMEA1_SDP_ARB_FINAL_VG20_BASE_IDX                                                            0
-#define mmMMEA1_EDC_CNT_VG20                                                                           0x0346
-#define mmMMEA1_EDC_CNT_VG20_BASE_IDX                                                                  0
-#define mmMMEA1_EDC_CNT2_VG20                                                                          0x0347
-#define mmMMEA1_EDC_CNT2_VG20_BASE_IDX                                                                 0
-#define mmMMEA1_EDC_MODE_VG20                                                                          0x0350
-#define mmMMEA1_EDC_MODE_VG20_BASE_IDX                                                                 0
-#define mmMMEA1_ERR_STATUS_VG20                                                                        0x0351
-#define mmMMEA1_ERR_STATUS_VG20_BASE_IDX                                                               0
-
-// addressBlock: mmhub_utcl2_vmsharedpfdec
-// base address: 0x6a040
-#define mmMC_VM_XGMI_LFB_CNTL                                                                          0x0823
-#define mmMC_VM_XGMI_LFB_CNTL_BASE_IDX                                                                 0
-#define mmMC_VM_XGMI_LFB_SIZE                                                                          0x0824
-#define mmMC_VM_XGMI_LFB_SIZE_BASE_IDX                                                                 0
-
-#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_sh_mask.h
deleted file mode 100644
index c24259ed12a1..000000000000
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_sh_mask.h
+++ /dev/null
@@ -1,257 +0,0 @@
-/*
- * Copyright (C) 2018  Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included
- * in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
- * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) 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 _mmhub_9_4_0_SH_MASK_HEADER
-#define _mmhub_9_4_0_SH_MASK_HEADER
-
-//MMEA0_SDP_ARB_FINAL
-#define MMEA0_SDP_ARB_FINAL__DRAM_BURST_LIMIT__SHIFT                                                          0x0
-#define MMEA0_SDP_ARB_FINAL__GMI_BURST_LIMIT__SHIFT                                                           0x5
-#define MMEA0_SDP_ARB_FINAL__IO_BURST_LIMIT__SHIFT                                                            0xa
-#define MMEA0_SDP_ARB_FINAL__BURST_LIMIT_MULTIPLIER__SHIFT                                                    0xf
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC0__SHIFT                                                                0x11
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC1__SHIFT                                                                0x12
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC2__SHIFT                                                                0x13
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC3__SHIFT                                                                0x14
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC4__SHIFT                                                                0x15
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC5__SHIFT                                                                0x16
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC6__SHIFT                                                                0x17
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC7__SHIFT                                                                0x18
-#define MMEA0_SDP_ARB_FINAL__ERREVENT_ON_ERROR__SHIFT                                                         0x19
-#define MMEA0_SDP_ARB_FINAL__HALTREQ_ON_ERROR__SHIFT                                                          0x1a
-#define MMEA0_SDP_ARB_FINAL__DRAM_BURST_LIMIT_MASK                                                            0x0000001FL
-#define MMEA0_SDP_ARB_FINAL__GMI_BURST_LIMIT_MASK                                                             0x000003E0L
-#define MMEA0_SDP_ARB_FINAL__IO_BURST_LIMIT_MASK                                                              0x00007C00L
-#define MMEA0_SDP_ARB_FINAL__BURST_LIMIT_MULTIPLIER_MASK                                                      0x00018000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC0_MASK                                                                  0x00020000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC1_MASK                                                                  0x00040000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC2_MASK                                                                  0x00080000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC3_MASK                                                                  0x00100000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC4_MASK                                                                  0x00200000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC5_MASK                                                                  0x00400000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC6_MASK                                                                  0x00800000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC7_MASK                                                                  0x01000000L
-#define MMEA0_SDP_ARB_FINAL__ERREVENT_ON_ERROR_MASK                                                           0x02000000L
-#define MMEA0_SDP_ARB_FINAL__HALTREQ_ON_ERROR_MASK                                                            0x04000000L
-//MMEA0_EDC_CNT
-#define MMEA0_EDC_CNT__DRAMRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
-#define MMEA0_EDC_CNT__DRAMRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
-#define MMEA0_EDC_CNT__DRAMWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
-#define MMEA0_EDC_CNT__DRAMWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
-#define MMEA0_EDC_CNT__DRAMWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
-#define MMEA0_EDC_CNT__DRAMWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
-#define MMEA0_EDC_CNT__RRET_TAGMEM_SEC_COUNT__SHIFT                                                           0xc
-#define MMEA0_EDC_CNT__RRET_TAGMEM_DED_COUNT__SHIFT                                                           0xe
-#define MMEA0_EDC_CNT__WRET_TAGMEM_SEC_COUNT__SHIFT                                                           0x10
-#define MMEA0_EDC_CNT__WRET_TAGMEM_DED_COUNT__SHIFT                                                           0x12
-#define MMEA0_EDC_CNT__DRAMRD_PAGEMEM_SED_COUNT__SHIFT                                                        0x14
-#define MMEA0_EDC_CNT__DRAMWR_PAGEMEM_SED_COUNT__SHIFT                                                        0x16
-#define MMEA0_EDC_CNT__IORD_CMDMEM_SED_COUNT__SHIFT                                                           0x18
-#define MMEA0_EDC_CNT__IOWR_CMDMEM_SED_COUNT__SHIFT                                                           0x1a
-#define MMEA0_EDC_CNT__IOWR_DATAMEM_SED_COUNT__SHIFT                                                          0x1c
-#define MMEA0_EDC_CNT__DRAMRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
-#define MMEA0_EDC_CNT__DRAMRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
-#define MMEA0_EDC_CNT__DRAMWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
-#define MMEA0_EDC_CNT__DRAMWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
-#define MMEA0_EDC_CNT__DRAMWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
-#define MMEA0_EDC_CNT__DRAMWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
-#define MMEA0_EDC_CNT__RRET_TAGMEM_SEC_COUNT_MASK                                                             0x00003000L
-#define MMEA0_EDC_CNT__RRET_TAGMEM_DED_COUNT_MASK                                                             0x0000C000L
-#define MMEA0_EDC_CNT__WRET_TAGMEM_SEC_COUNT_MASK                                                             0x00030000L
-#define MMEA0_EDC_CNT__WRET_TAGMEM_DED_COUNT_MASK                                                             0x000C0000L
-#define MMEA0_EDC_CNT__DRAMRD_PAGEMEM_SED_COUNT_MASK                                                          0x00300000L
-#define MMEA0_EDC_CNT__DRAMWR_PAGEMEM_SED_COUNT_MASK                                                          0x00C00000L
-#define MMEA0_EDC_CNT__IORD_CMDMEM_SED_COUNT_MASK                                                             0x03000000L
-#define MMEA0_EDC_CNT__IOWR_CMDMEM_SED_COUNT_MASK                                                             0x0C000000L
-#define MMEA0_EDC_CNT__IOWR_DATAMEM_SED_COUNT_MASK                                                            0x30000000L
-//MMEA0_EDC_CNT2
-#define MMEA0_EDC_CNT2__GMIRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
-#define MMEA0_EDC_CNT2__GMIRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
-#define MMEA0_EDC_CNT2__GMIWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
-#define MMEA0_EDC_CNT2__GMIWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
-#define MMEA0_EDC_CNT2__GMIWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
-#define MMEA0_EDC_CNT2__GMIWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
-#define MMEA0_EDC_CNT2__GMIRD_PAGEMEM_SED_COUNT__SHIFT                                                        0xc
-#define MMEA0_EDC_CNT2__GMIWR_PAGEMEM_SED_COUNT__SHIFT                                                        0xe
-#define MMEA0_EDC_CNT2__MAM_D0MEM_SED_COUNT__SHIFT                                                            0x10
-#define MMEA0_EDC_CNT2__MAM_D1MEM_SED_COUNT__SHIFT                                                            0x12
-#define MMEA0_EDC_CNT2__MAM_D2MEM_SED_COUNT__SHIFT                                                            0x14
-#define MMEA0_EDC_CNT2__MAM_D3MEM_SED_COUNT__SHIFT                                                            0x16
-#define MMEA0_EDC_CNT2__GMIRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
-#define MMEA0_EDC_CNT2__GMIRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
-#define MMEA0_EDC_CNT2__GMIWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
-#define MMEA0_EDC_CNT2__GMIWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
-#define MMEA0_EDC_CNT2__GMIWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
-#define MMEA0_EDC_CNT2__GMIWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
-#define MMEA0_EDC_CNT2__GMIRD_PAGEMEM_SED_COUNT_MASK                                                          0x00003000L
-#define MMEA0_EDC_CNT2__GMIWR_PAGEMEM_SED_COUNT_MASK                                                          0x0000C000L
-#define MMEA0_EDC_CNT2__MAM_D0MEM_SED_COUNT_MASK                                                              0x00030000L
-#define MMEA0_EDC_CNT2__MAM_D1MEM_SED_COUNT_MASK                                                              0x000C0000L
-#define MMEA0_EDC_CNT2__MAM_D2MEM_SED_COUNT_MASK                                                              0x00300000L
-#define MMEA0_EDC_CNT2__MAM_D3MEM_SED_COUNT_MASK                                                              0x00C00000L
-//MMEA0_EDC_MODE
-#define MMEA0_EDC_MODE__COUNT_FED_OUT__SHIFT                                                                  0x10
-#define MMEA0_EDC_MODE__GATE_FUE__SHIFT                                                                       0x11
-#define MMEA0_EDC_MODE__DED_MODE__SHIFT                                                                       0x14
-#define MMEA0_EDC_MODE__PROP_FED__SHIFT                                                                       0x1d
-#define MMEA0_EDC_MODE__BYPASS__SHIFT                                                                         0x1f
-#define MMEA0_EDC_MODE__COUNT_FED_OUT_MASK                                                                    0x00010000L
-#define MMEA0_EDC_MODE__GATE_FUE_MASK                                                                         0x00020000L
-#define MMEA0_EDC_MODE__DED_MODE_MASK                                                                         0x00300000L
-#define MMEA0_EDC_MODE__PROP_FED_MASK                                                                         0x20000000L
-#define MMEA0_EDC_MODE__BYPASS_MASK                                                                           0x80000000L
-//MMEA0_ERR_STATUS
-#define MMEA0_ERR_STATUS__SDP_RDRSP_STATUS__SHIFT                                                             0x0
-#define MMEA0_ERR_STATUS__SDP_WRRSP_STATUS__SHIFT                                                             0x4
-#define MMEA0_ERR_STATUS__SDP_RDRSP_DATASTATUS__SHIFT                                                         0x8
-#define MMEA0_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR__SHIFT                                                   0xa
-#define MMEA0_ERR_STATUS__CLEAR_ERROR_STATUS__SHIFT                                                           0xb
-#define MMEA0_ERR_STATUS__BUSY_ON_ERROR__SHIFT                                                                0xc
-#define MMEA0_ERR_STATUS__FUE_FLAG__SHIFT                                                                     0xd
-#define MMEA0_ERR_STATUS__SDP_RDRSP_STATUS_MASK                                                               0x0000000FL
-#define MMEA0_ERR_STATUS__SDP_WRRSP_STATUS_MASK                                                               0x000000F0L
-#define MMEA0_ERR_STATUS__SDP_RDRSP_DATASTATUS_MASK                                                           0x00000300L
-#define MMEA0_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR_MASK                                                     0x00000400L
-#define MMEA0_ERR_STATUS__CLEAR_ERROR_STATUS_MASK                                                             0x00000800L
-#define MMEA0_ERR_STATUS__BUSY_ON_ERROR_MASK                                                                  0x00001000L
-#define MMEA0_ERR_STATUS__FUE_FLAG_MASK                                                                       0x00002000L
-//MMEA1_SDP_ARB_FINAL
-#define MMEA1_SDP_ARB_FINAL__DRAM_BURST_LIMIT__SHIFT                                                          0x0
-#define MMEA1_SDP_ARB_FINAL__GMI_BURST_LIMIT__SHIFT                                                           0x5
-#define MMEA1_SDP_ARB_FINAL__IO_BURST_LIMIT__SHIFT                                                            0xa
-#define MMEA1_SDP_ARB_FINAL__BURST_LIMIT_MULTIPLIER__SHIFT                                                    0xf
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC0__SHIFT                                                                0x11
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC1__SHIFT                                                                0x12
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC2__SHIFT                                                                0x13
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC3__SHIFT                                                                0x14
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC4__SHIFT                                                                0x15
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC5__SHIFT                                                                0x16
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC6__SHIFT                                                                0x17
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC7__SHIFT                                                                0x18
-#define MMEA1_SDP_ARB_FINAL__ERREVENT_ON_ERROR__SHIFT                                                         0x19
-#define MMEA1_SDP_ARB_FINAL__HALTREQ_ON_ERROR__SHIFT                                                          0x1a
-#define MMEA1_SDP_ARB_FINAL__DRAM_BURST_LIMIT_MASK                                                            0x0000001FL
-#define MMEA1_SDP_ARB_FINAL__GMI_BURST_LIMIT_MASK                                                             0x000003E0L
-#define MMEA1_SDP_ARB_FINAL__IO_BURST_LIMIT_MASK                                                              0x00007C00L
-#define MMEA1_SDP_ARB_FINAL__BURST_LIMIT_MULTIPLIER_MASK                                                      0x00018000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC0_MASK                                                                  0x00020000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC1_MASK                                                                  0x00040000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC2_MASK                                                                  0x00080000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC3_MASK                                                                  0x00100000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC4_MASK                                                                  0x00200000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC5_MASK                                                                  0x00400000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC6_MASK                                                                  0x00800000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC7_MASK                                                                  0x01000000L
-#define MMEA1_SDP_ARB_FINAL__ERREVENT_ON_ERROR_MASK                                                           0x02000000L
-#define MMEA1_SDP_ARB_FINAL__HALTREQ_ON_ERROR_MASK                                                            0x04000000L
-//MMEA1_EDC_CNT
-#define MMEA1_EDC_CNT__DRAMRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
-#define MMEA1_EDC_CNT__DRAMRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
-#define MMEA1_EDC_CNT__DRAMWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
-#define MMEA1_EDC_CNT__DRAMWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
-#define MMEA1_EDC_CNT__DRAMWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
-#define MMEA1_EDC_CNT__DRAMWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
-#define MMEA1_EDC_CNT__RRET_TAGMEM_SEC_COUNT__SHIFT                                                           0xc
-#define MMEA1_EDC_CNT__RRET_TAGMEM_DED_COUNT__SHIFT                                                           0xe
-#define MMEA1_EDC_CNT__WRET_TAGMEM_SEC_COUNT__SHIFT                                                           0x10
-#define MMEA1_EDC_CNT__WRET_TAGMEM_DED_COUNT__SHIFT                                                           0x12
-#define MMEA1_EDC_CNT__DRAMRD_PAGEMEM_SED_COUNT__SHIFT                                                        0x14
-#define MMEA1_EDC_CNT__DRAMWR_PAGEMEM_SED_COUNT__SHIFT                                                        0x16
-#define MMEA1_EDC_CNT__IORD_CMDMEM_SED_COUNT__SHIFT                                                           0x18
-#define MMEA1_EDC_CNT__IOWR_CMDMEM_SED_COUNT__SHIFT                                                           0x1a
-#define MMEA1_EDC_CNT__IOWR_DATAMEM_SED_COUNT__SHIFT                                                          0x1c
-#define MMEA1_EDC_CNT__DRAMRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
-#define MMEA1_EDC_CNT__DRAMRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
-#define MMEA1_EDC_CNT__DRAMWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
-#define MMEA1_EDC_CNT__DRAMWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
-#define MMEA1_EDC_CNT__DRAMWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
-#define MMEA1_EDC_CNT__DRAMWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
-#define MMEA1_EDC_CNT__RRET_TAGMEM_SEC_COUNT_MASK                                                             0x00003000L
-#define MMEA1_EDC_CNT__RRET_TAGMEM_DED_COUNT_MASK                                                             0x0000C000L
-#define MMEA1_EDC_CNT__WRET_TAGMEM_SEC_COUNT_MASK                                                             0x00030000L
-#define MMEA1_EDC_CNT__WRET_TAGMEM_DED_COUNT_MASK                                                             0x000C0000L
-#define MMEA1_EDC_CNT__DRAMRD_PAGEMEM_SED_COUNT_MASK                                                          0x00300000L
-#define MMEA1_EDC_CNT__DRAMWR_PAGEMEM_SED_COUNT_MASK                                                          0x00C00000L
-#define MMEA1_EDC_CNT__IORD_CMDMEM_SED_COUNT_MASK                                                             0x03000000L
-#define MMEA1_EDC_CNT__IOWR_CMDMEM_SED_COUNT_MASK                                                             0x0C000000L
-#define MMEA1_EDC_CNT__IOWR_DATAMEM_SED_COUNT_MASK                                                            0x30000000L
-//MMEA1_EDC_CNT2
-#define MMEA1_EDC_CNT2__GMIRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
-#define MMEA1_EDC_CNT2__GMIRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
-#define MMEA1_EDC_CNT2__GMIWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
-#define MMEA1_EDC_CNT2__GMIWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
-#define MMEA1_EDC_CNT2__GMIWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
-#define MMEA1_EDC_CNT2__GMIWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
-#define MMEA1_EDC_CNT2__GMIRD_PAGEMEM_SED_COUNT__SHIFT                                                        0xc
-#define MMEA1_EDC_CNT2__GMIWR_PAGEMEM_SED_COUNT__SHIFT                                                        0xe
-#define MMEA1_EDC_CNT2__MAM_D0MEM_SED_COUNT__SHIFT                                                            0x10
-#define MMEA1_EDC_CNT2__MAM_D1MEM_SED_COUNT__SHIFT                                                            0x12
-#define MMEA1_EDC_CNT2__MAM_D2MEM_SED_COUNT__SHIFT                                                            0x14
-#define MMEA1_EDC_CNT2__MAM_D3MEM_SED_COUNT__SHIFT                                                            0x16
-#define MMEA1_EDC_CNT2__GMIRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
-#define MMEA1_EDC_CNT2__GMIRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
-#define MMEA1_EDC_CNT2__GMIWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
-#define MMEA1_EDC_CNT2__GMIWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
-#define MMEA1_EDC_CNT2__GMIWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
-#define MMEA1_EDC_CNT2__GMIWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
-#define MMEA1_EDC_CNT2__GMIRD_PAGEMEM_SED_COUNT_MASK                                                          0x00003000L
-#define MMEA1_EDC_CNT2__GMIWR_PAGEMEM_SED_COUNT_MASK                                                          0x0000C000L
-#define MMEA1_EDC_CNT2__MAM_D0MEM_SED_COUNT_MASK                                                              0x00030000L
-#define MMEA1_EDC_CNT2__MAM_D1MEM_SED_COUNT_MASK                                                              0x000C0000L
-#define MMEA1_EDC_CNT2__MAM_D2MEM_SED_COUNT_MASK                                                              0x00300000L
-#define MMEA1_EDC_CNT2__MAM_D3MEM_SED_COUNT_MASK                                                              0x00C00000L
-//MMEA1_EDC_MODE
-#define MMEA1_EDC_MODE__COUNT_FED_OUT__SHIFT                                                                  0x10
-#define MMEA1_EDC_MODE__GATE_FUE__SHIFT                                                                       0x11
-#define MMEA1_EDC_MODE__DED_MODE__SHIFT                                                                       0x14
-#define MMEA1_EDC_MODE__PROP_FED__SHIFT                                                                       0x1d
-#define MMEA1_EDC_MODE__BYPASS__SHIFT                                                                         0x1f
-#define MMEA1_EDC_MODE__COUNT_FED_OUT_MASK                                                                    0x00010000L
-#define MMEA1_EDC_MODE__GATE_FUE_MASK                                                                         0x00020000L
-#define MMEA1_EDC_MODE__DED_MODE_MASK                                                                         0x00300000L
-#define MMEA1_EDC_MODE__PROP_FED_MASK                                                                         0x20000000L
-#define MMEA1_EDC_MODE__BYPASS_MASK                                                                           0x80000000L
-//MMEA1_ERR_STATUS
-#define MMEA1_ERR_STATUS__SDP_RDRSP_STATUS__SHIFT                                                             0x0
-#define MMEA1_ERR_STATUS__SDP_WRRSP_STATUS__SHIFT                                                             0x4
-#define MMEA1_ERR_STATUS__SDP_RDRSP_DATASTATUS__SHIFT                                                         0x8
-#define MMEA1_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR__SHIFT                                                   0xa
-#define MMEA1_ERR_STATUS__CLEAR_ERROR_STATUS__SHIFT                                                           0xb
-#define MMEA1_ERR_STATUS__BUSY_ON_ERROR__SHIFT                                                                0xc
-#define MMEA1_ERR_STATUS__FUE_FLAG__SHIFT                                                                     0xd
-#define MMEA1_ERR_STATUS__SDP_RDRSP_STATUS_MASK                                                               0x0000000FL
-#define MMEA1_ERR_STATUS__SDP_WRRSP_STATUS_MASK                                                               0x000000F0L
-#define MMEA1_ERR_STATUS__SDP_RDRSP_DATASTATUS_MASK                                                           0x00000300L
-#define MMEA1_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR_MASK                                                     0x00000400L
-#define MMEA1_ERR_STATUS__CLEAR_ERROR_STATUS_MASK                                                             0x00000800L
-#define MMEA1_ERR_STATUS__BUSY_ON_ERROR_MASK                                                                  0x00001000L
-#define MMEA1_ERR_STATUS__FUE_FLAG_MASK                                                                       0x00002000L
-
-// addressBlock: mmhub_utcl2_vmsharedpfdec
-//MC_VM_XGMI_LFB_CNTL
-#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION__SHIFT                                                             0x0
-#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION__SHIFT                                                             0x4
-#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION_MASK                                                               0x00000007L
-#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION_MASK                                                               0x00000070L
-//MC_VM_XGMI_LFB_SIZE
-#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE__SHIFT                                                               0x0
-#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE_MASK                                                                 0x0000FFFFL
-
-#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_1_offset.h
index 043aa695d63f..0d6b594be775 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_1_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_1_offset.h
@@ -27,5 +27,7 @@
 #define mmUMCCH0_0_EccErrCnt_BASE_IDX                                                                  0
 #define mmMCA_UMC_UMC0_MCUMC_STATUST0                                                                  0x03c2
 #define mmMCA_UMC_UMC0_MCUMC_STATUST0_BASE_IDX                                                         0
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0                                                                    0x03c4
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0_BASE_IDX                                                           0
 
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_offset.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_offset.h
new file mode 100644
index 000000000000..ce005c674a18
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_offset.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2019  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) 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 _umc_6_1_2_OFFSET_HEADER
+#define _umc_6_1_2_OFFSET_HEADER
+
+#define mmUMCCH0_0_EccErrCntSel_ARCT                                     0x0360
+#define mmUMCCH0_0_EccErrCntSel_ARCT_BASE_IDX                            1
+#define mmUMCCH0_0_EccErrCnt_ARCT                                        0x0361
+#define mmUMCCH0_0_EccErrCnt_ARCT_BASE_IDX                               1
+#define mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT                               0x03c2
+#define mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT_BASE_IDX                      1
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0_ARCT                                 0x03c4
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0_ARCT_BASE_IDX                        1
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_sh_mask.h
new file mode 100644
index 000000000000..a5a8c993ec3a
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_sh_mask.h
@@ -0,0 +1,91 @@
+/*
+ * Copyright (C) 2020  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) 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 _umc_6_1_2_SH_MASK_HEADER
+#define _umc_6_1_2_SH_MASK_HEADER
+
+//UMCCH0_0_EccErrCntSel_ARCT
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrCntCsSel__SHIFT                                                          0x0
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrInt__SHIFT                                                               0xc
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrCntEn__SHIFT                                                             0xf
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrCntCsSel_MASK                                                            0x0000000FL
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrInt_MASK                                                                 0x00003000L
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrCntEn_MASK                                                               0x00008000L
+//UMCCH0_0_EccErrCnt_ARCT
+#define UMCCH0_0_EccErrCnt_ARCT__EccErrCnt__SHIFT                                                                  0x0
+#define UMCCH0_0_EccErrCnt_ARCT__EccErrCnt_MASK                                                                    0x0000FFFFL
+//MCA_UMC_UMC0_MCUMC_STATUST0_ARCT
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrorCode__SHIFT                                                         0x0
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrorCodeExt__SHIFT                                                      0x10
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV0__SHIFT                                                           0x16
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrCoreId__SHIFT                                                         0x20
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV1__SHIFT                                                           0x26
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Scrub__SHIFT                                                             0x28
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV2__SHIFT                                                           0x29
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Poison__SHIFT                                                            0x2b
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Deferred__SHIFT                                                          0x2c
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__UECC__SHIFT                                                              0x2d
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__CECC__SHIFT                                                              0x2e
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV3__SHIFT                                                           0x2f
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Transparent__SHIFT                                                       0x34
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__SyndV__SHIFT                                                             0x35
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV4__SHIFT                                                           0x36
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__TCC__SHIFT                                                               0x37
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrCoreIdVal__SHIFT                                                      0x38
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__PCC__SHIFT                                                               0x39
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__AddrV__SHIFT                                                             0x3a
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__MiscV__SHIFT                                                             0x3b
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__En__SHIFT                                                                0x3c
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__UC__SHIFT                                                                0x3d
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Overflow__SHIFT                                                          0x3e
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Val__SHIFT                                                               0x3f
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrorCode_MASK                                                           0x000000000000FFFFL
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrorCodeExt_MASK                                                        0x00000000003F0000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV0_MASK                                                             0x00000000FFC00000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrCoreId_MASK                                                           0x0000003F00000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV1_MASK                                                             0x000000C000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Scrub_MASK                                                               0x0000010000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV2_MASK                                                             0x0000060000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Poison_MASK                                                              0x0000080000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Deferred_MASK                                                            0x0000100000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__UECC_MASK                                                                0x0000200000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__CECC_MASK                                                                0x0000400000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV3_MASK                                                             0x000F800000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Transparent_MASK                                                         0x0010000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__SyndV_MASK                                                               0x0020000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV4_MASK                                                             0x0040000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__TCC_MASK                                                                 0x0080000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrCoreIdVal_MASK                                                        0x0100000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__PCC_MASK                                                                 0x0200000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__AddrV_MASK                                                               0x0400000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__MiscV_MASK                                                               0x0800000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__En_MASK                                                                  0x1000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__UC_MASK                                                                  0x2000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Overflow_MASK                                                            0x4000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Val_MASK                                                                 0x8000000000000000L
+//MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__ErrorAddr__SHIFT                                                           0x0
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__LSB__SHIFT                                                                 0x38
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__Reserved__SHIFT                                                            0x3e
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__ErrorAddr_MASK                                                             0x00FFFFFFFFFFFFFFL
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__LSB_MASK                                                                   0x3F00000000000000L
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__Reserved_MASK                                                              0xC000000000000000L
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index dd7cbc00a0aa..70146518174c 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -672,20 +672,6 @@ struct vram_usagebyfirmware_v2_1
   uint16_t  used_by_driver_in_kb; 
 };
 
-/* This is part of vram_usagebyfirmware_v2_1 */
-struct vram_reserve_block
-{
-	uint32_t start_address_in_kb;
-	uint16_t used_by_firmware_in_kb;
-	uint16_t used_by_driver_in_kb;
-};
-
-/* Definitions for constance */
-enum atomfirmware_internal_constants
-{
-	ONE_KiB	= 0x400,
-	ONE_MiB	= 0x100000,
-};
 
 /* 
   ***************************************************************************
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 2cd217e60125..a607b1034962 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -256,6 +256,10 @@ struct kfd2kgd_calls {
 			uint32_t wptr_shift, uint32_t wptr_mask,
 			struct mm_struct *mm);
 
+	int (*hiq_mqd_load)(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off);
+
 	int (*hqd_sdma_load)(struct kgd_dev *kgd, void *mqd,
 			     uint32_t __user *wptr, struct mm_struct *mm);
 
@@ -307,8 +311,6 @@ struct kfd2kgd_calls {
 
 	void (*set_vm_context_page_table_base)(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t page_table_base);
-	int (*invalidate_tlbs)(struct kgd_dev *kgd, uint16_t pasid);
-	int (*invalidate_tlbs_vmid)(struct kgd_dev *kgd, uint16_t vmid);
 	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
 	uint64_t (*get_hive_id)(struct kgd_dev *kgd);
 
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 7932eb163a00..c195575366a3 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -48,7 +48,6 @@ static int amd_powerplay_create(struct amdgpu_device *adev)
 
 	hwmgr->adev = adev;
 	hwmgr->not_vf = !amdgpu_sriov_vf(adev);
-	hwmgr->pm_en = (amdgpu_dpm && hwmgr->not_vf) ? true : false;
 	hwmgr->device = amdgpu_cgs_create_device(adev);
 	mutex_init(&hwmgr->smu_lock);
 	hwmgr->chip_family = adev->family;
@@ -928,9 +927,12 @@ static int pp_dpm_set_mp1_state(void *handle, enum pp_mp1_state mp1_state)
 {
 	struct pp_hwmgr *hwmgr = handle;
 
-	if (!hwmgr || !hwmgr->pm_en)
+	if (!hwmgr)
 		return -EINVAL;
 
+	if (!hwmgr->pm_en)
+		return 0;
+
 	if (hwmgr->hwmgr_func->set_mp1_state)
 		return hwmgr->hwmgr_func->set_mp1_state(hwmgr, mp1_state);
 
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index a23729d3174b..99469479e277 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -356,6 +356,35 @@ int smu_get_dpm_level_count(struct smu_context *smu, enum smu_clk_type clk_type,
 	return smu_get_dpm_freq_by_index(smu, clk_type, 0xff, value);
 }
 
+int smu_get_dpm_level_range(struct smu_context *smu, enum smu_clk_type clk_type,
+			    uint32_t *min_value, uint32_t *max_value)
+{
+	int ret = 0;
+	uint32_t level_count = 0;
+
+	if (!min_value && !max_value)
+		return -EINVAL;
+
+	if (min_value) {
+		/* by default, level 0 clock value as min value */
+		ret = smu_get_dpm_freq_by_index(smu, clk_type, 0, min_value);
+		if (ret)
+			return ret;
+	}
+
+	if (max_value) {
+		ret = smu_get_dpm_level_count(smu, clk_type, &level_count);
+		if (ret)
+			return ret;
+
+		ret = smu_get_dpm_freq_by_index(smu, clk_type, level_count - 1, max_value);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
 bool smu_clk_dpm_is_enabled(struct smu_context *smu, enum smu_clk_type clk_type)
 {
 	enum smu_feature_mask feature_id = 0;
@@ -404,10 +433,10 @@ int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type,
 
 	switch (block_type) {
 	case AMD_IP_BLOCK_TYPE_UVD:
-		ret = smu_dpm_set_uvd_enable(smu, gate);
+		ret = smu_dpm_set_uvd_enable(smu, !gate);
 		break;
 	case AMD_IP_BLOCK_TYPE_VCE:
-		ret = smu_dpm_set_vce_enable(smu, gate);
+		ret = smu_dpm_set_vce_enable(smu, !gate);
 		break;
 	case AMD_IP_BLOCK_TYPE_GFX:
 		ret = smu_gfx_off_control(smu, gate);
@@ -415,6 +444,9 @@ int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type,
 	case AMD_IP_BLOCK_TYPE_SDMA:
 		ret = smu_powergate_sdma(smu, gate);
 		break;
+	case AMD_IP_BLOCK_TYPE_JPEG:
+		ret = smu_dpm_set_jpeg_enable(smu, !gate);
+		break;
 	default:
 		break;
 	}
@@ -487,26 +519,25 @@ int smu_update_table(struct smu_context *smu, enum smu_table_id table_index, int
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct amdgpu_device *adev = smu->adev;
-	struct smu_table *table = NULL;
-	int ret = 0;
+	struct smu_table *table = &smu_table->driver_table;
 	int table_id = smu_table_get_index(smu, table_index);
+	uint32_t table_size;
+	int ret = 0;
 
 	if (!table_data || table_id >= SMU_TABLE_COUNT || table_id < 0)
 		return -EINVAL;
 
-	table = &smu_table->tables[table_index];
+	table_size = smu_table->tables[table_index].size;
 
-	if (drv2smu)
-		memcpy(table->cpu_addr, table_data, table->size);
+	if (drv2smu) {
+		memcpy(table->cpu_addr, table_data, table_size);
+		/*
+		 * Flush hdp cache: to guard the content seen by
+		 * GPU is consitent with CPU.
+		 */
+		amdgpu_asic_flush_hdp(adev, NULL);
+	}
 
-	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetDriverDramAddrHigh,
-					  upper_32_bits(table->mc_address));
-	if (ret)
-		return ret;
-	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetDriverDramAddrLow,
-					  lower_32_bits(table->mc_address));
-	if (ret)
-		return ret;
 	ret = smu_send_smc_msg_with_param(smu, drv2smu ?
 					  SMU_MSG_TransferTableDram2Smu :
 					  SMU_MSG_TransferTableSmu2Dram,
@@ -514,11 +545,10 @@ int smu_update_table(struct smu_context *smu, enum smu_table_id table_index, int
 	if (ret)
 		return ret;
 
-	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
-
-	if (!drv2smu)
-		memcpy(table_data, table->cpu_addr, table->size);
+	if (!drv2smu) {
+		amdgpu_asic_flush_hdp(adev, NULL);
+		memcpy(table_data, table->cpu_addr, table_size);
+	}
 
 	return ret;
 }
@@ -527,9 +557,12 @@ bool is_support_sw_smu(struct amdgpu_device *adev)
 {
 	if (adev->asic_type == CHIP_VEGA20)
 		return (amdgpu_dpm == 2) ? true : false;
-	else if (adev->asic_type >= CHIP_ARCTURUS)
-		return true;
-	else
+	else if (adev->asic_type >= CHIP_ARCTURUS) {
+		if (amdgpu_sriov_vf(adev)&& !amdgpu_sriov_is_pp_one_vf(adev))
+			return false;
+		else
+			return true;
+	} else
 		return false;
 }
 
@@ -637,12 +670,11 @@ int smu_feature_init_dpm(struct smu_context *smu)
 
 int smu_feature_is_enabled(struct smu_context *smu, enum smu_feature_mask mask)
 {
-	struct amdgpu_device *adev = smu->adev;
 	struct smu_feature *feature = &smu->smu_feature;
 	int feature_id;
 	int ret = 0;
 
-	if (adev->flags & AMD_IS_APU)
+	if (smu->is_apu)
 		return 1;
 
 	feature_id = smu_feature_get_index(smu, mask);
@@ -942,32 +974,56 @@ static int smu_init_fb_allocations(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = smu_table->tables;
+	struct smu_table *driver_table = &(smu_table->driver_table);
+	uint32_t max_table_size = 0;
 	int ret, i;
 
-	for (i = 0; i < SMU_TABLE_COUNT; i++) {
-		if (tables[i].size == 0)
-			continue;
+	/* VRAM allocation for tool table */
+	if (tables[SMU_TABLE_PMSTATUSLOG].size) {
 		ret = amdgpu_bo_create_kernel(adev,
-					      tables[i].size,
-					      tables[i].align,
-					      tables[i].domain,
-					      &tables[i].bo,
-					      &tables[i].mc_address,
-					      &tables[i].cpu_addr);
-		if (ret)
-			goto failed;
+					      tables[SMU_TABLE_PMSTATUSLOG].size,
+					      tables[SMU_TABLE_PMSTATUSLOG].align,
+					      tables[SMU_TABLE_PMSTATUSLOG].domain,
+					      &tables[SMU_TABLE_PMSTATUSLOG].bo,
+					      &tables[SMU_TABLE_PMSTATUSLOG].mc_address,
+					      &tables[SMU_TABLE_PMSTATUSLOG].cpu_addr);
+		if (ret) {
+			pr_err("VRAM allocation for tool table failed!\n");
+			return ret;
+		}
 	}
 
-	return 0;
-failed:
-	while (--i >= 0) {
+	/* VRAM allocation for driver table */
+	for (i = 0; i < SMU_TABLE_COUNT; i++) {
 		if (tables[i].size == 0)
 			continue;
-		amdgpu_bo_free_kernel(&tables[i].bo,
-				      &tables[i].mc_address,
-				      &tables[i].cpu_addr);
 
+		if (i == SMU_TABLE_PMSTATUSLOG)
+			continue;
+
+		if (max_table_size < tables[i].size)
+			max_table_size = tables[i].size;
+	}
+
+	driver_table->size = max_table_size;
+	driver_table->align = PAGE_SIZE;
+	driver_table->domain = AMDGPU_GEM_DOMAIN_VRAM;
+
+	ret = amdgpu_bo_create_kernel(adev,
+				      driver_table->size,
+				      driver_table->align,
+				      driver_table->domain,
+				      &driver_table->bo,
+				      &driver_table->mc_address,
+				      &driver_table->cpu_addr);
+	if (ret) {
+		pr_err("VRAM allocation for driver table failed!\n");
+		if (tables[SMU_TABLE_PMSTATUSLOG].mc_address)
+			amdgpu_bo_free_kernel(&tables[SMU_TABLE_PMSTATUSLOG].bo,
+					      &tables[SMU_TABLE_PMSTATUSLOG].mc_address,
+					      &tables[SMU_TABLE_PMSTATUSLOG].cpu_addr);
 	}
+
 	return ret;
 }
 
@@ -975,18 +1031,19 @@ static int smu_fini_fb_allocations(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = smu_table->tables;
-	uint32_t i = 0;
+	struct smu_table *driver_table = &(smu_table->driver_table);
 
 	if (!tables)
 		return 0;
 
-	for (i = 0; i < SMU_TABLE_COUNT; i++) {
-		if (tables[i].size == 0)
-			continue;
-		amdgpu_bo_free_kernel(&tables[i].bo,
-				      &tables[i].mc_address,
-				      &tables[i].cpu_addr);
-	}
+	if (tables[SMU_TABLE_PMSTATUSLOG].mc_address)
+		amdgpu_bo_free_kernel(&tables[SMU_TABLE_PMSTATUSLOG].bo,
+				      &tables[SMU_TABLE_PMSTATUSLOG].mc_address,
+				      &tables[SMU_TABLE_PMSTATUSLOG].cpu_addr);
+
+	amdgpu_bo_free_kernel(&driver_table->bo,
+			      &driver_table->mc_address,
+			      &driver_table->cpu_addr);
 
 	return 0;
 }
@@ -1056,28 +1113,31 @@ static int smu_smc_table_hw_init(struct smu_context *smu,
 	}
 
 	/* smu_dump_pptable(smu); */
+	if (!amdgpu_sriov_vf(adev)) {
+		ret = smu_set_driver_table_location(smu);
+		if (ret)
+			return ret;
 
-	/*
-	 * Copy pptable bo in the vram to smc with SMU MSGs such as
-	 * SetDriverDramAddr and TransferTableDram2Smu.
-	 */
-	ret = smu_write_pptable(smu);
-	if (ret)
-		return ret;
-
-	/* issue Run*Btc msg */
-	ret = smu_run_btc(smu);
-	if (ret)
-		return ret;
-
-	ret = smu_feature_set_allowed_mask(smu);
-	if (ret)
-		return ret;
+		/*
+		 * Copy pptable bo in the vram to smc with SMU MSGs such as
+		 * SetDriverDramAddr and TransferTableDram2Smu.
+		 */
+		ret = smu_write_pptable(smu);
+		if (ret)
+			return ret;
 
-	ret = smu_system_features_control(smu, true);
-	if (ret)
-		return ret;
+		/* issue Run*Btc msg */
+		ret = smu_run_btc(smu);
+		if (ret)
+			return ret;
+		ret = smu_feature_set_allowed_mask(smu);
+		if (ret)
+			return ret;
 
+		ret = smu_system_features_control(smu, true);
+		if (ret)
+			return ret;
+	}
 	if (adev->asic_type != CHIP_ARCTURUS) {
 		ret = smu_notify_display_change(smu);
 		if (ret)
@@ -1130,8 +1190,9 @@ static int smu_smc_table_hw_init(struct smu_context *smu,
 	/*
 	 * Set PMSTATUSLOG table bo address with SetToolsDramAddr MSG for tools.
 	 */
-	ret = smu_set_tool_table_location(smu);
-
+	if (!amdgpu_sriov_vf(adev)) {
+		ret = smu_set_tool_table_location(smu);
+	}
 	if (!smu_is_dpm_running(smu))
 		pr_info("dpm has been disabled\n");
 
@@ -1187,10 +1248,9 @@ static int smu_free_memory_pool(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *memory_pool = &smu_table->memory_pool;
-	int ret = 0;
 
 	if (memory_pool->size == SMU_MEMORY_POOL_SIZE_ZERO)
-		return ret;
+		return 0;
 
 	amdgpu_bo_free_kernel(&memory_pool->bo,
 			      &memory_pool->mc_address,
@@ -1198,7 +1258,7 @@ static int smu_free_memory_pool(struct smu_context *smu)
 
 	memset(memory_pool, 0, sizeof(struct smu_table));
 
-	return ret;
+	return 0;
 }
 
 static int smu_start_smc_engine(struct smu_context *smu)
@@ -1237,12 +1297,16 @@ static int smu_hw_init(void *handle)
 		return ret;
 	}
 
-	if (adev->flags & AMD_IS_APU) {
+	if (smu->is_apu) {
 		smu_powergate_sdma(&adev->smu, false);
 		smu_powergate_vcn(&adev->smu, false);
+		smu_powergate_jpeg(&adev->smu, false);
 		smu_set_gfx_cgpg(&adev->smu, true);
 	}
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
 	if (!smu->pm_enabled)
 		return 0;
 
@@ -1285,7 +1349,7 @@ failed:
 
 static int smu_stop_dpms(struct smu_context *smu)
 {
-	return smu_send_smc_msg(smu, SMU_MSG_DisableAllSmuFeatures);
+	return smu_system_features_control(smu, false);
 }
 
 static int smu_hw_fini(void *handle)
@@ -1295,36 +1359,45 @@ static int smu_hw_fini(void *handle)
 	struct smu_table_context *table_context = &smu->smu_table;
 	int ret = 0;
 
-	if (adev->flags & AMD_IS_APU) {
+	if (amdgpu_sriov_vf(adev)&& !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	if (smu->is_apu) {
 		smu_powergate_sdma(&adev->smu, true);
 		smu_powergate_vcn(&adev->smu, true);
+		smu_powergate_jpeg(&adev->smu, true);
 	}
 
-	ret = smu_stop_thermal_control(smu);
-	if (ret) {
-		pr_warn("Fail to stop thermal control!\n");
-		return ret;
-	}
+	if (!smu->pm_enabled)
+		return 0;
 
-	/*
-	 * For custom pptable uploading, skip the DPM features
-	 * disable process on Navi1x ASICs.
-	 *   - As the gfx related features are under control of
-	 *     RLC on those ASICs. RLC reinitialization will be
-	 *     needed to reenable them. That will cost much more
-	 *     efforts.
-	 *
-	 *   - SMU firmware can handle the DPM reenablement
-	 *     properly.
-	 */
-	if (!smu->uploading_custom_pp_table ||
-	    !((adev->asic_type >= CHIP_NAVI10) &&
-	      (adev->asic_type <= CHIP_NAVI12))) {
-		ret = smu_stop_dpms(smu);
+	if (!amdgpu_sriov_vf(adev)){
+		ret = smu_stop_thermal_control(smu);
 		if (ret) {
-			pr_warn("Fail to stop Dpms!\n");
+			pr_warn("Fail to stop thermal control!\n");
 			return ret;
 		}
+
+		/*
+		 * For custom pptable uploading, skip the DPM features
+		 * disable process on Navi1x ASICs.
+		 *   - As the gfx related features are under control of
+		 *     RLC on those ASICs. RLC reinitialization will be
+		 *     needed to reenable them. That will cost much more
+		 *     efforts.
+		 *
+		 *   - SMU firmware can handle the DPM reenablement
+		 *     properly.
+		 */
+		if (!smu->uploading_custom_pp_table ||
+				!((adev->asic_type >= CHIP_NAVI10) &&
+					(adev->asic_type <= CHIP_NAVI12))) {
+			ret = smu_stop_dpms(smu);
+			if (ret) {
+				pr_warn("Fail to stop Dpms!\n");
+				return ret;
+			}
+		}
 	}
 
 	kfree(table_context->driver_pptable);
@@ -1370,14 +1443,17 @@ static int smu_suspend(void *handle)
 	struct smu_context *smu = &adev->smu;
 	bool baco_feature_is_enabled = false;
 
-	if(!(adev->flags & AMD_IS_APU))
+	if (!smu->pm_enabled)
+		return 0;
+
+	if(!smu->is_apu)
 		baco_feature_is_enabled = smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT);
 
 	ret = smu_system_features_control(smu, false);
 	if (ret)
 		return ret;
 
-	if (adev->in_gpu_reset && baco_feature_is_enabled) {
+	if (baco_feature_is_enabled) {
 		ret = smu_feature_set_enabled(smu, SMU_FEATURE_BACO_BIT, true);
 		if (ret) {
 			pr_warn("set BACO feature enabled failed, return %d\n", ret);
@@ -1402,6 +1478,12 @@ static int smu_resume(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = &adev->smu;
 
+	if (amdgpu_sriov_vf(adev)&& !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	if (!smu->pm_enabled)
+		return 0;
+
 	pr_info("SMU is resuming...\n");
 
 	ret = smu_start_smc_engine(smu);
@@ -1600,43 +1682,6 @@ static int smu_enable_umd_pstate(void *handle,
 	return 0;
 }
 
-static int smu_default_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
-{
-	int ret = 0;
-	uint32_t sclk_mask, mclk_mask, soc_mask;
-
-	switch (level) {
-	case AMD_DPM_FORCED_LEVEL_HIGH:
-		ret = smu_force_dpm_limit_value(smu, true);
-		break;
-	case AMD_DPM_FORCED_LEVEL_LOW:
-		ret = smu_force_dpm_limit_value(smu, false);
-		break;
-	case AMD_DPM_FORCED_LEVEL_AUTO:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
-		ret = smu_unforce_dpm_levels(smu);
-		break;
-	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
-		ret = smu_get_profiling_clk_mask(smu, level,
-						 &sclk_mask,
-						 &mclk_mask,
-						 &soc_mask);
-		if (ret)
-			return ret;
-		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
-		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
-		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
-		break;
-	case AMD_DPM_FORCED_LEVEL_MANUAL:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
-	default:
-		break;
-	}
-	return ret;
-}
-
 int smu_adjust_power_state_dynamic(struct smu_context *smu,
 				   enum amd_dpm_forced_level level,
 				   bool skip_display_settings)
@@ -1664,7 +1709,7 @@ int smu_adjust_power_state_dynamic(struct smu_context *smu,
 	}
 
 	if (!skip_display_settings) {
-		ret = smu_notify_smc_dispaly_config(smu);
+		ret = smu_notify_smc_display_config(smu);
 		if (ret) {
 			pr_err("Failed to notify smc display config!");
 			return ret;
@@ -1674,11 +1719,8 @@ int smu_adjust_power_state_dynamic(struct smu_context *smu,
 	if (smu_dpm_ctx->dpm_level != level) {
 		ret = smu_asic_set_performance_level(smu, level);
 		if (ret) {
-			ret = smu_default_set_performance_level(smu, level);
-			if (ret) {
-				pr_err("Failed to set performance level!");
-				return ret;
-			}
+			pr_err("Failed to set performance level!");
+			return ret;
 		}
 
 		/* update the saved copy */
@@ -1920,27 +1962,25 @@ int smu_set_df_cstate(struct smu_context *smu,
 
 int smu_write_watermarks_table(struct smu_context *smu)
 {
-	int ret = 0;
-	struct smu_table_context *smu_table = &smu->smu_table;
-	struct smu_table *table = NULL;
-
-	table = &smu_table->tables[SMU_TABLE_WATERMARKS];
+	void *watermarks_table = smu->smu_table.watermarks_table;
 
-	if (!table->cpu_addr)
+	if (!watermarks_table)
 		return -EINVAL;
 
-	ret = smu_update_table(smu, SMU_TABLE_WATERMARKS, 0, table->cpu_addr,
+	return smu_update_table(smu,
+				SMU_TABLE_WATERMARKS,
+				0,
+				watermarks_table,
 				true);
-
-	return ret;
 }
 
 int smu_set_watermarks_for_clock_ranges(struct smu_context *smu,
 		struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges)
 {
-	int ret = 0;
-	struct smu_table *watermarks = &smu->smu_table.tables[SMU_TABLE_WATERMARKS];
-	void *table = watermarks->cpu_addr;
+	void *table = smu->smu_table.watermarks_table;
+
+	if (!table)
+		return -EINVAL;
 
 	mutex_lock(&smu->mutex);
 
@@ -1954,7 +1994,7 @@ int smu_set_watermarks_for_clock_ranges(struct smu_context *smu,
 
 	mutex_unlock(&smu->mutex);
 
-	return ret;
+	return 0;
 }
 
 const struct amd_ip_funcs smu_ip_funcs = {
@@ -2279,13 +2319,9 @@ int smu_set_active_display_count(struct smu_context *smu, uint32_t count)
 {
 	int ret = 0;
 
-	mutex_lock(&smu->mutex);
-
 	if (smu->ppt_funcs->set_active_display_count)
 		ret = smu->ppt_funcs->set_active_display_count(smu, count);
 
-	mutex_unlock(&smu->mutex);
-
 	return ret;
 }
 
@@ -2432,7 +2468,7 @@ bool smu_baco_is_support(struct smu_context *smu)
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->baco_is_support)
+	if (smu->ppt_funcs && smu->ppt_funcs->baco_is_support)
 		ret = smu->ppt_funcs->baco_is_support(smu);
 
 	mutex_unlock(&smu->mutex);
@@ -2452,14 +2488,28 @@ int smu_baco_get_state(struct smu_context *smu, enum smu_baco_state *state)
 	return 0;
 }
 
-int smu_baco_reset(struct smu_context *smu)
+int smu_baco_enter(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->baco_enter)
+		ret = smu->ppt_funcs->baco_enter(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_baco_exit(struct smu_context *smu)
 {
 	int ret = 0;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->baco_reset)
-		ret = smu->ppt_funcs->baco_reset(smu);
+	if (smu->ppt_funcs->baco_exit)
+		ret = smu->ppt_funcs->baco_exit(smu);
 
 	mutex_unlock(&smu->mutex);
 
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 472e9fed411a..14ba6aa876e2 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -179,6 +179,7 @@ static struct smu_11_0_cmn2aisc_mapping arcturus_table_map[SMU_TABLE_COUNT] = {
 	TAB_MAP(DRIVER_SMU_CONFIG),
 	TAB_MAP(OVERDRIVE),
 	TAB_MAP(I2C_COMMANDS),
+	TAB_MAP(ACTIVITY_MONITOR_COEFF),
 };
 
 static struct smu_11_0_cmn2aisc_mapping arcturus_pwr_src_map[SMU_POWER_SOURCE_COUNT] = {
@@ -280,10 +281,8 @@ static int arcturus_get_workload_type(struct smu_context *smu, enum PP_SMC_POWER
 		return -EINVAL;
 
 	mapping = arcturus_workload_map[profile];
-	if (!(mapping.valid_mapping)) {
-		pr_warn("Unsupported SMU power source: %d\n", profile);
+	if (!(mapping.valid_mapping))
 		return -EINVAL;
-	}
 
 	return mapping.map_to;
 }
@@ -304,6 +303,10 @@ static int arcturus_tables_init(struct smu_context *smu, struct smu_table *table
 	SMU_TABLE_INIT(tables, SMU_TABLE_I2C_COMMANDS, sizeof(SwI2cRequest_t),
 			       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 
+	SMU_TABLE_INIT(tables, SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+		       sizeof(DpmActivityMonitorCoeffInt_t), PAGE_SIZE,
+		       AMDGPU_GEM_DOMAIN_VRAM);
+
 	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
 	if (!smu_table->metrics_table)
 		return -ENOMEM;
@@ -495,6 +498,7 @@ static int arcturus_store_powerplay_table(struct smu_context *smu)
 {
 	struct smu_11_0_powerplay_table *powerplay_table = NULL;
 	struct smu_table_context *table_context = &smu->smu_table;
+	struct smu_baco_context *smu_baco = &smu->smu_baco;
 	int ret = 0;
 
 	if (!table_context->power_play_table)
@@ -507,6 +511,12 @@ static int arcturus_store_powerplay_table(struct smu_context *smu)
 
 	table_context->thermal_controller_type = powerplay_table->thermal_controller_type;
 
+	mutex_lock(&smu_baco->mutex);
+	if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO ||
+	    powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO)
+		smu_baco->platform_support = true;
+	mutex_unlock(&smu_baco->mutex);
+
 	return ret;
 }
 
@@ -1308,6 +1318,8 @@ static int arcturus_get_power_limit(struct smu_context *smu,
 static int arcturus_get_power_profile_mode(struct smu_context *smu,
 					   char *buf)
 {
+	struct amdgpu_device *adev = smu->adev;
+	DpmActivityMonitorCoeffInt_t activity_monitor;
 	static const char *profile_name[] = {
 					"BOOTUP_DEFAULT",
 					"3D_FULL_SCREEN",
@@ -1317,14 +1329,35 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu,
 					"COMPUTE",
 					"CUSTOM"};
 	static const char *title[] = {
-			"PROFILE_INDEX(NAME)"};
+			"PROFILE_INDEX(NAME)",
+			"CLOCK_TYPE(NAME)",
+			"FPS",
+			"UseRlcBusy",
+			"MinActiveFreqType",
+			"MinActiveFreq",
+			"BoosterFreqType",
+			"BoosterFreq",
+			"PD_Data_limit_c",
+			"PD_Data_error_coeff",
+			"PD_Data_error_rate_coeff"};
 	uint32_t i, size = 0;
 	int16_t workload_type = 0;
+	int result = 0;
+	uint32_t smu_version;
 
-	if (!smu->pm_enabled || !buf)
+	if (!buf)
 		return -EINVAL;
 
-	size += sprintf(buf + size, "%16s\n",
+	result = smu_get_smc_version(smu, NULL, &smu_version);
+	if (result)
+		return result;
+
+	if (smu_version >= 0x360d00 && !amdgpu_sriov_vf(adev))
+		size += sprintf(buf + size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
+			title[0], title[1], title[2], title[3], title[4], title[5],
+			title[6], title[7], title[8], title[9], title[10]);
+	else
+		size += sprintf(buf + size, "%16s\n",
 			title[0]);
 
 	for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) {
@@ -1336,8 +1369,50 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu,
 		if (workload_type < 0)
 			continue;
 
+		if (smu_version >= 0x360d00 && !amdgpu_sriov_vf(adev)) {
+			result = smu_update_table(smu,
+						  SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+						  workload_type,
+						  (void *)(&activity_monitor),
+						  false);
+			if (result) {
+				pr_err("[%s] Failed to get activity monitor!", __func__);
+				return result;
+			}
+		}
+
 		size += sprintf(buf + size, "%2d %14s%s\n",
 			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
+
+		if (smu_version >= 0x360d00 && !amdgpu_sriov_vf(adev)) {
+			size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+				" ",
+				0,
+				"GFXCLK",
+				activity_monitor.Gfx_FPS,
+				activity_monitor.Gfx_UseRlcBusy,
+				activity_monitor.Gfx_MinActiveFreqType,
+				activity_monitor.Gfx_MinActiveFreq,
+				activity_monitor.Gfx_BoosterFreqType,
+				activity_monitor.Gfx_BoosterFreq,
+				activity_monitor.Gfx_PD_Data_limit_c,
+				activity_monitor.Gfx_PD_Data_error_coeff,
+				activity_monitor.Gfx_PD_Data_error_rate_coeff);
+
+			size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+				" ",
+				1,
+				"UCLK",
+				activity_monitor.Mem_FPS,
+				activity_monitor.Mem_UseRlcBusy,
+				activity_monitor.Mem_MinActiveFreqType,
+				activity_monitor.Mem_MinActiveFreq,
+				activity_monitor.Mem_BoosterFreqType,
+				activity_monitor.Mem_BoosterFreq,
+				activity_monitor.Mem_PD_Data_limit_c,
+				activity_monitor.Mem_PD_Data_error_coeff,
+				activity_monitor.Mem_PD_Data_error_rate_coeff);
+		}
 	}
 
 	return size;
@@ -1347,18 +1422,69 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu,
 					   long *input,
 					   uint32_t size)
 {
+	DpmActivityMonitorCoeffInt_t activity_monitor;
 	int workload_type = 0;
 	uint32_t profile_mode = input[size];
 	int ret = 0;
-
-	if (!smu->pm_enabled)
-		return -EINVAL;
+	uint32_t smu_version;
 
 	if (profile_mode > PP_SMC_POWER_PROFILE_CUSTOM) {
 		pr_err("Invalid power profile mode %d\n", profile_mode);
 		return -EINVAL;
 	}
 
+	ret = smu_get_smc_version(smu, NULL, &smu_version);
+	if (ret)
+		return ret;
+
+	if ((profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) &&
+	     (smu_version >=0x360d00)) {
+		ret = smu_update_table(smu,
+				       SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+				       WORKLOAD_PPLIB_CUSTOM_BIT,
+				       (void *)(&activity_monitor),
+				       false);
+		if (ret) {
+			pr_err("[%s] Failed to get activity monitor!", __func__);
+			return ret;
+		}
+
+		switch (input[0]) {
+		case 0: /* Gfxclk */
+			activity_monitor.Gfx_FPS = input[1];
+			activity_monitor.Gfx_UseRlcBusy = input[2];
+			activity_monitor.Gfx_MinActiveFreqType = input[3];
+			activity_monitor.Gfx_MinActiveFreq = input[4];
+			activity_monitor.Gfx_BoosterFreqType = input[5];
+			activity_monitor.Gfx_BoosterFreq = input[6];
+			activity_monitor.Gfx_PD_Data_limit_c = input[7];
+			activity_monitor.Gfx_PD_Data_error_coeff = input[8];
+			activity_monitor.Gfx_PD_Data_error_rate_coeff = input[9];
+			break;
+		case 1: /* Uclk */
+			activity_monitor.Mem_FPS = input[1];
+			activity_monitor.Mem_UseRlcBusy = input[2];
+			activity_monitor.Mem_MinActiveFreqType = input[3];
+			activity_monitor.Mem_MinActiveFreq = input[4];
+			activity_monitor.Mem_BoosterFreqType = input[5];
+			activity_monitor.Mem_BoosterFreq = input[6];
+			activity_monitor.Mem_PD_Data_limit_c = input[7];
+			activity_monitor.Mem_PD_Data_error_coeff = input[8];
+			activity_monitor.Mem_PD_Data_error_rate_coeff = input[9];
+			break;
+		}
+
+		ret = smu_update_table(smu,
+				       SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+				       WORKLOAD_PPLIB_CUSTOM_BIT,
+				       (void *)(&activity_monitor),
+				       true);
+		if (ret) {
+			pr_err("[%s] Failed to set activity monitor!", __func__);
+			return ret;
+		}
+	}
+
 	/*
 	 * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT
 	 * Not all profile modes are supported on arcturus.
@@ -1897,7 +2023,7 @@ static int arcturus_i2c_eeprom_read_data(struct i2c_adapter *control,
 	SwI2cRequest_t req;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	struct smu_table_context *smu_table = &adev->smu.smu_table;
-	struct smu_table *table = &smu_table->tables[SMU_TABLE_I2C_COMMANDS];
+	struct smu_table *table = &smu_table->driver_table;
 
 	memset(&req, 0, sizeof(req));
 	arcturus_fill_eeprom_i2c_req(&req, false, address, numbytes, data);
@@ -2051,8 +2177,12 @@ static const struct i2c_algorithm arcturus_i2c_eeprom_i2c_algo = {
 static int arcturus_i2c_eeprom_control_init(struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct smu_context *smu = &adev->smu;
 	int res;
 
+	if (!smu->pm_enabled)
+		return -EOPNOTSUPP;
+
 	control->owner = THIS_MODULE;
 	control->class = I2C_CLASS_SPD;
 	control->dev.parent = &adev->pdev->dev;
@@ -2068,6 +2198,12 @@ static int arcturus_i2c_eeprom_control_init(struct i2c_adapter *control)
 
 static void arcturus_i2c_eeprom_control_fini(struct i2c_adapter *control)
 {
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct smu_context *smu = &adev->smu;
+
+	if (!smu->pm_enabled)
+		return;
+
 	i2c_del_adapter(control);
 }
 
@@ -2112,6 +2248,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.get_profiling_clk_mask = arcturus_get_profiling_clk_mask,
 	.get_power_profile_mode = arcturus_get_power_profile_mode,
 	.set_power_profile_mode = arcturus_set_power_profile_mode,
+	.set_performance_level = smu_v11_0_set_performance_level,
 	/* debug (internal used) */
 	.dump_pptable = arcturus_dump_pptable,
 	.get_power_limit = arcturus_get_power_limit,
@@ -2135,6 +2272,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.check_fw_version = smu_v11_0_check_fw_version,
 	.write_pptable = smu_v11_0_write_pptable,
 	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_driver_table_location = smu_v11_0_set_driver_table_location,
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
@@ -2163,7 +2301,8 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.baco_is_support= smu_v11_0_baco_is_support,
 	.baco_get_state = smu_v11_0_baco_get_state,
 	.baco_set_state = smu_v11_0_baco_set_state,
-	.baco_reset = smu_v11_0_baco_reset,
+	.baco_enter = smu_v11_0_baco_enter,
+	.baco_exit = smu_v11_0_baco_exit,
 	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index cc57fb953e62..9454ab50f9a1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -81,8 +81,8 @@ int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 	adev = hwmgr->adev;
 
 	/* Skip for suspend/resume case */
-	if (smum_is_dpm_running(hwmgr) && !amdgpu_passthrough(adev)
-		&& adev->in_suspend) {
+	if (!hwmgr->pp_one_vf && smum_is_dpm_running(hwmgr)
+	    && !amdgpu_passthrough(adev) && adev->in_suspend) {
 		pr_info("dpm has been enabled\n");
 		return 0;
 	}
@@ -99,6 +99,9 @@ int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 
 	PHM_FUNC_CHECK(hwmgr);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (!smum_is_dpm_running(hwmgr)) {
 		pr_info("dpm has been disabled\n");
 		return 0;
@@ -200,6 +203,9 @@ int phm_stop_thermal_controller(struct pp_hwmgr *hwmgr)
 {
 	PHM_FUNC_CHECK(hwmgr);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (hwmgr->hwmgr_func->stop_thermal_controller == NULL)
 		return -EINVAL;
 
@@ -237,6 +243,9 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 		TEMP_RANGE_MAX};
 	struct amdgpu_device *adev = hwmgr->adev;
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (hwmgr->hwmgr_func->get_thermal_temperature_range)
 		hwmgr->hwmgr_func->get_thermal_temperature_range(
 				hwmgr, &range);
@@ -263,6 +272,8 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 bool phm_check_smc_update_required_for_display_configuration(struct pp_hwmgr *hwmgr)
 {
 	PHM_FUNC_CHECK(hwmgr);
+	if (hwmgr->pp_one_vf)
+		return false;
 
 	if (hwmgr->hwmgr_func->check_smc_update_required_for_display_configuration == NULL)
 		return false;
@@ -482,6 +493,9 @@ int phm_disable_smc_firmware_ctf(struct pp_hwmgr *hwmgr)
 {
 	PHM_FUNC_CHECK(hwmgr);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (hwmgr->hwmgr_func->disable_smc_firmware_ctf == NULL)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index d2909c91d65b..f48fdc7f0382 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -221,6 +221,9 @@ int hwmgr_hw_init(struct pp_hwmgr *hwmgr)
 {
 	int ret = 0;
 
+	hwmgr->pp_one_vf = amdgpu_sriov_is_pp_one_vf((struct amdgpu_device *)hwmgr->adev);
+	hwmgr->pm_en = (amdgpu_dpm && (hwmgr->not_vf || hwmgr->pp_one_vf))
+			? true : false;
 	if (!hwmgr->pm_en)
 		return 0;
 
@@ -279,7 +282,7 @@ err:
 
 int hwmgr_hw_fini(struct pp_hwmgr *hwmgr)
 {
-	if (!hwmgr || !hwmgr->pm_en)
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->not_vf)
 		return 0;
 
 	phm_stop_thermal_controller(hwmgr);
@@ -299,7 +302,7 @@ int hwmgr_suspend(struct pp_hwmgr *hwmgr)
 {
 	int ret = 0;
 
-	if (!hwmgr || !hwmgr->pm_en)
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->not_vf)
 		return 0;
 
 	phm_disable_smc_firmware_ctf(hwmgr);
@@ -321,7 +324,7 @@ int hwmgr_resume(struct pp_hwmgr *hwmgr)
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!hwmgr->pm_en)
+	if (!hwmgr->not_vf || !hwmgr->pm_en)
 		return 0;
 
 	ret = phm_setup_asic(hwmgr);
@@ -365,6 +368,8 @@ int hwmgr_handle_task(struct pp_hwmgr *hwmgr, enum amd_pp_task task_id,
 
 	switch (task_id) {
 	case AMD_PP_TASK_DISPLAY_CONFIG_CHANGE:
+		if (!hwmgr->not_vf)
+			return ret;
 		ret = phm_pre_display_configuration_changed(hwmgr);
 		if (ret)
 			return ret;
@@ -381,6 +386,8 @@ int hwmgr_handle_task(struct pp_hwmgr *hwmgr, enum amd_pp_task task_id,
 		enum PP_StateUILabel requested_ui_label;
 		struct pp_power_state *requested_ps = NULL;
 
+		if (!hwmgr->not_vf)
+			return ret;
 		if (user_state == NULL) {
 			ret = -EINVAL;
 			break;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
index 6bf48934fdc4..31a32a79cfc2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
@@ -262,20 +262,22 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set
 	uint32_t index;
 	long workload;
 
-	if (!skip_display_settings)
-		phm_display_configuration_changed(hwmgr);
-
-	if (hwmgr->ps)
-		power_state_management(hwmgr, new_ps);
-	else
-		/*
-		 * for vega12/vega20 which does not support power state manager
-		 * DAL clock limits should also be honoured
-		 */
-		phm_apply_clock_adjust_rules(hwmgr);
-
-	if (!skip_display_settings)
-		phm_notify_smc_display_config_after_ps_adjustment(hwmgr);
+	if (hwmgr->not_vf) {
+		if (!skip_display_settings)
+			phm_display_configuration_changed(hwmgr);
+
+		if (hwmgr->ps)
+			power_state_management(hwmgr, new_ps);
+		else
+			/*
+			 * for vega12/vega20 which does not support power state manager
+			 * DAL clock limits should also be honoured
+			 */
+			phm_apply_clock_adjust_rules(hwmgr);
+
+		if (!skip_display_settings)
+			phm_notify_smc_display_config_after_ps_adjustment(hwmgr);
+	}
 
 	if (!phm_force_dpm_levels(hwmgr, hwmgr->request_dpm_level))
 		hwmgr->dpm_level = hwmgr->request_dpm_level;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 1115761982a7..4e8ab139bb3b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -1151,12 +1151,11 @@ static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 	struct smu10_hwmgr *data = hwmgr->backend;
 	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 	Watermarks_t *table = &(data->water_marks_table);
-	int result = 0;
 
 	smu_set_watermarks_for_clocks_ranges(table,wm_with_clock_ranges);
 	smum_smc_table_manager(hwmgr, (uint8_t *)table, (uint16_t)SMU10_WMTABLE, false);
 	data->water_marks_exist = true;
-	return result;
+	return 0;
 }
 
 static int smu10_smus_notify_pwe(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index f73dff68e799..d70abada66bf 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -4238,7 +4238,6 @@ static int smu7_check_mc_firmware(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
-	uint32_t vbios_version;
 	uint32_t tmp;
 
 	/* Read MC indirect register offset 0x9F bits [3:0] to see
@@ -4247,7 +4246,6 @@ static int smu7_check_mc_firmware(struct pp_hwmgr *hwmgr)
 	 */
 
 	smu7_get_mc_microcode_version(hwmgr);
-	vbios_version = hwmgr->microcode_version_info.MC & 0xf;
 
 	data->need_long_memory_training = false;
 
@@ -4945,7 +4943,7 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 			title[0], title[1], title[2], title[3],
 			title[4], title[5], title[6], title[7]);
 
-	len = sizeof(smu7_profiling) / sizeof(struct profile_mode_setting);
+	len = ARRAY_SIZE(smu7_profiling);
 
 	for (i = 0; i < len; i++) {
 		if (i == hwmgr->power_profile_mode) {
@@ -5077,13 +5075,11 @@ static int smu7_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_hw
 				PHM_PerformanceLevel *level)
 {
 	const struct smu7_power_state *ps;
-	struct smu7_hwmgr *data;
 	uint32_t i;
 
 	if (level == NULL || hwmgr == NULL || state == NULL)
 		return -EINVAL;
 
-	data = hwmgr->backend;
 	ps = cast_const_phw_smu7_power_state(state);
 
 	i = index > ps->performance_level_count - 1 ?
@@ -5189,13 +5185,11 @@ uint8_t smu7_get_sleep_divider_id_from_clock(uint32_t clock,
 
 int smu7_init_function_pointers(struct pp_hwmgr *hwmgr)
 {
-	int ret = 0;
-
 	hwmgr->hwmgr_func = &smu7_hwmgr_funcs;
 	if (hwmgr->pp_table_version == PP_TABLE_V0)
 		hwmgr->pptable_func = &pptable_funcs;
 	else if (hwmgr->pp_table_version == PP_TABLE_V1)
 		hwmgr->pptable_func = &pptable_v1_0_funcs;
 
-	return ret;
+	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index d71a492c87a3..92a65e3daff4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -912,6 +912,9 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	hwmgr->platform_descriptor.clockStep.memoryClock = 500;
 
 	data->total_active_cus = adev->gfx.cu_info.number;
+	if (!hwmgr->not_vf)
+		return result;
+
 	/* Setup default Overdrive Fan control settings */
 	data->odn_fan_table.target_fan_speed =
 			hwmgr->thermal_controller.advanceFanControlParameters.usMaxFanRPM;
@@ -979,6 +982,9 @@ static int vega10_setup_dpm_led_config(struct pp_hwmgr *hwmgr)
 
 static int vega10_setup_asic_task(struct pp_hwmgr *hwmgr)
 {
+	if (!hwmgr->not_vf)
+		return 0;
+
 	PP_ASSERT_WITH_CODE(!vega10_init_sclk_threshold(hwmgr),
 			"Failed to init sclk threshold!",
 			return -EINVAL);
@@ -2503,6 +2509,9 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 			"Failed to setup default DPM tables!",
 			return result);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	/* initialize ODN table */
 	if (hwmgr->od_enabled) {
 		if (odn_table->max_vddc) {
@@ -2826,6 +2835,8 @@ static int vega10_stop_dpm(struct pp_hwmgr *hwmgr, uint32_t bitmap)
 	struct vega10_hwmgr *data = hwmgr->backend;
 	uint32_t i, feature_mask = 0;
 
+	if (!hwmgr->not_vf)
+		return 0;
 
 	if(data->smu_features[GNLD_LED_DISPLAY].supported == true){
 		PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr,
@@ -2932,61 +2943,73 @@ static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 	struct vega10_hwmgr *data = hwmgr->backend;
 	int tmp_result, result = 0;
 
-	vega10_enable_disable_PCC_limit_feature(hwmgr, true);
-
-	smum_send_msg_to_smc_with_parameter(hwmgr,
-		PPSMC_MSG_ConfigureTelemetry, data->config_telemetry);
+	if (hwmgr->not_vf) {
+		vega10_enable_disable_PCC_limit_feature(hwmgr, true);
 
-	tmp_result = vega10_construct_voltage_tables(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to construct voltage tables!",
-			result = tmp_result);
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_ConfigureTelemetry, data->config_telemetry);
 
-	tmp_result = vega10_init_smc_table(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to initialize SMC table!",
-			result = tmp_result);
+		tmp_result = vega10_construct_voltage_tables(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to construct voltage tables!",
+				    result = tmp_result);
+	}
 
-	if (PP_CAP(PHM_PlatformCaps_ThermalController)) {
-		tmp_result = vega10_enable_thermal_protection(hwmgr);
+	if (hwmgr->not_vf || hwmgr->pp_one_vf) {
+		tmp_result = vega10_init_smc_table(hwmgr);
 		PP_ASSERT_WITH_CODE(!tmp_result,
-				"Failed to enable thermal protection!",
-				result = tmp_result);
+				    "Failed to initialize SMC table!",
+				    result = tmp_result);
 	}
 
-	tmp_result = vega10_enable_vrhot_feature(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to enable VR hot feature!",
-			result = tmp_result);
+	if (hwmgr->not_vf) {
+		if (PP_CAP(PHM_PlatformCaps_ThermalController)) {
+			tmp_result = vega10_enable_thermal_protection(hwmgr);
+			PP_ASSERT_WITH_CODE(!tmp_result,
+					    "Failed to enable thermal protection!",
+					    result = tmp_result);
+		}
 
-	tmp_result = vega10_enable_deep_sleep_master_switch(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to enable deep sleep master switch!",
-			result = tmp_result);
+		tmp_result = vega10_enable_vrhot_feature(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to enable VR hot feature!",
+				    result = tmp_result);
 
-	tmp_result = vega10_start_dpm(hwmgr, SMC_DPM_FEATURES);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to start DPM!", result = tmp_result);
+		tmp_result = vega10_enable_deep_sleep_master_switch(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to enable deep sleep master switch!",
+				    result = tmp_result);
+	}
 
-	/* enable didt, do not abort if failed didt */
-	tmp_result = vega10_enable_didt_config(hwmgr);
-	PP_ASSERT(!tmp_result,
-			"Failed to enable didt config!");
+	if (hwmgr->not_vf) {
+		tmp_result = vega10_start_dpm(hwmgr, SMC_DPM_FEATURES);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to start DPM!", result = tmp_result);
+	}
+
+	if (hwmgr->not_vf) {
+		/* enable didt, do not abort if failed didt */
+		tmp_result = vega10_enable_didt_config(hwmgr);
+		PP_ASSERT(!tmp_result,
+			  "Failed to enable didt config!");
+	}
 
 	tmp_result = vega10_enable_power_containment(hwmgr);
 	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to enable power containment!",
-			result = tmp_result);
+			    "Failed to enable power containment!",
+			    result = tmp_result);
 
-	tmp_result = vega10_power_control_set_level(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to power control set level!",
-			result = tmp_result);
+	if (hwmgr->not_vf) {
+		tmp_result = vega10_power_control_set_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to power control set level!",
+				    result = tmp_result);
 
-	tmp_result = vega10_enable_ulv(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to enable ULV!",
-			result = tmp_result);
+		tmp_result = vega10_enable_ulv(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to enable ULV!",
+				    result = tmp_result);
+	}
 
 	return result;
 }
@@ -3080,11 +3103,22 @@ static int vega10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr,
 	performance_level->soc_clock = socclk_dep_table->entries
 				[state_entry->ucSocClockIndexHigh].ulClk;
 	if (gfxclk_dep_table->ucRevId == 0) {
-		performance_level->gfx_clock = gfxclk_dep_table->entries
-			[state_entry->ucGfxClockIndexHigh].ulClk;
+		/* under vega10 pp one vf mode, the gfx clk dpm need be lower
+		 * to level-4 due to the limited 110w-power
+		 */
+		if (hwmgr->pp_one_vf && (state_entry->ucGfxClockIndexHigh > 0))
+			performance_level->gfx_clock =
+				gfxclk_dep_table->entries[4].ulClk;
+		else
+			performance_level->gfx_clock = gfxclk_dep_table->entries
+				[state_entry->ucGfxClockIndexHigh].ulClk;
 	} else if (gfxclk_dep_table->ucRevId == 1) {
 		patom_record_V2 = (ATOM_Vega10_GFXCLK_Dependency_Record_V2 *)gfxclk_dep_table->entries;
-		performance_level->gfx_clock = patom_record_V2[state_entry->ucGfxClockIndexHigh].ulClk;
+		if (hwmgr->pp_one_vf && (state_entry->ucGfxClockIndexHigh > 0))
+			performance_level->gfx_clock = patom_record_V2[4].ulClk;
+		else
+			performance_level->gfx_clock =
+				patom_record_V2[state_entry->ucGfxClockIndexHigh].ulClk;
 	}
 
 	performance_level->mem_clock = mclk_dep_table->entries
@@ -3495,6 +3529,7 @@ static int vega10_upload_dpm_bootup_level(struct pp_hwmgr *hwmgr)
 			smum_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetSoftMinGfxclkByIndex,
 				data->smc_state_table.gfx_boot_level);
+
 			data->dpm_table.gfx_table.dpm_state.soft_min_level =
 					data->smc_state_table.gfx_boot_level;
 		}
@@ -3503,7 +3538,8 @@ static int vega10_upload_dpm_bootup_level(struct pp_hwmgr *hwmgr)
 	if (!data->registry_data.mclk_dpm_key_disabled) {
 		if (data->smc_state_table.mem_boot_level !=
 				data->dpm_table.mem_table.dpm_state.soft_min_level) {
-			if (data->smc_state_table.mem_boot_level == NUM_UCLK_DPM_LEVELS - 1) {
+			if ((data->smc_state_table.mem_boot_level == NUM_UCLK_DPM_LEVELS - 1)
+			    && hwmgr->not_vf) {
 				socclk_idx = vega10_get_soc_index_for_max_uclk(hwmgr);
 				smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMinSocclkByIndex,
@@ -3518,6 +3554,9 @@ static int vega10_upload_dpm_bootup_level(struct pp_hwmgr *hwmgr)
 		}
 	}
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (!data->registry_data.socclk_dpm_key_disabled) {
 		if (data->smc_state_table.soc_boot_level !=
 				data->dpm_table.soc_table.dpm_state.soft_min_level) {
@@ -3560,6 +3599,9 @@ static int vega10_upload_dpm_max_level(struct pp_hwmgr *hwmgr)
 		}
 	}
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (!data->registry_data.socclk_dpm_key_disabled) {
 		if (data->smc_state_table.soc_max_level !=
 			data->dpm_table.soc_table.dpm_state.soft_max_level) {
@@ -4054,15 +4096,25 @@ static int vega10_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_fo
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
 		*mclk_mask = 0;
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
-		*sclk_mask = table_info->vdd_dep_on_sclk->count - 1;
+		/* under vega10  pp one vf mode, the gfx clk dpm need be lower
+		 * to level-4 due to the limited power
+		 */
+		if (hwmgr->pp_one_vf)
+			*sclk_mask = 4;
+		else
+			*sclk_mask = table_info->vdd_dep_on_sclk->count - 1;
 		*soc_mask = table_info->vdd_dep_on_socclk->count - 1;
 		*mclk_mask = table_info->vdd_dep_on_mclk->count - 1;
 	}
+
 	return 0;
 }
 
 static void vega10_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 {
+	if (!hwmgr->not_vf)
+		return;
+
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
 		vega10_fan_ctrl_set_fan_speed_percent(hwmgr, 100);
@@ -4176,6 +4228,9 @@ static int vega10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 		break;
 	}
 
+	if (!hwmgr->not_vf)
+		return ret;
+
 	if (!ret) {
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			vega10_set_fan_control_mode(hwmgr, AMD_FAN_CTRL_NONE);
@@ -4360,14 +4415,13 @@ static int vega10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 	struct vega10_hwmgr *data = hwmgr->backend;
 	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_range;
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
-	int result = 0;
 
 	if (!data->registry_data.disable_water_mark) {
 		smu_set_watermarks_for_clocks_ranges(table, wm_with_clock_ranges);
 		data->water_marks_bitmap = WaterMarksExist;
 	}
 
-	return result;
+	return 0;
 }
 
 static int vega10_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
@@ -4480,7 +4534,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct vega10_pcie_table *pcie_table = &(data->dpm_table.pcie_table);
 	struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep = NULL;
 
-	int i, now, size = 0;
+	int i, now, size = 0, count = 0;
 
 	switch (type) {
 	case PP_SCLK:
@@ -4490,7 +4544,12 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex);
 		now = smum_get_argument(hwmgr);
 
-		for (i = 0; i < sclk_table->count; i++)
+		if (hwmgr->pp_one_vf &&
+		    (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK))
+			count = 5;
+		else
+			count = sclk_table->count;
+		for (i = 0; i < count; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, sclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
@@ -4701,6 +4760,9 @@ static int vega10_disable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	int tmp_result, result = 0;
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (PP_CAP(PHM_PlatformCaps_ThermalController))
 		vega10_disable_thermal_protection(hwmgr);
 
@@ -5252,13 +5314,11 @@ static int vega10_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_
 				PHM_PerformanceLevel *level)
 {
 	const struct vega10_power_state *ps;
-	struct vega10_hwmgr *data;
 	uint32_t i;
 
 	if (level == NULL || hwmgr == NULL || state == NULL)
 		return -EINVAL;
 
-	data = hwmgr->backend;
 	ps = cast_const_phw_vega10_power_state(state);
 
 	i = index > ps->performance_level_count - 1 ?
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
index 6f26cb241ecc..0a677d4bc87b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
@@ -1343,6 +1343,9 @@ int vega10_enable_power_containment(struct pp_hwmgr *hwmgr)
 	hwmgr->default_power_limit = hwmgr->power_limit =
 			(uint32_t)(tdp_table->usMaximumPowerDeliveryLimit);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (PP_CAP(PHM_PlatformCaps_PowerContainment)) {
 		if (data->smu_features[GNLD_PPT].supported)
 			PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 7af9ad450ac4..aca61d1ff3c2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -499,8 +499,6 @@ static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
 static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 		PPCLK_e clkID, uint32_t index, uint32_t *clock)
 {
-	int result = 0;
-
 	/*
 	 *SMU expects the Clock ID to be in the top 16 bits.
 	 *Lower 16 bits specify the level
@@ -512,7 +510,7 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 
 	*clock = smum_get_argument(hwmgr);
 
-	return result;
+	return 0;
 }
 
 static int vega12_setup_single_dpm_table(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
index 5bcf0d684151..3b3ec5666051 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
@@ -872,7 +872,7 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr)
 		"[OverridePcieParameters] Attempt to override pcie params failed!",
 		return ret);
 
-	data->pcie_parameters_override = 1;
+	data->pcie_parameters_override = true;
 	data->pcie_gen_level1 = pcie_gen;
 	data->pcie_width_level1 = pcie_width;
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 41fce75b263f..b0591a8dda41 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -254,11 +254,21 @@ struct smu_table_context
 	unsigned long			metrics_time;
 	void				*metrics_table;
 	void				*clocks_table;
+	void				*watermarks_table;
 
 	void				*max_sustainable_clocks;
 	struct smu_bios_boot_up_values	boot_values;
 	void                            *driver_pptable;
 	struct smu_table		*tables;
+	/*
+	 * The driver table is just a staging buffer for
+	 * uploading/downloading content from the SMU.
+	 *
+	 * And the table_id for SMU_MSG_TransferTableSmu2Dram/
+	 * SMU_MSG_TransferTableDram2Smu instructs SMU
+	 * which content driver is interested.
+	 */
+	struct smu_table		driver_table;
 	struct smu_table		memory_pool;
 	uint8_t                         thermal_controller_type;
 
@@ -282,6 +292,7 @@ struct smu_power_gate {
 	bool uvd_gated;
 	bool vce_gated;
 	bool vcn_gated;
+	bool jpeg_gated;
 };
 
 struct smu_power_context {
@@ -437,12 +448,13 @@ struct pptable_funcs {
 	int (*set_power_profile_mode)(struct smu_context *smu, long *input, uint32_t size);
 	int (*dpm_set_uvd_enable)(struct smu_context *smu, bool enable);
 	int (*dpm_set_vce_enable)(struct smu_context *smu, bool enable);
+	int (*dpm_set_jpeg_enable)(struct smu_context *smu, bool enable);
 	int (*read_sensor)(struct smu_context *smu, enum amd_pp_sensors sensor,
 			   void *data, uint32_t *size);
 	int (*pre_display_config_changed)(struct smu_context *smu);
 	int (*display_config_changed)(struct smu_context *smu);
 	int (*apply_clocks_adjust_rules)(struct smu_context *smu);
-	int (*notify_smc_dispaly_config)(struct smu_context *smu);
+	int (*notify_smc_display_config)(struct smu_context *smu);
 	int (*force_dpm_limit_value)(struct smu_context *smu, bool highest);
 	int (*unforce_dpm_levels)(struct smu_context *smu);
 	int (*get_profiling_clk_mask)(struct smu_context *smu,
@@ -491,9 +503,11 @@ struct pptable_funcs {
 	int (*check_fw_version)(struct smu_context *smu);
 	int (*powergate_sdma)(struct smu_context *smu, bool gate);
 	int (*powergate_vcn)(struct smu_context *smu, bool gate);
+	int (*powergate_jpeg)(struct smu_context *smu, bool gate);
 	int (*set_gfx_cgpg)(struct smu_context *smu, bool enable);
 	int (*write_pptable)(struct smu_context *smu);
 	int (*set_min_dcef_deep_sleep)(struct smu_context *smu);
+	int (*set_driver_table_location)(struct smu_context *smu);
 	int (*set_tool_table_location)(struct smu_context *smu);
 	int (*notify_memory_pool_location)(struct smu_context *smu);
 	int (*set_last_dcef_min_deep_sleep_clk)(struct smu_context *smu);
@@ -544,7 +558,8 @@ struct pptable_funcs {
 	bool (*baco_is_support)(struct smu_context *smu);
 	enum smu_baco_state (*baco_get_state)(struct smu_context *smu);
 	int (*baco_set_state)(struct smu_context *smu, enum smu_baco_state state);
-	int (*baco_reset)(struct smu_context *smu);
+	int (*baco_enter)(struct smu_context *smu);
+	int (*baco_exit)(struct smu_context *smu);
 	int (*mode2_reset)(struct smu_context *smu);
 	int (*get_dpm_ultimate_freq)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *min, uint32_t *max);
 	int (*set_soft_freq_limited_range)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t min, uint32_t max);
@@ -626,7 +641,8 @@ bool smu_baco_is_support(struct smu_context *smu);
 
 int smu_baco_get_state(struct smu_context *smu, enum smu_baco_state *state);
 
-int smu_baco_reset(struct smu_context *smu);
+int smu_baco_enter(struct smu_context *smu);
+int smu_baco_exit(struct smu_context *smu);
 
 int smu_mode2_reset(struct smu_context *smu);
 
@@ -692,6 +708,8 @@ int smu_set_soft_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t min, uint32_t max);
 int smu_set_hard_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t min, uint32_t max);
+int smu_get_dpm_level_range(struct smu_context *smu, enum smu_clk_type clk_type,
+			    uint32_t *min_value, uint32_t *max_value);
 enum amd_dpm_forced_level smu_get_performance_level(struct smu_context *smu);
 int smu_force_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level);
 int smu_set_display_count(struct smu_context *smu, uint32_t count);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index af977675fd33..2ffb666b97e6 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -741,6 +741,7 @@ struct pp_hwmgr {
 	uint32_t smu_version;
 	bool not_vf;
 	bool pm_en;
+	bool pp_one_vf;
 	struct mutex smu_lock;
 
 	uint32_t pp_table_version;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
index a886f0644d24..ce5b5011c122 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
@@ -622,8 +622,14 @@ typedef struct {
   uint16_t     PccThresholdHigh;
   uint32_t     PaddingAPCC[6];  //FIXME pending SPEC
 
+  // OOB Settings
+  uint16_t BasePerformanceCardPower;
+  uint16_t MaxPerformanceCardPower;
+  uint16_t BasePerformanceFrequencyCap;   //In Mhz
+  uint16_t MaxPerformanceFrequencyCap;    //In Mhz
+
   // SECTION: Reserved
-  uint32_t     Reserved[11];
+  uint32_t     Reserved[9];
 
   // SECTION: BOARD PARAMETERS
 
@@ -823,7 +829,6 @@ typedef struct {
   uint32_t MmHubPadding[8]; // SMU internal use
 } AvfsFuseOverride_t;
 
-/* NOT CURRENTLY USED
 typedef struct {
   uint8_t   Gfx_ActiveHystLimit;
   uint8_t   Gfx_IdleHystLimit;
@@ -866,7 +871,6 @@ typedef struct {
 
   uint32_t  MmHubPadding[8]; // SMU internal use
 } DpmActivityMonitorCoeffInt_t;
-*/
 
 // These defines are used with the following messages:
 // SMC_MSG_TransferTableDram2Smu
@@ -878,11 +882,11 @@ typedef struct {
 #define TABLE_PMSTATUSLOG             4
 #define TABLE_SMU_METRICS             5
 #define TABLE_DRIVER_SMU_CONFIG       6
-//#define TABLE_ACTIVITY_MONITOR_COEFF  7
 #define TABLE_OVERDRIVE               7
 #define TABLE_WAFL_XGMI_TOPOLOGY      8
 #define TABLE_I2C_COMMANDS            9
-#define TABLE_COUNT                   10
+#define TABLE_ACTIVITY_MONITOR_COEFF  10
+#define TABLE_COUNT                   11
 
 // These defines are used with the SMC_MSG_SetUclkFastSwitch message.
 typedef enum {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h
index c27c82851468..2f85a34c0591 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if 
 // any structure is changed in this file
-#define SMU12_DRIVER_IF_VERSION 10
+#define SMU12_DRIVER_IF_VERSION 11
 
 typedef struct {
   int32_t value;
@@ -192,6 +192,11 @@ typedef struct {
   uint16_t SocTemperature;              //[centi-Celsius]
   uint16_t ThrottlerStatus;
   uint16_t spare;
+
+  uint16_t StapmOriginalLimit;          //[mW]
+  uint16_t StapmCurrentLimit;           //[mW]
+  uint16_t ApuPower;              //[mW]
+  uint16_t dGpuPower;               //[mW]
 } SmuMetrics_t;
 
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 719844257713..d5314d12628a 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -27,7 +27,7 @@
 
 #define SMU11_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU11_DRIVER_IF_VERSION_VG20 0x13
-#define SMU11_DRIVER_IF_VERSION_ARCT 0x10
+#define SMU11_DRIVER_IF_VERSION_ARCT 0x12
 #define SMU11_DRIVER_IF_VERSION_NV10 0x33
 #define SMU11_DRIVER_IF_VERSION_NV14 0x34
 
@@ -170,6 +170,8 @@ int smu_v11_0_write_pptable(struct smu_context *smu);
 
 int smu_v11_0_set_min_dcef_deep_sleep(struct smu_context *smu);
 
+int smu_v11_0_set_driver_table_location(struct smu_context *smu);
+
 int smu_v11_0_set_tool_table_location(struct smu_context *smu);
 
 int smu_v11_0_notify_memory_pool_location(struct smu_context *smu);
@@ -247,7 +249,8 @@ enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu);
 
 int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state);
 
-int smu_v11_0_baco_reset(struct smu_context *smu);
+int smu_v11_0_baco_enter(struct smu_context *smu);
+int smu_v11_0_baco_exit(struct smu_context *smu);
 
 int smu_v11_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
 						 uint32_t *min, uint32_t *max);
@@ -261,4 +264,7 @@ int smu_v11_0_set_default_od_settings(struct smu_context *smu, bool initialize,
 
 uint32_t smu_v11_0_get_max_power_limit(struct smu_context *smu);
 
+int smu_v11_0_set_performance_level(struct smu_context *smu,
+				    enum amd_dpm_forced_level level);
+
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
index 9d81d789c713..d79e54b5ebf6 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
@@ -57,8 +57,14 @@ int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate);
 
 int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate);
 
+int smu_v12_0_powergate_jpeg(struct smu_context *smu, bool gate);
+
 int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable);
 
+int smu_v12_0_read_sensor(struct smu_context *smu,
+			  enum amd_pp_sensors sensor,
+			  void *data, uint32_t *size);
+
 uint32_t smu_v12_0_get_gfxoff_status(struct smu_context *smu);
 
 int smu_v12_0_gfx_off_control(struct smu_context *smu, bool enable);
@@ -69,6 +75,13 @@ int smu_v12_0_fini_smc_tables(struct smu_context *smu);
 
 int smu_v12_0_populate_smc_tables(struct smu_context *smu);
 
+int smu_v12_0_get_enabled_mask(struct smu_context *smu,
+				      uint32_t *feature_mask, uint32_t num);
+
+int smu_v12_0_get_current_clk_freq(struct smu_context *smu,
+					  enum smu_clk_type clk_id,
+					  uint32_t *value);
+
 int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
 						 uint32_t *min, uint32_t *max);
 
@@ -77,4 +90,6 @@ int smu_v12_0_mode2_reset(struct smu_context *smu);
 int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t min, uint32_t max);
 
+int smu_v12_0_set_driver_table_location(struct smu_context *smu);
+
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index ca62e92e5a4f..93c66c69ca28 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -384,8 +384,10 @@ navi10_get_allowed_feature_mask(struct smu_context *smu,
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ATHUB_PG_BIT);
 
 	if (smu->adev->pg_flags & AMD_PG_SUPPORT_VCN)
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VCN_PG_BIT)
-				| FEATURE_MASK(FEATURE_JPEG_PG_BIT);
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VCN_PG_BIT);
+
+	if (smu->adev->pg_flags & AMD_PG_SUPPORT_JPEG)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_JPEG_PG_BIT);
 
 	/* disable DPM UCLK and DS SOCCLK on navi10 A0 secure board */
 	if (is_asic_secure(smu)) {
@@ -553,6 +555,10 @@ static int navi10_tables_init(struct smu_context *smu, struct smu_table *tables)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
+	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
+	if (!smu_table->watermarks_table)
+		return -ENOMEM;
+
 	return 0;
 }
 
@@ -668,6 +674,31 @@ static int navi10_dpm_set_uvd_enable(struct smu_context *smu, bool enable)
 	return ret;
 }
 
+static int navi10_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (enable) {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
+			ret = smu_send_smc_msg(smu, SMU_MSG_PowerUpJpeg);
+			if (ret)
+				return ret;
+		}
+		power_gate->jpeg_gated = false;
+	} else {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
+			ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownJpeg);
+			if (ret)
+				return ret;
+		}
+		power_gate->jpeg_gated = true;
+	}
+
+	return ret;
+}
+
 static int navi10_get_current_clk_freq_by_table(struct smu_context *smu,
 				       enum smu_clk_type clk_type,
 				       uint32_t *value)
@@ -1350,7 +1381,7 @@ static int navi10_get_profiling_clk_mask(struct smu_context *smu,
 	return ret;
 }
 
-static int navi10_notify_smc_dispaly_config(struct smu_context *smu)
+static int navi10_notify_smc_display_config(struct smu_context *smu)
 {
 	struct smu_clocks min_clocks = {0};
 	struct pp_display_clock_request clock_req;
@@ -1555,12 +1586,44 @@ static int navi10_get_uclk_dpm_states(struct smu_context *smu, uint32_t *clocks_
 	return 0;
 }
 
-static int navi10_set_peak_clock_by_device(struct smu_context *smu)
+static int navi10_set_performance_level(struct smu_context *smu,
+					enum amd_dpm_forced_level level);
+
+static int navi10_set_standard_performance_level(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+	uint32_t sclk_freq = 0, uclk_freq = 0;
+
+	switch (adev->asic_type) {
+	case CHIP_NAVI10:
+		sclk_freq = NAVI10_UMD_PSTATE_PROFILING_GFXCLK;
+		uclk_freq = NAVI10_UMD_PSTATE_PROFILING_MEMCLK;
+		break;
+	case CHIP_NAVI14:
+		sclk_freq = NAVI14_UMD_PSTATE_PROFILING_GFXCLK;
+		uclk_freq = NAVI14_UMD_PSTATE_PROFILING_MEMCLK;
+		break;
+	default:
+		/* by default, this is same as auto performance level */
+		return navi10_set_performance_level(smu, AMD_DPM_FORCED_LEVEL_AUTO);
+	}
+
+	ret = smu_set_soft_freq_range(smu, SMU_SCLK, sclk_freq, sclk_freq);
+	if (ret)
+		return ret;
+	ret = smu_set_soft_freq_range(smu, SMU_UCLK, uclk_freq, uclk_freq);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int navi10_set_peak_performance_level(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 	uint32_t sclk_freq = 0, uclk_freq = 0;
-	uint32_t uclk_level = 0;
 
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
@@ -1601,14 +1664,16 @@ static int navi10_set_peak_clock_by_device(struct smu_context *smu)
 			break;
 		}
 		break;
+	case CHIP_NAVI12:
+		sclk_freq = NAVI12_UMD_PSTATE_PEAK_GFXCLK;
+		break;
 	default:
-		return -EINVAL;
+		ret = smu_get_dpm_level_range(smu, SMU_SCLK, NULL, &sclk_freq);
+		if (ret)
+			return ret;
 	}
 
-	ret = smu_get_dpm_level_count(smu, SMU_UCLK, &uclk_level);
-	if (ret)
-		return ret;
-	ret = smu_get_dpm_freq_by_index(smu, SMU_UCLK, uclk_level - 1, &uclk_freq);
+	ret = smu_get_dpm_level_range(smu, SMU_UCLK, NULL, &uclk_freq);
 	if (ret)
 		return ret;
 
@@ -1622,19 +1687,45 @@ static int navi10_set_peak_clock_by_device(struct smu_context *smu)
 	return ret;
 }
 
-static int navi10_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
+static int navi10_set_performance_level(struct smu_context *smu,
+					enum amd_dpm_forced_level level)
 {
 	int ret = 0;
+	uint32_t sclk_mask, mclk_mask, soc_mask;
 
 	switch (level) {
+	case AMD_DPM_FORCED_LEVEL_HIGH:
+		ret = smu_force_dpm_limit_value(smu, true);
+		break;
+	case AMD_DPM_FORCED_LEVEL_LOW:
+		ret = smu_force_dpm_limit_value(smu, false);
+		break;
+	case AMD_DPM_FORCED_LEVEL_AUTO:
+		ret = smu_unforce_dpm_levels(smu);
+		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+		ret = navi10_set_standard_performance_level(smu);
+		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+		ret = smu_get_profiling_clk_mask(smu, level,
+						 &sclk_mask,
+						 &mclk_mask,
+						 &soc_mask);
+		if (ret)
+			return ret;
+		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
+		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
+		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
+		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
-		ret = navi10_set_peak_clock_by_device(smu);
+		ret = navi10_set_peak_performance_level(smu);
 		break;
+	case AMD_DPM_FORCED_LEVEL_MANUAL:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
 	default:
-		ret = -EINVAL;
 		break;
 	}
-
 	return ret;
 }
 
@@ -2015,6 +2106,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.get_allowed_feature_mask = navi10_get_allowed_feature_mask,
 	.set_default_dpm_table = navi10_set_default_dpm_table,
 	.dpm_set_uvd_enable = navi10_dpm_set_uvd_enable,
+	.dpm_set_jpeg_enable = navi10_dpm_set_jpeg_enable,
 	.get_current_clk_freq_by_table = navi10_get_current_clk_freq_by_table,
 	.print_clk_levels = navi10_print_clk_levels,
 	.force_clk_levels = navi10_force_clk_levels,
@@ -2022,7 +2114,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.get_clock_by_type_with_latency = navi10_get_clock_by_type_with_latency,
 	.pre_display_config_changed = navi10_pre_display_config_changed,
 	.display_config_changed = navi10_display_config_changed,
-	.notify_smc_dispaly_config = navi10_notify_smc_dispaly_config,
+	.notify_smc_display_config = navi10_notify_smc_display_config,
 	.force_dpm_limit_value = navi10_force_dpm_limit_value,
 	.unforce_dpm_levels = navi10_unforce_dpm_levels,
 	.is_dpm_running = navi10_is_dpm_running,
@@ -2055,6 +2147,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.check_fw_version = smu_v11_0_check_fw_version,
 	.write_pptable = smu_v11_0_write_pptable,
 	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_driver_table_location = smu_v11_0_set_driver_table_location,
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
@@ -2083,7 +2176,8 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.baco_is_support= smu_v11_0_baco_is_support,
 	.baco_get_state = smu_v11_0_baco_get_state,
 	.baco_set_state = smu_v11_0_baco_set_state,
-	.baco_reset = smu_v11_0_baco_reset,
+	.baco_enter = smu_v11_0_baco_enter,
+	.baco_exit = smu_v11_0_baco_exit,
 	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
index ec03c7992f6d..2abb4ba01db1 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
@@ -27,12 +27,26 @@
 #define NAVI10_PEAK_SCLK_XT  		(1755)
 #define NAVI10_PEAK_SCLK_XL  		(1625)
 
+#define NAVI10_UMD_PSTATE_PROFILING_GFXCLK    (1300)
+#define NAVI10_UMD_PSTATE_PROFILING_SOCCLK    (980)
+#define NAVI10_UMD_PSTATE_PROFILING_MEMCLK    (625)
+#define NAVI10_UMD_PSTATE_PROFILING_VCLK      (980)
+#define NAVI10_UMD_PSTATE_PROFILING_DCLK      (850)
+
 #define NAVI14_UMD_PSTATE_PEAK_XT_GFXCLK      (1670)
 #define NAVI14_UMD_PSTATE_PEAK_XTM_GFXCLK     (1448)
 #define NAVI14_UMD_PSTATE_PEAK_XLM_GFXCLK     (1181)
 #define NAVI14_UMD_PSTATE_PEAK_XTX_GFXCLK     (1717)
 #define NAVI14_UMD_PSTATE_PEAK_XL_GFXCLK      (1448)
 
+#define NAVI14_UMD_PSTATE_PROFILING_GFXCLK    (1200)
+#define NAVI14_UMD_PSTATE_PROFILING_SOCCLK    (900)
+#define NAVI14_UMD_PSTATE_PROFILING_MEMCLK    (600)
+#define NAVI14_UMD_PSTATE_PROFILING_VCLK      (900)
+#define NAVI14_UMD_PSTATE_PROFILING_DCLK      (800)
+
+#define NAVI12_UMD_PSTATE_PEAK_GFXCLK     (1100)
+
 #define NAVI10_VOLTAGE_SCALE (4)
 
 #define smnPCIE_LC_SPEED_CNTL			0x11140290
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 977bdd962e98..861e6410363b 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -31,6 +31,9 @@
 #include "renoir_ppt.h"
 
 
+#define CLK_MAP(clk, index) \
+	[SMU_##clk] = {1, (index)}
+
 #define MSG_MAP(msg, index) \
 	[SMU_MSG_##msg] = {1, (index)}
 
@@ -104,6 +107,14 @@ static struct smu_12_0_cmn2aisc_mapping renoir_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(SetHardMinFclkByFreq,           PPSMC_MSG_SetHardMinFclkByFreq),
 };
 
+static struct smu_12_0_cmn2aisc_mapping renoir_clk_map[SMU_CLK_COUNT] = {
+	CLK_MAP(GFXCLK, CLOCK_GFXCLK),
+	CLK_MAP(SCLK,	CLOCK_GFXCLK),
+	CLK_MAP(SOCCLK, CLOCK_SOCCLK),
+	CLK_MAP(UCLK, CLOCK_UMCCLK),
+	CLK_MAP(MCLK, CLOCK_UMCCLK),
+};
+
 static struct smu_12_0_cmn2aisc_mapping renoir_table_map[SMU_TABLE_COUNT] = {
 	TAB_MAP_VALID(WATERMARKS),
 	TAB_MAP_INVALID(CUSTOM_DPM),
@@ -125,6 +136,21 @@ static int renoir_get_smu_msg_index(struct smu_context *smc, uint32_t index)
 	return mapping.map_to;
 }
 
+static int renoir_get_smu_clk_index(struct smu_context *smc, uint32_t index)
+{
+	struct smu_12_0_cmn2aisc_mapping mapping;
+
+	if (index >= SMU_CLK_COUNT)
+		return -EINVAL;
+
+	mapping = renoir_clk_map[index];
+	if (!(mapping.valid_mapping)) {
+		return -EINVAL;
+	}
+
+	return mapping.map_to;
+}
+
 static int renoir_get_smu_table_index(struct smu_context *smc, uint32_t index)
 {
 	struct smu_12_0_cmn2aisc_mapping mapping;
@@ -139,6 +165,30 @@ static int renoir_get_smu_table_index(struct smu_context *smc, uint32_t index)
 	return mapping.map_to;
 }
 
+static int renoir_get_metrics_table(struct smu_context *smu,
+				    SmuMetrics_t *metrics_table)
+{
+	struct smu_table_context *smu_table= &smu->smu_table;
+	int ret = 0;
+
+	mutex_lock(&smu->metrics_lock);
+	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) {
+		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
+				(void *)smu_table->metrics_table, false);
+		if (ret) {
+			pr_info("Failed to export SMU metrics table!\n");
+			mutex_unlock(&smu->metrics_lock);
+			return ret;
+		}
+		smu_table->metrics_time = jiffies;
+	}
+
+	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	mutex_unlock(&smu->metrics_lock);
+
+	return ret;
+}
+
 static int renoir_tables_init(struct smu_context *smu, struct smu_table *tables)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
@@ -154,6 +204,15 @@ static int renoir_tables_init(struct smu_context *smu, struct smu_table *tables)
 	if (!smu_table->clocks_table)
 		return -ENOMEM;
 
+	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
+	if (!smu_table->metrics_table)
+		return -ENOMEM;
+	smu_table->metrics_time = 0;
+
+	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
+	if (!smu_table->watermarks_table)
+		return -ENOMEM;
+
 	return 0;
 }
 
@@ -187,8 +246,7 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 
 	memset(&metrics, 0, sizeof(metrics));
 
-	ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
-			       (void *)&metrics, false);
+	ret = renoir_get_metrics_table(smu, &metrics);
 	if (ret)
 		return ret;
 
@@ -301,6 +359,51 @@ static int renoir_dpm_set_uvd_enable(struct smu_context *smu, bool enable)
 	return ret;
 }
 
+static int renoir_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (enable) {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpJpeg, 0);
+			if (ret)
+				return ret;
+		}
+		power_gate->jpeg_gated = false;
+	} else {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerDownJpeg, 0);
+			if (ret)
+				return ret;
+		}
+		power_gate->jpeg_gated = true;
+	}
+
+	return ret;
+}
+
+static int renoir_get_current_clk_freq_by_table(struct smu_context *smu,
+				       enum smu_clk_type clk_type,
+				       uint32_t *value)
+{
+	int ret = 0, clk_id = 0;
+	SmuMetrics_t metrics;
+
+	ret = renoir_get_metrics_table(smu, &metrics);
+	if (ret)
+		return ret;
+
+	clk_id = smu_clk_get_index(smu, clk_type);
+	if (clk_id < 0)
+		return clk_id;
+
+	*value = metrics.ClockFrequency[clk_id];
+
+	return ret;
+}
+
 static int renoir_force_dpm_limit_value(struct smu_context *smu, bool highest)
 {
 	int ret = 0, i = 0;
@@ -361,6 +464,50 @@ static int renoir_unforce_dpm_levels(struct smu_context *smu) {
 	return ret;
 }
 
+static int renoir_get_gpu_temperature(struct smu_context *smu, uint32_t *value)
+{
+	int ret = 0;
+	SmuMetrics_t metrics;
+
+	if (!value)
+		return -EINVAL;
+
+	ret = renoir_get_metrics_table(smu, &metrics);
+	if (ret)
+		return ret;
+
+	*value = (metrics.GfxTemperature / 100) *
+		SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
+	return 0;
+}
+
+static int renoir_get_current_activity_percent(struct smu_context *smu,
+					       enum amd_pp_sensors sensor,
+					       uint32_t *value)
+{
+	int ret = 0;
+	SmuMetrics_t metrics;
+
+	if (!value)
+		return -EINVAL;
+
+	ret = renoir_get_metrics_table(smu, &metrics);
+	if (ret)
+		return ret;
+
+	switch (sensor) {
+	case AMDGPU_PP_SENSOR_GPU_LOAD:
+		*value = metrics.AverageGfxActivity / 100;
+		break;
+	default:
+		pr_err("Invalid sensor for retrieving clock activity\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int renoir_get_workload_type(struct smu_context *smu, uint32_t profile)
 {
 
@@ -565,19 +712,43 @@ static int renoir_set_peak_clock_by_device(struct smu_context *smu)
 	return ret;
 }
 
-static int renoir_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
+static int renoir_set_performance_level(struct smu_context *smu,
+					enum amd_dpm_forced_level level)
 {
 	int ret = 0;
+	uint32_t sclk_mask, mclk_mask, soc_mask;
 
 	switch (level) {
+	case AMD_DPM_FORCED_LEVEL_HIGH:
+		ret = smu_force_dpm_limit_value(smu, true);
+		break;
+	case AMD_DPM_FORCED_LEVEL_LOW:
+		ret = smu_force_dpm_limit_value(smu, false);
+		break;
+	case AMD_DPM_FORCED_LEVEL_AUTO:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+		ret = smu_unforce_dpm_levels(smu);
+		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+		ret = smu_get_profiling_clk_mask(smu, level,
+						 &sclk_mask,
+						 &mclk_mask,
+						 &soc_mask);
+		if (ret)
+			return ret;
+		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
+		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
+		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
+		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
 		ret = renoir_set_peak_clock_by_device(smu);
 		break;
+	case AMD_DPM_FORCED_LEVEL_MANUAL:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
 	default:
-		ret = -EINVAL;
 		break;
 	}
-
 	return ret;
 }
 
@@ -636,9 +807,17 @@ static int renoir_set_watermarks_table(
 	}
 
 	/* pass data to smu controller */
-	ret = smu_write_watermarks_table(smu);
+	if ((smu->watermarks_bitmap & WATERMARKS_EXIST) &&
+			!(smu->watermarks_bitmap & WATERMARKS_LOADED)) {
+		ret = smu_write_watermarks_table(smu);
+		if (ret) {
+			pr_err("Failed to update WMTABLE!");
+			return ret;
+		}
+		smu->watermarks_bitmap |= WATERMARKS_LOADED;
+	}
 
-	return ret;
+	return 0;
 }
 
 static int renoir_get_power_profile_mode(struct smu_context *smu,
@@ -674,8 +853,36 @@ static int renoir_get_power_profile_mode(struct smu_context *smu,
 	return size;
 }
 
+static int renoir_read_sensor(struct smu_context *smu,
+				 enum amd_pp_sensors sensor,
+				 void *data, uint32_t *size)
+{
+	int ret = 0;
+
+	if (!data || !size)
+		return -EINVAL;
+
+	mutex_lock(&smu->sensor_lock);
+	switch (sensor) {
+	case AMDGPU_PP_SENSOR_GPU_LOAD:
+		ret = renoir_get_current_activity_percent(smu, sensor, (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GPU_TEMP:
+		ret = renoir_get_gpu_temperature(smu, (uint32_t *)data);
+		*size = 4;
+		break;
+	default:
+		ret = smu_v12_0_read_sensor(smu, sensor, data, size);
+	}
+	mutex_unlock(&smu->sensor_lock);
+
+	return ret;
+}
+
 static const struct pptable_funcs renoir_ppt_funcs = {
 	.get_smu_msg_index = renoir_get_smu_msg_index,
+	.get_smu_clk_index = renoir_get_smu_clk_index,
 	.get_smu_table_index = renoir_get_smu_table_index,
 	.tables_init = renoir_tables_init,
 	.set_power_state = NULL,
@@ -683,6 +890,8 @@ static const struct pptable_funcs renoir_ppt_funcs = {
 	.print_clk_levels = renoir_print_clk_levels,
 	.get_current_power_state = renoir_get_current_power_state,
 	.dpm_set_uvd_enable = renoir_dpm_set_uvd_enable,
+	.dpm_set_jpeg_enable = renoir_dpm_set_jpeg_enable,
+	.get_current_clk_freq_by_table = renoir_get_current_clk_freq_by_table,
 	.force_dpm_limit_value = renoir_force_dpm_limit_value,
 	.unforce_dpm_levels = renoir_unforce_dpm_levels,
 	.get_workload_type = renoir_get_workload_type,
@@ -693,10 +902,12 @@ static const struct pptable_funcs renoir_ppt_funcs = {
 	.get_dpm_clock_table = renoir_get_dpm_clock_table,
 	.set_watermarks_table = renoir_set_watermarks_table,
 	.get_power_profile_mode = renoir_get_power_profile_mode,
+	.read_sensor = renoir_read_sensor,
 	.check_fw_status = smu_v12_0_check_fw_status,
 	.check_fw_version = smu_v12_0_check_fw_version,
 	.powergate_sdma = smu_v12_0_powergate_sdma,
 	.powergate_vcn = smu_v12_0_powergate_vcn,
+	.powergate_jpeg = smu_v12_0_powergate_jpeg,
 	.send_smc_msg_with_param = smu_v12_0_send_msg_with_param,
 	.read_smc_arg = smu_v12_0_read_arg,
 	.set_gfx_cgpg = smu_v12_0_set_gfx_cgpg,
@@ -704,9 +915,12 @@ static const struct pptable_funcs renoir_ppt_funcs = {
 	.init_smc_tables = smu_v12_0_init_smc_tables,
 	.fini_smc_tables = smu_v12_0_fini_smc_tables,
 	.populate_smc_tables = smu_v12_0_populate_smc_tables,
+	.get_enabled_mask = smu_v12_0_get_enabled_mask,
+	.get_current_clk_freq = smu_v12_0_get_current_clk_freq,
 	.get_dpm_ultimate_freq = smu_v12_0_get_dpm_ultimate_freq,
 	.mode2_reset = smu_v12_0_mode2_reset,
 	.set_soft_freq_limited_range = smu_v12_0_set_soft_freq_limited_range,
+	.set_driver_table_location = smu_v12_0_set_driver_table_location,
 };
 
 void renoir_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/powerplay/smu_internal.h b/drivers/gpu/drm/amd/powerplay/smu_internal.h
index 8872f8b2d502..783319ec8bf9 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_internal.h
+++ b/drivers/gpu/drm/amd/powerplay/smu_internal.h
@@ -42,6 +42,8 @@
 	((smu)->ppt_funcs->powergate_sdma ? (smu)->ppt_funcs->powergate_sdma((smu), (gate)) : 0)
 #define smu_powergate_vcn(smu, gate) \
 	((smu)->ppt_funcs->powergate_vcn ? (smu)->ppt_funcs->powergate_vcn((smu), (gate)) : 0)
+#define smu_powergate_jpeg(smu, gate) \
+	((smu)->ppt_funcs->powergate_jpeg ? (smu)->ppt_funcs->powergate_jpeg((smu), (gate)) : 0)
 
 #define smu_get_vbios_bootup_values(smu) \
 	((smu)->ppt_funcs->get_vbios_bootup_values ? (smu)->ppt_funcs->get_vbios_bootup_values((smu)) : 0)
@@ -59,6 +61,8 @@
 	((smu)->ppt_funcs->write_pptable ? (smu)->ppt_funcs->write_pptable((smu)) : 0)
 #define smu_set_min_dcef_deep_sleep(smu) \
 	((smu)->ppt_funcs->set_min_dcef_deep_sleep ? (smu)->ppt_funcs->set_min_dcef_deep_sleep((smu)) : 0)
+#define smu_set_driver_table_location(smu) \
+	((smu)->ppt_funcs->set_driver_table_location ? (smu)->ppt_funcs->set_driver_table_location((smu)) : 0)
 #define smu_set_tool_table_location(smu) \
 	((smu)->ppt_funcs->set_tool_table_location ? (smu)->ppt_funcs->set_tool_table_location((smu)) : 0)
 #define smu_notify_memory_pool_location(smu) \
@@ -127,8 +131,8 @@ int smu_send_smc_msg(struct smu_context *smu, enum smu_message_type msg);
 	((smu)->ppt_funcs->display_config_changed ? (smu)->ppt_funcs->display_config_changed((smu)) : 0)
 #define smu_apply_clocks_adjust_rules(smu) \
 	((smu)->ppt_funcs->apply_clocks_adjust_rules ? (smu)->ppt_funcs->apply_clocks_adjust_rules((smu)) : 0)
-#define smu_notify_smc_dispaly_config(smu) \
-	((smu)->ppt_funcs->notify_smc_dispaly_config ? (smu)->ppt_funcs->notify_smc_dispaly_config((smu)) : 0)
+#define smu_notify_smc_display_config(smu) \
+	((smu)->ppt_funcs->notify_smc_display_config ? (smu)->ppt_funcs->notify_smc_display_config((smu)) : 0)
 #define smu_force_dpm_limit_value(smu, highest) \
 	((smu)->ppt_funcs->force_dpm_limit_value ? (smu)->ppt_funcs->force_dpm_limit_value((smu), (highest)) : 0)
 #define smu_unforce_dpm_levels(smu) \
@@ -170,6 +174,8 @@ int smu_send_smc_msg(struct smu_context *smu, enum smu_message_type msg);
 	((smu)->ppt_funcs->dpm_set_uvd_enable ? (smu)->ppt_funcs->dpm_set_uvd_enable((smu), (enable)) : 0)
 #define smu_dpm_set_vce_enable(smu, enable) \
 	((smu)->ppt_funcs->dpm_set_vce_enable ? (smu)->ppt_funcs->dpm_set_vce_enable((smu), (enable)) : 0)
+#define smu_dpm_set_jpeg_enable(smu, enable) \
+	((smu)->ppt_funcs->dpm_set_jpeg_enable ? (smu)->ppt_funcs->dpm_set_jpeg_enable((smu), (enable)) : 0)
 
 #define smu_set_watermarks_table(smu, tab, clock_ranges) \
 	((smu)->ppt_funcs->set_watermarks_table ? (smu)->ppt_funcs->set_watermarks_table((smu), (tab), (clock_ranges)) : 0)
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index e4268a627eff..02f8c9cb89d9 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -37,6 +37,7 @@
 #include "soc15_common.h"
 #include "atom.h"
 #include "amd_pcie.h"
+#include "amdgpu_ras.h"
 
 #include "asic_reg/thm/thm_11_0_2_offset.h"
 #include "asic_reg/thm/thm_11_0_2_sh_mask.h"
@@ -79,15 +80,13 @@ static int smu_v11_0_wait_for_response(struct smu_context *smu)
 	for (i = 0; i < timeout; i++) {
 		cur_value = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
 		if ((cur_value & MP1_C2PMSG_90__CONTENT_MASK) != 0)
-			break;
+			return cur_value == 0x1 ? 0 : -EIO;
+
 		udelay(1);
 	}
 
 	/* timeout means wrong logic */
-	if (i == timeout)
-		return -ETIME;
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90) == 0x1 ? 0 : -EIO;
+	return -ETIME;
 }
 
 int
@@ -103,9 +102,11 @@ smu_v11_0_send_msg_with_param(struct smu_context *smu,
 		return index;
 
 	ret = smu_v11_0_wait_for_response(smu);
-	if (ret)
-		pr_err("failed send message: %10s (%d) \tparam: 0x%08x response %#x\n",
-		       smu_get_message_name(smu, msg), index, param, ret);
+	if (ret) {
+		pr_err("Msg issuing pre-check failed and "
+		       "SMU may be not in the right state!\n");
+		return ret;
+	}
 
 	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
@@ -449,8 +450,10 @@ int smu_v11_0_fini_smc_tables(struct smu_context *smu)
 
 	kfree(smu_table->tables);
 	kfree(smu_table->metrics_table);
+	kfree(smu_table->watermarks_table);
 	smu_table->tables = NULL;
 	smu_table->metrics_table = NULL;
+	smu_table->watermarks_table = NULL;
 	smu_table->metrics_time = 0;
 
 	ret = smu_v11_0_fini_dpm_context(smu);
@@ -773,6 +776,24 @@ int smu_v11_0_set_min_dcef_deep_sleep(struct smu_context *smu)
 	return smu_v11_0_set_deep_sleep_dcefclk(smu, table_context->boot_values.dcefclk / 100);
 }
 
+int smu_v11_0_set_driver_table_location(struct smu_context *smu)
+{
+	struct smu_table *driver_table = &smu->smu_table.driver_table;
+	int ret = 0;
+
+	if (driver_table->mc_address) {
+		ret = smu_send_smc_msg_with_param(smu,
+				SMU_MSG_SetDriverDramAddrHigh,
+				upper_32_bits(driver_table->mc_address));
+		if (!ret)
+			ret = smu_send_smc_msg_with_param(smu,
+				SMU_MSG_SetDriverDramAddrLow,
+				lower_32_bits(driver_table->mc_address));
+	}
+
+	return ret;
+}
+
 int smu_v11_0_set_tool_table_location(struct smu_context *smu)
 {
 	int ret = 0;
@@ -834,27 +855,33 @@ int smu_v11_0_get_enabled_mask(struct smu_context *smu,
 				      uint32_t *feature_mask, uint32_t num)
 {
 	uint32_t feature_mask_high = 0, feature_mask_low = 0;
+	struct smu_feature *feature = &smu->smu_feature;
 	int ret = 0;
 
 	if (!feature_mask || num < 2)
 		return -EINVAL;
 
-	ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesHigh);
-	if (ret)
-		return ret;
-	ret = smu_read_smc_arg(smu, &feature_mask_high);
-	if (ret)
-		return ret;
+	if (bitmap_empty(feature->enabled, feature->feature_num)) {
+		ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesHigh);
+		if (ret)
+			return ret;
+		ret = smu_read_smc_arg(smu, &feature_mask_high);
+		if (ret)
+			return ret;
 
-	ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesLow);
-	if (ret)
-		return ret;
-	ret = smu_read_smc_arg(smu, &feature_mask_low);
-	if (ret)
-		return ret;
+		ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesLow);
+		if (ret)
+			return ret;
+		ret = smu_read_smc_arg(smu, &feature_mask_low);
+		if (ret)
+			return ret;
 
-	feature_mask[0] = feature_mask_low;
-	feature_mask[1] = feature_mask_high;
+		feature_mask[0] = feature_mask_low;
+		feature_mask[1] = feature_mask_high;
+	} else {
+		bitmap_copy((unsigned long *)feature_mask, feature->enabled,
+			     feature->feature_num);
+	}
 
 	return ret;
 }
@@ -866,21 +893,24 @@ int smu_v11_0_system_features_control(struct smu_context *smu,
 	uint32_t feature_mask[2];
 	int ret = 0;
 
-	if (smu->pm_enabled) {
-		ret = smu_send_smc_msg(smu, (en ? SMU_MSG_EnableAllSmuFeatures :
-					     SMU_MSG_DisableAllSmuFeatures));
-		if (ret)
-			return ret;
-	}
-
-	ret = smu_feature_get_enabled_mask(smu, feature_mask, 2);
+	ret = smu_send_smc_msg(smu, (en ? SMU_MSG_EnableAllSmuFeatures :
+				     SMU_MSG_DisableAllSmuFeatures));
 	if (ret)
 		return ret;
 
-	bitmap_copy(feature->enabled, (unsigned long *)&feature_mask,
-		    feature->feature_num);
-	bitmap_copy(feature->supported, (unsigned long *)&feature_mask,
-		    feature->feature_num);
+	if (en) {
+		ret = smu_feature_get_enabled_mask(smu, feature_mask, 2);
+		if (ret)
+			return ret;
+
+		bitmap_copy(feature->enabled, (unsigned long *)&feature_mask,
+			    feature->feature_num);
+		bitmap_copy(feature->supported, (unsigned long *)&feature_mask,
+			    feature->feature_num);
+	} else {
+		bitmap_zero(feature->enabled, feature->feature_num);
+		bitmap_zero(feature->supported, feature->feature_num);
+	}
 
 	return ret;
 }
@@ -1124,11 +1154,12 @@ static int smu_v11_0_set_thermal_range(struct smu_context *smu,
 	int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
 	int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
+	struct smu_table_context *table_context = &smu->smu_table;
+	struct smu_11_0_powerplay_table *powerplay_table = table_context->power_play_table;
 
 	low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
 			range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
-	high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
-			range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+	high = min((uint16_t)SMU_THERMAL_MAXIMUM_ALERT_TEMP, powerplay_table->software_shutdown_temp);
 
 	if (low > high)
 		return -EINVAL;
@@ -1617,7 +1648,9 @@ bool smu_v11_0_baco_is_support(struct smu_context *smu)
 	if (!baco_support)
 		return false;
 
-	if (!smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
+	/* Arcturus does not support this bit mask */
+	if (smu_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) &&
+	   !smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
 		return false;
 
 	val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0);
@@ -1643,6 +1676,10 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state)
 {
 
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
+	struct amdgpu_device *adev = smu->adev;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	uint32_t bif_doorbell_intr_cntl;
+	uint32_t data;
 	int ret = 0;
 
 	if (smu_v11_0_baco_get_state(smu) == state)
@@ -1650,10 +1687,37 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state)
 
 	mutex_lock(&smu_baco->mutex);
 
-	if (state == SMU_BACO_STATE_ENTER)
-		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, BACO_SEQ_BACO);
-	else
+	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+
+	if (state == SMU_BACO_STATE_ENTER) {
+		bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl,
+						BIF_DOORBELL_INT_CNTL,
+						DOORBELL_INTERRUPT_DISABLE, 1);
+		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+		if (!ras || !ras->supported) {
+			data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL);
+			data |= 0x80000000;
+			WREG32_SOC15(THM, 0, mmTHM_BACO_CNTL, data);
+
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, 0);
+		} else {
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, 1);
+		}
+	} else {
 		ret = smu_send_smc_msg(smu, SMU_MSG_ExitBaco);
+		if (ret)
+			goto out;
+
+		bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl,
+						BIF_DOORBELL_INT_CNTL,
+						DOORBELL_INTERRUPT_DISABLE, 0);
+		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+		/* clear vbios scratch 6 and 7 for coming asic reinit */
+		WREG32(adev->bios_scratch_reg_offset + 6, 0);
+		WREG32(adev->bios_scratch_reg_offset + 7, 0);
+	}
 	if (ret)
 		goto out;
 
@@ -1663,13 +1727,17 @@ out:
 	return ret;
 }
 
-int smu_v11_0_baco_reset(struct smu_context *smu)
+int smu_v11_0_baco_enter(struct smu_context *smu)
 {
+	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
-	ret = smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
-	if (ret)
-		return ret;
+	/* Arcturus does not need this audio workaround */
+	if (adev->asic_type != CHIP_ARCTURUS) {
+		ret = smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
+		if (ret)
+			return ret;
+	}
 
 	ret = smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_ENTER);
 	if (ret)
@@ -1677,6 +1745,13 @@ int smu_v11_0_baco_reset(struct smu_context *smu)
 
 	msleep(10);
 
+	return ret;
+}
+
+int smu_v11_0_baco_exit(struct smu_context *smu)
+{
+	int ret = 0;
+
 	ret = smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_EXIT);
 	if (ret)
 		return ret;
@@ -1815,3 +1890,42 @@ int smu_v11_0_set_default_od_settings(struct smu_context *smu, bool initialize,
 	}
 	return ret;
 }
+
+int smu_v11_0_set_performance_level(struct smu_context *smu,
+				    enum amd_dpm_forced_level level)
+{
+	int ret = 0;
+	uint32_t sclk_mask, mclk_mask, soc_mask;
+
+	switch (level) {
+	case AMD_DPM_FORCED_LEVEL_HIGH:
+		ret = smu_force_dpm_limit_value(smu, true);
+		break;
+	case AMD_DPM_FORCED_LEVEL_LOW:
+		ret = smu_force_dpm_limit_value(smu, false);
+		break;
+	case AMD_DPM_FORCED_LEVEL_AUTO:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+		ret = smu_unforce_dpm_levels(smu);
+		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
+		ret = smu_get_profiling_clk_mask(smu, level,
+						 &sclk_mask,
+						 &mclk_mask,
+						 &soc_mask);
+		if (ret)
+			return ret;
+		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
+		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
+		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
+		break;
+	case AMD_DPM_FORCED_LEVEL_MANUAL:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
+	default:
+		break;
+	}
+	return ret;
+}
+
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
index 094cfc46adac..870e6db2907e 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
@@ -66,15 +66,13 @@ int smu_v12_0_wait_for_response(struct smu_context *smu)
 	for (i = 0; i < adev->usec_timeout; i++) {
 		cur_value = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
 		if ((cur_value & MP1_C2PMSG_90__CONTENT_MASK) != 0)
-			break;
+			return cur_value == 0x1 ? 0 : -EIO;
+
 		udelay(1);
 	}
 
 	/* timeout means wrong logic */
-	if (i == adev->usec_timeout)
-		return -ETIME;
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90) == 0x1 ? 0 : -EIO;
+	return -ETIME;
 }
 
 int
@@ -90,9 +88,11 @@ smu_v12_0_send_msg_with_param(struct smu_context *smu,
 		return index;
 
 	ret = smu_v12_0_wait_for_response(smu);
-	if (ret)
-		pr_err("Failed to send message 0x%x, response 0x%x, param 0x%x\n",
-		       index, ret, param);
+	if (ret) {
+		pr_err("Msg issuing pre-check failed and "
+		       "SMU may be not in the right state!\n");
+		return ret;
+	}
 
 	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
@@ -159,7 +159,7 @@ int smu_v12_0_check_fw_version(struct smu_context *smu)
 
 int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate)
 {
-	if (!(smu->adev->flags & AMD_IS_APU))
+	if (!smu->is_apu)
 		return 0;
 
 	if (gate)
@@ -170,7 +170,7 @@ int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate)
 
 int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate)
 {
-	if (!(smu->adev->flags & AMD_IS_APU))
+	if (!smu->is_apu)
 		return 0;
 
 	if (gate)
@@ -179,6 +179,17 @@ int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate)
 		return smu_send_smc_msg(smu, SMU_MSG_PowerUpVcn);
 }
 
+int smu_v12_0_powergate_jpeg(struct smu_context *smu, bool gate)
+{
+	if (!smu->is_apu)
+		return 0;
+
+	if (gate)
+		return smu_send_smc_msg_with_param(smu, SMU_MSG_PowerDownJpeg, 0);
+	else
+		return smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpJpeg, 0);
+}
+
 int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable)
 {
 	if (!(smu->adev->pg_flags & AMD_PG_SUPPORT_GFX_PG))
@@ -188,6 +199,39 @@ int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable)
 		SMU_MSG_SetGfxCGPG, enable ? 1 : 0);
 }
 
+int smu_v12_0_read_sensor(struct smu_context *smu,
+				 enum amd_pp_sensors sensor,
+				 void *data, uint32_t *size)
+{
+	int ret = 0;
+
+	if(!data || !size)
+		return -EINVAL;
+
+	switch (sensor) {
+	case AMDGPU_PP_SENSOR_GFX_MCLK:
+		ret = smu_get_current_clk_freq(smu, SMU_UCLK, (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GFX_SCLK:
+		ret = smu_get_current_clk_freq(smu, SMU_GFXCLK, (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_MIN_FAN_RPM:
+		*(uint32_t *)data = 0;
+		*size = 4;
+		break;
+	default:
+		ret = smu_common_read_sensor(smu, sensor, data, size);
+		break;
+	}
+
+	if (ret)
+		*size = 0;
+
+	return ret;
+}
+
 /**
  * smu_v12_0_get_gfxoff_status - get gfxoff status
  *
@@ -274,16 +318,57 @@ int smu_v12_0_fini_smc_tables(struct smu_context *smu)
 int smu_v12_0_populate_smc_tables(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct smu_table *table = NULL;
 
-	table = &smu_table->tables[SMU_TABLE_DPMCLOCKS];
-	if (!table)
+	return smu_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false);
+}
+
+int smu_v12_0_get_enabled_mask(struct smu_context *smu,
+				      uint32_t *feature_mask, uint32_t num)
+{
+	uint32_t feature_mask_high = 0, feature_mask_low = 0;
+	int ret = 0;
+
+	if (!feature_mask || num < 2)
 		return -EINVAL;
 
-	if (!table->cpu_addr)
+	ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesHigh);
+	if (ret)
+		return ret;
+	ret = smu_read_smc_arg(smu, &feature_mask_high);
+	if (ret)
+		return ret;
+
+	ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesLow);
+	if (ret)
+		return ret;
+	ret = smu_read_smc_arg(smu, &feature_mask_low);
+	if (ret)
+		return ret;
+
+	feature_mask[0] = feature_mask_low;
+	feature_mask[1] = feature_mask_high;
+
+	return ret;
+}
+
+int smu_v12_0_get_current_clk_freq(struct smu_context *smu,
+					  enum smu_clk_type clk_id,
+					  uint32_t *value)
+{
+	int ret = 0;
+	uint32_t freq = 0;
+
+	if (clk_id >= SMU_CLK_COUNT || !value)
 		return -EINVAL;
 
-	return smu_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false);
+	ret = smu_get_current_clk_freq_by_table(smu, clk_id, &freq);
+	if (ret)
+		return ret;
+
+	freq *= 100;
+	*value = freq;
+
+	return ret;
 }
 
 int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
@@ -421,3 +506,21 @@ int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_
 
 	return ret;
 }
+
+int smu_v12_0_set_driver_table_location(struct smu_context *smu)
+{
+	struct smu_table *driver_table = &smu->smu_table.driver_table;
+	int ret = 0;
+
+	if (driver_table->mc_address) {
+		ret = smu_send_smc_msg_with_param(smu,
+				SMU_MSG_SetDriverDramAddrHigh,
+				upper_32_bits(driver_table->mc_address));
+		if (!ret)
+			ret = smu_send_smc_msg_with_param(smu,
+				SMU_MSG_SetDriverDramAddrLow,
+				lower_32_bits(driver_table->mc_address));
+	}
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 15590fd86ef4..868e2d5f6e62 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -653,8 +653,8 @@ static int ci_min_max_v_gnbl_pm_lid_from_bapm_vddc(struct pp_hwmgr *hwmgr)
 static int ci_populate_bapm_vddc_base_leakage_sidd(struct pp_hwmgr *hwmgr)
 {
 	struct ci_smumgr *smu_data = (struct ci_smumgr *)(hwmgr->smu_backend);
-	uint16_t HiSidd = smu_data->power_tune_table.BapmVddCBaseLeakageHiSidd;
-	uint16_t LoSidd = smu_data->power_tune_table.BapmVddCBaseLeakageLoSidd;
+	uint16_t HiSidd;
+	uint16_t LoSidd;
 	struct phm_cac_tdp_table *cac_table = hwmgr->dyn_state.cac_dtp_table;
 
 	HiSidd = (uint16_t)(cac_table->usHighCACLeakage / 100 * 256);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index da025b1d302d..32ebb383c456 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -940,7 +940,7 @@ static int fiji_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 {
 	int result;
 	/* PP_Clocks minClocks; */
-	uint32_t threshold, mvdd;
+	uint32_t mvdd;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
@@ -973,8 +973,6 @@ static int fiji_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 	level->VoltageDownHyst = 0;
 	level->PowerThrottle = 0;
 
-	threshold = clock * data->fast_watermark_threshold / 100;
-
 	data->display_timing.min_clock_in_sr = hwmgr->display_config->min_core_set_clock_in_sr;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SclkDeepSleep))
@@ -1501,7 +1499,7 @@ static int fiji_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 	uint32_t dram_timing;
 	uint32_t dram_timing2;
 	uint32_t burstTime;
-	ULONG state, trrds, trrdl;
+	ULONG trrds, trrdl;
 	int result;
 
 	result = atomctrl_set_engine_dram_timings_rv770(hwmgr,
@@ -1513,7 +1511,6 @@ static int fiji_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 	dram_timing2 = cgs_read_register(hwmgr->device, mmMC_ARB_DRAM_TIMING2);
 	burstTime = cgs_read_register(hwmgr->device, mmMC_ARB_BURST_TIME);
 
-	state = PHM_GET_FIELD(burstTime, MC_ARB_BURST_TIME, STATE0);
 	trrds = PHM_GET_FIELD(burstTime, MC_ARB_BURST_TIME, TRRDS0);
 	trrdl = PHM_GET_FIELD(burstTime, MC_ARB_BURST_TIME, TRRDL0);
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
index aa0ee2b46135..2319400a3fcb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
@@ -137,7 +137,7 @@ static int smu10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			priv->smu_tables.entry[table_id].table_id);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, (uint8_t *)priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -150,6 +150,7 @@ static int smu10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 {
 	struct smu10_smumgr *priv =
 			(struct smu10_smumgr *)(hwmgr->smu_backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	PP_ASSERT_WITH_CODE(table_id < MAX_SMU_TABLE,
 			"Invalid SMU Table ID!", return -EINVAL;);
@@ -161,6 +162,8 @@ static int smu10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	smu10_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
index 742b3dc1f6cb..adfbcbe5d113 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
@@ -61,15 +61,29 @@ static uint32_t smu9_wait_for_response(struct pp_hwmgr *hwmgr)
 	uint32_t reg;
 	uint32_t ret;
 
-	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
+	/* Due to the L1 policy problem under SRIOV, we have to use
+	 * mmMP1_SMN_C2PMSG_103 as the driver response register
+	 */
+	if (hwmgr->pp_one_vf) {
+		reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_103);
 
-	ret = phm_wait_for_register_unequal(hwmgr, reg,
-			0, MP1_C2PMSG_90__CONTENT_MASK);
+		ret = phm_wait_for_register_unequal(hwmgr, reg,
+				0, MP1_C2PMSG_103__CONTENT_MASK);
 
-	if (ret)
-		pr_err("No response from smu\n");
+		if (ret)
+			pr_err("No response from smu\n");
 
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
+		return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_103);
+	} else {
+		reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
+
+		ret = phm_wait_for_register_unequal(hwmgr, reg,
+				0, MP1_C2PMSG_90__CONTENT_MASK);
+
+		if (ret)
+			pr_err("No response from smu\n");
+		return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
+	}
 }
 
 /*
@@ -83,7 +97,11 @@ static int smu9_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
+	if (hwmgr->pp_one_vf) {
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_101, msg);
+	} else {
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
+	}
 
 	return 0;
 }
@@ -101,7 +119,10 @@ int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 
 	smu9_wait_for_response(hwmgr);
 
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+	if (hwmgr->pp_one_vf)
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_103, 0);
+	else
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
 	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -127,9 +148,17 @@ int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 
 	smu9_wait_for_response(hwmgr);
 
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
+	/* Due to the L1 policy problem under SRIOV, we have to use
+	 * mmMP1_SMN_C2PMSG_101 as the driver message register and
+	 * mmMP1_SMN_C2PMSG_102 as the driver parameter register.
+	 */
+	if (hwmgr->pp_one_vf) {
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_103, 0);
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_102, parameter);
+	} else {
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
+	}
 
 	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -144,5 +173,8 @@ uint32_t smu9_get_argument(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
+	if (hwmgr->pp_one_vf)
+		return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_102);
+	else
+		return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
index 0f3836fd9666..715564009089 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
@@ -58,7 +58,7 @@ static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			priv->smu_tables.entry[table_id].table_id);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -70,6 +70,13 @@ static int vega10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 		uint8_t *table, int16_t table_id)
 {
 	struct vega10_smumgr *priv = hwmgr->smu_backend;
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	/* under sriov, vbios or hypervisor driver
+	 * has already copy table to smc so here only skip it
+	 */
+	if (!hwmgr->not_vf)
+		return 0;
 
 	PP_ASSERT_WITH_CODE(table_id < MAX_SMU_TABLE,
 			"Invalid SMU Table ID!", return -EINVAL);
@@ -81,6 +88,8 @@ static int vega10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
@@ -100,6 +109,14 @@ int vega10_enable_smc_features(struct pp_hwmgr *hwmgr,
 	int msg = enable ? PPSMC_MSG_EnableSmuFeatures :
 			PPSMC_MSG_DisableSmuFeatures;
 
+	/* VF has no permission to change smu feature due
+	 * to security concern even under pp one vf mode
+	 * it still can't do it. For vega10, the smu in
+	 * vbios will enable the appropriate features.
+	 * */
+	if (!hwmgr->not_vf)
+		return 0;
+
 	return smum_send_msg_to_smc_with_parameter(hwmgr,
 			msg, feature_mask);
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
index 90c782c132d2..a3915bfcce81 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
@@ -66,7 +66,7 @@ static int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			return -EINVAL);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -84,6 +84,7 @@ static int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 {
 	struct vega12_smumgr *priv =
 			(struct vega12_smumgr *)(hwmgr->smu_backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	PP_ASSERT_WITH_CODE(table_id < TABLE_COUNT,
 			"Invalid SMU Table ID!", return -EINVAL);
@@ -95,6 +96,8 @@ static int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
index f604612f411f..0db57fb83d30 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
@@ -189,7 +189,7 @@ static int vega20_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			return ret);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -207,6 +207,7 @@ static int vega20_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 {
 	struct vega20_smumgr *priv =
 			(struct vega20_smumgr *)(hwmgr->smu_backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 	int ret = 0;
 
 	PP_ASSERT_WITH_CODE(table_id < TABLE_COUNT,
@@ -219,6 +220,8 @@ static int vega20_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	PP_ASSERT_WITH_CODE((ret = vega20_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr))) == 0,
@@ -242,11 +245,14 @@ int vega20_set_activity_monitor_coeff(struct pp_hwmgr *hwmgr,
 {
 	struct vega20_smumgr *priv =
 			(struct vega20_smumgr *)(hwmgr->smu_backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 	int ret = 0;
 
 	memcpy(priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].table, table,
 			priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	PP_ASSERT_WITH_CODE((ret = vega20_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].mc_addr))) == 0,
@@ -290,7 +296,7 @@ int vega20_get_activity_monitor_coeff(struct pp_hwmgr *hwmgr,
 			return ret);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].table,
 			priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index ae18fbcb26fb..b0e0d67cd54b 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -1114,7 +1114,6 @@ static int vegam_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	SMIO_Pattern vol_level;
 	uint32_t mvdd;
-	uint16_t us_mvdd;
 
 	table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
 
@@ -1168,17 +1167,6 @@ static int vegam_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 			"in Clock Dependency Table",
 			);
 
-	us_mvdd = 0;
-	if ((SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
-			(data->mclk_dpm_key_disabled))
-		us_mvdd = data->vbios_boot_state.mvdd_bootup_value;
-	else {
-		if (!vegam_populate_mvdd_value(hwmgr,
-				data->dpm_table.mclk_table.dpm_levels[0].value,
-				&vol_level))
-			us_mvdd = vol_level.Voltage;
-	}
-
 	if (!vegam_populate_mvdd_value(hwmgr, 0, &vol_level))
 		table->MemoryACPILevel.MinMvdd = PP_HOST_TO_SMC_UL(vol_level.Voltage);
 	else
@@ -1383,11 +1371,16 @@ static int vegam_populate_smc_boot_level(struct pp_hwmgr *hwmgr,
 	result = phm_find_boot_level(&(data->dpm_table.sclk_table),
 			data->vbios_boot_state.sclk_bootup_value,
 			(uint32_t *)&(table->GraphicsBootLevel));
+	if (result)
+		return result;
 
 	result = phm_find_boot_level(&(data->dpm_table.mclk_table),
 			data->vbios_boot_state.mclk_bootup_value,
 			(uint32_t *)&(table->MemoryBootLevel));
 
+	if (result)
+		return result;
+
 	table->BootVddc  = data->vbios_boot_state.vddc_bootup_value *
 			VOLTAGE_SCALE;
 	table->BootVddci = data->vbios_boot_state.vddci_bootup_value *
@@ -1493,7 +1486,7 @@ static int vegam_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 	struct vegam_smumgr *smu_data =
 			(struct vegam_smumgr *)(hwmgr->smu_backend);
 
-	uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
+	uint8_t i, stretch_amount, volt_offset = 0;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
@@ -1532,11 +1525,9 @@ static int vegam_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 			(table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ?
 			table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 5;
 	/* Populate CKS Lookup Table */
-	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
-		stretch_amount2 = 0;
-	else if (stretch_amount == 3 || stretch_amount == 4)
-		stretch_amount2 = 1;
-	else {
+	if (!(stretch_amount == 1 || stretch_amount == 2 ||
+	      stretch_amount == 5 || stretch_amount == 3 ||
+	      stretch_amount == 4)) {
 		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
 				PHM_PlatformCaps_ClockStretcher);
 		PP_ASSERT_WITH_CODE(false,
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 0d3a3b0a934e..38febd5ca4da 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -338,6 +338,10 @@ static int vega20_tables_init(struct smu_context *smu, struct smu_table *tables)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
+	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
+	if (!smu_table->watermarks_table)
+		return -ENOMEM;
+
 	return 0;
 }
 
@@ -2235,7 +2239,7 @@ static int vega20_apply_clocks_adjust_rules(struct smu_context *smu)
 }
 
 static int
-vega20_notify_smc_dispaly_config(struct smu_context *smu)
+vega20_notify_smc_display_config(struct smu_context *smu)
 {
 	struct vega20_dpm_table *dpm_table = smu->smu_dpm.dpm_context;
 	struct vega20_single_dpm_table *memtable = &dpm_table->mem_table;
@@ -3194,6 +3198,7 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.get_od_percentage = vega20_get_od_percentage,
 	.get_power_profile_mode = vega20_get_power_profile_mode,
 	.set_power_profile_mode = vega20_set_power_profile_mode,
+	.set_performance_level = smu_v11_0_set_performance_level,
 	.set_od_percentage = vega20_set_od_percentage,
 	.set_default_od_settings = vega20_set_default_od_settings,
 	.od_edit_dpm_table = vega20_odn_edit_dpm_table,
@@ -3203,7 +3208,7 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.pre_display_config_changed = vega20_pre_display_config_changed,
 	.display_config_changed = vega20_display_config_changed,
 	.apply_clocks_adjust_rules = vega20_apply_clocks_adjust_rules,
-	.notify_smc_dispaly_config = vega20_notify_smc_dispaly_config,
+	.notify_smc_display_config = vega20_notify_smc_display_config,
 	.force_dpm_limit_value = vega20_force_dpm_limit_value,
 	.unforce_dpm_levels = vega20_unforce_dpm_levels,
 	.get_profiling_clk_mask = vega20_get_profiling_clk_mask,
@@ -3231,6 +3236,7 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.check_fw_version = smu_v11_0_check_fw_version,
 	.write_pptable = smu_v11_0_write_pptable,
 	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_driver_table_location = smu_v11_0_set_driver_table_location,
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
@@ -3259,7 +3265,8 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.baco_is_support= smu_v11_0_baco_is_support,
 	.baco_get_state = smu_v11_0_baco_get_state,
 	.baco_set_state = smu_v11_0_baco_set_state,
-	.baco_reset = smu_v11_0_baco_reset,
+	.baco_enter = smu_v11_0_baco_enter,
+	.baco_exit = smu_v11_0_baco_exit,
 	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
diff --git a/drivers/gpu/drm/arc/arcpgu_crtc.c b/drivers/gpu/drm/arc/arcpgu_crtc.c
index dfaddbb7da0d..8ae1e1f97a73 100644
--- a/drivers/gpu/drm/arc/arcpgu_crtc.c
+++ b/drivers/gpu/drm/arc/arcpgu_crtc.c
@@ -20,9 +20,10 @@
 
 #define ENCODE_PGU_XY(x, y)	((((x) - 1) << 16) | ((y) - 1))
 
-static struct simplefb_format supported_formats[] = {
-	{ "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0}, DRM_FORMAT_RGB565 },
-	{ "r8g8b8", 24, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_RGB888 },
+static const u32 arc_pgu_supported_formats[] = {
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
 };
 
 static void arc_pgu_set_pxl_fmt(struct drm_crtc *crtc)
@@ -30,22 +31,24 @@ static void arc_pgu_set_pxl_fmt(struct drm_crtc *crtc)
 	struct arcpgu_drm_private *arcpgu = crtc_to_arcpgu_priv(crtc);
 	const struct drm_framebuffer *fb = crtc->primary->state->fb;
 	uint32_t pixel_format = fb->format->format;
-	struct simplefb_format *format = NULL;
+	u32 format = DRM_FORMAT_INVALID;
 	int i;
+	u32 reg_ctrl;
 
-	for (i = 0; i < ARRAY_SIZE(supported_formats); i++) {
-		if (supported_formats[i].fourcc == pixel_format)
-			format = &supported_formats[i];
+	for (i = 0; i < ARRAY_SIZE(arc_pgu_supported_formats); i++) {
+		if (arc_pgu_supported_formats[i] == pixel_format)
+			format = arc_pgu_supported_formats[i];
 	}
 
-	if (WARN_ON(!format))
+	if (WARN_ON(format == DRM_FORMAT_INVALID))
 		return;
 
-	if (format->fourcc == DRM_FORMAT_RGB888)
-		arc_pgu_write(arcpgu, ARCPGU_REG_CTRL,
-			      arc_pgu_read(arcpgu, ARCPGU_REG_CTRL) |
-					   ARCPGU_MODE_RGB888_MASK);
-
+	reg_ctrl = arc_pgu_read(arcpgu, ARCPGU_REG_CTRL);
+	if (format == DRM_FORMAT_RGB565)
+		reg_ctrl &= ~ARCPGU_MODE_XRGB8888;
+	else
+		reg_ctrl |= ARCPGU_MODE_XRGB8888;
+	arc_pgu_write(arcpgu, ARCPGU_REG_CTRL, reg_ctrl);
 }
 
 static const struct drm_crtc_funcs arc_pgu_crtc_funcs = {
@@ -193,18 +196,15 @@ static struct drm_plane *arc_pgu_plane_init(struct drm_device *drm)
 {
 	struct arcpgu_drm_private *arcpgu = drm->dev_private;
 	struct drm_plane *plane = NULL;
-	u32 formats[ARRAY_SIZE(supported_formats)], i;
 	int ret;
 
 	plane = devm_kzalloc(drm->dev, sizeof(*plane), GFP_KERNEL);
 	if (!plane)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < ARRAY_SIZE(supported_formats); i++)
-		formats[i] = supported_formats[i].fourcc;
-
 	ret = drm_universal_plane_init(drm, plane, 0xff, &arc_pgu_plane_funcs,
-				       formats, ARRAY_SIZE(formats),
+				       arc_pgu_supported_formats,
+				       ARRAY_SIZE(arc_pgu_supported_formats),
 				       NULL,
 				       DRM_PLANE_TYPE_PRIMARY, NULL);
 	if (ret)
diff --git a/drivers/gpu/drm/arc/arcpgu_regs.h b/drivers/gpu/drm/arc/arcpgu_regs.h
index dab2c380f7f3..b689a382d556 100644
--- a/drivers/gpu/drm/arc/arcpgu_regs.h
+++ b/drivers/gpu/drm/arc/arcpgu_regs.h
@@ -25,7 +25,7 @@
 #define ARCPGU_CTRL_VS_POL_OFST	0x3
 #define ARCPGU_CTRL_HS_POL_MASK	0x1
 #define ARCPGU_CTRL_HS_POL_OFST	0x4
-#define ARCPGU_MODE_RGB888_MASK	0x04
+#define ARCPGU_MODE_XRGB8888	BIT(2)
 #define ARCPGU_STAT_BUSY_MASK	0x02
 
 #endif
diff --git a/drivers/gpu/drm/arm/display/Kconfig b/drivers/gpu/drm/arm/display/Kconfig
index e87ff8623076..cec0639e3aa1 100644
--- a/drivers/gpu/drm/arm/display/Kconfig
+++ b/drivers/gpu/drm/arm/display/Kconfig
@@ -12,9 +12,3 @@ config DRM_KOMEDA
 	  Processor driver. It supports the D71 variants of the hardware.
 
 	  If compiled as a module it will be called komeda.
-
-config DRM_KOMEDA_ERROR_PRINT
-	bool "Enable komeda error print"
-	depends on DRM_KOMEDA
-	help
-	  Choose this option to enable error printing.
diff --git a/drivers/gpu/drm/arm/display/include/malidp_product.h b/drivers/gpu/drm/arm/display/include/malidp_product.h
index 1053b11352eb..16a8a2c22c42 100644
--- a/drivers/gpu/drm/arm/display/include/malidp_product.h
+++ b/drivers/gpu/drm/arm/display/include/malidp_product.h
@@ -18,7 +18,8 @@
 #define MALIDP_CORE_ID_STATUS(__core_id)     (((__u32)(__core_id)) & 0xFF)
 
 /* Mali-display product IDs */
-#define MALIDP_D71_PRODUCT_ID   0x0071
+#define MALIDP_D71_PRODUCT_ID	0x0071
+#define MALIDP_D32_PRODUCT_ID	0x0032
 
 union komeda_config_id {
 	struct {
diff --git a/drivers/gpu/drm/arm/display/komeda/Makefile b/drivers/gpu/drm/arm/display/komeda/Makefile
index f095a1c68ac7..1931a7fa1a14 100644
--- a/drivers/gpu/drm/arm/display/komeda/Makefile
+++ b/drivers/gpu/drm/arm/display/komeda/Makefile
@@ -16,12 +16,11 @@ komeda-y := \
 	komeda_crtc.o \
 	komeda_plane.o \
 	komeda_wb_connector.o \
-	komeda_private_obj.o
+	komeda_private_obj.o \
+	komeda_event.o
 
 komeda-y += \
 	d71/d71_dev.o \
 	d71/d71_component.o
 
-komeda-$(CONFIG_DRM_KOMEDA_ERROR_PRINT) += komeda_event.o
-
 obj-$(CONFIG_DRM_KOMEDA) += komeda.o
diff --git a/drivers/gpu/drm/arm/display/komeda/d71/d71_component.c b/drivers/gpu/drm/arm/display/komeda/d71/d71_component.c
index f0ba26e282c3..8a02ade369db 100644
--- a/drivers/gpu/drm/arm/display/komeda/d71/d71_component.c
+++ b/drivers/gpu/drm/arm/display/komeda/d71/d71_component.c
@@ -1044,7 +1044,9 @@ static int d71_merger_init(struct d71_dev *d71,
 static void d71_improc_update(struct komeda_component *c,
 			      struct komeda_component_state *state)
 {
+	struct drm_crtc_state *crtc_st = state->crtc->state;
 	struct komeda_improc_state *st = to_improc_st(state);
+	struct d71_pipeline *pipe = to_d71_pipeline(c->pipeline);
 	u32 __iomem *reg = c->reg;
 	u32 index, mask = 0, ctrl = 0;
 
@@ -1055,6 +1057,24 @@ static void d71_improc_update(struct komeda_component *c,
 	malidp_write32(reg, BLK_SIZE, HV_SIZE(st->hsize, st->vsize));
 	malidp_write32(reg, IPS_DEPTH, st->color_depth);
 
+	if (crtc_st->color_mgmt_changed) {
+		mask |= IPS_CTRL_FT | IPS_CTRL_RGB;
+
+		if (crtc_st->gamma_lut) {
+			malidp_write_group(pipe->dou_ft_coeff_addr, FT_COEFF0,
+					   KOMEDA_N_GAMMA_COEFFS,
+					   st->fgamma_coeffs);
+			ctrl |= IPS_CTRL_FT; /* enable gamma */
+		}
+
+		if (crtc_st->ctm) {
+			malidp_write_group(reg, IPS_RGB_RGB_COEFF0,
+					   KOMEDA_N_CTM_COEFFS,
+					   st->ctm_coeffs);
+			ctrl |= IPS_CTRL_RGB; /* enable gamut */
+		}
+	}
+
 	mask |= IPS_CTRL_YUV | IPS_CTRL_CHD422 | IPS_CTRL_CHD420;
 
 	/* config color format */
@@ -1250,7 +1270,7 @@ static int d71_timing_ctrlr_init(struct d71_dev *d71,
 
 	ctrlr = to_ctrlr(c);
 
-	ctrlr->supports_dual_link = true;
+	ctrlr->supports_dual_link = d71->supports_dual_link;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c b/drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c
index 822b23a1ce75..00fa56c29b3e 100644
--- a/drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c
+++ b/drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c
@@ -20,8 +20,10 @@ static u64 get_lpu_event(struct d71_pipeline *d71_pipeline)
 		evts |= KOMEDA_EVENT_IBSY;
 	if (raw_status & LPU_IRQ_EOW)
 		evts |= KOMEDA_EVENT_EOW;
+	if (raw_status & LPU_IRQ_OVR)
+		evts |= KOMEDA_EVENT_OVR;
 
-	if (raw_status & (LPU_IRQ_ERR | LPU_IRQ_IBSY)) {
+	if (raw_status & (LPU_IRQ_ERR | LPU_IRQ_IBSY | LPU_IRQ_OVR)) {
 		u32 restore = 0, tbu_status;
 		/* Check error of LPU status */
 		status = malidp_read32(reg, BLK_STATUS);
@@ -45,6 +47,15 @@ static u64 get_lpu_event(struct d71_pipeline *d71_pipeline)
 			restore |= LPU_STATUS_ACE3;
 			evts |= KOMEDA_ERR_ACE3;
 		}
+		if (status & LPU_STATUS_FEMPTY) {
+			restore |= LPU_STATUS_FEMPTY;
+			evts |= KOMEDA_EVENT_EMPTY;
+		}
+		if (status & LPU_STATUS_FFULL) {
+			restore |= LPU_STATUS_FFULL;
+			evts |= KOMEDA_EVENT_FULL;
+		}
+
 		if (restore != 0)
 			malidp_write32_mask(reg, BLK_STATUS, restore, 0);
 
@@ -371,23 +382,33 @@ static int d71_enum_resources(struct komeda_dev *mdev)
 		goto err_cleanup;
 	}
 
-	/* probe PERIPH */
+	/* Only the legacy HW has the periph block, the newer merges the periph
+	 * into GCU
+	 */
 	value = malidp_read32(d71->periph_addr, BLK_BLOCK_INFO);
-	if (BLOCK_INFO_BLK_TYPE(value) != D71_BLK_TYPE_PERIPH) {
-		DRM_ERROR("access blk periph but got blk: %d.\n",
-			  BLOCK_INFO_BLK_TYPE(value));
-		err = -EINVAL;
-		goto err_cleanup;
+	if (BLOCK_INFO_BLK_TYPE(value) != D71_BLK_TYPE_PERIPH)
+		d71->periph_addr = NULL;
+
+	if (d71->periph_addr) {
+		/* probe PERIPHERAL in legacy HW */
+		value = malidp_read32(d71->periph_addr, PERIPH_CONFIGURATION_ID);
+
+		d71->max_line_size	= value & PERIPH_MAX_LINE_SIZE ? 4096 : 2048;
+		d71->max_vsize		= 4096;
+		d71->num_rich_layers	= value & PERIPH_NUM_RICH_LAYERS ? 2 : 1;
+		d71->supports_dual_link	= !!(value & PERIPH_SPLIT_EN);
+		d71->integrates_tbu	= !!(value & PERIPH_TBU_EN);
+	} else {
+		value = malidp_read32(d71->gcu_addr, GCU_CONFIGURATION_ID0);
+		d71->max_line_size	= GCU_MAX_LINE_SIZE(value);
+		d71->max_vsize		= GCU_MAX_NUM_LINES(value);
+
+		value = malidp_read32(d71->gcu_addr, GCU_CONFIGURATION_ID1);
+		d71->num_rich_layers	= GCU_NUM_RICH_LAYERS(value);
+		d71->supports_dual_link	= GCU_DISPLAY_SPLIT_EN(value);
+		d71->integrates_tbu	= GCU_DISPLAY_TBU_EN(value);
 	}
 
-	value = malidp_read32(d71->periph_addr, PERIPH_CONFIGURATION_ID);
-
-	d71->max_line_size	= value & PERIPH_MAX_LINE_SIZE ? 4096 : 2048;
-	d71->max_vsize		= 4096;
-	d71->num_rich_layers	= value & PERIPH_NUM_RICH_LAYERS ? 2 : 1;
-	d71->supports_dual_link	= value & PERIPH_SPLIT_EN ? true : false;
-	d71->integrates_tbu	= value & PERIPH_TBU_EN ? true : false;
-
 	for (i = 0; i < d71->num_pipelines; i++) {
 		pipe = komeda_pipeline_add(mdev, sizeof(struct d71_pipeline),
 					   &d71_pipeline_funcs);
@@ -414,8 +435,11 @@ static int d71_enum_resources(struct komeda_dev *mdev)
 		d71->pipes[i] = to_d71_pipeline(pipe);
 	}
 
-	/* loop the register blks and probe */
-	i = 2; /* exclude GCU and PERIPH */
+	/* loop the register blks and probe.
+	 * NOTE: d71->num_blocks includes reserved blocks.
+	 * d71->num_blocks = GCU + valid blocks + reserved blocks
+	 */
+	i = 1; /* exclude GCU */
 	offset = D71_BLOCK_SIZE; /* skip GCU */
 	while (i < d71->num_blocks) {
 		blk_base = mdev->reg_base + (offset >> 2);
@@ -425,9 +449,9 @@ static int d71_enum_resources(struct komeda_dev *mdev)
 			err = d71_probe_block(d71, &blk, blk_base);
 			if (err)
 				goto err_cleanup;
-			i++;
 		}
 
+		i++;
 		offset += D71_BLOCK_SIZE;
 	}
 
@@ -594,10 +618,26 @@ static const struct komeda_dev_funcs d71_chip_funcs = {
 const struct komeda_dev_funcs *
 d71_identify(u32 __iomem *reg_base, struct komeda_chip_info *chip)
 {
+	const struct komeda_dev_funcs *funcs;
+	u32 product_id;
+
+	chip->core_id = malidp_read32(reg_base, GLB_CORE_ID);
+
+	product_id = MALIDP_CORE_ID_PRODUCT_ID(chip->core_id);
+
+	switch (product_id) {
+	case MALIDP_D71_PRODUCT_ID:
+	case MALIDP_D32_PRODUCT_ID:
+		funcs = &d71_chip_funcs;
+		break;
+	default:
+		DRM_ERROR("Unsupported product: 0x%x\n", product_id);
+		return NULL;
+	}
+
 	chip->arch_id	= malidp_read32(reg_base, GLB_ARCH_ID);
-	chip->core_id	= malidp_read32(reg_base, GLB_CORE_ID);
 	chip->core_info	= malidp_read32(reg_base, GLB_CORE_INFO);
 	chip->bus_width	= D71_BUS_WIDTH_16_BYTES;
 
-	return &d71_chip_funcs;
+	return funcs;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/d71/d71_regs.h b/drivers/gpu/drm/arm/display/komeda/d71/d71_regs.h
index 1727dc993909..e80172a0b320 100644
--- a/drivers/gpu/drm/arm/display/komeda/d71/d71_regs.h
+++ b/drivers/gpu/drm/arm/display/komeda/d71/d71_regs.h
@@ -72,6 +72,19 @@
 #define GCU_CONTROL_MODE(x)	((x) & 0x7)
 #define GCU_CONTROL_SRST	BIT(16)
 
+/* GCU_CONFIGURATION registers */
+#define GCU_CONFIGURATION_ID0	0x100
+#define GCU_CONFIGURATION_ID1	0x104
+
+/* GCU configuration */
+#define GCU_MAX_LINE_SIZE(x)	((x) & 0xFFFF)
+#define GCU_MAX_NUM_LINES(x)	((x) >> 16)
+#define GCU_NUM_RICH_LAYERS(x)	((x) & 0x7)
+#define GCU_NUM_PIPELINES(x)	(((x) >> 3) & 0x7)
+#define GCU_NUM_SCALERS(x)	(((x) >> 6) & 0x7)
+#define GCU_DISPLAY_SPLIT_EN(x)	(((x) >> 16) & 0x1)
+#define GCU_DISPLAY_TBU_EN(x)	(((x) >> 17) & 0x1)
+
 /* GCU opmode */
 #define INACTIVE_MODE		0
 #define TBU_CONNECT_MODE	1
@@ -162,6 +175,7 @@
 #define TBU_DOUTSTDCAPB_MASK	0x3F
 
 /* LPU_IRQ_BITS */
+#define LPU_IRQ_OVR		BIT(9)
 #define LPU_IRQ_IBSY		BIT(10)
 #define LPU_IRQ_ERR		BIT(11)
 #define LPU_IRQ_EOW		BIT(12)
@@ -172,6 +186,8 @@
 #define LPU_STATUS_AXIE		BIT(4)
 #define LPU_STATUS_AXIRP	BIT(5)
 #define LPU_STATUS_AXIWP	BIT(6)
+#define LPU_STATUS_FEMPTY	BIT(11)
+#define LPU_STATUS_FFULL	BIT(14)
 #define LPU_STATUS_ACE0		BIT(16)
 #define LPU_STATUS_ACE1		BIT(17)
 #define LPU_STATUS_ACE2		BIT(18)
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
index 9d14a92dbb17..d8e449e6ebda 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
@@ -65,3 +65,69 @@ const s32 *komeda_select_yuv2rgb_coeffs(u32 color_encoding, u32 color_range)
 
 	return coeffs;
 }
+
+struct gamma_curve_sector {
+	u32 boundary_start;
+	u32 num_of_segments;
+	u32 segment_width;
+};
+
+struct gamma_curve_segment {
+	u32 start;
+	u32 end;
+};
+
+static struct gamma_curve_sector sector_tbl[] = {
+	{ 0,    4,  4   },
+	{ 16,   4,  4   },
+	{ 32,   4,  8   },
+	{ 64,   4,  16  },
+	{ 128,  4,  32  },
+	{ 256,  4,  64  },
+	{ 512,  16, 32  },
+	{ 1024, 24, 128 },
+};
+
+static void
+drm_lut_to_coeffs(struct drm_property_blob *lut_blob, u32 *coeffs,
+		  struct gamma_curve_sector *sector_tbl, u32 num_sectors)
+{
+	struct drm_color_lut *lut;
+	u32 i, j, in, num = 0;
+
+	if (!lut_blob)
+		return;
+
+	lut = lut_blob->data;
+
+	for (i = 0; i < num_sectors; i++) {
+		for (j = 0; j < sector_tbl[i].num_of_segments; j++) {
+			in = sector_tbl[i].boundary_start +
+			     j * sector_tbl[i].segment_width;
+
+			coeffs[num++] = drm_color_lut_extract(lut[in].red,
+						KOMEDA_COLOR_PRECISION);
+		}
+	}
+
+	coeffs[num] = BIT(KOMEDA_COLOR_PRECISION);
+}
+
+void drm_lut_to_fgamma_coeffs(struct drm_property_blob *lut_blob, u32 *coeffs)
+{
+	drm_lut_to_coeffs(lut_blob, coeffs, sector_tbl, ARRAY_SIZE(sector_tbl));
+}
+
+void drm_ctm_to_coeffs(struct drm_property_blob *ctm_blob, u32 *coeffs)
+{
+	struct drm_color_ctm *ctm;
+	u32 i;
+
+	if (!ctm_blob)
+		return;
+
+	ctm = ctm_blob->data;
+
+	for (i = 0; i < KOMEDA_N_CTM_COEFFS; i++)
+		coeffs[i] = drm_color_ctm_s31_32_to_qm_n(ctm->matrix[i], 3, 12);
+}
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.h b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.h
index a2df218f58e7..2f4668466112 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.h
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.h
@@ -11,7 +11,15 @@
 #include <drm/drm_color_mgmt.h>
 
 #define KOMEDA_N_YUV2RGB_COEFFS		12
+#define KOMEDA_N_RGB2YUV_COEFFS		12
+#define KOMEDA_COLOR_PRECISION		12
+#define KOMEDA_N_GAMMA_COEFFS		65
+#define KOMEDA_COLOR_LUT_SIZE		BIT(KOMEDA_COLOR_PRECISION)
+#define KOMEDA_N_CTM_COEFFS		9
+
+void drm_lut_to_fgamma_coeffs(struct drm_property_blob *lut_blob, u32 *coeffs);
+void drm_ctm_to_coeffs(struct drm_property_blob *ctm_blob, u32 *coeffs);
 
 const s32 *komeda_select_yuv2rgb_coeffs(u32 color_encoding, u32 color_range);
 
-#endif
+#endif /*_KOMEDA_COLOR_MGMT_H_*/
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
index 252015210fbc..56bd938961ee 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
@@ -5,6 +5,7 @@
  *
  */
 #include <linux/clk.h>
+#include <linux/pm_runtime.h>
 #include <linux/spinlock.h>
 
 #include <drm/drm_atomic.h>
@@ -274,6 +275,7 @@ static void
 komeda_crtc_atomic_enable(struct drm_crtc *crtc,
 			  struct drm_crtc_state *old)
 {
+	pm_runtime_get_sync(crtc->dev->dev);
 	komeda_crtc_prepare(to_kcrtc(crtc));
 	drm_crtc_vblank_on(crtc);
 	WARN_ON(drm_crtc_vblank_get(crtc));
@@ -372,6 +374,7 @@ komeda_crtc_atomic_disable(struct drm_crtc *crtc,
 	drm_crtc_vblank_put(crtc);
 	drm_crtc_vblank_off(crtc);
 	komeda_crtc_unprepare(kcrtc);
+	pm_runtime_put(crtc->dev->dev);
 }
 
 static void
@@ -617,6 +620,8 @@ static int komeda_crtc_add(struct komeda_kms_dev *kms,
 
 	crtc->port = kcrtc->master->of_output_port;
 
+	drm_crtc_enable_color_mgmt(crtc, 0, true, KOMEDA_COLOR_LUT_SIZE);
+
 	return err;
 }
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
index 937a6d4c4865..1d767473ba8a 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
@@ -10,6 +10,7 @@
 #include <linux/of_graph.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/dma-mapping.h>
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
@@ -27,12 +28,16 @@ static int komeda_register_show(struct seq_file *sf, void *x)
 
 	seq_puts(sf, "\n====== Komeda register dump =========\n");
 
+	pm_runtime_get_sync(mdev->dev);
+
 	if (mdev->funcs->dump_register)
 		mdev->funcs->dump_register(mdev, sf);
 
 	for (i = 0; i < mdev->n_pipelines; i++)
 		komeda_pipeline_dump_register(mdev->pipelines[i], sf);
 
+	pm_runtime_put(mdev->dev);
+
 	return 0;
 }
 
@@ -58,6 +63,8 @@ static void komeda_debugfs_init(struct komeda_dev *mdev)
 	mdev->debugfs_root = debugfs_create_dir("komeda", NULL);
 	debugfs_create_file("register", 0444, mdev->debugfs_root,
 			    mdev, &komeda_register_fops);
+	debugfs_create_x16("err_verbosity", 0664, mdev->debugfs_root,
+			   &mdev->err_verbosity);
 }
 #endif
 
@@ -113,22 +120,14 @@ static struct attribute_group komeda_sysfs_attr_group = {
 	.attrs = komeda_sysfs_entries,
 };
 
-static int komeda_parse_pipe_dt(struct komeda_dev *mdev, struct device_node *np)
+static int komeda_parse_pipe_dt(struct komeda_pipeline *pipe)
 {
-	struct komeda_pipeline *pipe;
+	struct device_node *np = pipe->of_node;
 	struct clk *clk;
-	u32 pipe_id;
-	int ret = 0;
-
-	ret = of_property_read_u32(np, "reg", &pipe_id);
-	if (ret != 0 || pipe_id >= mdev->n_pipelines)
-		return -EINVAL;
-
-	pipe = mdev->pipelines[pipe_id];
 
 	clk = of_clk_get_by_name(np, "pxclk");
 	if (IS_ERR(clk)) {
-		DRM_ERROR("get pxclk for pipeline %d failed!\n", pipe_id);
+		DRM_ERROR("get pxclk for pipeline %d failed!\n", pipe->id);
 		return PTR_ERR(clk);
 	}
 	pipe->pxlclk = clk;
@@ -142,7 +141,6 @@ static int komeda_parse_pipe_dt(struct komeda_dev *mdev, struct device_node *np)
 		of_graph_get_port_by_id(np, KOMEDA_OF_PORT_OUTPUT);
 
 	pipe->dual_link = pipe->of_output_links[0] && pipe->of_output_links[1];
-	pipe->of_node = of_node_get(np);
 
 	return 0;
 }
@@ -151,7 +149,9 @@ static int komeda_parse_dt(struct device *dev, struct komeda_dev *mdev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct device_node *child, *np = dev->of_node;
-	int ret;
+	struct komeda_pipeline *pipe;
+	u32 pipe_id = U32_MAX;
+	int ret = -1;
 
 	mdev->irq  = platform_get_irq(pdev, 0);
 	if (mdev->irq < 0) {
@@ -166,37 +166,44 @@ static int komeda_parse_dt(struct device *dev, struct komeda_dev *mdev)
 	ret = 0;
 
 	for_each_available_child_of_node(np, child) {
-		if (of_node_cmp(child->name, "pipeline") == 0) {
-			ret = komeda_parse_pipe_dt(mdev, child);
-			if (ret) {
-				DRM_ERROR("parse pipeline dt error!\n");
-				of_node_put(child);
-				break;
+		if (of_node_name_eq(child, "pipeline")) {
+			of_property_read_u32(child, "reg", &pipe_id);
+			if (pipe_id >= mdev->n_pipelines) {
+				DRM_WARN("Skip the redundant DT node: pipeline-%u.\n",
+					 pipe_id);
+				continue;
 			}
+			mdev->pipelines[pipe_id]->of_node = of_node_get(child);
 		}
 	}
 
-	return ret;
+	for (pipe_id = 0; pipe_id < mdev->n_pipelines; pipe_id++) {
+		pipe = mdev->pipelines[pipe_id];
+
+		if (!pipe->of_node) {
+			DRM_ERROR("Pipeline-%d doesn't have a DT node.\n",
+				  pipe->id);
+			return -EINVAL;
+		}
+		ret = komeda_parse_pipe_dt(pipe);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 struct komeda_dev *komeda_dev_create(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
-	const struct komeda_product_data *product;
+	komeda_identify_func komeda_identify;
 	struct komeda_dev *mdev;
-	struct resource *io_res;
 	int err = 0;
 
-	product = of_device_get_match_data(dev);
-	if (!product)
+	komeda_identify = of_device_get_match_data(dev);
+	if (!komeda_identify)
 		return ERR_PTR(-ENODEV);
 
-	io_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!io_res) {
-		DRM_ERROR("No registers defined.\n");
-		return ERR_PTR(-ENODEV);
-	}
-
 	mdev = devm_kzalloc(dev, sizeof(*mdev), GFP_KERNEL);
 	if (!mdev)
 		return ERR_PTR(-ENOMEM);
@@ -204,7 +211,7 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 	mutex_init(&mdev->lock);
 
 	mdev->dev = dev;
-	mdev->reg_base = devm_ioremap_resource(dev, io_res);
+	mdev->reg_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(mdev->reg_base)) {
 		DRM_ERROR("Map register space failed.\n");
 		err = PTR_ERR(mdev->reg_base);
@@ -222,11 +229,9 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 
 	clk_prepare_enable(mdev->aclk);
 
-	mdev->funcs = product->identify(mdev->reg_base, &mdev->chip);
-	if (!komeda_product_match(mdev, product->product_id)) {
-		DRM_ERROR("DT configured %x mismatch with real HW %x.\n",
-			  product->product_id,
-			  MALIDP_CORE_ID_PRODUCT_ID(mdev->chip.core_id));
+	mdev->funcs = komeda_identify(mdev->reg_base, &mdev->chip);
+	if (!mdev->funcs) {
+		DRM_ERROR("Failed to identify the HW.\n");
 		err = -ENODEV;
 		goto disable_clk;
 	}
@@ -263,15 +268,6 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 	if (!mdev->iommu)
 		DRM_INFO("continue without IOMMU support!\n");
 
-	if (mdev->iommu && mdev->funcs->connect_iommu) {
-		err = mdev->funcs->connect_iommu(mdev);
-		if (err) {
-			DRM_ERROR("connect iommu failed.\n");
-			mdev->iommu = NULL;
-			goto disable_clk;
-		}
-	}
-
 	clk_disable_unprepare(mdev->aclk);
 
 	err = sysfs_create_group(&dev->kobj, &komeda_sysfs_attr_group);
@@ -280,6 +276,8 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 		goto err_cleanup;
 	}
 
+	mdev->err_verbosity = KOMEDA_DEV_PRINT_ERR_EVENTS;
+
 #ifdef CONFIG_DEBUG_FS
 	komeda_debugfs_init(mdev);
 #endif
@@ -308,11 +306,6 @@ void komeda_dev_destroy(struct komeda_dev *mdev)
 	if (mdev->aclk)
 		clk_prepare_enable(mdev->aclk);
 
-	if (mdev->iommu && mdev->funcs->disconnect_iommu)
-		if (mdev->funcs->disconnect_iommu(mdev))
-			DRM_ERROR("disconnect iommu failed.\n");
-	mdev->iommu = NULL;
-
 	for (i = 0; i < mdev->n_pipelines; i++) {
 		komeda_pipeline_destroy(mdev, mdev->pipelines[i]);
 		mdev->pipelines[i] = NULL;
@@ -341,44 +334,26 @@ void komeda_dev_destroy(struct komeda_dev *mdev)
 
 int komeda_dev_resume(struct komeda_dev *mdev)
 {
-	int ret = 0;
-
 	clk_prepare_enable(mdev->aclk);
 
-	if (mdev->iommu && mdev->funcs->connect_iommu) {
-		ret = mdev->funcs->connect_iommu(mdev);
-		if (ret < 0) {
-			DRM_ERROR("connect iommu failed.\n");
-			goto disable_clk;
-		}
-	}
-
-	ret = mdev->funcs->enable_irq(mdev);
+	mdev->funcs->enable_irq(mdev);
 
-disable_clk:
-	clk_disable_unprepare(mdev->aclk);
+	if (mdev->iommu && mdev->funcs->connect_iommu)
+		if (mdev->funcs->connect_iommu(mdev))
+			DRM_ERROR("connect iommu failed.\n");
 
-	return ret;
+	return 0;
 }
 
 int komeda_dev_suspend(struct komeda_dev *mdev)
 {
-	int ret = 0;
-
-	clk_prepare_enable(mdev->aclk);
-
-	if (mdev->iommu && mdev->funcs->disconnect_iommu) {
-		ret = mdev->funcs->disconnect_iommu(mdev);
-		if (ret < 0) {
+	if (mdev->iommu && mdev->funcs->disconnect_iommu)
+		if (mdev->funcs->disconnect_iommu(mdev))
 			DRM_ERROR("disconnect iommu failed.\n");
-			goto disable_clk;
-		}
-	}
 
-	ret = mdev->funcs->disable_irq(mdev);
+	mdev->funcs->disable_irq(mdev);
 
-disable_clk:
 	clk_disable_unprepare(mdev->aclk);
 
-	return ret;
+	return 0;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.h b/drivers/gpu/drm/arm/display/komeda/komeda_dev.h
index 414200233b64..ce27f2f27c24 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.h
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.h
@@ -20,6 +20,8 @@
 #define KOMEDA_EVENT_OVR		BIT_ULL(4)
 #define KOMEDA_EVENT_EOW		BIT_ULL(5)
 #define KOMEDA_EVENT_MODE		BIT_ULL(6)
+#define KOMEDA_EVENT_FULL		BIT_ULL(7)
+#define KOMEDA_EVENT_EMPTY		BIT_ULL(8)
 
 #define KOMEDA_ERR_TETO			BIT_ULL(14)
 #define KOMEDA_ERR_TEMR			BIT_ULL(15)
@@ -49,12 +51,15 @@
 	KOMEDA_ERR_ZME		| KOMEDA_ERR_MERR	| KOMEDA_ERR_TCF |\
 	KOMEDA_ERR_TTNG		| KOMEDA_ERR_TTF)
 
-#define KOMEDA_WARN_EVENTS	KOMEDA_ERR_CSCE
+#define KOMEDA_WARN_EVENTS	\
+	(KOMEDA_ERR_CSCE | KOMEDA_EVENT_FULL | KOMEDA_EVENT_EMPTY)
 
-/* malidp device id */
-enum {
-	MALI_D71 = 0,
-};
+#define KOMEDA_INFO_EVENTS (0 \
+			    | KOMEDA_EVENT_VSYNC \
+			    | KOMEDA_EVENT_FLIP \
+			    | KOMEDA_EVENT_EOW \
+			    | KOMEDA_EVENT_MODE \
+			    )
 
 /* pipeline DT ports */
 enum {
@@ -69,12 +74,6 @@ struct komeda_chip_info {
 	u32 bus_width;
 };
 
-struct komeda_product_data {
-	u32 product_id;
-	const struct komeda_dev_funcs *(*identify)(u32 __iomem *reg,
-					     struct komeda_chip_info *info);
-};
-
 struct komeda_dev;
 
 struct komeda_events {
@@ -202,6 +201,23 @@ struct komeda_dev {
 
 	/** @debugfs_root: root directory of komeda debugfs */
 	struct dentry *debugfs_root;
+	/**
+	 * @err_verbosity: bitmask for how much extra info to print on error
+	 *
+	 * See KOMEDA_DEV_* macros for details. Low byte contains the debug
+	 * level categories, the high byte contains extra debug options.
+	 */
+	u16 err_verbosity;
+	/* Print a single line per error per frame with error events. */
+#define KOMEDA_DEV_PRINT_ERR_EVENTS BIT(0)
+	/* Print a single line per warning per frame with error events. */
+#define KOMEDA_DEV_PRINT_WARN_EVENTS BIT(1)
+	/* Print a single line per info event per frame with error events. */
+#define KOMEDA_DEV_PRINT_INFO_EVENTS BIT(2)
+	/* Dump DRM state on an error or warning event. */
+#define KOMEDA_DEV_PRINT_DUMP_STATE_ON_EVENT BIT(8)
+	/* Disable rate limiting of event prints (normally one per commit) */
+#define KOMEDA_DEV_PRINT_DISABLE_RATELIMIT BIT(12)
 };
 
 static inline bool
@@ -210,6 +226,9 @@ komeda_product_match(struct komeda_dev *mdev, u32 target)
 	return MALIDP_CORE_ID_PRODUCT_ID(mdev->chip.core_id) == target;
 }
 
+typedef const struct komeda_dev_funcs *
+(*komeda_identify_func)(u32 __iomem *reg, struct komeda_chip_info *chip);
+
 const struct komeda_dev_funcs *
 d71_identify(u32 __iomem *reg, struct komeda_chip_info *chip);
 
@@ -218,11 +237,7 @@ void komeda_dev_destroy(struct komeda_dev *mdev);
 
 struct komeda_dev *dev_to_mdev(struct device *dev);
 
-#ifdef CONFIG_DRM_KOMEDA_ERROR_PRINT
-void komeda_print_events(struct komeda_events *evts);
-#else
-static inline void komeda_print_events(struct komeda_events *evts) {}
-#endif
+void komeda_print_events(struct komeda_events *evts, struct drm_device *dev);
 
 int komeda_dev_resume(struct komeda_dev *mdev);
 int komeda_dev_suspend(struct komeda_dev *mdev);
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c
index d6c2222c5d33..ea5cd1e17304 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c
@@ -33,6 +33,12 @@ static void komeda_unbind(struct device *dev)
 		return;
 
 	komeda_kms_detach(mdrv->kms);
+
+	if (pm_runtime_enabled(dev))
+		pm_runtime_disable(dev);
+	else
+		komeda_dev_suspend(mdrv->mdev);
+
 	komeda_dev_destroy(mdrv->mdev);
 
 	dev_set_drvdata(dev, NULL);
@@ -54,6 +60,10 @@ static int komeda_bind(struct device *dev)
 		goto free_mdrv;
 	}
 
+	pm_runtime_enable(dev);
+	if (!pm_runtime_enabled(dev))
+		komeda_dev_resume(mdrv->mdev);
+
 	mdrv->kms = komeda_kms_attach(mdrv->mdev);
 	if (IS_ERR(mdrv->kms)) {
 		err = PTR_ERR(mdrv->kms);
@@ -65,6 +75,11 @@ static int komeda_bind(struct device *dev)
 	return 0;
 
 destroy_mdev:
+	if (pm_runtime_enabled(dev))
+		pm_runtime_disable(dev);
+	else
+		komeda_dev_suspend(mdrv->mdev);
+
 	komeda_dev_destroy(mdrv->mdev);
 
 free_mdrv:
@@ -123,29 +138,37 @@ static int komeda_platform_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct komeda_product_data komeda_products[] = {
-	[MALI_D71] = {
-		.product_id = MALIDP_D71_PRODUCT_ID,
-		.identify = d71_identify,
-	},
-};
-
 static const struct of_device_id komeda_of_match[] = {
-	{ .compatible = "arm,mali-d71", .data = &komeda_products[MALI_D71], },
+	{ .compatible = "arm,mali-d71", .data = d71_identify, },
+	{ .compatible = "arm,mali-d32", .data = d71_identify, },
 	{},
 };
 
 MODULE_DEVICE_TABLE(of, komeda_of_match);
 
+static int komeda_rt_pm_suspend(struct device *dev)
+{
+	struct komeda_drv *mdrv = dev_get_drvdata(dev);
+
+	return komeda_dev_suspend(mdrv->mdev);
+}
+
+static int komeda_rt_pm_resume(struct device *dev)
+{
+	struct komeda_drv *mdrv = dev_get_drvdata(dev);
+
+	return komeda_dev_resume(mdrv->mdev);
+}
+
 static int __maybe_unused komeda_pm_suspend(struct device *dev)
 {
 	struct komeda_drv *mdrv = dev_get_drvdata(dev);
-	struct drm_device *drm = &mdrv->kms->base;
 	int res;
 
-	res = drm_mode_config_helper_suspend(drm);
+	res = drm_mode_config_helper_suspend(&mdrv->kms->base);
 
-	komeda_dev_suspend(mdrv->mdev);
+	if (!pm_runtime_status_suspended(dev))
+		komeda_dev_suspend(mdrv->mdev);
 
 	return res;
 }
@@ -153,15 +176,16 @@ static int __maybe_unused komeda_pm_suspend(struct device *dev)
 static int __maybe_unused komeda_pm_resume(struct device *dev)
 {
 	struct komeda_drv *mdrv = dev_get_drvdata(dev);
-	struct drm_device *drm = &mdrv->kms->base;
 
-	komeda_dev_resume(mdrv->mdev);
+	if (!pm_runtime_status_suspended(dev))
+		komeda_dev_resume(mdrv->mdev);
 
-	return drm_mode_config_helper_resume(drm);
+	return drm_mode_config_helper_resume(&mdrv->kms->base);
 }
 
 static const struct dev_pm_ops komeda_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(komeda_pm_suspend, komeda_pm_resume)
+	SET_RUNTIME_PM_OPS(komeda_rt_pm_suspend, komeda_rt_pm_resume, NULL)
 };
 
 static struct platform_driver komeda_platform_driver = {
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_event.c b/drivers/gpu/drm/arm/display/komeda/komeda_event.c
index a36fb86cc054..53f944e66dfc 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_event.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_event.c
@@ -4,6 +4,7 @@
  * Author: James.Qian.Wang <james.qian.wang@arm.com>
  *
  */
+#include <drm/drm_atomic.h>
 #include <drm/drm_print.h>
 
 #include "komeda_dev.h"
@@ -16,6 +17,7 @@ struct komeda_str {
 
 /* return 0 on success,  < 0 on no space.
  */
+__printf(2, 3)
 static int komeda_sprintf(struct komeda_str *str, const char *fmt, ...)
 {
 	va_list args;
@@ -76,6 +78,8 @@ static void evt_str(struct komeda_str *str, u64 events)
 
 	/* LPU errors or events */
 	evt_sprintf(str, events & KOMEDA_EVENT_IBSY, "IBSY|");
+	evt_sprintf(str, events & KOMEDA_EVENT_EMPTY, "EMPTY|");
+	evt_sprintf(str, events & KOMEDA_EVENT_FULL, "FULL|");
 	evt_sprintf(str, events & KOMEDA_ERR_AXIE, "AXIE|");
 	evt_sprintf(str, events & KOMEDA_ERR_ACE0, "ACE0|");
 	evt_sprintf(str, events & KOMEDA_ERR_ACE1, "ACE1|");
@@ -107,20 +111,31 @@ static bool is_new_frame(struct komeda_events *a)
 	       (KOMEDA_EVENT_FLIP | KOMEDA_EVENT_EOW);
 }
 
-void komeda_print_events(struct komeda_events *evts)
+void komeda_print_events(struct komeda_events *evts, struct drm_device *dev)
 {
-	u64 print_evts = KOMEDA_ERR_EVENTS;
+	u64 print_evts = 0;
 	static bool en_print = true;
+	struct komeda_dev *mdev = dev->dev_private;
+	u16 const err_verbosity = mdev->err_verbosity;
+	u64 evts_mask = evts->global | evts->pipes[0] | evts->pipes[1];
 
 	/* reduce the same msg print, only print the first evt for one frame */
 	if (evts->global || is_new_frame(evts))
 		en_print = true;
-	if (!en_print)
+	if (!(err_verbosity & KOMEDA_DEV_PRINT_DISABLE_RATELIMIT) && !en_print)
 		return;
 
-	if ((evts->global | evts->pipes[0] | evts->pipes[1]) & print_evts) {
+	if (err_verbosity & KOMEDA_DEV_PRINT_ERR_EVENTS)
+		print_evts |= KOMEDA_ERR_EVENTS;
+	if (err_verbosity & KOMEDA_DEV_PRINT_WARN_EVENTS)
+		print_evts |= KOMEDA_WARN_EVENTS;
+	if (err_verbosity & KOMEDA_DEV_PRINT_INFO_EVENTS)
+		print_evts |= KOMEDA_INFO_EVENTS;
+
+	if (evts_mask & print_evts) {
 		char msg[256];
 		struct komeda_str str;
+		struct drm_printer p = drm_info_printer(dev->dev);
 
 		str.str = msg;
 		str.sz  = sizeof(msg);
@@ -134,6 +149,9 @@ void komeda_print_events(struct komeda_events *evts)
 		evt_str(&str, evts->pipes[1]);
 
 		DRM_ERROR("err detect: %s\n", msg);
+		if ((err_verbosity & KOMEDA_DEV_PRINT_DUMP_STATE_ON_EVENT) &&
+		    (evts_mask & (KOMEDA_ERR_EVENTS | KOMEDA_WARN_EVENTS)))
+			drm_state_dump(dev, &p);
 
 		en_print = false;
 	}
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
index 52648b4008bc..442d4656150a 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
@@ -48,7 +48,7 @@ static irqreturn_t komeda_kms_irq_handler(int irq, void *data)
 	memset(&evts, 0, sizeof(evts));
 	status = mdev->funcs->irq_handler(mdev, &evts);
 
-	komeda_print_events(&evts);
+	komeda_print_events(&evts, drm);
 
 	/* Notify the crtc to handle the events */
 	for (i = 0; i < kms->n_crtcs; i++)
@@ -308,10 +308,6 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev)
 	if (err)
 		goto free_component_binding;
 
-	err = mdev->funcs->enable_irq(mdev);
-	if (err)
-		goto free_component_binding;
-
 	drm->irq_enabled = true;
 
 	drm_kms_helper_poll_init(drm);
@@ -325,7 +321,6 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev)
 free_interrupts:
 	drm_kms_helper_poll_fini(drm);
 	drm->irq_enabled = false;
-	mdev->funcs->disable_irq(mdev);
 free_component_binding:
 	component_unbind_all(mdev->dev, drm);
 cleanup_mode_config:
@@ -347,7 +342,6 @@ void komeda_kms_detach(struct komeda_kms_dev *kms)
 	drm_kms_helper_poll_fini(drm);
 	drm_atomic_helper_shutdown(drm);
 	drm->irq_enabled = false;
-	mdev->funcs->disable_irq(mdev);
 	component_unbind_all(mdev->dev, drm);
 	drm_mode_config_cleanup(drm);
 	komeda_kms_cleanup_private_objs(kms);
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h
index bd6ca7c87037..ac8725e24853 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h
@@ -11,6 +11,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include "malidp_utils.h"
+#include "komeda_color_mgmt.h"
 
 #define KOMEDA_MAX_PIPELINES		2
 #define KOMEDA_PIPELINE_MAX_LAYERS	4
@@ -327,6 +328,8 @@ struct komeda_improc_state {
 	struct komeda_component_state base;
 	u8 color_format, color_depth;
 	u16 hsize, vsize;
+	u32 fgamma_coeffs[KOMEDA_N_GAMMA_COEFFS];
+	u32 ctm_coeffs[KOMEDA_N_CTM_COEFFS];
 };
 
 /* display timing controller */
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
index 52750116aa19..8f32ae7c25d0 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
@@ -802,6 +802,12 @@ komeda_improc_validate(struct komeda_improc *improc,
 		st->color_format = BIT(__ffs(avail_formats));
 	}
 
+	if (kcrtc_st->base.color_mgmt_changed) {
+		drm_lut_to_fgamma_coeffs(kcrtc_st->base.gamma_lut,
+					 st->fgamma_coeffs);
+		drm_ctm_to_coeffs(kcrtc_st->base.ctm, st->ctm_coeffs);
+	}
+
 	komeda_component_add_input(&st->base, &dflow->input, 0);
 	komeda_component_set_output(&dflow->input, &improc->base, 0);
 
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 3c70a53813bf..37715cc6064e 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -512,7 +512,7 @@ static int malidp_de_plane_check(struct drm_plane *plane,
 	int i, ret;
 	unsigned int block_w, block_h;
 
-	if (!state->crtc || !state->fb)
+	if (!state->crtc || WARN_ON(!state->fb))
 		return 0;
 
 	fb = state->fb;
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
index 090cc0d699ae..ac8a78bfda03 100644
--- a/drivers/gpu/drm/armada/armada_fbdev.c
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -16,7 +16,7 @@
 #include "armada_fb.h"
 #include "armada_gem.h"
 
-static /*const*/ struct fb_ops armada_fb_ops = {
+static const struct fb_ops armada_fb_ops = {
 	.owner		= THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_fillrect	= drm_fb_helper_cfb_fillrect,
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 93cf8b8bfcff..976685f2939e 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -461,16 +461,6 @@ static void armada_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
 	kfree(sgt);
 }
 
-static void *armada_gem_dmabuf_no_kmap(struct dma_buf *buf, unsigned long n)
-{
-	return NULL;
-}
-
-static void
-armada_gem_dmabuf_no_kunmap(struct dma_buf *buf, unsigned long n, void *addr)
-{
-}
-
 static int
 armada_gem_dmabuf_mmap(struct dma_buf *buf, struct vm_area_struct *vma)
 {
@@ -481,8 +471,6 @@ static const struct dma_buf_ops armada_gem_prime_dmabuf_ops = {
 	.map_dma_buf	= armada_gem_prime_map_dma_buf,
 	.unmap_dma_buf	= armada_gem_prime_unmap_dma_buf,
 	.release	= drm_gem_dmabuf_release,
-	.map		= armada_gem_dmabuf_no_kmap,
-	.unmap		= armada_gem_dmabuf_no_kunmap,
 	.mmap		= armada_gem_dmabuf_mmap,
 };
 
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index 1f17794b0890..30aa73a5d9b7 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -33,7 +33,6 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_vram_helper.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_probe_helper.h>
 
 #include "ast_drv.h"
@@ -86,9 +85,42 @@ static void ast_kick_out_firmware_fb(struct pci_dev *pdev)
 
 static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
+	struct drm_device *dev;
+	int ret;
+
 	ast_kick_out_firmware_fb(pdev);
 
-	return drm_get_pci_dev(pdev, ent, &driver);
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	dev = drm_dev_alloc(&driver, &pdev->dev);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto err_pci_disable_device;
+	}
+
+	dev->pdev = pdev;
+	pci_set_drvdata(pdev, dev);
+
+	ret = ast_driver_load(dev, ent->driver_data);
+	if (ret)
+		goto err_drm_dev_put;
+
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_ast_driver_unload;
+
+	return 0;
+
+err_ast_driver_unload:
+	ast_driver_unload(dev);
+err_drm_dev_put:
+	drm_dev_put(dev);
+err_pci_disable_device:
+	pci_disable_device(pdev);
+	return ret;
+
 }
 
 static void
@@ -96,17 +128,19 @@ ast_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
-	drm_put_dev(dev);
+	drm_dev_unregister(dev);
+	ast_driver_unload(dev);
+	drm_dev_put(dev);
 }
 
-
-
 static int ast_drm_freeze(struct drm_device *dev)
 {
-	drm_kms_helper_poll_disable(dev);
-	pci_save_state(dev->pdev);
-	drm_fb_helper_set_suspend_unlocked(dev->fb_helper, true);
+	int error;
 
+	error = drm_mode_config_helper_suspend(dev);
+	if (error)
+		return error;
+	pci_save_state(dev->pdev);
 	return 0;
 }
 
@@ -114,11 +148,7 @@ static int ast_drm_thaw(struct drm_device *dev)
 {
 	ast_post_gpu(dev);
 
-	drm_mode_config_reset(dev);
-	drm_helper_resume_force_mode(dev);
-	drm_fb_helper_set_suspend_unlocked(dev->fb_helper, false);
-
-	return 0;
+	return drm_mode_config_helper_resume(dev);
 }
 
 static int ast_drm_resume(struct drm_device *dev)
@@ -131,8 +161,6 @@ static int ast_drm_resume(struct drm_device *dev)
 	ret = ast_drm_thaw(dev);
 	if (ret)
 		return ret;
-
-	drm_kms_helper_poll_enable(dev);
 	return 0;
 }
 
@@ -150,6 +178,7 @@ static int ast_pm_suspend(struct device *dev)
 	pci_set_power_state(pdev, PCI_D3hot);
 	return 0;
 }
+
 static int ast_pm_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -165,7 +194,6 @@ static int ast_pm_freeze(struct device *dev)
 	if (!ddev || !ddev->dev_private)
 		return -ENODEV;
 	return ast_drm_freeze(ddev);
-
 }
 
 static int ast_pm_thaw(struct device *dev)
@@ -203,10 +231,9 @@ static struct pci_driver ast_pci_driver = {
 DEFINE_DRM_GEM_FOPS(ast_fops);
 
 static struct drm_driver driver = {
-	.driver_features = DRIVER_MODESET | DRIVER_GEM,
-
-	.load = ast_driver_load,
-	.unload = ast_driver_unload,
+	.driver_features = DRIVER_ATOMIC |
+			   DRIVER_GEM |
+			   DRIVER_MODESET,
 
 	.fops = &ast_fops,
 	.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index ff161bd622f3..f5d8780776ae 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -121,6 +121,9 @@ struct ast_private {
 		unsigned int next_index;
 	} cursor;
 
+	struct drm_plane primary_plane;
+	struct drm_plane cursor_plane;
+
 	bool support_wide_screen;
 	enum {
 		ast_use_p2a,
@@ -137,8 +140,6 @@ struct ast_private {
 int ast_driver_load(struct drm_device *dev, unsigned long flags);
 void ast_driver_unload(struct drm_device *dev);
 
-struct ast_gem_object;
-
 #define AST_IO_AR_PORT_WRITE		(0x40)
 #define AST_IO_MISC_PORT_WRITE		(0x42)
 #define AST_IO_VGA_ENABLE_PORT		(0x43)
@@ -280,6 +281,17 @@ struct ast_vbios_mode_info {
 	const struct ast_vbios_enhtable *enh_table;
 };
 
+struct ast_crtc_state {
+	struct drm_crtc_state base;
+
+	/* Last known format of primary plane */
+	const struct drm_format_info *format;
+
+	struct ast_vbios_mode_info vbios_mode_info;
+};
+
+#define to_ast_crtc_state(state) container_of(state, struct ast_crtc_state, base)
+
 extern int ast_mode_init(struct drm_device *dev);
 extern void ast_mode_fini(struct drm_device *dev);
 
@@ -289,10 +301,6 @@ extern void ast_mode_fini(struct drm_device *dev);
 int ast_mm_init(struct ast_private *ast);
 void ast_mm_fini(struct ast_private *ast);
 
-int ast_gem_create(struct drm_device *dev,
-		   u32 size, bool iskernel,
-		   struct drm_gem_object **obj);
-
 /* ast post */
 void ast_enable_vga(struct drm_device *dev);
 void ast_enable_mmio(struct drm_device *dev);
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 21715d6a9b56..b79f484e9bd2 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -28,6 +28,7 @@
 
 #include <linux/pci.h>
 
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem.h>
@@ -387,8 +388,33 @@ static int ast_get_dram_info(struct drm_device *dev)
 	return 0;
 }
 
+enum drm_mode_status ast_mode_config_mode_valid(struct drm_device *dev,
+						const struct drm_display_mode *mode)
+{
+	static const unsigned long max_bpp = 4; /* DRM_FORMAT_XRGBA8888 */
+
+	struct ast_private *ast = dev->dev_private;
+	unsigned long fbsize, fbpages, max_fbpages;
+
+	/* To support double buffering, a framebuffer may not
+	 * consume more than half of the available VRAM.
+	 */
+	max_fbpages = (ast->vram_size / 2) >> PAGE_SHIFT;
+
+	fbsize = mode->hdisplay * mode->vdisplay * max_bpp;
+	fbpages = DIV_ROUND_UP(fbsize, PAGE_SIZE);
+
+	if (fbpages > max_fbpages)
+		return MODE_MEM;
+
+	return MODE_OK;
+}
+
 static const struct drm_mode_config_funcs ast_mode_funcs = {
-	.fb_create = drm_gem_fb_create
+	.fb_create = drm_gem_fb_create,
+	.mode_valid = ast_mode_config_mode_valid,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 static u32 ast_get_vram_info(struct drm_device *dev)
@@ -506,6 +532,8 @@ int ast_driver_load(struct drm_device *dev, unsigned long flags)
 	if (ret)
 		goto out_free;
 
+	drm_mode_config_reset(dev);
+
 	ret = drm_fbdev_generic_setup(dev, 32);
 	if (ret)
 		goto out_free;
@@ -535,27 +563,3 @@ void ast_driver_unload(struct drm_device *dev)
 	pci_iounmap(dev->pdev, ast->regs);
 	kfree(ast);
 }
-
-int ast_gem_create(struct drm_device *dev,
-		   u32 size, bool iskernel,
-		   struct drm_gem_object **obj)
-{
-	struct drm_gem_vram_object *gbo;
-	int ret;
-
-	*obj = NULL;
-
-	size = roundup(size, PAGE_SIZE);
-	if (size == 0)
-		return -EINVAL;
-
-	gbo = drm_gem_vram_create(dev, &dev->vram_mm->bdev, size, 0, false);
-	if (IS_ERR(gbo)) {
-		ret = PTR_ERR(gbo);
-		if (ret != -ERESTARTSYS)
-			DRM_ERROR("failed to allocate GEM object\n");
-		return ret;
-	}
-	*obj = &gbo->bo.base;
-	return 0;
-}
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index b13eaa2619ab..34608f0499eb 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -31,6 +31,9 @@
 #include <linux/export.h>
 #include <linux/pci.h>
 
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_atomic_state_helper.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fourcc.h>
@@ -43,11 +46,14 @@
 
 static struct ast_i2c_chan *ast_i2c_create(struct drm_device *dev);
 static void ast_i2c_destroy(struct ast_i2c_chan *i2c);
-static int ast_cursor_set(struct drm_crtc *crtc,
-			  struct drm_file *file_priv,
-			  uint32_t handle,
-			  uint32_t width,
-			  uint32_t height);
+static int ast_cursor_move(struct drm_crtc *crtc,
+			   int x, int y);
+
+
+static u32 copy_cursor_image(u8 *src, u8 *dst, int width, int height);
+static int ast_cursor_update(void *dst, void *src, unsigned int width,
+			     unsigned int height);
+static void ast_cursor_set_base(struct ast_private *ast, u64 address);
 static int ast_cursor_move(struct drm_crtc *crtc,
 			   int x, int y);
 
@@ -65,9 +71,8 @@ static inline void ast_load_palette_index(struct ast_private *ast,
 	ast_io_read8(ast, AST_IO_SEQ_PORT);
 }
 
-static void ast_crtc_load_lut(struct drm_crtc *crtc)
+static void ast_crtc_load_lut(struct ast_private *ast, struct drm_crtc *crtc)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
 	u16 *r, *g, *b;
 	int i;
 
@@ -82,36 +87,32 @@ static void ast_crtc_load_lut(struct drm_crtc *crtc)
 		ast_load_palette_index(ast, i, *r++ >> 8, *g++ >> 8, *b++ >> 8);
 }
 
-static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mode *mode,
+static bool ast_get_vbios_mode_info(const struct drm_format_info *format,
+				    const struct drm_display_mode *mode,
 				    struct drm_display_mode *adjusted_mode,
 				    struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
-	const struct drm_framebuffer *fb = crtc->primary->fb;
-	u32 refresh_rate_index = 0, mode_id, color_index, refresh_rate;
+	u32 refresh_rate_index = 0, refresh_rate;
 	const struct ast_vbios_enhtable *best = NULL;
 	u32 hborder, vborder;
 	bool check_sync;
 
-	switch (fb->format->cpp[0] * 8) {
+	switch (format->cpp[0] * 8) {
 	case 8:
 		vbios_mode->std_table = &vbios_stdtable[VGAModeIndex];
-		color_index = VGAModeIndex - 1;
 		break;
 	case 16:
 		vbios_mode->std_table = &vbios_stdtable[HiCModeIndex];
-		color_index = HiCModeIndex;
 		break;
 	case 24:
 	case 32:
 		vbios_mode->std_table = &vbios_stdtable[TrueCModeIndex];
-		color_index = TrueCModeIndex;
 		break;
 	default:
 		return false;
 	}
 
-	switch (crtc->mode.crtc_hdisplay) {
+	switch (mode->crtc_hdisplay) {
 	case 640:
 		vbios_mode->enh_table = &res_640x480[refresh_rate_index];
 		break;
@@ -122,7 +123,7 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		vbios_mode->enh_table = &res_1024x768[refresh_rate_index];
 		break;
 	case 1280:
-		if (crtc->mode.crtc_vdisplay == 800)
+		if (mode->crtc_vdisplay == 800)
 			vbios_mode->enh_table = &res_1280x800[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1280x1024[refresh_rate_index];
@@ -134,7 +135,7 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		vbios_mode->enh_table = &res_1440x900[refresh_rate_index];
 		break;
 	case 1600:
-		if (crtc->mode.crtc_vdisplay == 900)
+		if (mode->crtc_vdisplay == 900)
 			vbios_mode->enh_table = &res_1600x900[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1600x1200[refresh_rate_index];
@@ -143,7 +144,7 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		vbios_mode->enh_table = &res_1680x1050[refresh_rate_index];
 		break;
 	case 1920:
-		if (crtc->mode.crtc_vdisplay == 1080)
+		if (mode->crtc_vdisplay == 1080)
 			vbios_mode->enh_table = &res_1920x1080[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1920x1200[refresh_rate_index];
@@ -154,7 +155,8 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 
 	refresh_rate = drm_mode_vrefresh(mode);
 	check_sync = vbios_mode->enh_table->flags & WideScreenMode;
-	do {
+
+	while (1) {
 		const struct ast_vbios_enhtable *loop = vbios_mode->enh_table;
 
 		while (loop->refresh_rate != 0xff) {
@@ -178,7 +180,8 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		if (best || !check_sync)
 			break;
 		check_sync = 0;
-	} while (1);
+	}
+
 	if (best)
 		vbios_mode->enh_table = best;
 
@@ -203,38 +206,67 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 					 vbios_mode->enh_table->vfp +
 					 vbios_mode->enh_table->vsync);
 
-	refresh_rate_index = vbios_mode->enh_table->refresh_rate_index;
-	mode_id = vbios_mode->enh_table->mode_id;
+	return true;
+}
 
-	if (ast->chip == AST1180) {
-		/* TODO 1180 */
-	} else {
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8c, (u8)((color_index & 0xf) << 4));
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8d, refresh_rate_index & 0xff);
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8e, mode_id & 0xff);
-
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0x00);
-		if (vbios_mode->enh_table->flags & NewModeInfo) {
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x92,
-					  fb->format->cpp[0] * 8);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x93, adjusted_mode->clock / 1000);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x94, adjusted_mode->crtc_hdisplay);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x95, adjusted_mode->crtc_hdisplay >> 8);
-
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x96, adjusted_mode->crtc_vdisplay);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x97, adjusted_mode->crtc_vdisplay >> 8);
-		}
+static void ast_set_vbios_color_reg(struct ast_private *ast,
+				    const struct drm_format_info *format,
+				    const struct ast_vbios_mode_info *vbios_mode)
+{
+	u32 color_index;
+
+	switch (format->cpp[0]) {
+	case 1:
+		color_index = VGAModeIndex - 1;
+		break;
+	case 2:
+		color_index = HiCModeIndex;
+		break;
+	case 3:
+	case 4:
+		color_index = TrueCModeIndex;
+	default:
+		return;
 	}
 
-	return true;
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8c, (u8)((color_index & 0x0f) << 4));
+
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0x00);
+
+	if (vbios_mode->enh_table->flags & NewModeInfo) {
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x92, format->cpp[0] * 8);
+	}
+}
+
+static void ast_set_vbios_mode_reg(struct ast_private *ast,
+				   const struct drm_display_mode *adjusted_mode,
+				   const struct ast_vbios_mode_info *vbios_mode)
+{
+	u32 refresh_rate_index, mode_id;
+
+	refresh_rate_index = vbios_mode->enh_table->refresh_rate_index;
+	mode_id = vbios_mode->enh_table->mode_id;
 
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8d, refresh_rate_index & 0xff);
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8e, mode_id & 0xff);
 
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0x00);
+
+	if (vbios_mode->enh_table->flags & NewModeInfo) {
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x93, adjusted_mode->clock / 1000);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x94, adjusted_mode->crtc_hdisplay);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x95, adjusted_mode->crtc_hdisplay >> 8);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x96, adjusted_mode->crtc_vdisplay);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x97, adjusted_mode->crtc_vdisplay >> 8);
+	}
 }
-static void ast_set_std_reg(struct drm_crtc *crtc, struct drm_display_mode *mode,
+
+static void ast_set_std_reg(struct ast_private *ast,
+			    struct drm_display_mode *mode,
 			    struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
 	const struct ast_vbios_stdtable *stdtable;
 	u32 i;
 	u8 jreg;
@@ -244,18 +276,21 @@ static void ast_set_std_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 	jreg = stdtable->misc;
 	ast_io_write8(ast, AST_IO_MISC_PORT_WRITE, jreg);
 
-	/* Set SEQ */
+	/* Set SEQ; except Screen Disable field */
 	ast_set_index_reg(ast, AST_IO_SEQ_PORT, 0x00, 0x03);
-	for (i = 0; i < 4; i++) {
+	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x01, 0xdf, stdtable->seq[0]);
+	for (i = 1; i < 4; i++) {
 		jreg = stdtable->seq[i];
-		if (!i)
-			jreg |= 0x20;
 		ast_set_index_reg(ast, AST_IO_SEQ_PORT, (i + 1) , jreg);
 	}
 
-	/* Set CRTC */
+	/* Set CRTC; except base address and offset */
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x11, 0x7f, 0x00);
-	for (i = 0; i < 25; i++)
+	for (i = 0; i < 12; i++)
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, i, stdtable->crtc[i]);
+	for (i = 14; i < 19; i++)
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, i, stdtable->crtc[i]);
+	for (i = 20; i < 25; i++)
 		ast_set_index_reg(ast, AST_IO_CRTC_PORT, i, stdtable->crtc[i]);
 
 	/* set AR */
@@ -276,10 +311,10 @@ static void ast_set_std_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 		ast_set_index_reg(ast, AST_IO_GR_PORT, i, stdtable->gr[i]);
 }
 
-static void ast_set_crtc_reg(struct drm_crtc *crtc, struct drm_display_mode *mode,
+static void ast_set_crtc_reg(struct ast_private *ast,
+			     struct drm_display_mode *mode,
 			     struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
 	u8 jreg05 = 0, jreg07 = 0, jreg09 = 0, jregAC = 0, jregAD = 0, jregAE = 0;
 	u16 temp, precache = 0;
 
@@ -385,11 +420,9 @@ static void ast_set_crtc_reg(struct drm_crtc *crtc, struct drm_display_mode *mod
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x11, 0x7f, 0x80);
 }
 
-static void ast_set_offset_reg(struct drm_crtc *crtc)
+static void ast_set_offset_reg(struct ast_private *ast,
+			       struct drm_framebuffer *fb)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
-	const struct drm_framebuffer *fb = crtc->primary->fb;
-
 	u16 offset;
 
 	offset = fb->pitches[0] >> 3;
@@ -397,10 +430,10 @@ static void ast_set_offset_reg(struct drm_crtc *crtc)
 	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xb0, (offset >> 8) & 0x3f);
 }
 
-static void ast_set_dclk_reg(struct drm_device *dev, struct drm_display_mode *mode,
+static void ast_set_dclk_reg(struct ast_private *ast,
+			     struct drm_display_mode *mode,
 			     struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = dev->dev_private;
 	const struct ast_vbios_dclk_info *clk_info;
 
 	if (ast->chip == AST2500)
@@ -415,14 +448,12 @@ static void ast_set_dclk_reg(struct drm_device *dev, struct drm_display_mode *mo
 			       ((clk_info->param3 & 0x3) << 4));
 }
 
-static void ast_set_ext_reg(struct drm_crtc *crtc, struct drm_display_mode *mode,
-			     struct ast_vbios_mode_info *vbios_mode)
+static void ast_set_color_reg(struct ast_private *ast,
+			      const struct drm_format_info *format)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
-	const struct drm_framebuffer *fb = crtc->primary->fb;
 	u8 jregA0 = 0, jregA3 = 0, jregA8 = 0;
 
-	switch (fb->format->cpp[0] * 8) {
+	switch (format->cpp[0] * 8) {
 	case 8:
 		jregA0 = 0x70;
 		jregA3 = 0x01;
@@ -444,7 +475,10 @@ static void ast_set_ext_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa0, 0x8f, jregA0);
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xf0, jregA3);
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa8, 0xfd, jregA8);
+}
 
+static void ast_set_crtthd_reg(struct ast_private *ast)
+{
 	/* Set Threshold */
 	if (ast->chip == AST2300 || ast->chip == AST2400 ||
 	    ast->chip == AST2500) {
@@ -462,10 +496,10 @@ static void ast_set_ext_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 	}
 }
 
-static void ast_set_sync_reg(struct drm_device *dev, struct drm_display_mode *mode,
-		      struct ast_vbios_mode_info *vbios_mode)
+static void ast_set_sync_reg(struct ast_private *ast,
+			     struct drm_display_mode *mode,
+			     struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = dev->dev_private;
 	u8 jreg;
 
 	jreg  = ast_io_read8(ast, AST_IO_MISC_PORT_READ);
@@ -475,23 +509,9 @@ static void ast_set_sync_reg(struct drm_device *dev, struct drm_display_mode *mo
 	ast_io_write8(ast, AST_IO_MISC_PORT_WRITE, jreg);
 }
 
-static bool ast_set_dac_reg(struct drm_crtc *crtc, struct drm_display_mode *mode,
-		     struct ast_vbios_mode_info *vbios_mode)
-{
-	const struct drm_framebuffer *fb = crtc->primary->fb;
-
-	switch (fb->format->cpp[0] * 8) {
-	case 8:
-		break;
-	default:
-		return false;
-	}
-	return true;
-}
-
-static void ast_set_start_address_crt1(struct drm_crtc *crtc, unsigned offset)
+static void ast_set_start_address_crt1(struct ast_private *ast,
+				       unsigned offset)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
 	u32 addr;
 
 	addr = offset >> 2;
@@ -501,6 +521,247 @@ static void ast_set_start_address_crt1(struct drm_crtc *crtc, unsigned offset)
 
 }
 
+/*
+ * Primary plane
+ */
+
+static const uint32_t ast_primary_plane_formats[] = {
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_C8,
+};
+
+static int ast_primary_plane_helper_atomic_check(struct drm_plane *plane,
+						 struct drm_plane_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+	struct ast_crtc_state *ast_crtc_state;
+	int ret;
+
+	if (!state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc);
+
+	ret = drm_atomic_helper_check_plane_state(state, crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, true);
+	if (ret)
+		return ret;
+
+	if (!state->visible)
+		return 0;
+
+	ast_crtc_state = to_ast_crtc_state(crtc_state);
+
+	ast_crtc_state->format = state->fb->format;
+
+	return 0;
+}
+
+void ast_primary_plane_helper_atomic_update(struct drm_plane *plane,
+					    struct drm_plane_state *old_state)
+{
+	struct ast_private *ast = plane->dev->dev_private;
+	struct drm_plane_state *state = plane->state;
+	struct drm_gem_vram_object *gbo;
+	s64 gpu_addr;
+
+	gbo = drm_gem_vram_of_gem(state->fb->obj[0]);
+	gpu_addr = drm_gem_vram_offset(gbo);
+	if (WARN_ON_ONCE(gpu_addr < 0))
+		return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */
+
+	ast_set_offset_reg(ast, state->fb);
+	ast_set_start_address_crt1(ast, (u32)gpu_addr);
+
+	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0x00);
+}
+
+static void
+ast_primary_plane_helper_atomic_disable(struct drm_plane *plane,
+					struct drm_plane_state *old_state)
+{
+	struct ast_private *ast = plane->dev->dev_private;
+
+	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0x20);
+}
+
+static const struct drm_plane_helper_funcs ast_primary_plane_helper_funcs = {
+	.prepare_fb = drm_gem_vram_plane_helper_prepare_fb,
+	.cleanup_fb = drm_gem_vram_plane_helper_cleanup_fb,
+	.atomic_check = ast_primary_plane_helper_atomic_check,
+	.atomic_update = ast_primary_plane_helper_atomic_update,
+	.atomic_disable = ast_primary_plane_helper_atomic_disable,
+};
+
+static const struct drm_plane_funcs ast_primary_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = drm_plane_cleanup,
+	.reset = drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+};
+
+/*
+ * Cursor plane
+ */
+
+static const uint32_t ast_cursor_plane_formats[] = {
+	DRM_FORMAT_ARGB8888,
+};
+
+static int
+ast_cursor_plane_helper_prepare_fb(struct drm_plane *plane,
+				   struct drm_plane_state *new_state)
+{
+	struct drm_framebuffer *fb = new_state->fb;
+	struct drm_crtc *crtc = new_state->crtc;
+	struct drm_gem_vram_object *gbo;
+	struct ast_private *ast;
+	int ret;
+	void *src, *dst;
+
+	if (!crtc || !fb)
+		return 0;
+
+	if (WARN_ON_ONCE(fb->width > AST_MAX_HWC_WIDTH) ||
+	    WARN_ON_ONCE(fb->height > AST_MAX_HWC_HEIGHT))
+		return -EINVAL; /* BUG: didn't test in atomic_check() */
+
+	ast = crtc->dev->dev_private;
+
+	gbo = drm_gem_vram_of_gem(fb->obj[0]);
+	src = drm_gem_vram_vmap(gbo);
+	if (IS_ERR(src)) {
+		ret = PTR_ERR(src);
+		goto err_drm_gem_vram_unpin;
+	}
+
+	dst = drm_gem_vram_vmap(ast->cursor.gbo[ast->cursor.next_index]);
+	if (IS_ERR(dst)) {
+		ret = PTR_ERR(dst);
+		goto err_drm_gem_vram_vunmap_src;
+	}
+
+	ret = ast_cursor_update(dst, src, fb->width, fb->height);
+	if (ret)
+		goto err_drm_gem_vram_vunmap_dst;
+
+	/* Always unmap buffers here. Destination buffers are
+	 * perma-pinned while the driver is active. We're only
+	 * changing ref-counters here.
+	 */
+	drm_gem_vram_vunmap(ast->cursor.gbo[ast->cursor.next_index], dst);
+	drm_gem_vram_vunmap(gbo, src);
+
+	return 0;
+
+err_drm_gem_vram_vunmap_dst:
+	drm_gem_vram_vunmap(ast->cursor.gbo[ast->cursor.next_index], dst);
+err_drm_gem_vram_vunmap_src:
+	drm_gem_vram_vunmap(gbo, src);
+err_drm_gem_vram_unpin:
+	drm_gem_vram_unpin(gbo);
+	return ret;
+}
+
+static int ast_cursor_plane_helper_atomic_check(struct drm_plane *plane,
+						struct drm_plane_state *state)
+{
+	struct drm_framebuffer *fb = state->fb;
+	struct drm_crtc_state *crtc_state;
+	int ret;
+
+	if (!state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc);
+
+	ret = drm_atomic_helper_check_plane_state(state, crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  true, true);
+	if (ret)
+		return ret;
+
+	if (!state->visible)
+		return 0;
+
+	if (fb->width > AST_MAX_HWC_WIDTH || fb->height > AST_MAX_HWC_HEIGHT)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void
+ast_cursor_plane_helper_atomic_update(struct drm_plane *plane,
+				      struct drm_plane_state *old_state)
+{
+	struct drm_plane_state *state = plane->state;
+	struct drm_crtc *crtc = state->crtc;
+	struct drm_framebuffer *fb = state->fb;
+	struct ast_private *ast = plane->dev->dev_private;
+	struct ast_crtc *ast_crtc = to_ast_crtc(crtc);
+	struct drm_gem_vram_object *gbo;
+	s64 off;
+	u8 jreg;
+
+	ast_crtc->offset_x = AST_MAX_HWC_WIDTH - fb->width;
+	ast_crtc->offset_y = AST_MAX_HWC_WIDTH - fb->height;
+
+	if (state->fb != old_state->fb) {
+		/* A new cursor image was installed. */
+		gbo = ast->cursor.gbo[ast->cursor.next_index];
+		off = drm_gem_vram_offset(gbo);
+		if (WARN_ON_ONCE(off < 0))
+			return; /* Bug: we didn't pin cursor HW BO to VRAM. */
+		ast_cursor_set_base(ast, off);
+
+		++ast->cursor.next_index;
+		ast->cursor.next_index %= ARRAY_SIZE(ast->cursor.gbo);
+	}
+
+	ast_cursor_move(crtc, state->crtc_x, state->crtc_y);
+
+	jreg = 0x2;
+	/* enable ARGB cursor */
+	jreg |= 1;
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xcb, 0xfc, jreg);
+}
+
+static void
+ast_cursor_plane_helper_atomic_disable(struct drm_plane *plane,
+				       struct drm_plane_state *old_state)
+{
+	struct ast_private *ast = plane->dev->dev_private;
+
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xcb, 0xfc, 0x00);
+}
+
+static const struct drm_plane_helper_funcs ast_cursor_plane_helper_funcs = {
+	.prepare_fb = ast_cursor_plane_helper_prepare_fb,
+	.cleanup_fb = NULL, /* not required for cursor plane */
+	.atomic_check = ast_cursor_plane_helper_atomic_check,
+	.atomic_update = ast_cursor_plane_helper_atomic_update,
+	.atomic_disable = ast_cursor_plane_helper_atomic_disable,
+};
+
+static const struct drm_plane_funcs ast_cursor_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = drm_plane_cleanup,
+	.reset = drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+};
+
+/*
+ * CRTC
+ */
+
 static void ast_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct ast_private *ast = crtc->dev->dev_private;
@@ -508,179 +769,196 @@ static void ast_crtc_dpms(struct drm_crtc *crtc, int mode)
 	if (ast->chip == AST1180)
 		return;
 
+	/* TODO: Maybe control display signal generation with
+	 *       Sync Enable (bit CR17.7).
+	 */
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
-		ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0);
 		if (ast->tx_chip_type == AST_TX_DP501)
 			ast_set_dp501_video_output(crtc->dev, 1);
-		ast_crtc_load_lut(crtc);
+		ast_crtc_load_lut(ast, crtc);
 		break;
 	case DRM_MODE_DPMS_OFF:
 		if (ast->tx_chip_type == AST_TX_DP501)
 			ast_set_dp501_video_output(crtc->dev, 0);
-		ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0x20);
 		break;
 	}
 }
 
-static int ast_crtc_do_set_base(struct drm_crtc *crtc,
-				struct drm_framebuffer *fb,
-				int x, int y, int atomic)
+static int ast_crtc_helper_atomic_check(struct drm_crtc *crtc,
+					struct drm_crtc_state *state)
 {
-	struct drm_gem_vram_object *gbo;
-	int ret;
-	s64 gpu_addr;
+	struct ast_private *ast = crtc->dev->dev_private;
+	struct ast_crtc_state *ast_state;
+	const struct drm_format_info *format;
+	bool succ;
 
-	if (!atomic && fb) {
-		gbo = drm_gem_vram_of_gem(fb->obj[0]);
-		drm_gem_vram_unpin(gbo);
+	if (ast->chip == AST1180) {
+		DRM_ERROR("AST 1180 modesetting not supported\n");
+		return -EINVAL;
 	}
 
-	gbo = drm_gem_vram_of_gem(crtc->primary->fb->obj[0]);
+	ast_state = to_ast_crtc_state(state);
 
-	ret = drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM);
-	if (ret)
-		return ret;
-	gpu_addr = drm_gem_vram_offset(gbo);
-	if (gpu_addr < 0) {
-		ret = (int)gpu_addr;
-		goto err_drm_gem_vram_unpin;
-	}
+	format = ast_state->format;
+	if (!format)
+		return 0;
 
-	ast_set_offset_reg(crtc);
-	ast_set_start_address_crt1(crtc, (u32)gpu_addr);
+	succ = ast_get_vbios_mode_info(format, &state->mode,
+				       &state->adjusted_mode,
+				       &ast_state->vbios_mode_info);
+	if (!succ)
+		return -EINVAL;
 
 	return 0;
-
-err_drm_gem_vram_unpin:
-	drm_gem_vram_unpin(gbo);
-	return ret;
 }
 
-static int ast_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
-			     struct drm_framebuffer *old_fb)
+static void ast_crtc_helper_atomic_begin(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
 {
-	return ast_crtc_do_set_base(crtc, old_fb, x, y, 0);
+	struct ast_private *ast = crtc->dev->dev_private;
+
+	ast_open_key(ast);
 }
 
-static int ast_crtc_mode_set(struct drm_crtc *crtc,
-			     struct drm_display_mode *mode,
-			     struct drm_display_mode *adjusted_mode,
-			     int x, int y,
-			     struct drm_framebuffer *old_fb)
+static void ast_crtc_helper_atomic_flush(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct ast_private *ast = crtc->dev->dev_private;
-	struct ast_vbios_mode_info vbios_mode;
-	bool ret;
-	if (ast->chip == AST1180) {
-		DRM_ERROR("AST 1180 modesetting not supported\n");
-		return -EINVAL;
-	}
+	struct ast_private *ast = dev->dev_private;
+	struct ast_crtc_state *ast_state;
+	const struct drm_format_info *format;
+	struct ast_vbios_mode_info *vbios_mode_info;
+	struct drm_display_mode *adjusted_mode;
 
-	ret = ast_get_vbios_mode_info(crtc, mode, adjusted_mode, &vbios_mode);
-	if (ret == false)
-		return -EINVAL;
-	ast_open_key(ast);
+	crtc->state->no_vblank = true;
 
-	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06);
+	ast_state = to_ast_crtc_state(crtc->state);
 
-	ast_set_std_reg(crtc, adjusted_mode, &vbios_mode);
-	ast_set_crtc_reg(crtc, adjusted_mode, &vbios_mode);
-	ast_set_offset_reg(crtc);
-	ast_set_dclk_reg(dev, adjusted_mode, &vbios_mode);
-	ast_set_ext_reg(crtc, adjusted_mode, &vbios_mode);
-	ast_set_sync_reg(dev, adjusted_mode, &vbios_mode);
-	ast_set_dac_reg(crtc, adjusted_mode, &vbios_mode);
+	format = ast_state->format;
+	if (!format)
+		return;
 
-	ast_crtc_mode_set_base(crtc, x, y, old_fb);
+	vbios_mode_info = &ast_state->vbios_mode_info;
 
-	return 0;
-}
+	ast_set_color_reg(ast, format);
+	ast_set_vbios_color_reg(ast, format, vbios_mode_info);
 
-static void ast_crtc_disable(struct drm_crtc *crtc)
-{
-	DRM_DEBUG_KMS("\n");
-	ast_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
-	if (crtc->primary->fb) {
-		struct drm_framebuffer *fb = crtc->primary->fb;
-		struct drm_gem_vram_object *gbo =
-			drm_gem_vram_of_gem(fb->obj[0]);
+	if (!crtc->state->mode_changed)
+		return;
 
-		drm_gem_vram_unpin(gbo);
-	}
-	crtc->primary->fb = NULL;
+	adjusted_mode = &crtc->state->adjusted_mode;
+
+	ast_set_vbios_mode_reg(ast, adjusted_mode, vbios_mode_info);
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06);
+	ast_set_std_reg(ast, adjusted_mode, vbios_mode_info);
+	ast_set_crtc_reg(ast, adjusted_mode, vbios_mode_info);
+	ast_set_dclk_reg(ast, adjusted_mode, vbios_mode_info);
+	ast_set_crtthd_reg(ast);
+	ast_set_sync_reg(ast, adjusted_mode, vbios_mode_info);
 }
 
-static void ast_crtc_prepare(struct drm_crtc *crtc)
+static void
+ast_crtc_helper_atomic_enable(struct drm_crtc *crtc,
+			      struct drm_crtc_state *old_crtc_state)
 {
-
+	ast_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
 }
 
-static void ast_crtc_commit(struct drm_crtc *crtc)
+static void
+ast_crtc_helper_atomic_disable(struct drm_crtc *crtc,
+			       struct drm_crtc_state *old_crtc_state)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
-	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0);
-	ast_crtc_load_lut(crtc);
+	ast_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 }
 
-
 static const struct drm_crtc_helper_funcs ast_crtc_helper_funcs = {
-	.dpms = ast_crtc_dpms,
-	.mode_set = ast_crtc_mode_set,
-	.mode_set_base = ast_crtc_mode_set_base,
-	.disable = ast_crtc_disable,
-	.prepare = ast_crtc_prepare,
-	.commit = ast_crtc_commit,
-
+	.atomic_check = ast_crtc_helper_atomic_check,
+	.atomic_begin = ast_crtc_helper_atomic_begin,
+	.atomic_flush = ast_crtc_helper_atomic_flush,
+	.atomic_enable = ast_crtc_helper_atomic_enable,
+	.atomic_disable = ast_crtc_helper_atomic_disable,
 };
 
-static void ast_crtc_reset(struct drm_crtc *crtc)
+static void ast_crtc_destroy(struct drm_crtc *crtc)
 {
-
+	drm_crtc_cleanup(crtc);
+	kfree(crtc);
 }
 
-static int ast_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-			      u16 *blue, uint32_t size,
-			      struct drm_modeset_acquire_ctx *ctx)
+static struct drm_crtc_state *
+ast_crtc_atomic_duplicate_state(struct drm_crtc *crtc)
 {
-	ast_crtc_load_lut(crtc);
+	struct ast_crtc_state *new_ast_state, *ast_state;
 
-	return 0;
-}
+	if (WARN_ON(!crtc->state))
+		return NULL;
 
+	new_ast_state = kmalloc(sizeof(*new_ast_state), GFP_KERNEL);
+	if (!new_ast_state)
+		return NULL;
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &new_ast_state->base);
 
-static void ast_crtc_destroy(struct drm_crtc *crtc)
+	ast_state = to_ast_crtc_state(crtc->state);
+
+	new_ast_state->format = ast_state->format;
+	memcpy(&new_ast_state->vbios_mode_info, &ast_state->vbios_mode_info,
+	       sizeof(new_ast_state->vbios_mode_info));
+
+	return &new_ast_state->base;
+}
+
+static void ast_crtc_atomic_destroy_state(struct drm_crtc *crtc,
+					  struct drm_crtc_state *state)
 {
-	drm_crtc_cleanup(crtc);
-	kfree(crtc);
+	struct ast_crtc_state *ast_state = to_ast_crtc_state(state);
+
+	__drm_atomic_helper_crtc_destroy_state(&ast_state->base);
+	kfree(ast_state);
 }
 
 static const struct drm_crtc_funcs ast_crtc_funcs = {
-	.cursor_set = ast_cursor_set,
-	.cursor_move = ast_cursor_move,
-	.reset = ast_crtc_reset,
+	.reset = drm_atomic_helper_crtc_reset,
 	.set_config = drm_crtc_helper_set_config,
-	.gamma_set = ast_crtc_gamma_set,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 	.destroy = ast_crtc_destroy,
+	.set_config = drm_atomic_helper_set_config,
+	.page_flip = drm_atomic_helper_page_flip,
+	.atomic_duplicate_state = ast_crtc_atomic_duplicate_state,
+	.atomic_destroy_state = ast_crtc_atomic_destroy_state,
 };
 
 static int ast_crtc_init(struct drm_device *dev)
 {
+	struct ast_private *ast = dev->dev_private;
 	struct ast_crtc *crtc;
+	int ret;
 
 	crtc = kzalloc(sizeof(struct ast_crtc), GFP_KERNEL);
 	if (!crtc)
 		return -ENOMEM;
 
-	drm_crtc_init(dev, &crtc->base, &ast_crtc_funcs);
+	ret = drm_crtc_init_with_planes(dev, &crtc->base, &ast->primary_plane,
+					&ast->cursor_plane, &ast_crtc_funcs,
+					NULL);
+	if (ret)
+		goto err_kfree;
+
 	drm_mode_crtc_set_gamma_size(&crtc->base, 256);
 	drm_crtc_helper_add(&crtc->base, &ast_crtc_helper_funcs);
 	return 0;
+
+err_kfree:
+	kfree(crtc);
+	return ret;
 }
 
+/*
+ * Encoder
+ */
+
 static void ast_encoder_destroy(struct drm_encoder *encoder)
 {
 	drm_encoder_cleanup(encoder);
@@ -691,35 +969,6 @@ static const struct drm_encoder_funcs ast_enc_funcs = {
 	.destroy = ast_encoder_destroy,
 };
 
-static void ast_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-
-}
-
-static void ast_encoder_mode_set(struct drm_encoder *encoder,
-			       struct drm_display_mode *mode,
-			       struct drm_display_mode *adjusted_mode)
-{
-}
-
-static void ast_encoder_prepare(struct drm_encoder *encoder)
-{
-
-}
-
-static void ast_encoder_commit(struct drm_encoder *encoder)
-{
-
-}
-
-
-static const struct drm_encoder_helper_funcs ast_enc_helper_funcs = {
-	.dpms = ast_encoder_dpms,
-	.prepare = ast_encoder_prepare,
-	.commit = ast_encoder_commit,
-	.mode_set = ast_encoder_mode_set,
-};
-
 static int ast_encoder_init(struct drm_device *dev)
 {
 	struct ast_encoder *ast_encoder;
@@ -730,12 +979,15 @@ static int ast_encoder_init(struct drm_device *dev)
 
 	drm_encoder_init(dev, &ast_encoder->base, &ast_enc_funcs,
 			 DRM_MODE_ENCODER_DAC, NULL);
-	drm_encoder_helper_add(&ast_encoder->base, &ast_enc_helper_funcs);
 
 	ast_encoder->base.possible_crtcs = 1;
 	return 0;
 }
 
+/*
+ * Connector
+ */
+
 static int ast_get_modes(struct drm_connector *connector)
 {
 	struct ast_connector *ast_connector = to_ast_connector(connector);
@@ -834,14 +1086,16 @@ static void ast_connector_destroy(struct drm_connector *connector)
 }
 
 static const struct drm_connector_helper_funcs ast_connector_helper_funcs = {
-	.mode_valid = ast_mode_valid,
 	.get_modes = ast_get_modes,
+	.mode_valid = ast_mode_valid,
 };
 
 static const struct drm_connector_funcs ast_connector_funcs = {
-	.dpms = drm_helper_connector_dpms,
+	.reset = drm_atomic_helper_connector_reset,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = ast_connector_destroy,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
 static int ast_connector_init(struct drm_device *dev)
@@ -890,8 +1144,7 @@ static int ast_cursor_init(struct drm_device *dev)
 	size = roundup(AST_HWC_SIZE + AST_HWC_SIGNATURE_SIZE, PAGE_SIZE);
 
 	for (i = 0; i < ARRAY_SIZE(ast->cursor.gbo); ++i) {
-		gbo = drm_gem_vram_create(dev, &dev->vram_mm->bdev,
-					  size, 0, false);
+		gbo = drm_gem_vram_create(dev, size, 0);
 		if (IS_ERR(gbo)) {
 			ret = PTR_ERR(gbo);
 			goto err_drm_gem_vram_put;
@@ -934,10 +1187,39 @@ static void ast_cursor_fini(struct drm_device *dev)
 
 int ast_mode_init(struct drm_device *dev)
 {
+	struct ast_private *ast = dev->dev_private;
+	int ret;
+
+	memset(&ast->primary_plane, 0, sizeof(ast->primary_plane));
+	ret = drm_universal_plane_init(dev, &ast->primary_plane, 0x01,
+				       &ast_primary_plane_funcs,
+				       ast_primary_plane_formats,
+				       ARRAY_SIZE(ast_primary_plane_formats),
+				       NULL, DRM_PLANE_TYPE_PRIMARY, NULL);
+	if (ret) {
+		DRM_ERROR("ast: drm_universal_plane_init() failed: %d\n", ret);
+		return ret;
+	}
+	drm_plane_helper_add(&ast->primary_plane,
+			     &ast_primary_plane_helper_funcs);
+
+	ret = drm_universal_plane_init(dev, &ast->cursor_plane, 0x01,
+				       &ast_cursor_plane_funcs,
+				       ast_cursor_plane_formats,
+				       ARRAY_SIZE(ast_cursor_plane_formats),
+				       NULL, DRM_PLANE_TYPE_CURSOR, NULL);
+	if (ret) {
+		DRM_ERROR("drm_universal_plane_failed(): %d\n", ret);
+		return ret;
+	}
+	drm_plane_helper_add(&ast->cursor_plane,
+			     &ast_cursor_plane_helper_funcs);
+
 	ast_cursor_init(dev);
 	ast_crtc_init(dev);
 	ast_encoder_init(dev);
 	ast_connector_init(dev);
+
 	return 0;
 }
 
@@ -1153,106 +1435,6 @@ static void ast_cursor_set_base(struct ast_private *ast, u64 address)
 	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xca, addr2);
 }
 
-static int ast_show_cursor(struct drm_crtc *crtc, void *src,
-			   unsigned int width, unsigned int height)
-{
-	struct ast_private *ast = crtc->dev->dev_private;
-	struct ast_crtc *ast_crtc = to_ast_crtc(crtc);
-	struct drm_gem_vram_object *gbo;
-	void *dst;
-	s64 off;
-	int ret;
-	u8 jreg;
-
-	gbo = ast->cursor.gbo[ast->cursor.next_index];
-	dst = drm_gem_vram_vmap(gbo);
-	if (IS_ERR(dst))
-		return PTR_ERR(dst);
-	off = drm_gem_vram_offset(gbo);
-	if (off < 0) {
-		ret = (int)off;
-		goto err_drm_gem_vram_vunmap;
-	}
-
-	ret = ast_cursor_update(dst, src, width, height);
-	if (ret)
-		goto err_drm_gem_vram_vunmap;
-	ast_cursor_set_base(ast, off);
-
-	ast_crtc->offset_x = AST_MAX_HWC_WIDTH - width;
-	ast_crtc->offset_y = AST_MAX_HWC_WIDTH - height;
-
-	jreg = 0x2;
-	/* enable ARGB cursor */
-	jreg |= 1;
-	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xcb, 0xfc, jreg);
-
-	++ast->cursor.next_index;
-	ast->cursor.next_index %= ARRAY_SIZE(ast->cursor.gbo);
-
-	drm_gem_vram_vunmap(gbo, dst);
-
-	return 0;
-
-err_drm_gem_vram_vunmap:
-	drm_gem_vram_vunmap(gbo, dst);
-	return ret;
-}
-
-static void ast_hide_cursor(struct drm_crtc *crtc)
-{
-	struct ast_private *ast = crtc->dev->dev_private;
-
-	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xcb, 0xfc, 0x00);
-}
-
-static int ast_cursor_set(struct drm_crtc *crtc,
-			  struct drm_file *file_priv,
-			  uint32_t handle,
-			  uint32_t width,
-			  uint32_t height)
-{
-	struct drm_gem_object *obj;
-	struct drm_gem_vram_object *gbo;
-	u8 *src;
-	int ret;
-
-	if (!handle) {
-		ast_hide_cursor(crtc);
-		return 0;
-	}
-
-	if (width > AST_MAX_HWC_WIDTH || height > AST_MAX_HWC_HEIGHT)
-		return -EINVAL;
-
-	obj = drm_gem_object_lookup(file_priv, handle);
-	if (!obj) {
-		DRM_ERROR("Cannot find cursor object %x for crtc\n", handle);
-		return -ENOENT;
-	}
-	gbo = drm_gem_vram_of_gem(obj);
-	src = drm_gem_vram_vmap(gbo);
-	if (IS_ERR(src)) {
-		ret = PTR_ERR(src);
-		goto err_drm_gem_object_put_unlocked;
-	}
-
-	ret = ast_show_cursor(crtc, src, width, height);
-	if (ret)
-		goto err_drm_gem_vram_vunmap;
-
-	drm_gem_vram_vunmap(gbo, src);
-	drm_gem_object_put_unlocked(obj);
-
-	return 0;
-
-err_drm_gem_vram_vunmap:
-	drm_gem_vram_vunmap(gbo, src);
-err_drm_gem_object_put_unlocked:
-	drm_gem_object_put_unlocked(obj);
-	return ret;
-}
-
 static int ast_cursor_move(struct drm_crtc *crtc,
 			   int x, int y)
 {
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index f2e73e6d46b8..10985134ce0b 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -73,7 +73,11 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 	unsigned long prate;
 	unsigned int mask = ATMEL_HLCDC_CLKDIV_MASK | ATMEL_HLCDC_CLKPOL;
 	unsigned int cfg = 0;
-	int div;
+	int div, ret;
+
+	ret = clk_prepare_enable(crtc->dc->hlcdc->sys_clk);
+	if (ret)
+		return;
 
 	vm.vfront_porch = adj->crtc_vsync_start - adj->crtc_vdisplay;
 	vm.vback_porch = adj->crtc_vtotal - adj->crtc_vsync_end;
@@ -95,14 +99,14 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 		     (adj->crtc_hdisplay - 1) |
 		     ((adj->crtc_vdisplay - 1) << 16));
 
+	prate = clk_get_rate(crtc->dc->hlcdc->sys_clk);
+	mode_rate = adj->crtc_clock * 1000;
 	if (!crtc->dc->desc->fixed_clksrc) {
+		prate *= 2;
 		cfg |= ATMEL_HLCDC_CLKSEL;
 		mask |= ATMEL_HLCDC_CLKSEL;
 	}
 
-	prate = 2 * clk_get_rate(crtc->dc->hlcdc->sys_clk);
-	mode_rate = adj->crtc_clock * 1000;
-
 	div = DIV_ROUND_UP(prate, mode_rate);
 	if (div < 2) {
 		div = 2;
@@ -117,8 +121,8 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 		int div_low = prate / mode_rate;
 
 		if (div_low >= 2 &&
-		    ((prate / div_low - mode_rate) <
-		     10 * (mode_rate - prate / div)))
+		    (10 * (prate / div_low - mode_rate) <
+		     (mode_rate - prate / div)))
 			/*
 			 * At least 10 times better when using a higher
 			 * frequency than requested, instead of a lower.
@@ -147,6 +151,8 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 			   ATMEL_HLCDC_VSPSU | ATMEL_HLCDC_VSPHO |
 			   ATMEL_HLCDC_GUARDTIME_MASK | ATMEL_HLCDC_MODE_MASK,
 			   cfg);
+
+	clk_disable_unprepare(crtc->dc->hlcdc->sys_clk);
 }
 
 static enum drm_mode_status
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index 92640298ad41..112aa5066cee 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -557,12 +557,6 @@ static irqreturn_t atmel_hlcdc_dc_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static struct drm_framebuffer *atmel_hlcdc_fb_create(struct drm_device *dev,
-		struct drm_file *file_priv, const struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	return drm_gem_fb_create(dev, file_priv, mode_cmd);
-}
-
 struct atmel_hlcdc_dc_commit {
 	struct work_struct work;
 	struct drm_device *dev;
@@ -657,7 +651,7 @@ error:
 }
 
 static const struct drm_mode_config_funcs mode_config_funcs = {
-	.fb_create = atmel_hlcdc_fb_create,
+	.fb_create = drm_gem_fb_create,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = atmel_hlcdc_dc_atomic_commit,
 };
@@ -727,18 +721,10 @@ static int atmel_hlcdc_dc_load(struct drm_device *dev)
 	dc->hlcdc = dev_get_drvdata(dev->dev->parent);
 	dev->dev_private = dc;
 
-	if (dc->desc->fixed_clksrc) {
-		ret = clk_prepare_enable(dc->hlcdc->sys_clk);
-		if (ret) {
-			dev_err(dev->dev, "failed to enable sys_clk\n");
-			goto err_destroy_wq;
-		}
-	}
-
 	ret = clk_prepare_enable(dc->hlcdc->periph_clk);
 	if (ret) {
 		dev_err(dev->dev, "failed to enable periph_clk\n");
-		goto err_sys_clk_disable;
+		goto err_destroy_wq;
 	}
 
 	pm_runtime_enable(dev->dev);
@@ -774,9 +760,6 @@ static int atmel_hlcdc_dc_load(struct drm_device *dev)
 err_periph_clk_disable:
 	pm_runtime_disable(dev->dev);
 	clk_disable_unprepare(dc->hlcdc->periph_clk);
-err_sys_clk_disable:
-	if (dc->desc->fixed_clksrc)
-		clk_disable_unprepare(dc->hlcdc->sys_clk);
 
 err_destroy_wq:
 	destroy_workqueue(dc->wq);
@@ -801,8 +784,6 @@ static void atmel_hlcdc_dc_unload(struct drm_device *dev)
 
 	pm_runtime_disable(dev->dev);
 	clk_disable_unprepare(dc->hlcdc->periph_clk);
-	if (dc->desc->fixed_clksrc)
-		clk_disable_unprepare(dc->hlcdc->sys_clk);
 	destroy_workqueue(dc->wq);
 }
 
@@ -916,8 +897,6 @@ static int atmel_hlcdc_dc_drm_suspend(struct device *dev)
 	regmap_read(regmap, ATMEL_HLCDC_IMR, &dc->suspend.imr);
 	regmap_write(regmap, ATMEL_HLCDC_IDR, dc->suspend.imr);
 	clk_disable_unprepare(dc->hlcdc->periph_clk);
-	if (dc->desc->fixed_clksrc)
-		clk_disable_unprepare(dc->hlcdc->sys_clk);
 
 	return 0;
 }
@@ -927,8 +906,6 @@ static int atmel_hlcdc_dc_drm_resume(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct atmel_hlcdc_dc *dc = drm_dev->dev_private;
 
-	if (dc->desc->fixed_clksrc)
-		clk_prepare_enable(dc->hlcdc->sys_clk);
 	clk_prepare_enable(dc->hlcdc->periph_clk);
 	regmap_write(dc->hlcdc->regmap, ATMEL_HLCDC_IER, dc->suspend.imr);
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index 034f202dfe8f..40800ec5700a 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -604,7 +604,7 @@ static int atmel_hlcdc_plane_atomic_check(struct drm_plane *p,
 	int ret;
 	int i;
 
-	if (!state->base.crtc || !fb)
+	if (!state->base.crtc || WARN_ON(!fb))
 		return 0;
 
 	crtc_state = drm_atomic_get_existing_crtc_state(s->state, s->crtc);
diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c
index e567bdfa2ab8..b615b7dfdd9d 100644
--- a/drivers/gpu/drm/bochs/bochs_hw.c
+++ b/drivers/gpu/drm/bochs/bochs_hw.c
@@ -255,7 +255,7 @@ void bochs_hw_setformat(struct bochs_device *bochs,
 		DRM_ERROR("%s: Huh? Got framebuffer format 0x%x",
 			  __func__, format->format);
 		break;
-	};
+	}
 }
 
 void bochs_hw_setbase(struct bochs_device *bochs,
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index 34362976cd6f..0b9ca5862455 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -16,16 +16,6 @@ config DRM_PANEL_BRIDGE
 menu "Display Interface Bridges"
 	depends on DRM && DRM_BRIDGE
 
-config DRM_ANALOGIX_ANX78XX
-	tristate "Analogix ANX78XX bridge"
-	select DRM_KMS_HELPER
-	select REGMAP_I2C
-	---help---
-	  ANX78XX is an ultra-low power Full-HD SlimPort transmitter
-	  designed for portable devices. The ANX78XX transforms
-	  the HDMI output of an application processor to MyDP
-	  or DisplayPort.
-
 config DRM_CDNS_DSI
 	tristate "Cadence DPI/DSI bridge"
 	select DRM_KMS_HELPER
@@ -45,14 +35,14 @@ config DRM_DUMB_VGA_DAC
 	  Support for non-programmable RGB to VGA DAC bridges, such as ADI
 	  ADV7123, TI THS8134 and THS8135 or passive resistor ladder DACs.
 
-config DRM_LVDS_ENCODER
-	tristate "Transparent parallel to LVDS encoder support"
+config DRM_LVDS_CODEC
+	tristate "Transparent LVDS encoders and decoders support"
 	depends on OF
 	select DRM_KMS_HELPER
 	select DRM_PANEL_BRIDGE
 	help
-	  Support for transparent parallel to LVDS encoders that don't require
-	  any configuration.
+	  Support for transparent LVDS encoders and decoders that don't
+	  require any configuration.
 
 config DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW
 	tristate "MegaChips stdp4028-ge-b850v3-fw and stdp2690-ge-b850v3-fw"
@@ -60,10 +50,10 @@ config DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW
 	select DRM_KMS_HELPER
 	select DRM_PANEL
 	---help---
-          This is a driver for the display bridges of
-          GE B850v3 that convert dual channel LVDS
-          to DP++. This is used with the i.MX6 imx-ldb
-          driver. You are likely to say N here.
+	  This is a driver for the display bridges of
+	  GE B850v3 that convert dual channel LVDS
+	  to DP++. This is used with the i.MX6 imx-ldb
+	  driver. You are likely to say N here.
 
 config DRM_NXP_PTN3460
 	tristate "NXP PTN3460 DP/LVDS bridge"
diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile
index 4934fcf5a6f8..cd16ce830270 100644
--- a/drivers/gpu/drm/bridge/Makefile
+++ b/drivers/gpu/drm/bridge/Makefile
@@ -1,8 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_DRM_ANALOGIX_ANX78XX) += analogix-anx78xx.o
 obj-$(CONFIG_DRM_CDNS_DSI) += cdns-dsi.o
 obj-$(CONFIG_DRM_DUMB_VGA_DAC) += dumb-vga-dac.o
-obj-$(CONFIG_DRM_LVDS_ENCODER) += lvds-encoder.o
+obj-$(CONFIG_DRM_LVDS_CODEC) += lvds-codec.o
 obj-$(CONFIG_DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW) += megachips-stdpxxxx-ge-b850v3-fw.o
 obj-$(CONFIG_DRM_NXP_PTN3460) += nxp-ptn3460.o
 obj-$(CONFIG_DRM_PARADE_PS8622) += parade-ps8622.o
@@ -12,8 +11,9 @@ obj-$(CONFIG_DRM_SII9234) += sii9234.o
 obj-$(CONFIG_DRM_THINE_THC63LVD1024) += thc63lvd1024.o
 obj-$(CONFIG_DRM_TOSHIBA_TC358764) += tc358764.o
 obj-$(CONFIG_DRM_TOSHIBA_TC358767) += tc358767.o
-obj-$(CONFIG_DRM_ANALOGIX_DP) += analogix/
 obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/
 obj-$(CONFIG_DRM_TI_SN65DSI86) += ti-sn65dsi86.o
 obj-$(CONFIG_DRM_TI_TFP410) += ti-tfp410.o
+
+obj-y += analogix/
 obj-y += synopsys/
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.h b/drivers/gpu/drm/bridge/analogix-anx78xx.h
deleted file mode 100644
index 55d6c2109740..000000000000
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.h
+++ /dev/null
@@ -1,703 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright(c) 2016, Analogix Semiconductor. All rights reserved.
- */
-
-#ifndef __ANX78xx_H
-#define __ANX78xx_H
-
-/***************************************************************/
-/* Register definitions for RX_PO                              */
-/***************************************************************/
-
-/*
- * System Control and Status
- */
-
-/* Software Reset Register 1 */
-#define SP_SOFTWARE_RESET1_REG		0x11
-#define SP_VIDEO_RST			BIT(4)
-#define SP_HDCP_MAN_RST			BIT(2)
-#define SP_TMDS_RST			BIT(1)
-#define SP_SW_MAN_RST			BIT(0)
-
-/* System Status Register */
-#define SP_SYSTEM_STATUS_REG		0x14
-#define SP_TMDS_CLOCK_DET		BIT(1)
-#define SP_TMDS_DE_DET			BIT(0)
-
-/* HDMI Status Register */
-#define SP_HDMI_STATUS_REG		0x15
-#define SP_HDMI_AUD_LAYOUT		BIT(3)
-#define SP_HDMI_DET			BIT(0)
-#  define SP_DVI_MODE			0
-#  define SP_HDMI_MODE			1
-
-/* HDMI Mute Control Register */
-#define SP_HDMI_MUTE_CTRL_REG		0x16
-#define SP_AUD_MUTE			BIT(1)
-#define SP_VID_MUTE			BIT(0)
-
-/* System Power Down Register 1 */
-#define SP_SYSTEM_POWER_DOWN1_REG	0x18
-#define SP_PWDN_CTRL			BIT(0)
-
-/*
- * Audio and Video Auto Control
- */
-
-/* Auto Audio and Video Control register */
-#define SP_AUDVID_CTRL_REG		0x20
-#define SP_AVC_OE			BIT(7)
-#define SP_AAC_OE			BIT(6)
-#define SP_AVC_EN			BIT(1)
-#define SP_AAC_EN			BIT(0)
-
-/* Audio Exception Enable Registers */
-#define SP_AUD_EXCEPTION_ENABLE_BASE	(0x24 - 1)
-/* Bits for Audio Exception Enable Register 3 */
-#define SP_AEC_EN21			BIT(5)
-
-/*
- * Interrupt
- */
-
-/* Interrupt Status Register 1 */
-#define SP_INT_STATUS1_REG		0x31
-/* Bits for Interrupt Status Register 1 */
-#define SP_HDMI_DVI			BIT(7)
-#define SP_CKDT_CHG			BIT(6)
-#define SP_SCDT_CHG			BIT(5)
-#define SP_PCLK_CHG			BIT(4)
-#define SP_PLL_UNLOCK			BIT(3)
-#define SP_CABLE_PLUG_CHG		BIT(2)
-#define SP_SET_MUTE			BIT(1)
-#define SP_SW_INTR			BIT(0)
-/* Bits for Interrupt Status Register 2 */
-#define SP_HDCP_ERR			BIT(5)
-#define SP_AUDIO_SAMPLE_CHG		BIT(0)	/* undocumented */
-/* Bits for Interrupt Status Register 3 */
-#define SP_AUD_MODE_CHG			BIT(0)
-/* Bits for Interrupt Status Register 5 */
-#define SP_AUDIO_RCV			BIT(0)
-/* Bits for Interrupt Status Register 6 */
-#define SP_INT_STATUS6_REG		0x36
-#define SP_CTS_RCV			BIT(7)
-#define SP_NEW_AUD_PKT			BIT(4)
-#define SP_NEW_AVI_PKT			BIT(1)
-#define SP_NEW_CP_PKT			BIT(0)
-/* Bits for Interrupt Status Register 7 */
-#define SP_NO_VSI			BIT(7)
-#define SP_NEW_VS			BIT(4)
-
-/* Interrupt Mask 1 Status Registers */
-#define SP_INT_MASK1_REG		0x41
-
-/* HDMI US TIMER Control Register */
-#define SP_HDMI_US_TIMER_CTRL_REG	0x49
-#define SP_MS_TIMER_MARGIN_10_8_MASK	0x07
-
-/*
- * TMDS Control
- */
-
-/* TMDS Control Registers */
-#define SP_TMDS_CTRL_BASE		(0x50 - 1)
-/* Bits for TMDS Control Register 7 */
-#define SP_PD_RT			BIT(0)
-
-/*
- * Video Control
- */
-
-/* Video Status Register */
-#define SP_VIDEO_STATUS_REG		0x70
-#define SP_COLOR_DEPTH_MASK		0xf0
-#define SP_COLOR_DEPTH_SHIFT		4
-#  define SP_COLOR_DEPTH_MODE_LEGACY	0x00
-#  define SP_COLOR_DEPTH_MODE_24BIT	0x04
-#  define SP_COLOR_DEPTH_MODE_30BIT	0x05
-#  define SP_COLOR_DEPTH_MODE_36BIT	0x06
-#  define SP_COLOR_DEPTH_MODE_48BIT	0x07
-
-/* Video Data Range Control Register */
-#define SP_VID_DATA_RANGE_CTRL_REG	0x83
-#define SP_R2Y_INPUT_LIMIT		BIT(1)
-
-/* Pixel Clock High Resolution Counter Registers */
-#define SP_PCLK_HIGHRES_CNT_BASE	(0x8c - 1)
-
-/*
- * Audio Control
- */
-
-/* Number of Audio Channels Status Registers */
-#define SP_AUD_CH_STATUS_REG_NUM	6
-
-/* Audio IN S/PDIF Channel Status Registers */
-#define SP_AUD_SPDIF_CH_STATUS_BASE	0xc7
-
-/* Audio IN S/PDIF Channel Status Register 4 */
-#define SP_FS_FREQ_MASK			0x0f
-#  define SP_FS_FREQ_44100HZ		0x00
-#  define SP_FS_FREQ_48000HZ		0x02
-#  define SP_FS_FREQ_32000HZ		0x03
-#  define SP_FS_FREQ_88200HZ		0x08
-#  define SP_FS_FREQ_96000HZ		0x0a
-#  define SP_FS_FREQ_176400HZ		0x0c
-#  define SP_FS_FREQ_192000HZ		0x0e
-
-/*
- * Micellaneous Control Block
- */
-
-/* CHIP Control Register */
-#define SP_CHIP_CTRL_REG		0xe3
-#define SP_MAN_HDMI5V_DET		BIT(3)
-#define SP_PLLLOCK_CKDT_EN		BIT(2)
-#define SP_ANALOG_CKDT_EN		BIT(1)
-#define SP_DIGITAL_CKDT_EN		BIT(0)
-
-/* Packet Receiving Status Register */
-#define SP_PACKET_RECEIVING_STATUS_REG	0xf3
-#define SP_AVI_RCVD			BIT(5)
-#define SP_VSI_RCVD			BIT(1)
-
-/***************************************************************/
-/* Register definitions for RX_P1                              */
-/***************************************************************/
-
-/* HDCP BCAPS Shadow Register */
-#define SP_HDCP_BCAPS_SHADOW_REG	0x2a
-#define SP_BCAPS_REPEATER		BIT(5)
-
-/* HDCP Status Register */
-#define SP_RX_HDCP_STATUS_REG		0x3f
-#define SP_AUTH_EN			BIT(4)
-
-/*
- * InfoFrame and Control Packet Registers
- */
-
-/* AVI InfoFrame packet checksum */
-#define SP_AVI_INFOFRAME_CHECKSUM	0xa3
-
-/* AVI InfoFrame Registers */
-#define SP_AVI_INFOFRAME_DATA_BASE	0xa4
-
-#define SP_AVI_COLOR_F_MASK		0x60
-#define SP_AVI_COLOR_F_SHIFT		5
-
-/* Audio InfoFrame Registers */
-#define SP_AUD_INFOFRAME_DATA_BASE	0xc4
-#define SP_AUD_INFOFRAME_LAYOUT_MASK	0x0f
-
-/* MPEG/HDMI Vendor Specific InfoFrame Packet type code */
-#define SP_MPEG_VS_INFOFRAME_TYPE_REG	0xe0
-
-/* MPEG/HDMI Vendor Specific InfoFrame Packet length */
-#define SP_MPEG_VS_INFOFRAME_LEN_REG	0xe2
-
-/* MPEG/HDMI Vendor Specific InfoFrame Packet version number */
-#define SP_MPEG_VS_INFOFRAME_VER_REG	0xe1
-
-/* MPEG/HDMI Vendor Specific InfoFrame Packet content */
-#define SP_MPEG_VS_INFOFRAME_DATA_BASE	0xe4
-
-/* General Control Packet Register */
-#define SP_GENERAL_CTRL_PACKET_REG	0x9f
-#define SP_CLEAR_AVMUTE			BIT(4)
-#define SP_SET_AVMUTE			BIT(0)
-
-/***************************************************************/
-/* Register definitions for TX_P0                              */
-/***************************************************************/
-
-/* HDCP Status Register */
-#define SP_TX_HDCP_STATUS_REG		0x00
-#define SP_AUTH_FAIL			BIT(5)
-#define SP_AUTHEN_PASS			BIT(1)
-
-/* HDCP Control Register 0 */
-#define SP_HDCP_CTRL0_REG		0x01
-#define SP_RX_REPEATER			BIT(6)
-#define SP_RE_AUTH			BIT(5)
-#define SP_SW_AUTH_OK			BIT(4)
-#define SP_HARD_AUTH_EN			BIT(3)
-#define SP_HDCP_ENC_EN			BIT(2)
-#define SP_BKSV_SRM_PASS		BIT(1)
-#define SP_KSVLIST_VLD			BIT(0)
-/* HDCP Function Enabled */
-#define SP_HDCP_FUNCTION_ENABLED	(BIT(0) | BIT(1) | BIT(2) | BIT(3))
-
-/* HDCP Receiver BSTATUS Register 0 */
-#define	SP_HDCP_RX_BSTATUS0_REG		0x1b
-/* HDCP Receiver BSTATUS Register 1 */
-#define	SP_HDCP_RX_BSTATUS1_REG		0x1c
-
-/* HDCP Embedded "Blue Screen" Content Registers */
-#define SP_HDCP_VID0_BLUE_SCREEN_REG	0x2c
-#define SP_HDCP_VID1_BLUE_SCREEN_REG	0x2d
-#define SP_HDCP_VID2_BLUE_SCREEN_REG	0x2e
-
-/* HDCP Wait R0 Timing Register */
-#define SP_HDCP_WAIT_R0_TIME_REG	0x40
-
-/* HDCP Link Integrity Check Timer Register */
-#define SP_HDCP_LINK_CHECK_TIMER_REG	0x41
-
-/* HDCP Repeater Ready Wait Timer Register */
-#define SP_HDCP_RPTR_RDY_WAIT_TIME_REG	0x42
-
-/* HDCP Auto Timer Register */
-#define SP_HDCP_AUTO_TIMER_REG		0x51
-
-/* HDCP Key Status Register */
-#define SP_HDCP_KEY_STATUS_REG		0x5e
-
-/* HDCP Key Command Register */
-#define SP_HDCP_KEY_COMMAND_REG		0x5f
-#define SP_DISABLE_SYNC_HDCP		BIT(2)
-
-/* OTP Memory Key Protection Registers */
-#define SP_OTP_KEY_PROTECT1_REG		0x60
-#define SP_OTP_KEY_PROTECT2_REG		0x61
-#define SP_OTP_KEY_PROTECT3_REG		0x62
-#define SP_OTP_PSW1			0xa2
-#define SP_OTP_PSW2			0x7e
-#define SP_OTP_PSW3			0xc6
-
-/* DP System Control Registers */
-#define SP_DP_SYSTEM_CTRL_BASE		(0x80 - 1)
-/* Bits for DP System Control Register 2 */
-#define SP_CHA_STA			BIT(2)
-/* Bits for DP System Control Register 3 */
-#define SP_HPD_STATUS			BIT(6)
-#define SP_STRM_VALID			BIT(2)
-/* Bits for DP System Control Register 4 */
-#define SP_ENHANCED_MODE		BIT(3)
-
-/* DP Video Control Register */
-#define SP_DP_VIDEO_CTRL_REG		0x84
-#define SP_COLOR_F_MASK			0x06
-#define SP_COLOR_F_SHIFT		1
-#define SP_BPC_MASK			0xe0
-#define SP_BPC_SHIFT			5
-#  define SP_BPC_6BITS			0x00
-#  define SP_BPC_8BITS			0x01
-#  define SP_BPC_10BITS			0x02
-#  define SP_BPC_12BITS			0x03
-
-/* DP Audio Control Register */
-#define SP_DP_AUDIO_CTRL_REG		0x87
-#define SP_AUD_EN			BIT(0)
-
-/* 10us Pulse Generate Timer Registers */
-#define SP_I2C_GEN_10US_TIMER0_REG	0x88
-#define SP_I2C_GEN_10US_TIMER1_REG	0x89
-
-/* Packet Send Control Register */
-#define SP_PACKET_SEND_CTRL_REG		0x90
-#define SP_AUD_IF_UP			BIT(7)
-#define SP_AVI_IF_UD			BIT(6)
-#define SP_MPEG_IF_UD			BIT(5)
-#define SP_SPD_IF_UD			BIT(4)
-#define SP_AUD_IF_EN			BIT(3)
-#define SP_AVI_IF_EN			BIT(2)
-#define SP_MPEG_IF_EN			BIT(1)
-#define SP_SPD_IF_EN			BIT(0)
-
-/* DP HDCP Control Register */
-#define SP_DP_HDCP_CTRL_REG		0x92
-#define SP_AUTO_EN			BIT(7)
-#define SP_AUTO_START			BIT(5)
-#define SP_LINK_POLLING			BIT(1)
-
-/* DP Main Link Bandwidth Setting Register */
-#define SP_DP_MAIN_LINK_BW_SET_REG	0xa0
-#define SP_LINK_BW_SET_MASK		0x1f
-#define SP_INITIAL_SLIM_M_AUD_SEL	BIT(5)
-
-/* DP Training Pattern Set Register */
-#define SP_DP_TRAINING_PATTERN_SET_REG	0xa2
-
-/* DP Lane 0 Link Training Control Register */
-#define SP_DP_LANE0_LT_CTRL_REG		0xa3
-#define SP_TX_SW_SET_MASK		0x1b
-#define SP_MAX_PRE_REACH		BIT(5)
-#define SP_MAX_DRIVE_REACH		BIT(4)
-#define SP_PRE_EMP_LEVEL1		BIT(3)
-#define SP_DRVIE_CURRENT_LEVEL1		BIT(0)
-
-/* DP Link Training Control Register */
-#define SP_DP_LT_CTRL_REG		0xa8
-#define SP_LT_ERROR_TYPE_MASK		0x70
-#  define SP_LT_NO_ERROR		0x00
-#  define SP_LT_AUX_WRITE_ERROR		0x01
-#  define SP_LT_MAX_DRIVE_REACHED	0x02
-#  define SP_LT_WRONG_LANE_COUNT_SET	0x03
-#  define SP_LT_LOOP_SAME_5_TIME	0x04
-#  define SP_LT_CR_FAIL_IN_EQ		0x05
-#  define SP_LT_EQ_LOOP_5_TIME		0x06
-#define SP_LT_EN			BIT(0)
-
-/* DP CEP Training Control Registers */
-#define SP_DP_CEP_TRAINING_CTRL0_REG	0xa9
-#define SP_DP_CEP_TRAINING_CTRL1_REG	0xaa
-
-/* DP Debug Register 1 */
-#define SP_DP_DEBUG1_REG		0xb0
-#define SP_DEBUG_PLL_LOCK		BIT(4)
-#define SP_POLLING_EN			BIT(1)
-
-/* DP Polling Control Register */
-#define SP_DP_POLLING_CTRL_REG		0xb4
-#define SP_AUTO_POLLING_DISABLE		BIT(0)
-
-/* DP Link Debug Control Register */
-#define SP_DP_LINK_DEBUG_CTRL_REG	0xb8
-#define SP_M_VID_DEBUG			BIT(5)
-#define SP_NEW_PRBS7			BIT(4)
-#define SP_INSERT_ER			BIT(1)
-#define SP_PRBS31_EN			BIT(0)
-
-/* AUX Misc control Register */
-#define SP_AUX_MISC_CTRL_REG		0xbf
-
-/* DP PLL control Register */
-#define SP_DP_PLL_CTRL_REG		0xc7
-#define SP_PLL_RST			BIT(6)
-
-/* DP Analog Power Down Register */
-#define SP_DP_ANALOG_POWER_DOWN_REG	0xc8
-#define SP_CH0_PD			BIT(0)
-
-/* DP Misc Control Register */
-#define SP_DP_MISC_CTRL_REG		0xcd
-#define SP_EQ_TRAINING_LOOP		BIT(6)
-
-/* DP Extra I2C Device Address Register */
-#define SP_DP_EXTRA_I2C_DEV_ADDR_REG	0xce
-#define SP_I2C_STRETCH_DISABLE		BIT(7)
-
-#define SP_I2C_EXTRA_ADDR		0x50
-
-/* DP Downspread Control Register 1 */
-#define SP_DP_DOWNSPREAD_CTRL1_REG	0xd0
-
-/* DP M Value Calculation Control Register */
-#define SP_DP_M_CALCULATION_CTRL_REG	0xd9
-#define SP_M_GEN_CLK_SEL		BIT(0)
-
-/* AUX Channel Access Status Register */
-#define SP_AUX_CH_STATUS_REG		0xe0
-#define SP_AUX_STATUS			0x0f
-
-/* AUX Channel DEFER Control Register */
-#define SP_AUX_DEFER_CTRL_REG		0xe2
-#define SP_DEFER_CTRL_EN		BIT(7)
-
-/* DP Buffer Data Count Register */
-#define SP_BUF_DATA_COUNT_REG		0xe4
-#define SP_BUF_DATA_COUNT_MASK		0x1f
-#define SP_BUF_CLR			BIT(7)
-
-/* DP AUX Channel Control Register 1 */
-#define SP_DP_AUX_CH_CTRL1_REG		0xe5
-#define SP_AUX_TX_COMM_MASK		0x0f
-#define SP_AUX_LENGTH_MASK		0xf0
-#define SP_AUX_LENGTH_SHIFT		4
-
-/* DP AUX CH Address Register 0 */
-#define SP_AUX_ADDR_7_0_REG		0xe6
-
-/* DP AUX CH Address Register 1 */
-#define SP_AUX_ADDR_15_8_REG		0xe7
-
-/* DP AUX CH Address Register 2 */
-#define SP_AUX_ADDR_19_16_REG		0xe8
-#define SP_AUX_ADDR_19_16_MASK		0x0f
-
-/* DP AUX Channel Control Register 2 */
-#define SP_DP_AUX_CH_CTRL2_REG		0xe9
-#define SP_AUX_SEL_RXCM			BIT(6)
-#define SP_AUX_CHSEL			BIT(3)
-#define SP_AUX_PN_INV			BIT(2)
-#define SP_ADDR_ONLY			BIT(1)
-#define SP_AUX_EN			BIT(0)
-
-/* DP Video Stream Control InfoFrame Register */
-#define SP_DP_3D_VSC_CTRL_REG		0xea
-#define SP_INFO_FRAME_VSC_EN		BIT(0)
-
-/* DP Video Stream Data Byte 1 Register */
-#define SP_DP_VSC_DB1_REG		0xeb
-
-/* DP AUX Channel Control Register 3 */
-#define SP_DP_AUX_CH_CTRL3_REG		0xec
-#define SP_WAIT_COUNTER_7_0_MASK	0xff
-
-/* DP AUX Channel Control Register 4 */
-#define SP_DP_AUX_CH_CTRL4_REG		0xed
-
-/* DP AUX Buffer Data Registers */
-#define SP_DP_BUF_DATA0_REG		0xf0
-
-/***************************************************************/
-/* Register definitions for TX_P2                              */
-/***************************************************************/
-
-/*
- * Core Register Definitions
- */
-
-/* Device ID Low Byte Register */
-#define SP_DEVICE_IDL_REG		0x02
-
-/* Device ID High Byte Register */
-#define SP_DEVICE_IDH_REG		0x03
-
-/* Device version register */
-#define SP_DEVICE_VERSION_REG		0x04
-
-/* Power Down Control Register */
-#define SP_POWERDOWN_CTRL_REG		0x05
-#define SP_REGISTER_PD			BIT(7)
-#define SP_HDCP_PD			BIT(5)
-#define SP_AUDIO_PD			BIT(4)
-#define SP_VIDEO_PD			BIT(3)
-#define SP_LINK_PD			BIT(2)
-#define SP_TOTAL_PD			BIT(1)
-
-/* Reset Control Register 1 */
-#define SP_RESET_CTRL1_REG		0x06
-#define SP_MISC_RST			BIT(7)
-#define SP_VIDCAP_RST			BIT(6)
-#define SP_VIDFIF_RST			BIT(5)
-#define SP_AUDFIF_RST			BIT(4)
-#define SP_AUDCAP_RST			BIT(3)
-#define SP_HDCP_RST			BIT(2)
-#define SP_SW_RST			BIT(1)
-#define SP_HW_RST			BIT(0)
-
-/* Reset Control Register 2 */
-#define SP_RESET_CTRL2_REG		0x07
-#define SP_AUX_RST			BIT(2)
-#define SP_SERDES_FIFO_RST		BIT(1)
-#define SP_I2C_REG_RST			BIT(0)
-
-/* Video Control Register 1 */
-#define SP_VID_CTRL1_REG		0x08
-#define SP_VIDEO_EN			BIT(7)
-#define SP_VIDEO_MUTE			BIT(2)
-#define SP_DE_GEN			BIT(1)
-#define SP_DEMUX			BIT(0)
-
-/* Video Control Register 2 */
-#define SP_VID_CTRL2_REG		0x09
-#define SP_IN_COLOR_F_MASK		0x03
-#define SP_IN_YC_BIT_SEL		BIT(2)
-#define SP_IN_BPC_MASK			0x70
-#define SP_IN_BPC_SHIFT			4
-#  define SP_IN_BPC_12BIT		0x03
-#  define SP_IN_BPC_10BIT		0x02
-#  define SP_IN_BPC_8BIT		0x01
-#  define SP_IN_BPC_6BIT		0x00
-#define SP_IN_D_RANGE			BIT(7)
-
-/* Video Control Register 3 */
-#define SP_VID_CTRL3_REG		0x0a
-#define SP_HPD_OUT			BIT(6)
-
-/* Video Control Register 5 */
-#define SP_VID_CTRL5_REG		0x0c
-#define SP_CSC_STD_SEL			BIT(7)
-#define SP_XVYCC_RNG_LMT		BIT(6)
-#define SP_RANGE_Y2R			BIT(5)
-#define SP_CSPACE_Y2R			BIT(4)
-#define SP_RGB_RNG_LMT			BIT(3)
-#define SP_Y_RNG_LMT			BIT(2)
-#define SP_RANGE_R2Y			BIT(1)
-#define SP_CSPACE_R2Y			BIT(0)
-
-/* Video Control Register 6 */
-#define SP_VID_CTRL6_REG		0x0d
-#define SP_TEST_PATTERN_EN		BIT(7)
-#define SP_VIDEO_PROCESS_EN		BIT(6)
-#define SP_VID_US_MODE			BIT(3)
-#define SP_VID_DS_MODE			BIT(2)
-#define SP_UP_SAMPLE			BIT(1)
-#define SP_DOWN_SAMPLE			BIT(0)
-
-/* Video Control Register 8 */
-#define SP_VID_CTRL8_REG		0x0f
-#define SP_VID_VRES_TH			BIT(0)
-
-/* Total Line Status Low Byte Register */
-#define SP_TOTAL_LINE_STAL_REG		0x24
-
-/* Total Line Status High Byte Register */
-#define SP_TOTAL_LINE_STAH_REG		0x25
-
-/* Active Line Status Low Byte Register */
-#define SP_ACT_LINE_STAL_REG		0x26
-
-/* Active Line Status High Byte Register */
-#define SP_ACT_LINE_STAH_REG		0x27
-
-/* Vertical Front Porch Status Register */
-#define SP_V_F_PORCH_STA_REG		0x28
-
-/* Vertical SYNC Width Status Register */
-#define SP_V_SYNC_STA_REG		0x29
-
-/* Vertical Back Porch Status Register */
-#define SP_V_B_PORCH_STA_REG		0x2a
-
-/* Total Pixel Status Low Byte Register */
-#define SP_TOTAL_PIXEL_STAL_REG		0x2b
-
-/* Total Pixel Status High Byte Register */
-#define SP_TOTAL_PIXEL_STAH_REG		0x2c
-
-/* Active Pixel Status Low Byte Register */
-#define SP_ACT_PIXEL_STAL_REG		0x2d
-
-/* Active Pixel Status High Byte Register */
-#define SP_ACT_PIXEL_STAH_REG		0x2e
-
-/* Horizontal Front Porch Status Low Byte Register */
-#define SP_H_F_PORCH_STAL_REG		0x2f
-
-/* Horizontal Front Porch Statys High Byte Register */
-#define SP_H_F_PORCH_STAH_REG		0x30
-
-/* Horizontal SYNC Width Status Low Byte Register */
-#define SP_H_SYNC_STAL_REG		0x31
-
-/* Horizontal SYNC Width Status High Byte Register */
-#define SP_H_SYNC_STAH_REG		0x32
-
-/* Horizontal Back Porch Status Low Byte Register */
-#define SP_H_B_PORCH_STAL_REG		0x33
-
-/* Horizontal Back Porch Status High Byte Register */
-#define SP_H_B_PORCH_STAH_REG		0x34
-
-/* InfoFrame AVI Packet DB1 Register */
-#define SP_INFOFRAME_AVI_DB1_REG	0x70
-
-/* Bit Control Specific Register */
-#define SP_BIT_CTRL_SPECIFIC_REG	0x80
-#define SP_BIT_CTRL_SELECT_SHIFT	1
-#define SP_ENABLE_BIT_CTRL		BIT(0)
-
-/* InfoFrame Audio Packet DB1 Register */
-#define SP_INFOFRAME_AUD_DB1_REG	0x83
-
-/* InfoFrame MPEG Packet DB1 Register */
-#define SP_INFOFRAME_MPEG_DB1_REG	0xb0
-
-/* Audio Channel Status Registers */
-#define SP_AUD_CH_STATUS_BASE		0xd0
-
-/* Audio Channel Num Register 5 */
-#define SP_I2S_CHANNEL_NUM_MASK		0xe0
-#  define SP_I2S_CH_NUM_1		(0x00 << 5)
-#  define SP_I2S_CH_NUM_2		(0x01 << 5)
-#  define SP_I2S_CH_NUM_3		(0x02 << 5)
-#  define SP_I2S_CH_NUM_4		(0x03 << 5)
-#  define SP_I2S_CH_NUM_5		(0x04 << 5)
-#  define SP_I2S_CH_NUM_6		(0x05 << 5)
-#  define SP_I2S_CH_NUM_7		(0x06 << 5)
-#  define SP_I2S_CH_NUM_8		(0x07 << 5)
-#define SP_EXT_VUCP			BIT(2)
-#define SP_VBIT				BIT(1)
-#define SP_AUDIO_LAYOUT			BIT(0)
-
-/* Analog Debug Register 2 */
-#define SP_ANALOG_DEBUG2_REG		0xdd
-#define SP_FORCE_SW_OFF_BYPASS		0x20
-#define SP_XTAL_FRQ			0x1c
-#  define SP_XTAL_FRQ_19M2		(0x00 << 2)
-#  define SP_XTAL_FRQ_24M		(0x01 << 2)
-#  define SP_XTAL_FRQ_25M		(0x02 << 2)
-#  define SP_XTAL_FRQ_26M		(0x03 << 2)
-#  define SP_XTAL_FRQ_27M		(0x04 << 2)
-#  define SP_XTAL_FRQ_38M4		(0x05 << 2)
-#  define SP_XTAL_FRQ_52M		(0x06 << 2)
-#define SP_POWERON_TIME_1P5MS		0x03
-
-/* Analog Control 0 Register */
-#define SP_ANALOG_CTRL0_REG		0xe1
-
-/* Common Interrupt Status Register 1 */
-#define SP_COMMON_INT_STATUS_BASE	(0xf1 - 1)
-#define SP_PLL_LOCK_CHG			0x40
-
-/* Common Interrupt Status Register 2 */
-#define SP_COMMON_INT_STATUS2		0xf2
-#define SP_HDCP_AUTH_CHG		BIT(1)
-#define SP_HDCP_AUTH_DONE		BIT(0)
-
-#define SP_HDCP_LINK_CHECK_FAIL		BIT(0)
-
-/* Common Interrupt Status Register 4 */
-#define SP_COMMON_INT_STATUS4_REG	0xf4
-#define SP_HPD_IRQ			BIT(6)
-#define SP_HPD_ESYNC_ERR		BIT(4)
-#define SP_HPD_CHG			BIT(2)
-#define SP_HPD_LOST			BIT(1)
-#define SP_HPD_PLUG			BIT(0)
-
-/* DP Interrupt Status Register */
-#define SP_DP_INT_STATUS1_REG		0xf7
-#define SP_TRAINING_FINISH		BIT(5)
-#define SP_POLLING_ERR			BIT(4)
-
-/* Common Interrupt Mask Register */
-#define SP_COMMON_INT_MASK_BASE		(0xf8 - 1)
-
-#define SP_COMMON_INT_MASK4_REG		0xfb
-
-/* DP Interrupts Mask Register */
-#define SP_DP_INT_MASK1_REG		0xfe
-
-/* Interrupt Control Register */
-#define SP_INT_CTRL_REG			0xff
-
-/***************************************************************/
-/* Register definitions for TX_P1                              */
-/***************************************************************/
-
-/* DP TX Link Training Control Register */
-#define SP_DP_TX_LT_CTRL0_REG		0x30
-
-/* PD 1.2 Lint Training 80bit Pattern Register */
-#define SP_DP_LT_80BIT_PATTERN0_REG	0x80
-#define SP_DP_LT_80BIT_PATTERN_REG_NUM	10
-
-/* Audio Interface Control Register 0 */
-#define SP_AUD_INTERFACE_CTRL0_REG	0x5f
-#define SP_AUD_INTERFACE_DISABLE	0x80
-
-/* Audio Interface Control Register 2 */
-#define SP_AUD_INTERFACE_CTRL2_REG	0x60
-#define SP_M_AUD_ADJUST_ST		0x04
-
-/* Audio Interface Control Register 3 */
-#define SP_AUD_INTERFACE_CTRL3_REG	0x62
-
-/* Audio Interface Control Register 4 */
-#define SP_AUD_INTERFACE_CTRL4_REG	0x67
-
-/* Audio Interface Control Register 5 */
-#define SP_AUD_INTERFACE_CTRL5_REG	0x68
-
-/* Audio Interface Control Register 6 */
-#define SP_AUD_INTERFACE_CTRL6_REG	0x69
-
-/* Firmware Version Register */
-#define SP_FW_VER_REG			0xb7
-
-#endif
diff --git a/drivers/gpu/drm/bridge/analogix/Kconfig b/drivers/gpu/drm/bridge/analogix/Kconfig
index e930ff9b5cd4..e1fa7d820373 100644
--- a/drivers/gpu/drm/bridge/analogix/Kconfig
+++ b/drivers/gpu/drm/bridge/analogix/Kconfig
@@ -1,4 +1,27 @@
 # SPDX-License-Identifier: GPL-2.0-only
+config DRM_ANALOGIX_ANX6345
+	tristate "Analogix ANX6345 bridge"
+	depends on OF
+	select DRM_ANALOGIX_DP
+	select DRM_KMS_HELPER
+	select REGMAP_I2C
+	help
+	  ANX6345 is an ultra-low Full-HD DisplayPort/eDP
+	  transmitter designed for portable devices. The
+	  ANX6345 transforms the LVTTL RGB output of an
+	  application processor to eDP or DisplayPort.
+
+config DRM_ANALOGIX_ANX78XX
+	tristate "Analogix ANX78XX bridge"
+	select DRM_ANALOGIX_DP
+	select DRM_KMS_HELPER
+	select REGMAP_I2C
+	help
+	  ANX78XX is an ultra-low power Full-HD SlimPort transmitter
+	  designed for portable devices. The ANX78XX transforms
+	  the HDMI output of an application processor to MyDP
+	  or DisplayPort.
+
 config DRM_ANALOGIX_DP
 	tristate
 	depends on DRM
diff --git a/drivers/gpu/drm/bridge/analogix/Makefile b/drivers/gpu/drm/bridge/analogix/Makefile
index fdbf3fd2f087..97669b374098 100644
--- a/drivers/gpu/drm/bridge/analogix/Makefile
+++ b/drivers/gpu/drm/bridge/analogix/Makefile
@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-analogix_dp-objs := analogix_dp_core.o analogix_dp_reg.o
+analogix_dp-objs := analogix_dp_core.o analogix_dp_reg.o analogix-i2c-dptx.o
+obj-$(CONFIG_DRM_ANALOGIX_ANX6345) += analogix-anx6345.o
+obj-$(CONFIG_DRM_ANALOGIX_ANX78XX) += analogix-anx78xx.o
 obj-$(CONFIG_DRM_ANALOGIX_DP) += analogix_dp.o
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
new file mode 100644
index 000000000000..56f55c53abfd
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
@@ -0,0 +1,817 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor.
+ * Copyright(c) 2017, Icenowy Zheng <icenowy@aosc.io>
+ *
+ * Based on anx7808 driver obtained from chromeos with copyright:
+ * Copyright(c) 2013, Google Inc.
+ */
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/types.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_bridge.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_dp_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_of.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_print.h>
+#include <drm/drm_probe_helper.h>
+
+#include "analogix-i2c-dptx.h"
+#include "analogix-i2c-txcommon.h"
+
+#define POLL_DELAY		50000 /* us */
+#define POLL_TIMEOUT		5000000 /* us */
+
+#define I2C_IDX_DPTX		0
+#define I2C_IDX_TXCOM		1
+
+static const u8 anx6345_i2c_addresses[] = {
+	[I2C_IDX_DPTX]	= 0x70,
+	[I2C_IDX_TXCOM]	= 0x72,
+};
+#define I2C_NUM_ADDRESSES	ARRAY_SIZE(anx6345_i2c_addresses)
+
+struct anx6345 {
+	struct drm_dp_aux aux;
+	struct drm_bridge bridge;
+	struct i2c_client *client;
+	struct edid *edid;
+	struct drm_connector connector;
+	struct drm_panel *panel;
+	struct regulator *dvdd12;
+	struct regulator *dvdd25;
+	struct gpio_desc *gpiod_reset;
+	struct mutex lock;	/* protect EDID access */
+
+	/* I2C Slave addresses of ANX6345 are mapped as DPTX and SYS */
+	struct i2c_client *i2c_clients[I2C_NUM_ADDRESSES];
+	struct regmap *map[I2C_NUM_ADDRESSES];
+
+	u16 chipid;
+	u8 dpcd[DP_RECEIVER_CAP_SIZE];
+
+	bool powered;
+};
+
+static inline struct anx6345 *connector_to_anx6345(struct drm_connector *c)
+{
+	return container_of(c, struct anx6345, connector);
+}
+
+static inline struct anx6345 *bridge_to_anx6345(struct drm_bridge *bridge)
+{
+	return container_of(bridge, struct anx6345, bridge);
+}
+
+static int anx6345_set_bits(struct regmap *map, u8 reg, u8 mask)
+{
+	return regmap_update_bits(map, reg, mask, mask);
+}
+
+static int anx6345_clear_bits(struct regmap *map, u8 reg, u8 mask)
+{
+	return regmap_update_bits(map, reg, mask, 0);
+}
+
+static ssize_t anx6345_aux_transfer(struct drm_dp_aux *aux,
+				    struct drm_dp_aux_msg *msg)
+{
+	struct anx6345 *anx6345 = container_of(aux, struct anx6345, aux);
+
+	return anx_dp_aux_transfer(anx6345->map[I2C_IDX_DPTX], msg);
+}
+
+static int anx6345_dp_link_training(struct anx6345 *anx6345)
+{
+	unsigned int value;
+	u8 dp_bw, dpcd[2];
+	int err;
+
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM],
+				 SP_POWERDOWN_CTRL_REG,
+				 SP_TOTAL_PD);
+	if (err)
+		return err;
+
+	err = drm_dp_dpcd_readb(&anx6345->aux, DP_MAX_LINK_RATE, &dp_bw);
+	if (err < 0)
+		return err;
+
+	switch (dp_bw) {
+	case DP_LINK_BW_1_62:
+	case DP_LINK_BW_2_7:
+		break;
+
+	default:
+		DRM_DEBUG_KMS("DP bandwidth (%#02x) not supported\n", dp_bw);
+		return -EINVAL;
+	}
+
+	err = anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM], SP_VID_CTRL1_REG,
+			       SP_VIDEO_MUTE);
+	if (err)
+		return err;
+
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM],
+				 SP_VID_CTRL1_REG, SP_VIDEO_EN);
+	if (err)
+		return err;
+
+	/* Get DPCD info */
+	err = drm_dp_dpcd_read(&anx6345->aux, DP_DPCD_REV,
+			       &anx6345->dpcd, DP_RECEIVER_CAP_SIZE);
+	if (err < 0) {
+		DRM_ERROR("Failed to read DPCD: %d\n", err);
+		return err;
+	}
+
+	/* Clear channel x SERDES power down */
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_DPTX],
+				 SP_DP_ANALOG_POWER_DOWN_REG, SP_CH0_PD);
+	if (err)
+		return err;
+
+	/*
+	 * Power up the sink (DP_SET_POWER register is only available on DPCD
+	 * v1.1 and later).
+	 */
+	if (anx6345->dpcd[DP_DPCD_REV] >= 0x11) {
+		err = drm_dp_dpcd_readb(&anx6345->aux, DP_SET_POWER, &dpcd[0]);
+		if (err < 0) {
+			DRM_ERROR("Failed to read DP_SET_POWER register: %d\n",
+				  err);
+			return err;
+		}
+
+		dpcd[0] &= ~DP_SET_POWER_MASK;
+		dpcd[0] |= DP_SET_POWER_D0;
+
+		err = drm_dp_dpcd_writeb(&anx6345->aux, DP_SET_POWER, dpcd[0]);
+		if (err < 0) {
+			DRM_ERROR("Failed to power up DisplayPort link: %d\n",
+				  err);
+			return err;
+		}
+
+		/*
+		 * According to the DP 1.1 specification, a "Sink Device must
+		 * exit the power saving state within 1 ms" (Section 2.5.3.1,
+		 * Table 5-52, "Sink Control Field" (register 0x600).
+		 */
+		usleep_range(1000, 2000);
+	}
+
+	/* Possibly enable downspread on the sink */
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_DOWNSPREAD_CTRL1_REG, 0);
+	if (err)
+		return err;
+
+	if (anx6345->dpcd[DP_MAX_DOWNSPREAD] & DP_MAX_DOWNSPREAD_0_5) {
+		DRM_DEBUG("Enable downspread on the sink\n");
+		/* 4000PPM */
+		err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+				   SP_DP_DOWNSPREAD_CTRL1_REG, 8);
+		if (err)
+			return err;
+
+		err = drm_dp_dpcd_writeb(&anx6345->aux, DP_DOWNSPREAD_CTRL,
+					 DP_SPREAD_AMP_0_5);
+		if (err < 0)
+			return err;
+	} else {
+		err = drm_dp_dpcd_writeb(&anx6345->aux, DP_DOWNSPREAD_CTRL, 0);
+		if (err < 0)
+			return err;
+	}
+
+	/* Set the lane count and the link rate on the sink */
+	if (drm_dp_enhanced_frame_cap(anx6345->dpcd))
+		err = anx6345_set_bits(anx6345->map[I2C_IDX_DPTX],
+				       SP_DP_SYSTEM_CTRL_BASE + 4,
+				       SP_ENHANCED_MODE);
+	else
+		err = anx6345_clear_bits(anx6345->map[I2C_IDX_DPTX],
+					 SP_DP_SYSTEM_CTRL_BASE + 4,
+					 SP_ENHANCED_MODE);
+	if (err)
+		return err;
+
+	dpcd[0] = drm_dp_max_link_rate(anx6345->dpcd);
+	dpcd[0] = drm_dp_link_rate_to_bw_code(dpcd[0]);
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_MAIN_LINK_BW_SET_REG, dpcd[0]);
+	if (err)
+		return err;
+
+	dpcd[1] = drm_dp_max_lane_count(anx6345->dpcd);
+
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_LANE_COUNT_SET_REG, dpcd[1]);
+	if (err)
+		return err;
+
+	if (drm_dp_enhanced_frame_cap(anx6345->dpcd))
+		dpcd[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
+
+	err = drm_dp_dpcd_write(&anx6345->aux, DP_LINK_BW_SET, dpcd,
+				sizeof(dpcd));
+
+	if (err < 0) {
+		DRM_ERROR("Failed to configure link: %d\n", err);
+		return err;
+	}
+
+	/* Start training on the source */
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX], SP_DP_LT_CTRL_REG,
+			   SP_LT_EN);
+	if (err)
+		return err;
+
+	return regmap_read_poll_timeout(anx6345->map[I2C_IDX_DPTX],
+				       SP_DP_LT_CTRL_REG,
+				       value, !(value & SP_DP_LT_INPROGRESS),
+				       POLL_DELAY, POLL_TIMEOUT);
+}
+
+static int anx6345_tx_initialization(struct anx6345 *anx6345)
+{
+	int err, i;
+
+	/* FIXME: colordepth is hardcoded for now */
+	err = regmap_write(anx6345->map[I2C_IDX_TXCOM], SP_VID_CTRL2_REG,
+			   SP_IN_BPC_6BIT << SP_IN_BPC_SHIFT);
+	if (err)
+		return err;
+
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX], SP_DP_PLL_CTRL_REG, 0);
+	if (err)
+		return err;
+
+	err = regmap_write(anx6345->map[I2C_IDX_TXCOM],
+			   SP_ANALOG_DEBUG1_REG, 0);
+	if (err)
+		return err;
+
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_LINK_DEBUG_CTRL_REG,
+			   SP_NEW_PRBS7 | SP_M_VID_DEBUG);
+	if (err)
+		return err;
+
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_ANALOG_POWER_DOWN_REG, 0);
+	if (err)
+		return err;
+
+	/* Force HPD */
+	err = anx6345_set_bits(anx6345->map[I2C_IDX_DPTX],
+			       SP_DP_SYSTEM_CTRL_BASE + 3,
+			       SP_HPD_FORCE | SP_HPD_CTRL);
+	if (err)
+		return err;
+
+	for (i = 0; i < 4; i++) {
+		/* 4 lanes */
+		err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+				   SP_DP_LANE0_LT_CTRL_REG + i, 0);
+		if (err)
+			return err;
+	}
+
+	/* Reset AUX */
+	err = anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM],
+			       SP_RESET_CTRL2_REG, SP_AUX_RST);
+	if (err)
+		return err;
+
+	return anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM],
+				 SP_RESET_CTRL2_REG, SP_AUX_RST);
+}
+
+static void anx6345_poweron(struct anx6345 *anx6345)
+{
+	int err;
+
+	/* Ensure reset is asserted before starting power on sequence */
+	gpiod_set_value_cansleep(anx6345->gpiod_reset, 1);
+	usleep_range(1000, 2000);
+
+	err = regulator_enable(anx6345->dvdd12);
+	if (err) {
+		DRM_ERROR("Failed to enable dvdd12 regulator: %d\n",
+			  err);
+		return;
+	}
+
+	/* T1 - delay between VDD12 and VDD25 should be 0-2ms */
+	usleep_range(1000, 2000);
+
+	err = regulator_enable(anx6345->dvdd25);
+	if (err) {
+		DRM_ERROR("Failed to enable dvdd25 regulator: %d\n",
+			  err);
+		return;
+	}
+
+	/* T2 - delay between RESETN and all power rail stable,
+	 * should be 2-5ms
+	 */
+	usleep_range(2000, 5000);
+
+	gpiod_set_value_cansleep(anx6345->gpiod_reset, 0);
+
+	/* Power on registers module */
+	anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM], SP_POWERDOWN_CTRL_REG,
+			 SP_HDCP_PD | SP_AUDIO_PD | SP_VIDEO_PD | SP_LINK_PD);
+	anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM], SP_POWERDOWN_CTRL_REG,
+			   SP_REGISTER_PD | SP_TOTAL_PD);
+
+	if (anx6345->panel)
+		drm_panel_prepare(anx6345->panel);
+
+	anx6345->powered = true;
+}
+
+static void anx6345_poweroff(struct anx6345 *anx6345)
+{
+	int err;
+
+	gpiod_set_value_cansleep(anx6345->gpiod_reset, 1);
+	usleep_range(1000, 2000);
+
+	if (anx6345->panel)
+		drm_panel_unprepare(anx6345->panel);
+
+	err = regulator_disable(anx6345->dvdd25);
+	if (err) {
+		DRM_ERROR("Failed to disable dvdd25 regulator: %d\n",
+			  err);
+		return;
+	}
+
+	usleep_range(5000, 10000);
+
+	err = regulator_disable(anx6345->dvdd12);
+	if (err) {
+		DRM_ERROR("Failed to disable dvdd12 regulator: %d\n",
+			  err);
+		return;
+	}
+
+	usleep_range(1000, 2000);
+
+	anx6345->powered = false;
+}
+
+static int anx6345_start(struct anx6345 *anx6345)
+{
+	int err;
+
+	if (!anx6345->powered)
+		anx6345_poweron(anx6345);
+
+	/* Power on needed modules */
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM],
+				SP_POWERDOWN_CTRL_REG,
+				SP_VIDEO_PD | SP_LINK_PD);
+
+	err = anx6345_tx_initialization(anx6345);
+	if (err) {
+		DRM_ERROR("Failed eDP transmitter initialization: %d\n", err);
+		anx6345_poweroff(anx6345);
+		return err;
+	}
+
+	err = anx6345_dp_link_training(anx6345);
+	if (err) {
+		DRM_ERROR("Failed link training: %d\n", err);
+		anx6345_poweroff(anx6345);
+		return err;
+	}
+
+	/*
+	 * This delay seems to help keep the hardware in a good state. Without
+	 * it, there are times where it fails silently.
+	 */
+	usleep_range(10000, 15000);
+
+	return 0;
+}
+
+static int anx6345_config_dp_output(struct anx6345 *anx6345)
+{
+	int err;
+
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM], SP_VID_CTRL1_REG,
+				 SP_VIDEO_MUTE);
+	if (err)
+		return err;
+
+	/* Enable DP output */
+	err = anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM], SP_VID_CTRL1_REG,
+			       SP_VIDEO_EN);
+	if (err)
+		return err;
+
+	/* Force stream valid */
+	return anx6345_set_bits(anx6345->map[I2C_IDX_DPTX],
+			       SP_DP_SYSTEM_CTRL_BASE + 3,
+			       SP_STRM_FORCE | SP_STRM_CTRL);
+}
+
+static int anx6345_get_downstream_info(struct anx6345 *anx6345)
+{
+	u8 value;
+	int err;
+
+	err = drm_dp_dpcd_readb(&anx6345->aux, DP_SINK_COUNT, &value);
+	if (err < 0) {
+		DRM_ERROR("Get sink count failed %d\n", err);
+		return err;
+	}
+
+	if (!DP_GET_SINK_COUNT(value)) {
+		DRM_ERROR("Downstream disconnected\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int anx6345_get_modes(struct drm_connector *connector)
+{
+	struct anx6345 *anx6345 = connector_to_anx6345(connector);
+	int err, num_modes = 0;
+	bool power_off = false;
+
+	mutex_lock(&anx6345->lock);
+
+	if (!anx6345->edid) {
+		if (!anx6345->powered) {
+			anx6345_poweron(anx6345);
+			power_off = true;
+		}
+
+		err = anx6345_get_downstream_info(anx6345);
+		if (err) {
+			DRM_ERROR("Failed to get downstream info: %d\n", err);
+			goto unlock;
+		}
+
+		anx6345->edid = drm_get_edid(connector, &anx6345->aux.ddc);
+		if (!anx6345->edid)
+			DRM_ERROR("Failed to read EDID from panel\n");
+
+		err = drm_connector_update_edid_property(connector,
+							 anx6345->edid);
+		if (err) {
+			DRM_ERROR("Failed to update EDID property: %d\n", err);
+			goto unlock;
+		}
+	}
+
+	num_modes += drm_add_edid_modes(connector, anx6345->edid);
+
+unlock:
+	if (power_off)
+		anx6345_poweroff(anx6345);
+
+	mutex_unlock(&anx6345->lock);
+
+	if (!num_modes && anx6345->panel)
+		num_modes += drm_panel_get_modes(anx6345->panel, connector);
+
+	return num_modes;
+}
+
+static const struct drm_connector_helper_funcs anx6345_connector_helper_funcs = {
+	.get_modes = anx6345_get_modes,
+};
+
+static void
+anx6345_connector_destroy(struct drm_connector *connector)
+{
+	struct anx6345 *anx6345 = connector_to_anx6345(connector);
+
+	if (anx6345->panel)
+		drm_panel_detach(anx6345->panel);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs anx6345_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = anx6345_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int anx6345_bridge_attach(struct drm_bridge *bridge)
+{
+	struct anx6345 *anx6345 = bridge_to_anx6345(bridge);
+	int err;
+
+	if (!bridge->encoder) {
+		DRM_ERROR("Parent encoder object not found");
+		return -ENODEV;
+	}
+
+	/* Register aux channel */
+	anx6345->aux.name = "DP-AUX";
+	anx6345->aux.dev = &anx6345->client->dev;
+	anx6345->aux.transfer = anx6345_aux_transfer;
+
+	err = drm_dp_aux_register(&anx6345->aux);
+	if (err < 0) {
+		DRM_ERROR("Failed to register aux channel: %d\n", err);
+		return err;
+	}
+
+	err = drm_connector_init(bridge->dev, &anx6345->connector,
+				 &anx6345_connector_funcs,
+				 DRM_MODE_CONNECTOR_eDP);
+	if (err) {
+		DRM_ERROR("Failed to initialize connector: %d\n", err);
+		return err;
+	}
+
+	drm_connector_helper_add(&anx6345->connector,
+				 &anx6345_connector_helper_funcs);
+
+	err = drm_connector_register(&anx6345->connector);
+	if (err) {
+		DRM_ERROR("Failed to register connector: %d\n", err);
+		return err;
+	}
+
+	anx6345->connector.polled = DRM_CONNECTOR_POLL_HPD;
+
+	err = drm_connector_attach_encoder(&anx6345->connector,
+					   bridge->encoder);
+	if (err) {
+		DRM_ERROR("Failed to link up connector to encoder: %d\n", err);
+		return err;
+	}
+
+	if (anx6345->panel) {
+		err = drm_panel_attach(anx6345->panel, &anx6345->connector);
+		if (err) {
+			DRM_ERROR("Failed to attach panel: %d\n", err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static enum drm_mode_status
+anx6345_bridge_mode_valid(struct drm_bridge *bridge,
+			  const struct drm_display_mode *mode)
+{
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		return MODE_NO_INTERLACE;
+
+	/* Max 1200p at 5.4 Ghz, one lane */
+	if (mode->clock > 154000)
+		return MODE_CLOCK_HIGH;
+
+	return MODE_OK;
+}
+
+static void anx6345_bridge_disable(struct drm_bridge *bridge)
+{
+	struct anx6345 *anx6345 = bridge_to_anx6345(bridge);
+
+	/* Power off all modules except configuration registers access */
+	anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM], SP_POWERDOWN_CTRL_REG,
+			 SP_HDCP_PD | SP_AUDIO_PD | SP_VIDEO_PD | SP_LINK_PD);
+	if (anx6345->panel)
+		drm_panel_disable(anx6345->panel);
+
+	if (anx6345->powered)
+		anx6345_poweroff(anx6345);
+}
+
+static void anx6345_bridge_enable(struct drm_bridge *bridge)
+{
+	struct anx6345 *anx6345 = bridge_to_anx6345(bridge);
+	int err;
+
+	if (anx6345->panel)
+		drm_panel_enable(anx6345->panel);
+
+	err = anx6345_start(anx6345);
+	if (err) {
+		DRM_ERROR("Failed to initialize: %d\n", err);
+		return;
+	}
+
+	err = anx6345_config_dp_output(anx6345);
+	if (err)
+		DRM_ERROR("Failed to enable DP output: %d\n", err);
+}
+
+static const struct drm_bridge_funcs anx6345_bridge_funcs = {
+	.attach = anx6345_bridge_attach,
+	.mode_valid = anx6345_bridge_mode_valid,
+	.disable = anx6345_bridge_disable,
+	.enable = anx6345_bridge_enable,
+};
+
+static void unregister_i2c_dummy_clients(struct anx6345 *anx6345)
+{
+	unsigned int i;
+
+	for (i = 1; i < ARRAY_SIZE(anx6345->i2c_clients); i++)
+		if (anx6345->i2c_clients[i] &&
+		    anx6345->i2c_clients[i]->addr != anx6345->client->addr)
+			i2c_unregister_device(anx6345->i2c_clients[i]);
+}
+
+static const struct regmap_config anx6345_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = 0xff,
+	.cache_type = REGCACHE_NONE,
+};
+
+static const u16 anx6345_chipid_list[] = {
+	0x6345,
+};
+
+static bool anx6345_get_chip_id(struct anx6345 *anx6345)
+{
+	unsigned int i, idl, idh, version;
+
+	if (regmap_read(anx6345->map[I2C_IDX_TXCOM], SP_DEVICE_IDL_REG, &idl))
+		return false;
+
+	if (regmap_read(anx6345->map[I2C_IDX_TXCOM], SP_DEVICE_IDH_REG, &idh))
+		return false;
+
+	anx6345->chipid = (u8)idl | ((u8)idh << 8);
+
+	if (regmap_read(anx6345->map[I2C_IDX_TXCOM], SP_DEVICE_VERSION_REG,
+			&version))
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(anx6345_chipid_list); i++) {
+		if (anx6345->chipid == anx6345_chipid_list[i]) {
+			DRM_INFO("Found ANX%x (ver. %d) eDP Transmitter\n",
+				 anx6345->chipid, version);
+			return true;
+		}
+	}
+
+	DRM_ERROR("ANX%x (ver. %d) not supported by this driver\n",
+		  anx6345->chipid, version);
+
+	return false;
+}
+
+static int anx6345_i2c_probe(struct i2c_client *client,
+			     const struct i2c_device_id *id)
+{
+	struct anx6345 *anx6345;
+	struct device *dev;
+	int i, err;
+
+	anx6345 = devm_kzalloc(&client->dev, sizeof(*anx6345), GFP_KERNEL);
+	if (!anx6345)
+		return -ENOMEM;
+
+	mutex_init(&anx6345->lock);
+
+	anx6345->bridge.of_node = client->dev.of_node;
+
+	anx6345->client = client;
+	i2c_set_clientdata(client, anx6345);
+
+	dev = &anx6345->client->dev;
+
+	err = drm_of_find_panel_or_bridge(client->dev.of_node, 1, 0,
+					  &anx6345->panel, NULL);
+	if (err == -EPROBE_DEFER)
+		return err;
+
+	if (err)
+		DRM_DEBUG("No panel found\n");
+
+	/* 1.2V digital core power regulator  */
+	anx6345->dvdd12 = devm_regulator_get(dev, "dvdd12-supply");
+	if (IS_ERR(anx6345->dvdd12)) {
+		DRM_ERROR("dvdd12-supply not found\n");
+		return PTR_ERR(anx6345->dvdd12);
+	}
+
+	/* 2.5V digital core power regulator  */
+	anx6345->dvdd25 = devm_regulator_get(dev, "dvdd25-supply");
+	if (IS_ERR(anx6345->dvdd25)) {
+		DRM_ERROR("dvdd25-supply not found\n");
+		return PTR_ERR(anx6345->dvdd25);
+	}
+
+	/* GPIO for chip reset */
+	anx6345->gpiod_reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(anx6345->gpiod_reset)) {
+		DRM_ERROR("Reset gpio not found\n");
+		return PTR_ERR(anx6345->gpiod_reset);
+	}
+
+	/* Map slave addresses of ANX6345 */
+	for (i = 0; i < I2C_NUM_ADDRESSES; i++) {
+		if (anx6345_i2c_addresses[i] >> 1 != client->addr)
+			anx6345->i2c_clients[i] = i2c_new_dummy_device(client->adapter,
+						anx6345_i2c_addresses[i] >> 1);
+		else
+			anx6345->i2c_clients[i] = client;
+
+		if (IS_ERR(anx6345->i2c_clients[i])) {
+			err = PTR_ERR(anx6345->i2c_clients[i]);
+			DRM_ERROR("Failed to reserve I2C bus %02x\n",
+				  anx6345_i2c_addresses[i]);
+			goto err_unregister_i2c;
+		}
+
+		anx6345->map[i] = devm_regmap_init_i2c(anx6345->i2c_clients[i],
+						       &anx6345_regmap_config);
+		if (IS_ERR(anx6345->map[i])) {
+			err = PTR_ERR(anx6345->map[i]);
+			DRM_ERROR("Failed regmap initialization %02x\n",
+				  anx6345_i2c_addresses[i]);
+			goto err_unregister_i2c;
+		}
+	}
+
+	/* Look for supported chip ID */
+	anx6345_poweron(anx6345);
+	if (anx6345_get_chip_id(anx6345)) {
+		anx6345->bridge.funcs = &anx6345_bridge_funcs;
+		drm_bridge_add(&anx6345->bridge);
+
+		return 0;
+	} else {
+		anx6345_poweroff(anx6345);
+		err = -ENODEV;
+	}
+
+err_unregister_i2c:
+	unregister_i2c_dummy_clients(anx6345);
+	return err;
+}
+
+static int anx6345_i2c_remove(struct i2c_client *client)
+{
+	struct anx6345 *anx6345 = i2c_get_clientdata(client);
+
+	drm_bridge_remove(&anx6345->bridge);
+
+	unregister_i2c_dummy_clients(anx6345);
+
+	kfree(anx6345->edid);
+
+	mutex_destroy(&anx6345->lock);
+
+	return 0;
+}
+
+static const struct i2c_device_id anx6345_id[] = {
+	{ "anx6345", 0 },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, anx6345_id);
+
+static const struct of_device_id anx6345_match_table[] = {
+	{ .compatible = "analogix,anx6345", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, anx6345_match_table);
+
+static struct i2c_driver anx6345_driver = {
+	.driver = {
+		   .name = "anx6345",
+		   .of_match_table = of_match_ptr(anx6345_match_table),
+		  },
+	.probe = anx6345_i2c_probe,
+	.remove = anx6345_i2c_remove,
+	.id_table = anx6345_id,
+};
+module_i2c_driver(anx6345_driver);
+
+MODULE_DESCRIPTION("ANX6345 eDP Transmitter driver");
+MODULE_AUTHOR("Icenowy Zheng <icenowy@aosc.io>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
index 274989f96a91..41867be03751 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
@@ -36,8 +36,6 @@
 #define I2C_IDX_RX_P1		4
 
 #define XTAL_CLK		270 /* 27M */
-#define AUX_CH_BUFFER_SIZE	16
-#define AUX_WAIT_TIMEOUT_MS	15
 
 static const u8 anx7808_i2c_addresses[] = {
 	[I2C_IDX_TX_P0] = 0x78,
@@ -107,153 +105,11 @@ static int anx78xx_clear_bits(struct regmap *map, u8 reg, u8 mask)
 	return regmap_update_bits(map, reg, mask, 0);
 }
 
-static bool anx78xx_aux_op_finished(struct anx78xx *anx78xx)
-{
-	unsigned int value;
-	int err;
-
-	err = regmap_read(anx78xx->map[I2C_IDX_TX_P0], SP_DP_AUX_CH_CTRL2_REG,
-			  &value);
-	if (err < 0)
-		return false;
-
-	return (value & SP_AUX_EN) == 0;
-}
-
-static int anx78xx_aux_wait(struct anx78xx *anx78xx)
-{
-	unsigned long timeout;
-	unsigned int status;
-	int err;
-
-	timeout = jiffies + msecs_to_jiffies(AUX_WAIT_TIMEOUT_MS) + 1;
-
-	while (!anx78xx_aux_op_finished(anx78xx)) {
-		if (time_after(jiffies, timeout)) {
-			if (!anx78xx_aux_op_finished(anx78xx)) {
-				DRM_ERROR("Timed out waiting AUX to finish\n");
-				return -ETIMEDOUT;
-			}
-
-			break;
-		}
-
-		usleep_range(1000, 2000);
-	}
-
-	/* Read the AUX channel access status */
-	err = regmap_read(anx78xx->map[I2C_IDX_TX_P0], SP_AUX_CH_STATUS_REG,
-			  &status);
-	if (err < 0) {
-		DRM_ERROR("Failed to read from AUX channel: %d\n", err);
-		return err;
-	}
-
-	if (status & SP_AUX_STATUS) {
-		DRM_ERROR("Failed to wait for AUX channel (status: %02x)\n",
-			  status);
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static int anx78xx_aux_address(struct anx78xx *anx78xx, unsigned int addr)
-{
-	int err;
-
-	err = regmap_write(anx78xx->map[I2C_IDX_TX_P0], SP_AUX_ADDR_7_0_REG,
-			   addr & 0xff);
-	if (err)
-		return err;
-
-	err = regmap_write(anx78xx->map[I2C_IDX_TX_P0], SP_AUX_ADDR_15_8_REG,
-			   (addr & 0xff00) >> 8);
-	if (err)
-		return err;
-
-	/*
-	 * DP AUX CH Address Register #2, only update bits[3:0]
-	 * [7:4] RESERVED
-	 * [3:0] AUX_ADDR[19:16], Register control AUX CH address.
-	 */
-	err = regmap_update_bits(anx78xx->map[I2C_IDX_TX_P0],
-				 SP_AUX_ADDR_19_16_REG,
-				 SP_AUX_ADDR_19_16_MASK,
-				 (addr & 0xf0000) >> 16);
-
-	if (err)
-		return err;
-
-	return 0;
-}
-
 static ssize_t anx78xx_aux_transfer(struct drm_dp_aux *aux,
 				    struct drm_dp_aux_msg *msg)
 {
 	struct anx78xx *anx78xx = container_of(aux, struct anx78xx, aux);
-	u8 ctrl1 = msg->request;
-	u8 ctrl2 = SP_AUX_EN;
-	u8 *buffer = msg->buffer;
-	int err;
-
-	/* The DP AUX transmit and receive buffer has 16 bytes. */
-	if (WARN_ON(msg->size > AUX_CH_BUFFER_SIZE))
-		return -E2BIG;
-
-	/* Zero-sized messages specify address-only transactions. */
-	if (msg->size < 1)
-		ctrl2 |= SP_ADDR_ONLY;
-	else	/* For non-zero-sized set the length field. */
-		ctrl1 |= (msg->size - 1) << SP_AUX_LENGTH_SHIFT;
-
-	if ((msg->request & DP_AUX_I2C_READ) == 0) {
-		/* When WRITE | MOT write values to data buffer */
-		err = regmap_bulk_write(anx78xx->map[I2C_IDX_TX_P0],
-					SP_DP_BUF_DATA0_REG, buffer,
-					msg->size);
-		if (err)
-			return err;
-	}
-
-	/* Write address and request */
-	err = anx78xx_aux_address(anx78xx, msg->address);
-	if (err)
-		return err;
-
-	err = regmap_write(anx78xx->map[I2C_IDX_TX_P0], SP_DP_AUX_CH_CTRL1_REG,
-			   ctrl1);
-	if (err)
-		return err;
-
-	/* Start transaction */
-	err = regmap_update_bits(anx78xx->map[I2C_IDX_TX_P0],
-				 SP_DP_AUX_CH_CTRL2_REG, SP_ADDR_ONLY |
-				 SP_AUX_EN, ctrl2);
-	if (err)
-		return err;
-
-	err = anx78xx_aux_wait(anx78xx);
-	if (err)
-		return err;
-
-	msg->reply = DP_AUX_I2C_REPLY_ACK;
-
-	if ((msg->size > 0) && (msg->request & DP_AUX_I2C_READ)) {
-		/* Read values from data buffer */
-		err = regmap_bulk_read(anx78xx->map[I2C_IDX_TX_P0],
-				       SP_DP_BUF_DATA0_REG, buffer,
-				       msg->size);
-		if (err)
-			return err;
-	}
-
-	err = anx78xx_clear_bits(anx78xx->map[I2C_IDX_TX_P0],
-				 SP_DP_AUX_CH_CTRL2_REG, SP_ADDR_ONLY);
-	if (err)
-		return err;
-
-	return msg->size;
+	return anx_dp_aux_transfer(anx78xx->map[I2C_IDX_TX_P0], msg);
 }
 
 static int anx78xx_set_hpd(struct anx78xx *anx78xx)
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.h b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.h
new file mode 100644
index 000000000000..db2a2725acb2
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.h
@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor. All rights reserved.
+ */
+
+#ifndef __ANX78xx_H
+#define __ANX78xx_H
+
+#include "analogix-i2c-dptx.h"
+#include "analogix-i2c-txcommon.h"
+
+/***************************************************************/
+/* Register definitions for RX_PO                              */
+/***************************************************************/
+
+/*
+ * System Control and Status
+ */
+
+/* Software Reset Register 1 */
+#define SP_SOFTWARE_RESET1_REG		0x11
+#define SP_VIDEO_RST			BIT(4)
+#define SP_HDCP_MAN_RST			BIT(2)
+#define SP_TMDS_RST			BIT(1)
+#define SP_SW_MAN_RST			BIT(0)
+
+/* System Status Register */
+#define SP_SYSTEM_STATUS_REG		0x14
+#define SP_TMDS_CLOCK_DET		BIT(1)
+#define SP_TMDS_DE_DET			BIT(0)
+
+/* HDMI Status Register */
+#define SP_HDMI_STATUS_REG		0x15
+#define SP_HDMI_AUD_LAYOUT		BIT(3)
+#define SP_HDMI_DET			BIT(0)
+#  define SP_DVI_MODE			0
+#  define SP_HDMI_MODE			1
+
+/* HDMI Mute Control Register */
+#define SP_HDMI_MUTE_CTRL_REG		0x16
+#define SP_AUD_MUTE			BIT(1)
+#define SP_VID_MUTE			BIT(0)
+
+/* System Power Down Register 1 */
+#define SP_SYSTEM_POWER_DOWN1_REG	0x18
+#define SP_PWDN_CTRL			BIT(0)
+
+/*
+ * Audio and Video Auto Control
+ */
+
+/* Auto Audio and Video Control register */
+#define SP_AUDVID_CTRL_REG		0x20
+#define SP_AVC_OE			BIT(7)
+#define SP_AAC_OE			BIT(6)
+#define SP_AVC_EN			BIT(1)
+#define SP_AAC_EN			BIT(0)
+
+/* Audio Exception Enable Registers */
+#define SP_AUD_EXCEPTION_ENABLE_BASE	(0x24 - 1)
+/* Bits for Audio Exception Enable Register 3 */
+#define SP_AEC_EN21			BIT(5)
+
+/*
+ * Interrupt
+ */
+
+/* Interrupt Status Register 1 */
+#define SP_INT_STATUS1_REG		0x31
+/* Bits for Interrupt Status Register 1 */
+#define SP_HDMI_DVI			BIT(7)
+#define SP_CKDT_CHG			BIT(6)
+#define SP_SCDT_CHG			BIT(5)
+#define SP_PCLK_CHG			BIT(4)
+#define SP_PLL_UNLOCK			BIT(3)
+#define SP_CABLE_PLUG_CHG		BIT(2)
+#define SP_SET_MUTE			BIT(1)
+#define SP_SW_INTR			BIT(0)
+/* Bits for Interrupt Status Register 2 */
+#define SP_HDCP_ERR			BIT(5)
+#define SP_AUDIO_SAMPLE_CHG		BIT(0)	/* undocumented */
+/* Bits for Interrupt Status Register 3 */
+#define SP_AUD_MODE_CHG			BIT(0)
+/* Bits for Interrupt Status Register 5 */
+#define SP_AUDIO_RCV			BIT(0)
+/* Bits for Interrupt Status Register 6 */
+#define SP_INT_STATUS6_REG		0x36
+#define SP_CTS_RCV			BIT(7)
+#define SP_NEW_AUD_PKT			BIT(4)
+#define SP_NEW_AVI_PKT			BIT(1)
+#define SP_NEW_CP_PKT			BIT(0)
+/* Bits for Interrupt Status Register 7 */
+#define SP_NO_VSI			BIT(7)
+#define SP_NEW_VS			BIT(4)
+
+/* Interrupt Mask 1 Status Registers */
+#define SP_INT_MASK1_REG		0x41
+
+/* HDMI US TIMER Control Register */
+#define SP_HDMI_US_TIMER_CTRL_REG	0x49
+#define SP_MS_TIMER_MARGIN_10_8_MASK	0x07
+
+/*
+ * TMDS Control
+ */
+
+/* TMDS Control Registers */
+#define SP_TMDS_CTRL_BASE		(0x50 - 1)
+/* Bits for TMDS Control Register 7 */
+#define SP_PD_RT			BIT(0)
+
+/*
+ * Video Control
+ */
+
+/* Video Status Register */
+#define SP_VIDEO_STATUS_REG		0x70
+#define SP_COLOR_DEPTH_MASK		0xf0
+#define SP_COLOR_DEPTH_SHIFT		4
+#  define SP_COLOR_DEPTH_MODE_LEGACY	0x00
+#  define SP_COLOR_DEPTH_MODE_24BIT	0x04
+#  define SP_COLOR_DEPTH_MODE_30BIT	0x05
+#  define SP_COLOR_DEPTH_MODE_36BIT	0x06
+#  define SP_COLOR_DEPTH_MODE_48BIT	0x07
+
+/* Video Data Range Control Register */
+#define SP_VID_DATA_RANGE_CTRL_REG	0x83
+#define SP_R2Y_INPUT_LIMIT		BIT(1)
+
+/* Pixel Clock High Resolution Counter Registers */
+#define SP_PCLK_HIGHRES_CNT_BASE	(0x8c - 1)
+
+/*
+ * Audio Control
+ */
+
+/* Number of Audio Channels Status Registers */
+#define SP_AUD_CH_STATUS_REG_NUM	6
+
+/* Audio IN S/PDIF Channel Status Registers */
+#define SP_AUD_SPDIF_CH_STATUS_BASE	0xc7
+
+/* Audio IN S/PDIF Channel Status Register 4 */
+#define SP_FS_FREQ_MASK			0x0f
+#  define SP_FS_FREQ_44100HZ		0x00
+#  define SP_FS_FREQ_48000HZ		0x02
+#  define SP_FS_FREQ_32000HZ		0x03
+#  define SP_FS_FREQ_88200HZ		0x08
+#  define SP_FS_FREQ_96000HZ		0x0a
+#  define SP_FS_FREQ_176400HZ		0x0c
+#  define SP_FS_FREQ_192000HZ		0x0e
+
+/*
+ * Micellaneous Control Block
+ */
+
+/* CHIP Control Register */
+#define SP_CHIP_CTRL_REG		0xe3
+#define SP_MAN_HDMI5V_DET		BIT(3)
+#define SP_PLLLOCK_CKDT_EN		BIT(2)
+#define SP_ANALOG_CKDT_EN		BIT(1)
+#define SP_DIGITAL_CKDT_EN		BIT(0)
+
+/* Packet Receiving Status Register */
+#define SP_PACKET_RECEIVING_STATUS_REG	0xf3
+#define SP_AVI_RCVD			BIT(5)
+#define SP_VSI_RCVD			BIT(1)
+
+/***************************************************************/
+/* Register definitions for RX_P1                              */
+/***************************************************************/
+
+/* HDCP BCAPS Shadow Register */
+#define SP_HDCP_BCAPS_SHADOW_REG	0x2a
+#define SP_BCAPS_REPEATER		BIT(5)
+
+/* HDCP Status Register */
+#define SP_RX_HDCP_STATUS_REG		0x3f
+#define SP_AUTH_EN			BIT(4)
+
+/*
+ * InfoFrame and Control Packet Registers
+ */
+
+/* AVI InfoFrame packet checksum */
+#define SP_AVI_INFOFRAME_CHECKSUM	0xa3
+
+/* AVI InfoFrame Registers */
+#define SP_AVI_INFOFRAME_DATA_BASE	0xa4
+
+#define SP_AVI_COLOR_F_MASK		0x60
+#define SP_AVI_COLOR_F_SHIFT		5
+
+/* Audio InfoFrame Registers */
+#define SP_AUD_INFOFRAME_DATA_BASE	0xc4
+#define SP_AUD_INFOFRAME_LAYOUT_MASK	0x0f
+
+/* MPEG/HDMI Vendor Specific InfoFrame Packet type code */
+#define SP_MPEG_VS_INFOFRAME_TYPE_REG	0xe0
+
+/* MPEG/HDMI Vendor Specific InfoFrame Packet length */
+#define SP_MPEG_VS_INFOFRAME_LEN_REG	0xe2
+
+/* MPEG/HDMI Vendor Specific InfoFrame Packet version number */
+#define SP_MPEG_VS_INFOFRAME_VER_REG	0xe1
+
+/* MPEG/HDMI Vendor Specific InfoFrame Packet content */
+#define SP_MPEG_VS_INFOFRAME_DATA_BASE	0xe4
+
+/* General Control Packet Register */
+#define SP_GENERAL_CTRL_PACKET_REG	0x9f
+#define SP_CLEAR_AVMUTE			BIT(4)
+#define SP_SET_AVMUTE			BIT(0)
+
+/***************************************************************/
+/* Register definitions for TX_P1                              */
+/***************************************************************/
+
+/* DP TX Link Training Control Register */
+#define SP_DP_TX_LT_CTRL0_REG		0x30
+
+/* PD 1.2 Lint Training 80bit Pattern Register */
+#define SP_DP_LT_80BIT_PATTERN0_REG	0x80
+#define SP_DP_LT_80BIT_PATTERN_REG_NUM	10
+
+/* Audio Interface Control Register 0 */
+#define SP_AUD_INTERFACE_CTRL0_REG	0x5f
+#define SP_AUD_INTERFACE_DISABLE	0x80
+
+/* Audio Interface Control Register 2 */
+#define SP_AUD_INTERFACE_CTRL2_REG	0x60
+#define SP_M_AUD_ADJUST_ST		0x04
+
+/* Audio Interface Control Register 3 */
+#define SP_AUD_INTERFACE_CTRL3_REG	0x62
+
+/* Audio Interface Control Register 4 */
+#define SP_AUD_INTERFACE_CTRL4_REG	0x67
+
+/* Audio Interface Control Register 5 */
+#define SP_AUD_INTERFACE_CTRL5_REG	0x68
+
+/* Audio Interface Control Register 6 */
+#define SP_AUD_INTERFACE_CTRL6_REG	0x69
+
+/* Firmware Version Register */
+#define SP_FW_VER_REG			0xb7
+
+#endif
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.c b/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.c
new file mode 100644
index 000000000000..fe40bab21530
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.c
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor.
+ *
+ * Based on anx7808 driver obtained from chromeos with copyright:
+ * Copyright(c) 2013, Google Inc.
+ */
+#include <linux/regmap.h>
+
+#include <drm/drm.h>
+#include <drm/drm_dp_helper.h>
+#include <drm/drm_print.h>
+
+#include "analogix-i2c-dptx.h"
+
+#define AUX_WAIT_TIMEOUT_MS	15
+#define AUX_CH_BUFFER_SIZE	16
+
+static int anx_i2c_dp_clear_bits(struct regmap *map, u8 reg, u8 mask)
+{
+	return regmap_update_bits(map, reg, mask, 0);
+}
+
+static bool anx_dp_aux_op_finished(struct regmap *map_dptx)
+{
+	unsigned int value;
+	int err;
+
+	err = regmap_read(map_dptx, SP_DP_AUX_CH_CTRL2_REG, &value);
+	if (err < 0)
+		return false;
+
+	return (value & SP_AUX_EN) == 0;
+}
+
+static int anx_dp_aux_wait(struct regmap *map_dptx)
+{
+	unsigned long timeout;
+	unsigned int status;
+	int err;
+
+	timeout = jiffies + msecs_to_jiffies(AUX_WAIT_TIMEOUT_MS) + 1;
+
+	while (!anx_dp_aux_op_finished(map_dptx)) {
+		if (time_after(jiffies, timeout)) {
+			if (!anx_dp_aux_op_finished(map_dptx)) {
+				DRM_ERROR("Timed out waiting AUX to finish\n");
+				return -ETIMEDOUT;
+			}
+
+			break;
+		}
+
+		usleep_range(1000, 2000);
+	}
+
+	/* Read the AUX channel access status */
+	err = regmap_read(map_dptx, SP_AUX_CH_STATUS_REG, &status);
+	if (err < 0) {
+		DRM_ERROR("Failed to read from AUX channel: %d\n", err);
+		return err;
+	}
+
+	if (status & SP_AUX_STATUS) {
+		DRM_ERROR("Failed to wait for AUX channel (status: %02x)\n",
+			  status);
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int anx_dp_aux_address(struct regmap *map_dptx, unsigned int addr)
+{
+	int err;
+
+	err = regmap_write(map_dptx, SP_AUX_ADDR_7_0_REG, addr & 0xff);
+	if (err)
+		return err;
+
+	err = regmap_write(map_dptx, SP_AUX_ADDR_15_8_REG,
+			   (addr & 0xff00) >> 8);
+	if (err)
+		return err;
+
+	/*
+	 * DP AUX CH Address Register #2, only update bits[3:0]
+	 * [7:4] RESERVED
+	 * [3:0] AUX_ADDR[19:16], Register control AUX CH address.
+	 */
+	err = regmap_update_bits(map_dptx, SP_AUX_ADDR_19_16_REG,
+				 SP_AUX_ADDR_19_16_MASK,
+				 (addr & 0xf0000) >> 16);
+
+	if (err)
+		return err;
+
+	return 0;
+}
+
+ssize_t anx_dp_aux_transfer(struct regmap *map_dptx,
+				struct drm_dp_aux_msg *msg)
+{
+	u8 ctrl1 = msg->request;
+	u8 ctrl2 = SP_AUX_EN;
+	u8 *buffer = msg->buffer;
+	int err;
+
+	/* The DP AUX transmit and receive buffer has 16 bytes. */
+	if (WARN_ON(msg->size > AUX_CH_BUFFER_SIZE))
+		return -E2BIG;
+
+	/* Zero-sized messages specify address-only transactions. */
+	if (msg->size < 1)
+		ctrl2 |= SP_ADDR_ONLY;
+	else	/* For non-zero-sized set the length field. */
+		ctrl1 |= (msg->size - 1) << SP_AUX_LENGTH_SHIFT;
+
+	if ((msg->size > 0) && ((msg->request & DP_AUX_I2C_READ) == 0)) {
+		/* When WRITE | MOT write values to data buffer */
+		err = regmap_bulk_write(map_dptx,
+					SP_DP_BUF_DATA0_REG, buffer,
+					msg->size);
+		if (err)
+			return err;
+	}
+
+	/* Write address and request */
+	err = anx_dp_aux_address(map_dptx, msg->address);
+	if (err)
+		return err;
+
+	err = regmap_write(map_dptx, SP_DP_AUX_CH_CTRL1_REG, ctrl1);
+	if (err)
+		return err;
+
+	/* Start transaction */
+	err = regmap_update_bits(map_dptx, SP_DP_AUX_CH_CTRL2_REG,
+				 SP_ADDR_ONLY | SP_AUX_EN, ctrl2);
+	if (err)
+		return err;
+
+	err = anx_dp_aux_wait(map_dptx);
+	if (err)
+		return err;
+
+	msg->reply = DP_AUX_I2C_REPLY_ACK;
+
+	if ((msg->size > 0) && (msg->request & DP_AUX_I2C_READ)) {
+		/* Read values from data buffer */
+		err = regmap_bulk_read(map_dptx,
+				       SP_DP_BUF_DATA0_REG, buffer,
+				       msg->size);
+		if (err)
+			return err;
+	}
+
+	err = anx_i2c_dp_clear_bits(map_dptx, SP_DP_AUX_CH_CTRL2_REG,
+				    SP_ADDR_ONLY);
+	if (err)
+		return err;
+
+	return msg->size;
+}
+EXPORT_SYMBOL_GPL(anx_dp_aux_transfer);
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.h b/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.h
new file mode 100644
index 000000000000..663c4bea6e70
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.h
@@ -0,0 +1,256 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor.
+ *
+ * Based on anx7808 driver obtained from chromeos with copyright:
+ * Copyright(c) 2013, Google Inc.
+ */
+#ifndef _ANALOGIX_I2C_DPTX_H_
+#define _ANALOGIX_I2C_DPTX_H_
+
+/***************************************************************/
+/* Register definitions for TX_P0                              */
+/***************************************************************/
+
+/* HDCP Status Register */
+#define SP_TX_HDCP_STATUS_REG		0x00
+#define SP_AUTH_FAIL			BIT(5)
+#define SP_AUTHEN_PASS			BIT(1)
+
+/* HDCP Control Register 0 */
+#define SP_HDCP_CTRL0_REG		0x01
+#define SP_RX_REPEATER			BIT(6)
+#define SP_RE_AUTH			BIT(5)
+#define SP_SW_AUTH_OK			BIT(4)
+#define SP_HARD_AUTH_EN			BIT(3)
+#define SP_HDCP_ENC_EN			BIT(2)
+#define SP_BKSV_SRM_PASS		BIT(1)
+#define SP_KSVLIST_VLD			BIT(0)
+/* HDCP Function Enabled */
+#define SP_HDCP_FUNCTION_ENABLED	(BIT(0) | BIT(1) | BIT(2) | BIT(3))
+
+/* HDCP Receiver BSTATUS Register 0 */
+#define	SP_HDCP_RX_BSTATUS0_REG		0x1b
+/* HDCP Receiver BSTATUS Register 1 */
+#define	SP_HDCP_RX_BSTATUS1_REG		0x1c
+
+/* HDCP Embedded "Blue Screen" Content Registers */
+#define SP_HDCP_VID0_BLUE_SCREEN_REG	0x2c
+#define SP_HDCP_VID1_BLUE_SCREEN_REG	0x2d
+#define SP_HDCP_VID2_BLUE_SCREEN_REG	0x2e
+
+/* HDCP Wait R0 Timing Register */
+#define SP_HDCP_WAIT_R0_TIME_REG	0x40
+
+/* HDCP Link Integrity Check Timer Register */
+#define SP_HDCP_LINK_CHECK_TIMER_REG	0x41
+
+/* HDCP Repeater Ready Wait Timer Register */
+#define SP_HDCP_RPTR_RDY_WAIT_TIME_REG	0x42
+
+/* HDCP Auto Timer Register */
+#define SP_HDCP_AUTO_TIMER_REG		0x51
+
+/* HDCP Key Status Register */
+#define SP_HDCP_KEY_STATUS_REG		0x5e
+
+/* HDCP Key Command Register */
+#define SP_HDCP_KEY_COMMAND_REG		0x5f
+#define SP_DISABLE_SYNC_HDCP		BIT(2)
+
+/* OTP Memory Key Protection Registers */
+#define SP_OTP_KEY_PROTECT1_REG		0x60
+#define SP_OTP_KEY_PROTECT2_REG		0x61
+#define SP_OTP_KEY_PROTECT3_REG		0x62
+#define SP_OTP_PSW1			0xa2
+#define SP_OTP_PSW2			0x7e
+#define SP_OTP_PSW3			0xc6
+
+/* DP System Control Registers */
+#define SP_DP_SYSTEM_CTRL_BASE		(0x80 - 1)
+/* Bits for DP System Control Register 2 */
+#define SP_CHA_STA			BIT(2)
+/* Bits for DP System Control Register 3 */
+#define SP_HPD_STATUS			BIT(6)
+#define SP_HPD_FORCE			BIT(5)
+#define SP_HPD_CTRL			BIT(4)
+#define SP_STRM_VALID			BIT(2)
+#define SP_STRM_FORCE			BIT(1)
+#define SP_STRM_CTRL			BIT(0)
+/* Bits for DP System Control Register 4 */
+#define SP_ENHANCED_MODE		BIT(3)
+
+/* DP Video Control Register */
+#define SP_DP_VIDEO_CTRL_REG		0x84
+#define SP_COLOR_F_MASK			0x06
+#define SP_COLOR_F_SHIFT		1
+#define SP_BPC_MASK			0xe0
+#define SP_BPC_SHIFT			5
+#  define SP_BPC_6BITS			0x00
+#  define SP_BPC_8BITS			0x01
+#  define SP_BPC_10BITS			0x02
+#  define SP_BPC_12BITS			0x03
+
+/* DP Audio Control Register */
+#define SP_DP_AUDIO_CTRL_REG		0x87
+#define SP_AUD_EN			BIT(0)
+
+/* 10us Pulse Generate Timer Registers */
+#define SP_I2C_GEN_10US_TIMER0_REG	0x88
+#define SP_I2C_GEN_10US_TIMER1_REG	0x89
+
+/* Packet Send Control Register */
+#define SP_PACKET_SEND_CTRL_REG		0x90
+#define SP_AUD_IF_UP			BIT(7)
+#define SP_AVI_IF_UD			BIT(6)
+#define SP_MPEG_IF_UD			BIT(5)
+#define SP_SPD_IF_UD			BIT(4)
+#define SP_AUD_IF_EN			BIT(3)
+#define SP_AVI_IF_EN			BIT(2)
+#define SP_MPEG_IF_EN			BIT(1)
+#define SP_SPD_IF_EN			BIT(0)
+
+/* DP HDCP Control Register */
+#define SP_DP_HDCP_CTRL_REG		0x92
+#define SP_AUTO_EN			BIT(7)
+#define SP_AUTO_START			BIT(5)
+#define SP_LINK_POLLING			BIT(1)
+
+/* DP Main Link Bandwidth Setting Register */
+#define SP_DP_MAIN_LINK_BW_SET_REG	0xa0
+#define SP_LINK_BW_SET_MASK		0x1f
+#define SP_INITIAL_SLIM_M_AUD_SEL	BIT(5)
+
+/* DP Lane Count Setting Register */
+#define SP_DP_LANE_COUNT_SET_REG	0xa1
+
+/* DP Training Pattern Set Register */
+#define SP_DP_TRAINING_PATTERN_SET_REG	0xa2
+
+/* DP Lane 0 Link Training Control Register */
+#define SP_DP_LANE0_LT_CTRL_REG		0xa3
+#define SP_TX_SW_SET_MASK		0x1b
+#define SP_MAX_PRE_REACH		BIT(5)
+#define SP_MAX_DRIVE_REACH		BIT(4)
+#define SP_PRE_EMP_LEVEL1		BIT(3)
+#define SP_DRVIE_CURRENT_LEVEL1		BIT(0)
+
+/* DP Link Training Control Register */
+#define SP_DP_LT_CTRL_REG		0xa8
+#define SP_DP_LT_INPROGRESS		0x80
+#define SP_LT_ERROR_TYPE_MASK		0x70
+#  define SP_LT_NO_ERROR		0x00
+#  define SP_LT_AUX_WRITE_ERROR		0x01
+#  define SP_LT_MAX_DRIVE_REACHED	0x02
+#  define SP_LT_WRONG_LANE_COUNT_SET	0x03
+#  define SP_LT_LOOP_SAME_5_TIME	0x04
+#  define SP_LT_CR_FAIL_IN_EQ		0x05
+#  define SP_LT_EQ_LOOP_5_TIME		0x06
+#define SP_LT_EN			BIT(0)
+
+/* DP CEP Training Control Registers */
+#define SP_DP_CEP_TRAINING_CTRL0_REG	0xa9
+#define SP_DP_CEP_TRAINING_CTRL1_REG	0xaa
+
+/* DP Debug Register 1 */
+#define SP_DP_DEBUG1_REG		0xb0
+#define SP_DEBUG_PLL_LOCK		BIT(4)
+#define SP_POLLING_EN			BIT(1)
+
+/* DP Polling Control Register */
+#define SP_DP_POLLING_CTRL_REG		0xb4
+#define SP_AUTO_POLLING_DISABLE		BIT(0)
+
+/* DP Link Debug Control Register */
+#define SP_DP_LINK_DEBUG_CTRL_REG	0xb8
+#define SP_M_VID_DEBUG			BIT(5)
+#define SP_NEW_PRBS7			BIT(4)
+#define SP_INSERT_ER			BIT(1)
+#define SP_PRBS31_EN			BIT(0)
+
+/* AUX Misc control Register */
+#define SP_AUX_MISC_CTRL_REG		0xbf
+
+/* DP PLL control Register */
+#define SP_DP_PLL_CTRL_REG		0xc7
+#define SP_PLL_RST			BIT(6)
+
+/* DP Analog Power Down Register */
+#define SP_DP_ANALOG_POWER_DOWN_REG	0xc8
+#define SP_CH0_PD			BIT(0)
+
+/* DP Misc Control Register */
+#define SP_DP_MISC_CTRL_REG		0xcd
+#define SP_EQ_TRAINING_LOOP		BIT(6)
+
+/* DP Extra I2C Device Address Register */
+#define SP_DP_EXTRA_I2C_DEV_ADDR_REG	0xce
+#define SP_I2C_STRETCH_DISABLE		BIT(7)
+
+#define SP_I2C_EXTRA_ADDR		0x50
+
+/* DP Downspread Control Register 1 */
+#define SP_DP_DOWNSPREAD_CTRL1_REG	0xd0
+
+/* DP M Value Calculation Control Register */
+#define SP_DP_M_CALCULATION_CTRL_REG	0xd9
+#define SP_M_GEN_CLK_SEL		BIT(0)
+
+/* AUX Channel Access Status Register */
+#define SP_AUX_CH_STATUS_REG		0xe0
+#define SP_AUX_STATUS			0x0f
+
+/* AUX Channel DEFER Control Register */
+#define SP_AUX_DEFER_CTRL_REG		0xe2
+#define SP_DEFER_CTRL_EN		BIT(7)
+
+/* DP Buffer Data Count Register */
+#define SP_BUF_DATA_COUNT_REG		0xe4
+#define SP_BUF_DATA_COUNT_MASK		0x1f
+#define SP_BUF_CLR			BIT(7)
+
+/* DP AUX Channel Control Register 1 */
+#define SP_DP_AUX_CH_CTRL1_REG		0xe5
+#define SP_AUX_TX_COMM_MASK		0x0f
+#define SP_AUX_LENGTH_MASK		0xf0
+#define SP_AUX_LENGTH_SHIFT		4
+
+/* DP AUX CH Address Register 0 */
+#define SP_AUX_ADDR_7_0_REG		0xe6
+
+/* DP AUX CH Address Register 1 */
+#define SP_AUX_ADDR_15_8_REG		0xe7
+
+/* DP AUX CH Address Register 2 */
+#define SP_AUX_ADDR_19_16_REG		0xe8
+#define SP_AUX_ADDR_19_16_MASK		0x0f
+
+/* DP AUX Channel Control Register 2 */
+#define SP_DP_AUX_CH_CTRL2_REG		0xe9
+#define SP_AUX_SEL_RXCM			BIT(6)
+#define SP_AUX_CHSEL			BIT(3)
+#define SP_AUX_PN_INV			BIT(2)
+#define SP_ADDR_ONLY			BIT(1)
+#define SP_AUX_EN			BIT(0)
+
+/* DP Video Stream Control InfoFrame Register */
+#define SP_DP_3D_VSC_CTRL_REG		0xea
+#define SP_INFO_FRAME_VSC_EN		BIT(0)
+
+/* DP Video Stream Data Byte 1 Register */
+#define SP_DP_VSC_DB1_REG		0xeb
+
+/* DP AUX Channel Control Register 3 */
+#define SP_DP_AUX_CH_CTRL3_REG		0xec
+#define SP_WAIT_COUNTER_7_0_MASK	0xff
+
+/* DP AUX Channel Control Register 4 */
+#define SP_DP_AUX_CH_CTRL4_REG		0xed
+
+/* DP AUX Buffer Data Registers */
+#define SP_DP_BUF_DATA0_REG		0xf0
+
+ssize_t anx_dp_aux_transfer(struct regmap *map_dptx,
+				struct drm_dp_aux_msg *msg);
+
+#endif
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-i2c-txcommon.h b/drivers/gpu/drm/bridge/analogix/analogix-i2c-txcommon.h
new file mode 100644
index 000000000000..3c843497d835
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-i2c-txcommon.h
@@ -0,0 +1,234 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor. All rights reserved.
+ */
+#ifndef _ANALOGIX_I2C_TXCOMMON_H_
+#define _ANALOGIX_I2C_TXCOMMON_H_
+
+/***************************************************************/
+/* Register definitions for TX_P2                              */
+/***************************************************************/
+
+/*
+ * Core Register Definitions
+ */
+
+/* Device ID Low Byte Register */
+#define SP_DEVICE_IDL_REG		0x02
+
+/* Device ID High Byte Register */
+#define SP_DEVICE_IDH_REG		0x03
+
+/* Device version register */
+#define SP_DEVICE_VERSION_REG		0x04
+
+/* Power Down Control Register */
+#define SP_POWERDOWN_CTRL_REG		0x05
+#define SP_REGISTER_PD			BIT(7)
+#define SP_HDCP_PD			BIT(5)
+#define SP_AUDIO_PD			BIT(4)
+#define SP_VIDEO_PD			BIT(3)
+#define SP_LINK_PD			BIT(2)
+#define SP_TOTAL_PD			BIT(1)
+
+/* Reset Control Register 1 */
+#define SP_RESET_CTRL1_REG		0x06
+#define SP_MISC_RST			BIT(7)
+#define SP_VIDCAP_RST			BIT(6)
+#define SP_VIDFIF_RST			BIT(5)
+#define SP_AUDFIF_RST			BIT(4)
+#define SP_AUDCAP_RST			BIT(3)
+#define SP_HDCP_RST			BIT(2)
+#define SP_SW_RST			BIT(1)
+#define SP_HW_RST			BIT(0)
+
+/* Reset Control Register 2 */
+#define SP_RESET_CTRL2_REG		0x07
+#define SP_AUX_RST			BIT(2)
+#define SP_SERDES_FIFO_RST		BIT(1)
+#define SP_I2C_REG_RST			BIT(0)
+
+/* Video Control Register 1 */
+#define SP_VID_CTRL1_REG		0x08
+#define SP_VIDEO_EN			BIT(7)
+#define SP_VIDEO_MUTE			BIT(2)
+#define SP_DE_GEN			BIT(1)
+#define SP_DEMUX			BIT(0)
+
+/* Video Control Register 2 */
+#define SP_VID_CTRL2_REG		0x09
+#define SP_IN_COLOR_F_MASK		0x03
+#define SP_IN_YC_BIT_SEL		BIT(2)
+#define SP_IN_BPC_MASK			0x70
+#define SP_IN_BPC_SHIFT			4
+#  define SP_IN_BPC_12BIT		0x03
+#  define SP_IN_BPC_10BIT		0x02
+#  define SP_IN_BPC_8BIT		0x01
+#  define SP_IN_BPC_6BIT		0x00
+#define SP_IN_D_RANGE			BIT(7)
+
+/* Video Control Register 3 */
+#define SP_VID_CTRL3_REG		0x0a
+#define SP_HPD_OUT			BIT(6)
+
+/* Video Control Register 5 */
+#define SP_VID_CTRL5_REG		0x0c
+#define SP_CSC_STD_SEL			BIT(7)
+#define SP_XVYCC_RNG_LMT		BIT(6)
+#define SP_RANGE_Y2R			BIT(5)
+#define SP_CSPACE_Y2R			BIT(4)
+#define SP_RGB_RNG_LMT			BIT(3)
+#define SP_Y_RNG_LMT			BIT(2)
+#define SP_RANGE_R2Y			BIT(1)
+#define SP_CSPACE_R2Y			BIT(0)
+
+/* Video Control Register 6 */
+#define SP_VID_CTRL6_REG		0x0d
+#define SP_TEST_PATTERN_EN		BIT(7)
+#define SP_VIDEO_PROCESS_EN		BIT(6)
+#define SP_VID_US_MODE			BIT(3)
+#define SP_VID_DS_MODE			BIT(2)
+#define SP_UP_SAMPLE			BIT(1)
+#define SP_DOWN_SAMPLE			BIT(0)
+
+/* Video Control Register 8 */
+#define SP_VID_CTRL8_REG		0x0f
+#define SP_VID_VRES_TH			BIT(0)
+
+/* Total Line Status Low Byte Register */
+#define SP_TOTAL_LINE_STAL_REG		0x24
+
+/* Total Line Status High Byte Register */
+#define SP_TOTAL_LINE_STAH_REG		0x25
+
+/* Active Line Status Low Byte Register */
+#define SP_ACT_LINE_STAL_REG		0x26
+
+/* Active Line Status High Byte Register */
+#define SP_ACT_LINE_STAH_REG		0x27
+
+/* Vertical Front Porch Status Register */
+#define SP_V_F_PORCH_STA_REG		0x28
+
+/* Vertical SYNC Width Status Register */
+#define SP_V_SYNC_STA_REG		0x29
+
+/* Vertical Back Porch Status Register */
+#define SP_V_B_PORCH_STA_REG		0x2a
+
+/* Total Pixel Status Low Byte Register */
+#define SP_TOTAL_PIXEL_STAL_REG		0x2b
+
+/* Total Pixel Status High Byte Register */
+#define SP_TOTAL_PIXEL_STAH_REG		0x2c
+
+/* Active Pixel Status Low Byte Register */
+#define SP_ACT_PIXEL_STAL_REG		0x2d
+
+/* Active Pixel Status High Byte Register */
+#define SP_ACT_PIXEL_STAH_REG		0x2e
+
+/* Horizontal Front Porch Status Low Byte Register */
+#define SP_H_F_PORCH_STAL_REG		0x2f
+
+/* Horizontal Front Porch Statys High Byte Register */
+#define SP_H_F_PORCH_STAH_REG		0x30
+
+/* Horizontal SYNC Width Status Low Byte Register */
+#define SP_H_SYNC_STAL_REG		0x31
+
+/* Horizontal SYNC Width Status High Byte Register */
+#define SP_H_SYNC_STAH_REG		0x32
+
+/* Horizontal Back Porch Status Low Byte Register */
+#define SP_H_B_PORCH_STAL_REG		0x33
+
+/* Horizontal Back Porch Status High Byte Register */
+#define SP_H_B_PORCH_STAH_REG		0x34
+
+/* InfoFrame AVI Packet DB1 Register */
+#define SP_INFOFRAME_AVI_DB1_REG	0x70
+
+/* Bit Control Specific Register */
+#define SP_BIT_CTRL_SPECIFIC_REG	0x80
+#define SP_BIT_CTRL_SELECT_SHIFT	1
+#define SP_ENABLE_BIT_CTRL		BIT(0)
+
+/* InfoFrame Audio Packet DB1 Register */
+#define SP_INFOFRAME_AUD_DB1_REG	0x83
+
+/* InfoFrame MPEG Packet DB1 Register */
+#define SP_INFOFRAME_MPEG_DB1_REG	0xb0
+
+/* Audio Channel Status Registers */
+#define SP_AUD_CH_STATUS_BASE		0xd0
+
+/* Audio Channel Num Register 5 */
+#define SP_I2S_CHANNEL_NUM_MASK		0xe0
+#  define SP_I2S_CH_NUM_1		(0x00 << 5)
+#  define SP_I2S_CH_NUM_2		(0x01 << 5)
+#  define SP_I2S_CH_NUM_3		(0x02 << 5)
+#  define SP_I2S_CH_NUM_4		(0x03 << 5)
+#  define SP_I2S_CH_NUM_5		(0x04 << 5)
+#  define SP_I2S_CH_NUM_6		(0x05 << 5)
+#  define SP_I2S_CH_NUM_7		(0x06 << 5)
+#  define SP_I2S_CH_NUM_8		(0x07 << 5)
+#define SP_EXT_VUCP			BIT(2)
+#define SP_VBIT				BIT(1)
+#define SP_AUDIO_LAYOUT			BIT(0)
+
+/* Analog Debug Register 1 */
+#define SP_ANALOG_DEBUG1_REG		0xdc
+
+/* Analog Debug Register 2 */
+#define SP_ANALOG_DEBUG2_REG		0xdd
+#define SP_FORCE_SW_OFF_BYPASS		0x20
+#define SP_XTAL_FRQ			0x1c
+#  define SP_XTAL_FRQ_19M2		(0x00 << 2)
+#  define SP_XTAL_FRQ_24M		(0x01 << 2)
+#  define SP_XTAL_FRQ_25M		(0x02 << 2)
+#  define SP_XTAL_FRQ_26M		(0x03 << 2)
+#  define SP_XTAL_FRQ_27M		(0x04 << 2)
+#  define SP_XTAL_FRQ_38M4		(0x05 << 2)
+#  define SP_XTAL_FRQ_52M		(0x06 << 2)
+#define SP_POWERON_TIME_1P5MS		0x03
+
+/* Analog Control 0 Register */
+#define SP_ANALOG_CTRL0_REG		0xe1
+
+/* Common Interrupt Status Register 1 */
+#define SP_COMMON_INT_STATUS_BASE	(0xf1 - 1)
+#define SP_PLL_LOCK_CHG			0x40
+
+/* Common Interrupt Status Register 2 */
+#define SP_COMMON_INT_STATUS2		0xf2
+#define SP_HDCP_AUTH_CHG		BIT(1)
+#define SP_HDCP_AUTH_DONE		BIT(0)
+
+#define SP_HDCP_LINK_CHECK_FAIL		BIT(0)
+
+/* Common Interrupt Status Register 4 */
+#define SP_COMMON_INT_STATUS4_REG	0xf4
+#define SP_HPD_IRQ			BIT(6)
+#define SP_HPD_ESYNC_ERR		BIT(4)
+#define SP_HPD_CHG			BIT(2)
+#define SP_HPD_LOST			BIT(1)
+#define SP_HPD_PLUG			BIT(0)
+
+/* DP Interrupt Status Register */
+#define SP_DP_INT_STATUS1_REG		0xf7
+#define SP_TRAINING_FINISH		BIT(5)
+#define SP_POLLING_ERR			BIT(4)
+
+/* Common Interrupt Mask Register */
+#define SP_COMMON_INT_MASK_BASE		(0xf8 - 1)
+
+#define SP_COMMON_INT_MASK4_REG		0xfb
+
+/* DP Interrupts Mask Register */
+#define SP_DP_INT_MASK1_REG		0xfe
+
+/* Interrupt Control Register */
+#define SP_INT_CTRL_REG			0xff
+
+#endif /* _ANALOGIX_I2C_TXCOMMON_H_ */
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index bb411fe52ae8..6effe532f820 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1111,7 +1111,7 @@ static int analogix_dp_get_modes(struct drm_connector *connector)
 	int ret, num_modes = 0;
 
 	if (dp->plat_data->panel) {
-		num_modes += drm_panel_get_modes(dp->plat_data->panel);
+		num_modes += drm_panel_get_modes(dp->plat_data->panel, connector);
 	} else {
 		ret = analogix_dp_prepare_panel(dp, true, false);
 		if (ret) {
diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
index 3a5bd4e7fd1e..b7c97f060241 100644
--- a/drivers/gpu/drm/bridge/cdns-dsi.c
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -512,7 +512,7 @@ static int cdns_dsi_mode2cfg(struct cdns_dsi *dsi,
 	struct cdns_dsi_output *output = &dsi->output;
 	unsigned int tmp;
 	bool sync_pulse = false;
-	int bpp, nlanes;
+	int bpp;
 
 	memset(dsi_cfg, 0, sizeof(*dsi_cfg));
 
@@ -520,7 +520,6 @@ static int cdns_dsi_mode2cfg(struct cdns_dsi *dsi,
 		sync_pulse = true;
 
 	bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format);
-	nlanes = output->dev->lanes;
 
 	if (mode_valid_check)
 		tmp = mode->htotal -
@@ -785,13 +784,12 @@ static void cdns_dsi_bridge_enable(struct drm_bridge *bridge)
 	unsigned long tx_byte_period;
 	struct cdns_dsi_cfg dsi_cfg;
 	u32 tmp, reg_wakeup, div;
-	int bpp, nlanes;
+	int nlanes;
 
 	if (WARN_ON(pm_runtime_get_sync(dsi->base.dev) < 0))
 		return;
 
 	mode = &bridge->encoder->crtc->state->adjusted_mode;
-	bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format);
 	nlanes = output->dev->lanes;
 
 	WARN_ON_ONCE(cdns_dsi_check_conf(dsi, mode, &dsi_cfg, false));
diff --git a/drivers/gpu/drm/bridge/lvds-codec.c b/drivers/gpu/drm/bridge/lvds-codec.c
new file mode 100644
index 000000000000..5f04cc11227e
--- /dev/null
+++ b/drivers/gpu/drm/bridge/lvds-codec.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2019 Renesas Electronics Corporation
+ * Copyright (C) 2016 Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ */
+
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_graph.h>
+#include <linux/platform_device.h>
+
+#include <drm/drm_bridge.h>
+#include <drm/drm_panel.h>
+
+struct lvds_codec {
+	struct drm_bridge bridge;
+	struct drm_bridge *panel_bridge;
+	struct gpio_desc *powerdown_gpio;
+	u32 connector_type;
+};
+
+static int lvds_codec_attach(struct drm_bridge *bridge)
+{
+	struct lvds_codec *lvds_codec = container_of(bridge,
+						     struct lvds_codec, bridge);
+
+	return drm_bridge_attach(bridge->encoder, lvds_codec->panel_bridge,
+				 bridge);
+}
+
+static void lvds_codec_enable(struct drm_bridge *bridge)
+{
+	struct lvds_codec *lvds_codec = container_of(bridge,
+						     struct lvds_codec, bridge);
+
+	if (lvds_codec->powerdown_gpio)
+		gpiod_set_value_cansleep(lvds_codec->powerdown_gpio, 0);
+}
+
+static void lvds_codec_disable(struct drm_bridge *bridge)
+{
+	struct lvds_codec *lvds_codec = container_of(bridge,
+						     struct lvds_codec, bridge);
+
+	if (lvds_codec->powerdown_gpio)
+		gpiod_set_value_cansleep(lvds_codec->powerdown_gpio, 1);
+}
+
+static struct drm_bridge_funcs funcs = {
+	.attach = lvds_codec_attach,
+	.enable = lvds_codec_enable,
+	.disable = lvds_codec_disable,
+};
+
+static int lvds_codec_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *panel_node;
+	struct drm_panel *panel;
+	struct lvds_codec *lvds_codec;
+
+	lvds_codec = devm_kzalloc(dev, sizeof(*lvds_codec), GFP_KERNEL);
+	if (!lvds_codec)
+		return -ENOMEM;
+
+	lvds_codec->connector_type = (uintptr_t)of_device_get_match_data(dev);
+	lvds_codec->powerdown_gpio = devm_gpiod_get_optional(dev, "powerdown",
+							     GPIOD_OUT_HIGH);
+	if (IS_ERR(lvds_codec->powerdown_gpio)) {
+		int err = PTR_ERR(lvds_codec->powerdown_gpio);
+
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "powerdown GPIO failure: %d\n", err);
+		return err;
+	}
+
+	/* Locate the panel DT node. */
+	panel_node = of_graph_get_remote_node(dev->of_node, 1, 0);
+	if (!panel_node) {
+		dev_dbg(dev, "panel DT node not found\n");
+		return -ENXIO;
+	}
+
+	panel = of_drm_find_panel(panel_node);
+	of_node_put(panel_node);
+	if (IS_ERR(panel)) {
+		dev_dbg(dev, "panel not found, deferring probe\n");
+		return PTR_ERR(panel);
+	}
+
+	lvds_codec->panel_bridge =
+		devm_drm_panel_bridge_add_typed(dev, panel,
+						lvds_codec->connector_type);
+	if (IS_ERR(lvds_codec->panel_bridge))
+		return PTR_ERR(lvds_codec->panel_bridge);
+
+	/*
+	 * The panel_bridge bridge is attached to the panel's of_node,
+	 * but we need a bridge attached to our of_node for our user
+	 * to look up.
+	 */
+	lvds_codec->bridge.of_node = dev->of_node;
+	lvds_codec->bridge.funcs = &funcs;
+	drm_bridge_add(&lvds_codec->bridge);
+
+	platform_set_drvdata(pdev, lvds_codec);
+
+	return 0;
+}
+
+static int lvds_codec_remove(struct platform_device *pdev)
+{
+	struct lvds_codec *lvds_codec = platform_get_drvdata(pdev);
+
+	drm_bridge_remove(&lvds_codec->bridge);
+
+	return 0;
+}
+
+static const struct of_device_id lvds_codec_match[] = {
+	{
+		.compatible = "lvds-decoder",
+		.data = (void *)DRM_MODE_CONNECTOR_DPI,
+	},
+	{
+		.compatible = "lvds-encoder",
+		.data = (void *)DRM_MODE_CONNECTOR_LVDS,
+	},
+	{
+		.compatible = "thine,thc63lvdm83d",
+		.data = (void *)DRM_MODE_CONNECTOR_LVDS,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, lvds_codec_match);
+
+static struct platform_driver lvds_codec_driver = {
+	.probe	= lvds_codec_probe,
+	.remove	= lvds_codec_remove,
+	.driver		= {
+		.name		= "lvds-codec",
+		.of_match_table	= lvds_codec_match,
+	},
+};
+module_platform_driver(lvds_codec_driver);
+
+MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
+MODULE_DESCRIPTION("LVDS encoders and decoders");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/bridge/lvds-encoder.c b/drivers/gpu/drm/bridge/lvds-encoder.c
deleted file mode 100644
index e2132a8d5106..000000000000
--- a/drivers/gpu/drm/bridge/lvds-encoder.c
+++ /dev/null
@@ -1,155 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2016 Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- */
-
-#include <linux/gpio/consumer.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_graph.h>
-#include <linux/platform_device.h>
-
-#include <drm/drm_bridge.h>
-#include <drm/drm_panel.h>
-
-struct lvds_encoder {
-	struct drm_bridge bridge;
-	struct drm_bridge *panel_bridge;
-	struct gpio_desc *powerdown_gpio;
-};
-
-static int lvds_encoder_attach(struct drm_bridge *bridge)
-{
-	struct lvds_encoder *lvds_encoder = container_of(bridge,
-							 struct lvds_encoder,
-							 bridge);
-
-	return drm_bridge_attach(bridge->encoder, lvds_encoder->panel_bridge,
-				 bridge);
-}
-
-static void lvds_encoder_enable(struct drm_bridge *bridge)
-{
-	struct lvds_encoder *lvds_encoder = container_of(bridge,
-							 struct lvds_encoder,
-							 bridge);
-
-	if (lvds_encoder->powerdown_gpio)
-		gpiod_set_value_cansleep(lvds_encoder->powerdown_gpio, 0);
-}
-
-static void lvds_encoder_disable(struct drm_bridge *bridge)
-{
-	struct lvds_encoder *lvds_encoder = container_of(bridge,
-							 struct lvds_encoder,
-							 bridge);
-
-	if (lvds_encoder->powerdown_gpio)
-		gpiod_set_value_cansleep(lvds_encoder->powerdown_gpio, 1);
-}
-
-static struct drm_bridge_funcs funcs = {
-	.attach = lvds_encoder_attach,
-	.enable = lvds_encoder_enable,
-	.disable = lvds_encoder_disable,
-};
-
-static int lvds_encoder_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct device_node *port;
-	struct device_node *endpoint;
-	struct device_node *panel_node;
-	struct drm_panel *panel;
-	struct lvds_encoder *lvds_encoder;
-
-	lvds_encoder = devm_kzalloc(dev, sizeof(*lvds_encoder), GFP_KERNEL);
-	if (!lvds_encoder)
-		return -ENOMEM;
-
-	lvds_encoder->powerdown_gpio = devm_gpiod_get_optional(dev, "powerdown",
-							       GPIOD_OUT_HIGH);
-	if (IS_ERR(lvds_encoder->powerdown_gpio)) {
-		int err = PTR_ERR(lvds_encoder->powerdown_gpio);
-
-		if (err != -EPROBE_DEFER)
-			dev_err(dev, "powerdown GPIO failure: %d\n", err);
-		return err;
-	}
-
-	/* Locate the panel DT node. */
-	port = of_graph_get_port_by_id(dev->of_node, 1);
-	if (!port) {
-		dev_dbg(dev, "port 1 not found\n");
-		return -ENXIO;
-	}
-
-	endpoint = of_get_child_by_name(port, "endpoint");
-	of_node_put(port);
-	if (!endpoint) {
-		dev_dbg(dev, "no endpoint for port 1\n");
-		return -ENXIO;
-	}
-
-	panel_node = of_graph_get_remote_port_parent(endpoint);
-	of_node_put(endpoint);
-	if (!panel_node) {
-		dev_dbg(dev, "no remote endpoint for port 1\n");
-		return -ENXIO;
-	}
-
-	panel = of_drm_find_panel(panel_node);
-	of_node_put(panel_node);
-	if (IS_ERR(panel)) {
-		dev_dbg(dev, "panel not found, deferring probe\n");
-		return PTR_ERR(panel);
-	}
-
-	lvds_encoder->panel_bridge =
-		devm_drm_panel_bridge_add_typed(dev, panel,
-						DRM_MODE_CONNECTOR_LVDS);
-	if (IS_ERR(lvds_encoder->panel_bridge))
-		return PTR_ERR(lvds_encoder->panel_bridge);
-
-	/* The panel_bridge bridge is attached to the panel's of_node,
-	 * but we need a bridge attached to our of_node for our user
-	 * to look up.
-	 */
-	lvds_encoder->bridge.of_node = dev->of_node;
-	lvds_encoder->bridge.funcs = &funcs;
-	drm_bridge_add(&lvds_encoder->bridge);
-
-	platform_set_drvdata(pdev, lvds_encoder);
-
-	return 0;
-}
-
-static int lvds_encoder_remove(struct platform_device *pdev)
-{
-	struct lvds_encoder *lvds_encoder = platform_get_drvdata(pdev);
-
-	drm_bridge_remove(&lvds_encoder->bridge);
-
-	return 0;
-}
-
-static const struct of_device_id lvds_encoder_match[] = {
-	{ .compatible = "lvds-encoder" },
-	{ .compatible = "thine,thc63lvdm83d" },
-	{},
-};
-MODULE_DEVICE_TABLE(of, lvds_encoder_match);
-
-static struct platform_driver lvds_encoder_driver = {
-	.probe	= lvds_encoder_probe,
-	.remove	= lvds_encoder_remove,
-	.driver		= {
-		.name		= "lvds-encoder",
-		.of_match_table	= lvds_encoder_match,
-	},
-};
-module_platform_driver(lvds_encoder_driver);
-
-MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
-MODULE_DESCRIPTION("Transparent parallel to LVDS encoder");
-MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index f4e293e7cf64..f66777e24968 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -37,7 +37,7 @@ static int panel_bridge_connector_get_modes(struct drm_connector *connector)
 	struct panel_bridge *panel_bridge =
 		drm_connector_to_panel_bridge(connector);
 
-	return drm_panel_get_modes(panel_bridge->panel);
+	return drm_panel_get_modes(panel_bridge->panel, connector);
 }
 
 static const struct drm_connector_helper_funcs
@@ -289,3 +289,21 @@ struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev,
 	return bridge;
 }
 EXPORT_SYMBOL(devm_drm_panel_bridge_add_typed);
+
+/**
+ * drm_panel_bridge_connector - return the connector for the panel bridge
+ *
+ * drm_panel_bridge creates the connector.
+ * This function gives external access to the connector.
+ *
+ * Returns: Pointer to drm_connector
+ */
+struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge)
+{
+	struct panel_bridge *panel_bridge;
+
+	panel_bridge = drm_bridge_to_panel_bridge(bridge);
+
+	return &panel_bridge->connector;
+}
+EXPORT_SYMBOL(drm_panel_bridge_connector);
diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c
index b7a72dfdcac3..10c47c008b40 100644
--- a/drivers/gpu/drm/bridge/parade-ps8622.c
+++ b/drivers/gpu/drm/bridge/parade-ps8622.c
@@ -461,7 +461,7 @@ static int ps8622_get_modes(struct drm_connector *connector)
 
 	ps8622 = connector_to_ps8622(connector);
 
-	return drm_panel_get_modes(ps8622->panel);
+	return drm_panel_get_modes(ps8622->panel, connector);
 }
 
 static const struct drm_connector_helper_funcs ps8622_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
index 2b7539701b42..dd56996fe9c7 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
@@ -291,7 +291,7 @@ static irqreturn_t snd_dw_hdmi_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static struct snd_pcm_hardware dw_hdmi_hw = {
+static const struct snd_pcm_hardware dw_hdmi_hw = {
 	.info = SNDRV_PCM_INFO_INTERLEAVED |
 		SNDRV_PCM_INFO_BLOCK_TRANSFER |
 		SNDRV_PCM_INFO_MMAP |
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
index b6e793bb653c..b18351b6760a 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
@@ -719,7 +719,15 @@ static void dw_mipi_dsi_vertical_timing_config(struct dw_mipi_dsi *dsi,
 
 static void dw_mipi_dsi_dphy_timing_config(struct dw_mipi_dsi *dsi)
 {
+	const struct dw_mipi_dsi_phy_ops *phy_ops = dsi->plat_data->phy_ops;
+	struct dw_mipi_dsi_dphy_timing timing;
 	u32 hw_version;
+	int ret;
+
+	ret = phy_ops->get_timing(dsi->plat_data->priv_data,
+				  dsi->lane_mbps, &timing);
+	if (ret)
+		DRM_DEV_ERROR(dsi->dev, "Retrieving phy timings failed\n");
 
 	/*
 	 * TODO dw drv improvements
@@ -732,16 +740,20 @@ static void dw_mipi_dsi_dphy_timing_config(struct dw_mipi_dsi *dsi)
 	hw_version = dsi_read(dsi, DSI_VERSION) & VERSION;
 
 	if (hw_version >= HWVER_131) {
-		dsi_write(dsi, DSI_PHY_TMR_CFG, PHY_HS2LP_TIME_V131(0x40) |
-			  PHY_LP2HS_TIME_V131(0x40));
+		dsi_write(dsi, DSI_PHY_TMR_CFG,
+			  PHY_HS2LP_TIME_V131(timing.data_hs2lp) |
+			  PHY_LP2HS_TIME_V131(timing.data_lp2hs));
 		dsi_write(dsi, DSI_PHY_TMR_RD_CFG, MAX_RD_TIME_V131(10000));
 	} else {
-		dsi_write(dsi, DSI_PHY_TMR_CFG, PHY_HS2LP_TIME(0x40) |
-			  PHY_LP2HS_TIME(0x40) | MAX_RD_TIME(10000));
+		dsi_write(dsi, DSI_PHY_TMR_CFG,
+			  PHY_HS2LP_TIME(timing.data_hs2lp) |
+			  PHY_LP2HS_TIME(timing.data_lp2hs) |
+			  MAX_RD_TIME(10000));
 	}
 
-	dsi_write(dsi, DSI_PHY_TMR_LPCLK_CFG, PHY_CLKHS2LP_TIME(0x40)
-		  | PHY_CLKLP2HS_TIME(0x40));
+	dsi_write(dsi, DSI_PHY_TMR_LPCLK_CFG,
+		  PHY_CLKHS2LP_TIME(timing.clk_hs2lp) |
+		  PHY_CLKLP2HS_TIME(timing.clk_lp2hs));
 }
 
 static void dw_mipi_dsi_dphy_interface_config(struct dw_mipi_dsi *dsi)
@@ -798,9 +810,6 @@ static void dw_mipi_dsi_bridge_post_disable(struct drm_bridge *bridge)
 	struct dw_mipi_dsi *dsi = bridge_to_dsi(bridge);
 	const struct dw_mipi_dsi_phy_ops *phy_ops = dsi->plat_data->phy_ops;
 
-	if (phy_ops->power_off)
-		phy_ops->power_off(dsi->plat_data->priv_data);
-
 	/*
 	 * Switch to command mode before panel-bridge post_disable &
 	 * panel unprepare.
@@ -817,6 +826,9 @@ static void dw_mipi_dsi_bridge_post_disable(struct drm_bridge *bridge)
 	 */
 	dsi->panel_bridge->funcs->post_disable(dsi->panel_bridge);
 
+	if (phy_ops->power_off)
+		phy_ops->power_off(dsi->plat_data->priv_data);
+
 	if (dsi->slave) {
 		dw_mipi_dsi_disable(dsi->slave);
 		clk_disable_unprepare(dsi->slave->pclk);
@@ -883,6 +895,9 @@ static void dw_mipi_dsi_mode_set(struct dw_mipi_dsi *dsi,
 
 	/* Switch to cmd mode for panel-bridge pre_enable & panel prepare */
 	dw_mipi_dsi_set_mode(dsi, 0);
+
+	if (phy_ops->power_on)
+		phy_ops->power_on(dsi->plat_data->priv_data);
 }
 
 static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge,
@@ -899,15 +914,11 @@ static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge,
 static void dw_mipi_dsi_bridge_enable(struct drm_bridge *bridge)
 {
 	struct dw_mipi_dsi *dsi = bridge_to_dsi(bridge);
-	const struct dw_mipi_dsi_phy_ops *phy_ops = dsi->plat_data->phy_ops;
 
 	/* Switch to video mode for panel-bridge enable & panel enable */
 	dw_mipi_dsi_set_mode(dsi, MIPI_DSI_MODE_VIDEO);
 	if (dsi->slave)
 		dw_mipi_dsi_set_mode(dsi->slave, MIPI_DSI_MODE_VIDEO);
-
-	if (phy_ops->power_on)
-		phy_ops->power_on(dsi->plat_data->priv_data);
 }
 
 static enum drm_mode_status
@@ -991,7 +1002,8 @@ __dw_mipi_dsi_probe(struct platform_device *pdev,
 	dsi->dev = dev;
 	dsi->plat_data = plat_data;
 
-	if (!plat_data->phy_ops->init || !plat_data->phy_ops->get_lane_mbps) {
+	if (!plat_data->phy_ops->init || !plat_data->phy_ops->get_lane_mbps ||
+	    !plat_data->phy_ops->get_timing) {
 		DRM_ERROR("Phy not properly configured\n");
 		return ERR_PTR(-ENODEV);
 	}
diff --git a/drivers/gpu/drm/bridge/tc358764.c b/drivers/gpu/drm/bridge/tc358764.c
index db298f550a5a..96207fcfde19 100644
--- a/drivers/gpu/drm/bridge/tc358764.c
+++ b/drivers/gpu/drm/bridge/tc358764.c
@@ -282,7 +282,7 @@ static int tc358764_get_modes(struct drm_connector *connector)
 {
 	struct tc358764 *ctx = connector_to_tc358764(connector);
 
-	return drm_panel_get_modes(ctx->panel);
+	return drm_panel_get_modes(ctx->panel, connector);
 }
 
 static const
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 8029478ffebb..3709e5ace724 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -1346,7 +1346,7 @@ static int tc_connector_get_modes(struct drm_connector *connector)
 		return 0;
 	}
 
-	count = drm_panel_get_modes(tc->panel);
+	count = drm_panel_get_modes(tc->panel, connector);
 	if (count > 0)
 		return count;
 
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 43abf01ebd4c..9a2dd986afa5 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -206,7 +206,7 @@ static int ti_sn_bridge_connector_get_modes(struct drm_connector *connector)
 {
 	struct ti_sn_bridge *pdata = connector_to_ti_sn_bridge(connector);
 
-	return drm_panel_get_modes(pdata->panel);
+	return drm_panel_get_modes(pdata->panel, connector);
 }
 
 static enum drm_mode_status
diff --git a/drivers/gpu/drm/drm_agpsupport.c b/drivers/gpu/drm/drm_agpsupport.c
index 6e09f27fd9d6..4c7ad46fdd21 100644
--- a/drivers/gpu/drm/drm_agpsupport.c
+++ b/drivers/gpu/drm/drm_agpsupport.c
@@ -212,7 +212,7 @@ int drm_agp_alloc(struct drm_device *dev, struct drm_agp_buffer *request)
 	if (!entry)
 		return -ENOMEM;
 
-	pages = (request->size + PAGE_SIZE - 1) / PAGE_SIZE;
+	pages = DIV_ROUND_UP(request->size, PAGE_SIZE);
 	type = (u32) request->type;
 	memory = agp_allocate_memory(dev->agp->bridge, pages, type);
 	if (!memory) {
@@ -325,7 +325,7 @@ int drm_agp_bind(struct drm_device *dev, struct drm_agp_binding *request)
 	entry = drm_agp_lookup_entry(dev, request->handle);
 	if (!entry || entry->bound)
 		return -EINVAL;
-	page = (request->offset + PAGE_SIZE - 1) / PAGE_SIZE;
+	page = DIV_ROUND_UP(request->offset, PAGE_SIZE);
 	retcode = drm_bind_agp(entry->memory, page);
 	if (retcode)
 		return retcode;
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 14aeaf736321..d33691512a8e 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -251,7 +251,7 @@ EXPORT_SYMBOL(drm_atomic_state_clear);
  * @ref: This atomic state to deallocate
  *
  * This frees all memory associated with an atomic state, including all the
- * per-object state for planes, crtcs and connectors.
+ * per-object state for planes, CRTCs and connectors.
  */
 void __drm_atomic_state_free(struct kref *ref)
 {
@@ -272,12 +272,12 @@ void __drm_atomic_state_free(struct kref *ref)
 EXPORT_SYMBOL(__drm_atomic_state_free);
 
 /**
- * drm_atomic_get_crtc_state - get crtc state
+ * drm_atomic_get_crtc_state - get CRTC state
  * @state: global atomic state object
- * @crtc: crtc to get state object for
+ * @crtc: CRTC to get state object for
  *
- * This function returns the crtc state for the given crtc, allocating it if
- * needed. It will also grab the relevant crtc lock to make sure that the state
+ * This function returns the CRTC state for the given CRTC, allocating it if
+ * needed. It will also grab the relevant CRTC lock to make sure that the state
  * is consistent.
  *
  * Returns:
@@ -688,10 +688,12 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
  * associated state struct &drm_private_state.
  *
  * Similar to userspace-exposed objects, private state structures can be
- * acquired by calling drm_atomic_get_private_obj_state(). Since this function
- * does not take care of locking, drivers should wrap it for each type of
- * private state object they have with the required call to drm_modeset_lock()
- * for the corresponding &drm_modeset_lock.
+ * acquired by calling drm_atomic_get_private_obj_state(). This also takes care
+ * of locking, hence drivers should not have a need to call drm_modeset_lock()
+ * directly. Sequence of the actual hardware state commit is not handled,
+ * drivers might need to keep track of struct drm_crtc_commit within subclassed
+ * structure of &drm_private_state as necessary, e.g. similar to
+ * &drm_plane_state.commit. See also &drm_atomic_state.fake_commit.
  *
  * All private state structures contained in a &drm_atomic_state update can be
  * iterated using for_each_oldnew_private_obj_in_state(),
@@ -1016,14 +1018,14 @@ static void drm_atomic_connector_print_state(struct drm_printer *p,
 }
 
 /**
- * drm_atomic_add_affected_connectors - add connectors for crtc
+ * drm_atomic_add_affected_connectors - add connectors for CRTC
  * @state: atomic state
- * @crtc: DRM crtc
+ * @crtc: DRM CRTC
  *
  * This function walks the current configuration and adds all connectors
  * currently using @crtc to the atomic configuration @state. Note that this
  * function must acquire the connection mutex. This can potentially cause
- * unneeded seralization if the update is just for the planes on one crtc. Hence
+ * unneeded seralization if the update is just for the planes on one CRTC. Hence
  * drivers and helpers should only call this when really needed (e.g. when a
  * full modeset needs to happen due to some change).
  *
@@ -1076,9 +1078,9 @@ drm_atomic_add_affected_connectors(struct drm_atomic_state *state,
 EXPORT_SYMBOL(drm_atomic_add_affected_connectors);
 
 /**
- * drm_atomic_add_affected_planes - add planes for crtc
+ * drm_atomic_add_affected_planes - add planes for CRTC
  * @state: atomic state
- * @crtc: DRM crtc
+ * @crtc: DRM CRTC
  *
  * This function walks the current configuration and adds all planes
  * currently used by @crtc to the atomic configuration @state. This is useful
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index b191d39c071d..4511c2e07bb9 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -150,8 +150,8 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 	 * is not set, an error is returned. Userspace can provide a solution
 	 * through the atomic ioctl.
 	 *
-	 * If the flag is set conflicting connectors are removed from the crtc
-	 * and the crtc is disabled if no encoder is left. This preserves
+	 * If the flag is set conflicting connectors are removed from the CRTC
+	 * and the CRTC is disabled if no encoder is left. This preserves
 	 * compatibility with the legacy set_config behavior.
 	 */
 	drm_connector_list_iter_begin(state->dev, &conn_iter);
@@ -220,7 +220,7 @@ set_best_encoder(struct drm_atomic_state *state,
 		crtc = conn_state->connector->state->crtc;
 
 		/* A NULL crtc is an error here because we should have
-		 *  duplicated a NULL best_encoder when crtc was NULL.
+		 * duplicated a NULL best_encoder when crtc was NULL.
 		 * As an exception restoring duplicated atomic state
 		 * during resume is allowed, so don't warn when
 		 * best_encoder is equal to encoder we intend to set.
@@ -419,6 +419,7 @@ mode_fixup(struct drm_atomic_state *state)
 	for_each_new_connector_in_state(state, connector, new_conn_state, i) {
 		const struct drm_encoder_helper_funcs *funcs;
 		struct drm_encoder *encoder;
+		struct drm_bridge *bridge;
 
 		WARN_ON(!!new_conn_state->best_encoder != !!new_conn_state->crtc);
 
@@ -435,8 +436,10 @@ mode_fixup(struct drm_atomic_state *state)
 		encoder = new_conn_state->best_encoder;
 		funcs = encoder->helper_private;
 
-		ret = drm_bridge_mode_fixup(encoder->bridge, &new_crtc_state->mode,
-				&new_crtc_state->adjusted_mode);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		ret = drm_bridge_chain_mode_fixup(bridge,
+					&new_crtc_state->mode,
+					&new_crtc_state->adjusted_mode);
 		if (!ret) {
 			DRM_DEBUG_ATOMIC("Bridge fixup failed\n");
 			return -EINVAL;
@@ -492,6 +495,7 @@ static enum drm_mode_status mode_valid_path(struct drm_connector *connector,
 					    struct drm_crtc *crtc,
 					    const struct drm_display_mode *mode)
 {
+	struct drm_bridge *bridge;
 	enum drm_mode_status ret;
 
 	ret = drm_encoder_mode_valid(encoder, mode);
@@ -501,7 +505,8 @@ static enum drm_mode_status mode_valid_path(struct drm_connector *connector,
 		return ret;
 	}
 
-	ret = drm_bridge_mode_valid(encoder->bridge, mode);
+	bridge = drm_bridge_chain_get_first_bridge(encoder);
+	ret = drm_bridge_chain_mode_valid(bridge, mode);
 	if (ret != MODE_OK) {
 		DRM_DEBUG_ATOMIC("[BRIDGE] mode_valid() failed\n");
 		return ret;
@@ -556,27 +561,27 @@ mode_valid(struct drm_atomic_state *state)
  * @state: the driver state object
  *
  * Check the state object to see if the requested state is physically possible.
- * This does all the crtc and connector related computations for an atomic
+ * This does all the CRTC and connector related computations for an atomic
  * update and adds any additional connectors needed for full modesets. It calls
  * the various per-object callbacks in the follow order:
  *
  * 1. &drm_connector_helper_funcs.atomic_best_encoder for determining the new encoder.
  * 2. &drm_connector_helper_funcs.atomic_check to validate the connector state.
- * 3. If it's determined a modeset is needed then all connectors on the affected crtc
- *    crtc are added and &drm_connector_helper_funcs.atomic_check is run on them.
+ * 3. If it's determined a modeset is needed then all connectors on the affected
+ *    CRTC are added and &drm_connector_helper_funcs.atomic_check is run on them.
  * 4. &drm_encoder_helper_funcs.mode_valid, &drm_bridge_funcs.mode_valid and
  *    &drm_crtc_helper_funcs.mode_valid are called on the affected components.
  * 5. &drm_bridge_funcs.mode_fixup is called on all encoder bridges.
  * 6. &drm_encoder_helper_funcs.atomic_check is called to validate any encoder state.
- *    This function is only called when the encoder will be part of a configured crtc,
+ *    This function is only called when the encoder will be part of a configured CRTC,
  *    it must not be used for implementing connector property validation.
  *    If this function is NULL, &drm_atomic_encoder_helper_funcs.mode_fixup is called
  *    instead.
- * 7. &drm_crtc_helper_funcs.mode_fixup is called last, to fix up the mode with crtc constraints.
+ * 7. &drm_crtc_helper_funcs.mode_fixup is called last, to fix up the mode with CRTC constraints.
  *
  * &drm_crtc_state.mode_changed is set when the input mode is changed.
  * &drm_crtc_state.connectors_changed is set when a connector is added or
- * removed from the crtc.  &drm_crtc_state.active_changed is set when
+ * removed from the CRTC.  &drm_crtc_state.active_changed is set when
  * &drm_crtc_state.active changes, which is used for DPMS.
  * See also: drm_atomic_crtc_needs_modeset()
  *
@@ -687,7 +692,7 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 
 	/*
 	 * After all the routing has been prepared we need to add in any
-	 * connector which is itself unchanged, but whose crtc changes its
+	 * connector which is itself unchanged, but whose CRTC changes its
 	 * configuration. This must be done before calling mode_fixup in case a
 	 * crtc only changed its mode but has the same set of connectors.
 	 */
@@ -736,13 +741,13 @@ EXPORT_SYMBOL(drm_atomic_helper_check_modeset);
 /**
  * drm_atomic_helper_check_plane_state() - Check plane state for validity
  * @plane_state: plane state to check
- * @crtc_state: crtc state to check
+ * @crtc_state: CRTC state to check
  * @min_scale: minimum @src:@dest scaling factor in 16.16 fixed point
  * @max_scale: maximum @src:@dest scaling factor in 16.16 fixed point
  * @can_position: is it legal to position the plane such that it
- *                doesn't cover the entire crtc?  This will generally
+ *                doesn't cover the entire CRTC?  This will generally
  *                only be false for primary planes.
- * @can_update_disabled: can the plane be updated while the crtc
+ * @can_update_disabled: can the plane be updated while the CRTC
  *                       is disabled?
  *
  * Checks that a desired plane update is valid, and updates various
@@ -839,7 +844,7 @@ EXPORT_SYMBOL(drm_atomic_helper_check_plane_state);
  * &drm_crtc_helper_funcs.atomic_check and &drm_plane_helper_funcs.atomic_check
  * hooks provided by the driver.
  *
- * It also sets &drm_crtc_state.planes_changed to indicate that a crtc has
+ * It also sets &drm_crtc_state.planes_changed to indicate that a CRTC has
  * updated planes.
  *
  * RETURNS:
@@ -903,7 +908,7 @@ EXPORT_SYMBOL(drm_atomic_helper_check_planes);
  * @state: the driver state object
  *
  * Check the state object to see if the requested state is physically possible.
- * Only crtcs and planes have check callbacks, so for any additional (global)
+ * Only CRTCs and planes have check callbacks, so for any additional (global)
  * checking that a driver needs it can simply wrap that around this function.
  * Drivers without such needs can directly use this as their
  * &drm_mode_config_funcs.atomic_check callback.
@@ -956,14 +961,14 @@ crtc_needs_disable(struct drm_crtc_state *old_state,
 		   struct drm_crtc_state *new_state)
 {
 	/*
-	 * No new_state means the crtc is off, so the only criteria is whether
+	 * No new_state means the CRTC is off, so the only criteria is whether
 	 * it's currently active or in self refresh mode.
 	 */
 	if (!new_state)
 		return drm_atomic_crtc_effectively_active(old_state);
 
 	/*
-	 * We need to run through the crtc_funcs->disable() function if the crtc
+	 * We need to run through the crtc_funcs->disable() function if the CRTC
 	 * is currently on, if it's transitioning to self refresh mode, or if
 	 * it's in self refresh mode and needs to be fully disabled.
 	 */
@@ -984,6 +989,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
 	for_each_oldnew_connector_in_state(old_state, connector, old_conn_state, new_conn_state, i) {
 		const struct drm_encoder_helper_funcs *funcs;
 		struct drm_encoder *encoder;
+		struct drm_bridge *bridge;
 
 		/* Shut down everything that's in the changeset and currently
 		 * still on. So need to check the old, saved state. */
@@ -1020,7 +1026,8 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
 		 * Each encoder has at most one connector (since we always steal
 		 * it away), so we won't call disable hooks twice.
 		 */
-		drm_atomic_bridge_disable(encoder->bridge, old_state);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		drm_atomic_bridge_chain_disable(bridge, old_state);
 
 		/* Right function depends upon target state. */
 		if (funcs) {
@@ -1034,7 +1041,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
 				funcs->dpms(encoder, DRM_MODE_DPMS_OFF);
 		}
 
-		drm_atomic_bridge_post_disable(encoder->bridge, old_state);
+		drm_atomic_bridge_chain_post_disable(bridge, old_state);
 	}
 
 	for_each_oldnew_crtc_in_state(old_state, crtc, old_crtc_state, new_crtc_state, i) {
@@ -1080,7 +1087,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
  * @old_state: atomic state object with old state structures
  *
  * This function updates all the various legacy modeset state pointers in
- * connectors, encoders and crtcs. It also updates the timestamping constants
+ * connectors, encoders and CRTCs. It also updates the timestamping constants
  * used for precise vblank timestamps by calling
  * drm_calc_timestamping_constants().
  *
@@ -1188,6 +1195,7 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *old_state)
 		const struct drm_encoder_helper_funcs *funcs;
 		struct drm_encoder *encoder;
 		struct drm_display_mode *mode, *adjusted_mode;
+		struct drm_bridge *bridge;
 
 		if (!new_conn_state->best_encoder)
 			continue;
@@ -1215,7 +1223,8 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *old_state)
 			funcs->mode_set(encoder, mode, adjusted_mode);
 		}
 
-		drm_bridge_mode_set(encoder->bridge, mode, adjusted_mode);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		drm_bridge_chain_mode_set(bridge, mode, adjusted_mode);
 	}
 }
 
@@ -1227,7 +1236,7 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *old_state)
  * This function shuts down all the outputs that need to be shut down and
  * prepares them (if required) with the new mode.
  *
- * For compatibility with legacy crtc helpers this should be called before
+ * For compatibility with legacy CRTC helpers this should be called before
  * drm_atomic_helper_commit_planes(), which is what the default commit function
  * does. But drivers with different needs can group the modeset commits together
  * and do the plane commits at the end. This is useful for drivers doing runtime
@@ -1273,7 +1282,7 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev,
  * This function enables all the outputs with the new configuration which had to
  * be turned off for the update.
  *
- * For compatibility with legacy crtc helpers this should be called after
+ * For compatibility with legacy CRTC helpers this should be called after
  * drm_atomic_helper_commit_planes(), which is what the default commit function
  * does. But drivers with different needs can group the modeset commits together
  * and do the plane commits at the end. This is useful for drivers doing runtime
@@ -1314,6 +1323,7 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 	for_each_new_connector_in_state(old_state, connector, new_conn_state, i) {
 		const struct drm_encoder_helper_funcs *funcs;
 		struct drm_encoder *encoder;
+		struct drm_bridge *bridge;
 
 		if (!new_conn_state->best_encoder)
 			continue;
@@ -1332,7 +1342,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 		 * Each encoder has at most one connector (since we always steal
 		 * it away), so we won't call enable hooks twice.
 		 */
-		drm_atomic_bridge_pre_enable(encoder->bridge, old_state);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		drm_atomic_bridge_chain_pre_enable(bridge, old_state);
 
 		if (funcs) {
 			if (funcs->atomic_enable)
@@ -1343,7 +1354,7 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 				funcs->commit(encoder);
 		}
 
-		drm_atomic_bridge_enable(encoder->bridge, old_state);
+		drm_atomic_bridge_chain_enable(bridge, old_state);
 	}
 
 	drm_atomic_helper_commit_writebacks(dev, old_state);
@@ -1403,12 +1414,12 @@ int drm_atomic_helper_wait_for_fences(struct drm_device *dev,
 EXPORT_SYMBOL(drm_atomic_helper_wait_for_fences);
 
 /**
- * drm_atomic_helper_wait_for_vblanks - wait for vblank on crtcs
+ * drm_atomic_helper_wait_for_vblanks - wait for vblank on CRTCs
  * @dev: DRM device
  * @old_state: atomic state object with old state structures
  *
- * Helper to, after atomic commit, wait for vblanks on all effected
- * crtcs (ie. before cleaning up old framebuffers using
+ * Helper to, after atomic commit, wait for vblanks on all affected
+ * CRTCs (ie. before cleaning up old framebuffers using
  * drm_atomic_helper_cleanup_planes()). It will only wait on CRTCs where the
  * framebuffers have actually changed to optimize for the legacy cursor and
  * plane update use-case.
@@ -1467,10 +1478,10 @@ EXPORT_SYMBOL(drm_atomic_helper_wait_for_vblanks);
  * @dev: DRM device
  * @old_state: atomic state object with old state structures
  *
- * Helper to, after atomic commit, wait for page flips on all effected
+ * Helper to, after atomic commit, wait for page flips on all affected
  * crtcs (ie. before cleaning up old framebuffers using
  * drm_atomic_helper_cleanup_planes()). Compared to
- * drm_atomic_helper_wait_for_vblanks() this waits for the completion of on all
+ * drm_atomic_helper_wait_for_vblanks() this waits for the completion on all
  * CRTCs, assuming that cursors-only updates are signalling their completion
  * immediately (or using a different path).
  *
@@ -1834,17 +1845,21 @@ EXPORT_SYMBOL(drm_atomic_helper_commit);
 /**
  * DOC: implementing nonblocking commit
  *
- * Nonblocking atomic commits have to be implemented in the following sequence:
+ * Nonblocking atomic commits should use struct &drm_crtc_commit to sequence
+ * different operations against each another. Locks, especially struct
+ * &drm_modeset_lock, should not be held in worker threads or any other
+ * asynchronous context used to commit the hardware state.
+ *
+ * drm_atomic_helper_commit() implements the recommended sequence for
+ * nonblocking commits, using drm_atomic_helper_setup_commit() internally:
  *
- * 1. Run drm_atomic_helper_prepare_planes() first. This is the only function
- * which commit needs to call which can fail, so we want to run it first and
+ * 1. Run drm_atomic_helper_prepare_planes(). Since this can fail and we
+ * need to propagate out of memory/VRAM errors to userspace, it must be called
  * synchronously.
  *
  * 2. Synchronize with any outstanding nonblocking commit worker threads which
- * might be affected the new state update. This can be done by either cancelling
- * or flushing the work items, depending upon whether the driver can deal with
- * cancelled updates. Note that it is important to ensure that the framebuffer
- * cleanup is still done when cancelling.
+ * might be affected by the new state update. This is handled by
+ * drm_atomic_helper_setup_commit().
  *
  * Asynchronous workers need to have sufficient parallelism to be able to run
  * different atomic commits on different CRTCs in parallel. The simplest way to
@@ -1855,21 +1870,29 @@ EXPORT_SYMBOL(drm_atomic_helper_commit);
  * must be done as one global operation, and enabling or disabling a CRTC can
  * take a long time. But even that is not required.
  *
+ * IMPORTANT: A &drm_atomic_state update for multiple CRTCs is sequenced
+ * against all CRTCs therein. Therefore for atomic state updates which only flip
+ * planes the driver must not get the struct &drm_crtc_state of unrelated CRTCs
+ * in its atomic check code: This would prevent committing of atomic updates to
+ * multiple CRTCs in parallel. In general, adding additional state structures
+ * should be avoided as much as possible, because this reduces parallelism in
+ * (nonblocking) commits, both due to locking and due to commit sequencing
+ * requirements.
+ *
  * 3. The software state is updated synchronously with
  * drm_atomic_helper_swap_state(). Doing this under the protection of all modeset
- * locks means concurrent callers never see inconsistent state. And doing this
- * while it's guaranteed that no relevant nonblocking worker runs means that
- * nonblocking workers do not need grab any locks. Actually they must not grab
- * locks, for otherwise the work flushing will deadlock.
+ * locks means concurrent callers never see inconsistent state. Note that commit
+ * workers do not hold any locks; their access is only coordinated through
+ * ordering. If workers would access state only through the pointers in the
+ * free-standing state objects (currently not the case for any driver) then even
+ * multiple pending commits could be in-flight at the same time.
  *
  * 4. Schedule a work item to do all subsequent steps, using the split-out
  * commit helpers: a) pre-plane commit b) plane commit c) post-plane commit and
  * then cleaning up the framebuffers after the old framebuffer is no longer
- * being displayed.
- *
- * The above scheme is implemented in the atomic helper libraries in
- * drm_atomic_helper_commit() using a bunch of helper functions. See
- * drm_atomic_helper_setup_commit() for a starting point.
+ * being displayed. The scheduled work should synchronize against other workers
+ * using the &drm_crtc_commit infrastructure as needed. See
+ * drm_atomic_helper_setup_commit() for more details.
  */
 
 static int stall_checks(struct drm_crtc *crtc, bool nonblock)
@@ -2098,7 +2121,7 @@ EXPORT_SYMBOL(drm_atomic_helper_setup_commit);
  *
  * This function waits for all preceeding commits that touch the same CRTC as
  * @old_state to both be committed to the hardware (as signalled by
- * drm_atomic_helper_commit_hw_done) and executed by the hardware (as signalled
+ * drm_atomic_helper_commit_hw_done()) and executed by the hardware (as signalled
  * by calling drm_crtc_send_vblank_event() on the &drm_crtc_state.event).
  *
  * This is part of the atomic helper support for nonblocking commits, see
@@ -2185,7 +2208,7 @@ EXPORT_SYMBOL(drm_atomic_helper_wait_for_dependencies);
  * drm_atomic_helper_fake_vblank - fake VBLANK events if needed
  * @old_state: atomic state object with old state structures
  *
- * This function walks all CRTCs and fake VBLANK events on those with
+ * This function walks all CRTCs and fakes VBLANK events on those with
  * &drm_crtc_state.no_vblank set to true and &drm_crtc_state.event != NULL.
  * The primary use of this function is writeback connectors working in oneshot
  * mode and faking VBLANK events. In this case they only fake the VBLANK event
@@ -2381,7 +2404,7 @@ static bool plane_crtc_active(const struct drm_plane_state *state)
  * @flags: flags for committing plane state
  *
  * This function commits the new plane state using the plane and atomic helper
- * functions for planes and crtcs. It assumes that the atomic state has already
+ * functions for planes and CRTCs. It assumes that the atomic state has already
  * been pushed into the relevant object state pointers, since this step can no
  * longer fail.
  *
@@ -2502,15 +2525,15 @@ void drm_atomic_helper_commit_planes(struct drm_device *dev,
 EXPORT_SYMBOL(drm_atomic_helper_commit_planes);
 
 /**
- * drm_atomic_helper_commit_planes_on_crtc - commit plane state for a crtc
- * @old_crtc_state: atomic state object with the old crtc state
+ * drm_atomic_helper_commit_planes_on_crtc - commit plane state for a CRTC
+ * @old_crtc_state: atomic state object with the old CRTC state
  *
  * This function commits the new plane state using the plane and atomic helper
- * functions for planes on the specific crtc. It assumes that the atomic state
+ * functions for planes on the specific CRTC. It assumes that the atomic state
  * has already been pushed into the relevant object state pointers, since this
  * step can no longer fail.
  *
- * This function is useful when plane updates should be done crtc-by-crtc
+ * This function is useful when plane updates should be done CRTC-by-CRTC
  * instead of one global step like drm_atomic_helper_commit_planes() does.
  *
  * This function can only be savely used when planes are not allowed to move
@@ -2800,10 +2823,10 @@ EXPORT_SYMBOL(drm_atomic_helper_swap_state);
  * @plane: plane object to update
  * @crtc: owning CRTC of owning plane
  * @fb: framebuffer to flip onto plane
- * @crtc_x: x offset of primary plane on crtc
- * @crtc_y: y offset of primary plane on crtc
- * @crtc_w: width of primary plane rectangle on crtc
- * @crtc_h: height of primary plane rectangle on crtc
+ * @crtc_x: x offset of primary plane on @crtc
+ * @crtc_y: y offset of primary plane on @crtc
+ * @crtc_w: width of primary plane rectangle on @crtc
+ * @crtc_h: height of primary plane rectangle on @crtc
  * @src_x: x offset of @fb for panning
  * @src_y: y offset of @fb for panning
  * @src_w: width of source rectangle in @fb
@@ -2909,7 +2932,7 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_plane);
  * @set: mode set configuration
  * @ctx: lock acquisition context
  *
- * Provides a default crtc set_config handler using the atomic driver interface.
+ * Provides a default CRTC set_config handler using the atomic driver interface.
  *
  * NOTE: For backwards compatibility with old userspace this automatically
  * resets the "link-status" property to GOOD, to force any link
@@ -3322,7 +3345,7 @@ static int page_flip_common(struct drm_atomic_state *state,
 
 /**
  * drm_atomic_helper_page_flip - execute a legacy page flip
- * @crtc: DRM crtc
+ * @crtc: DRM CRTC
  * @fb: DRM framebuffer
  * @event: optional DRM event to signal upon completion
  * @flags: flip flags for non-vblank sync'ed updates
@@ -3366,7 +3389,7 @@ EXPORT_SYMBOL(drm_atomic_helper_page_flip);
 
 /**
  * drm_atomic_helper_page_flip_target - do page flip on target vblank period.
- * @crtc: DRM crtc
+ * @crtc: DRM CRTC
  * @fb: DRM framebuffer
  * @event: optional DRM event to signal upon completion
  * @flags: flip flags for non-vblank sync'ed updates
diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c
index d0a937fb0c56..7cf3cf936547 100644
--- a/drivers/gpu/drm/drm_atomic_state_helper.c
+++ b/drivers/gpu/drm/drm_atomic_state_helper.c
@@ -58,6 +58,22 @@
  */
 
 /**
+ * __drm_atomic_helper_crtc_state_reset - reset the CRTC state
+ * @crtc_state: atomic CRTC state, must not be NULL
+ * @crtc: CRTC object, must not be NULL
+ *
+ * Initializes the newly allocated @crtc_state with default
+ * values. This is useful for drivers that subclass the CRTC state.
+ */
+void
+__drm_atomic_helper_crtc_state_reset(struct drm_crtc_state *crtc_state,
+				     struct drm_crtc *crtc)
+{
+	crtc_state->crtc = crtc;
+}
+EXPORT_SYMBOL(__drm_atomic_helper_crtc_state_reset);
+
+/**
  * __drm_atomic_helper_crtc_reset - reset state on CRTC
  * @crtc: drm CRTC
  * @crtc_state: CRTC state to assign
@@ -74,7 +90,7 @@ __drm_atomic_helper_crtc_reset(struct drm_crtc *crtc,
 			       struct drm_crtc_state *crtc_state)
 {
 	if (crtc_state)
-		crtc_state->crtc = crtc;
+		__drm_atomic_helper_crtc_state_reset(crtc_state, crtc);
 
 	crtc->state = crtc_state;
 }
@@ -212,23 +228,43 @@ void drm_atomic_helper_crtc_destroy_state(struct drm_crtc *crtc,
 EXPORT_SYMBOL(drm_atomic_helper_crtc_destroy_state);
 
 /**
- * __drm_atomic_helper_plane_reset - resets planes state to default values
+ * __drm_atomic_helper_plane_state_reset - resets plane state to default values
+ * @plane_state: atomic plane state, must not be NULL
  * @plane: plane object, must not be NULL
- * @state: atomic plane state, must not be NULL
  *
- * Initializes plane state to default. This is useful for drivers that subclass
- * the plane state.
+ * Initializes the newly allocated @plane_state with default
+ * values. This is useful for drivers that subclass the CRTC state.
  */
-void __drm_atomic_helper_plane_reset(struct drm_plane *plane,
-				     struct drm_plane_state *state)
+void __drm_atomic_helper_plane_state_reset(struct drm_plane_state *plane_state,
+					   struct drm_plane *plane)
 {
-	state->plane = plane;
-	state->rotation = DRM_MODE_ROTATE_0;
+	plane_state->plane = plane;
+	plane_state->rotation = DRM_MODE_ROTATE_0;
 
-	state->alpha = DRM_BLEND_ALPHA_OPAQUE;
-	state->pixel_blend_mode = DRM_MODE_BLEND_PREMULTI;
+	plane_state->alpha = DRM_BLEND_ALPHA_OPAQUE;
+	plane_state->pixel_blend_mode = DRM_MODE_BLEND_PREMULTI;
+}
+EXPORT_SYMBOL(__drm_atomic_helper_plane_state_reset);
 
-	plane->state = state;
+/**
+ * __drm_atomic_helper_plane_reset - reset state on plane
+ * @plane: drm plane
+ * @plane_state: plane state to assign
+ *
+ * Initializes the newly allocated @plane_state and assigns it to
+ * the &drm_crtc->state pointer of @plane, usually required when
+ * initializing the drivers or when called from the &drm_plane_funcs.reset
+ * hook.
+ *
+ * This is useful for drivers that subclass the plane state.
+ */
+void __drm_atomic_helper_plane_reset(struct drm_plane *plane,
+				     struct drm_plane_state *plane_state)
+{
+	if (plane_state)
+		__drm_atomic_helper_plane_state_reset(plane_state, plane);
+
+	plane->state = plane_state;
 }
 EXPORT_SYMBOL(__drm_atomic_helper_plane_reset);
 
@@ -336,6 +372,22 @@ void drm_atomic_helper_plane_destroy_state(struct drm_plane *plane,
 EXPORT_SYMBOL(drm_atomic_helper_plane_destroy_state);
 
 /**
+ * __drm_atomic_helper_connector_state_reset - reset the connector state
+ * @conn_state: atomic connector state, must not be NULL
+ * @connector: connectotr object, must not be NULL
+ *
+ * Initializes the newly allocated @conn_state with default
+ * values. This is useful for drivers that subclass the connector state.
+ */
+void
+__drm_atomic_helper_connector_state_reset(struct drm_connector_state *conn_state,
+					  struct drm_connector *connector)
+{
+	conn_state->connector = connector;
+}
+EXPORT_SYMBOL(__drm_atomic_helper_connector_state_reset);
+
+/**
  * __drm_atomic_helper_connector_reset - reset state on connector
  * @connector: drm connector
  * @conn_state: connector state to assign
@@ -352,7 +404,7 @@ __drm_atomic_helper_connector_reset(struct drm_connector *connector,
 				    struct drm_connector_state *conn_state)
 {
 	if (conn_state)
-		conn_state->connector = connector;
+		__drm_atomic_helper_connector_state_reset(conn_state, connector);
 
 	connector->state = conn_state;
 }
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index 0d466d3b0809..a1e5e262bae2 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -160,12 +160,12 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 EXPORT_SYMBOL(drm_atomic_set_mode_prop_for_crtc);
 
 /**
- * drm_atomic_set_crtc_for_plane - set crtc for plane
+ * drm_atomic_set_crtc_for_plane - set CRTC for plane
  * @plane_state: the plane whose incoming state to update
- * @crtc: crtc to use for the plane
+ * @crtc: CRTC to use for the plane
  *
- * Changing the assigned crtc for a plane requires us to grab the lock and state
- * for the new crtc, as needed. This function takes care of all these details
+ * Changing the assigned CRTC for a plane requires us to grab the lock and state
+ * for the new CRTC, as needed. This function takes care of all these details
  * besides updating the pointer in the state object itself.
  *
  * Returns:
@@ -279,12 +279,12 @@ drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state,
 EXPORT_SYMBOL(drm_atomic_set_fence_for_plane);
 
 /**
- * drm_atomic_set_crtc_for_connector - set crtc for connector
+ * drm_atomic_set_crtc_for_connector - set CRTC for connector
  * @conn_state: atomic state object for the connector
- * @crtc: crtc to use for the connector
+ * @crtc: CRTC to use for the connector
  *
- * Changing the assigned crtc for a connector requires us to grab the lock and
- * state for the new crtc, as needed. This function takes care of all these
+ * Changing the assigned CRTC for a connector requires us to grab the lock and
+ * state for the new CRTC, as needed. This function takes care of all these
  * details besides updating the pointer in the state object itself.
  *
  * Returns:
diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c
index cba537c99e43..c2cf0c90fa26 100644
--- a/drivers/gpu/drm/drm_bridge.c
+++ b/drivers/gpu/drm/drm_bridge.c
@@ -55,7 +55,7 @@
  * just provide additional hooks to get the desired output at the end of the
  * encoder chain.
  *
- * Bridges can also be chained up using the &drm_bridge.next pointer.
+ * Bridges can also be chained up using the &drm_bridge.chain_node field.
  *
  * Both legacy CRTC helpers and the new atomic modeset helpers support bridges.
  */
@@ -128,20 +128,21 @@ int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge,
 	bridge->dev = encoder->dev;
 	bridge->encoder = encoder;
 
+	if (previous)
+		list_add(&bridge->chain_node, &previous->chain_node);
+	else
+		list_add(&bridge->chain_node, &encoder->bridge_chain);
+
 	if (bridge->funcs->attach) {
 		ret = bridge->funcs->attach(bridge);
 		if (ret < 0) {
+			list_del(&bridge->chain_node);
 			bridge->dev = NULL;
 			bridge->encoder = NULL;
 			return ret;
 		}
 	}
 
-	if (previous)
-		previous->next = bridge;
-	else
-		encoder->bridge = bridge;
-
 	return 0;
 }
 EXPORT_SYMBOL(drm_bridge_attach);
@@ -157,6 +158,7 @@ void drm_bridge_detach(struct drm_bridge *bridge)
 	if (bridge->funcs->detach)
 		bridge->funcs->detach(bridge);
 
+	list_del(&bridge->chain_node);
 	bridge->dev = NULL;
 }
 
@@ -172,8 +174,8 @@ void drm_bridge_detach(struct drm_bridge *bridge)
  */
 
 /**
- * drm_bridge_mode_fixup - fixup proposed mode for all bridges in the
- *			   encoder chain
+ * drm_bridge_chain_mode_fixup - fixup proposed mode for all bridges in the
+ *				 encoder chain
  * @bridge: bridge control structure
  * @mode: desired mode to be set for the bridge
  * @adjusted_mode: updated mode that works for this bridge
@@ -186,27 +188,31 @@ void drm_bridge_detach(struct drm_bridge *bridge)
  * RETURNS:
  * true on success, false on failure
  */
-bool drm_bridge_mode_fixup(struct drm_bridge *bridge,
-			const struct drm_display_mode *mode,
-			struct drm_display_mode *adjusted_mode)
+bool drm_bridge_chain_mode_fixup(struct drm_bridge *bridge,
+				 const struct drm_display_mode *mode,
+				 struct drm_display_mode *adjusted_mode)
 {
-	bool ret = true;
+	struct drm_encoder *encoder;
 
 	if (!bridge)
 		return true;
 
-	if (bridge->funcs->mode_fixup)
-		ret = bridge->funcs->mode_fixup(bridge, mode, adjusted_mode);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (!bridge->funcs->mode_fixup)
+			continue;
 
-	ret = ret && drm_bridge_mode_fixup(bridge->next, mode, adjusted_mode);
+		if (!bridge->funcs->mode_fixup(bridge, mode, adjusted_mode))
+			return false;
+	}
 
-	return ret;
+	return true;
 }
-EXPORT_SYMBOL(drm_bridge_mode_fixup);
+EXPORT_SYMBOL(drm_bridge_chain_mode_fixup);
 
 /**
- * drm_bridge_mode_valid - validate the mode against all bridges in the
- * 			   encoder chain.
+ * drm_bridge_chain_mode_valid - validate the mode against all bridges in the
+ *				 encoder chain.
  * @bridge: bridge control structure
  * @mode: desired mode to be validated
  *
@@ -219,26 +225,33 @@ EXPORT_SYMBOL(drm_bridge_mode_fixup);
  * RETURNS:
  * MODE_OK on success, drm_mode_status Enum error code on failure
  */
-enum drm_mode_status drm_bridge_mode_valid(struct drm_bridge *bridge,
-					   const struct drm_display_mode *mode)
+enum drm_mode_status
+drm_bridge_chain_mode_valid(struct drm_bridge *bridge,
+			    const struct drm_display_mode *mode)
 {
-	enum drm_mode_status ret = MODE_OK;
+	struct drm_encoder *encoder;
 
 	if (!bridge)
-		return ret;
+		return MODE_OK;
 
-	if (bridge->funcs->mode_valid)
-		ret = bridge->funcs->mode_valid(bridge, mode);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		enum drm_mode_status ret;
 
-	if (ret != MODE_OK)
-		return ret;
+		if (!bridge->funcs->mode_valid)
+			continue;
 
-	return drm_bridge_mode_valid(bridge->next, mode);
+		ret = bridge->funcs->mode_valid(bridge, mode);
+		if (ret != MODE_OK)
+			return ret;
+	}
+
+	return MODE_OK;
 }
-EXPORT_SYMBOL(drm_bridge_mode_valid);
+EXPORT_SYMBOL(drm_bridge_chain_mode_valid);
 
 /**
- * drm_bridge_disable - disables all bridges in the encoder chain
+ * drm_bridge_chain_disable - disables all bridges in the encoder chain
  * @bridge: bridge control structure
  *
  * Calls &drm_bridge_funcs.disable op for all the bridges in the encoder
@@ -247,20 +260,28 @@ EXPORT_SYMBOL(drm_bridge_mode_valid);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_disable(struct drm_bridge *bridge)
+void drm_bridge_chain_disable(struct drm_bridge *bridge)
 {
+	struct drm_encoder *encoder;
+	struct drm_bridge *iter;
+
 	if (!bridge)
 		return;
 
-	drm_bridge_disable(bridge->next);
+	encoder = bridge->encoder;
+	list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) {
+		if (iter->funcs->disable)
+			iter->funcs->disable(iter);
 
-	if (bridge->funcs->disable)
-		bridge->funcs->disable(bridge);
+		if (iter == bridge)
+			break;
+	}
 }
-EXPORT_SYMBOL(drm_bridge_disable);
+EXPORT_SYMBOL(drm_bridge_chain_disable);
 
 /**
- * drm_bridge_post_disable - cleans up after disabling all bridges in the encoder chain
+ * drm_bridge_chain_post_disable - cleans up after disabling all bridges in the
+ *				   encoder chain
  * @bridge: bridge control structure
  *
  * Calls &drm_bridge_funcs.post_disable op for all the bridges in the
@@ -269,47 +290,53 @@ EXPORT_SYMBOL(drm_bridge_disable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_post_disable(struct drm_bridge *bridge)
+void drm_bridge_chain_post_disable(struct drm_bridge *bridge)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->post_disable)
-		bridge->funcs->post_disable(bridge);
-
-	drm_bridge_post_disable(bridge->next);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->post_disable)
+			bridge->funcs->post_disable(bridge);
+	}
 }
-EXPORT_SYMBOL(drm_bridge_post_disable);
+EXPORT_SYMBOL(drm_bridge_chain_post_disable);
 
 /**
- * drm_bridge_mode_set - set proposed mode for all bridges in the
- *			 encoder chain
+ * drm_bridge_chain_mode_set - set proposed mode for all bridges in the
+ *			       encoder chain
  * @bridge: bridge control structure
- * @mode: desired mode to be set for the bridge
- * @adjusted_mode: updated mode that works for this bridge
+ * @mode: desired mode to be set for the encoder chain
+ * @adjusted_mode: updated mode that works for this encoder chain
  *
  * Calls &drm_bridge_funcs.mode_set op for all the bridges in the
  * encoder chain, starting from the first bridge to the last.
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_mode_set(struct drm_bridge *bridge,
-			 const struct drm_display_mode *mode,
-			 const struct drm_display_mode *adjusted_mode)
+void drm_bridge_chain_mode_set(struct drm_bridge *bridge,
+			       const struct drm_display_mode *mode,
+			       const struct drm_display_mode *adjusted_mode)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->mode_set)
-		bridge->funcs->mode_set(bridge, mode, adjusted_mode);
-
-	drm_bridge_mode_set(bridge->next, mode, adjusted_mode);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->mode_set)
+			bridge->funcs->mode_set(bridge, mode, adjusted_mode);
+	}
 }
-EXPORT_SYMBOL(drm_bridge_mode_set);
+EXPORT_SYMBOL(drm_bridge_chain_mode_set);
 
 /**
- * drm_bridge_pre_enable - prepares for enabling all
- *			   bridges in the encoder chain
+ * drm_bridge_chain_pre_enable - prepares for enabling all bridges in the
+ *				 encoder chain
  * @bridge: bridge control structure
  *
  * Calls &drm_bridge_funcs.pre_enable op for all the bridges in the encoder
@@ -318,20 +345,24 @@ EXPORT_SYMBOL(drm_bridge_mode_set);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_pre_enable(struct drm_bridge *bridge)
+void drm_bridge_chain_pre_enable(struct drm_bridge *bridge)
 {
+	struct drm_encoder *encoder;
+	struct drm_bridge *iter;
+
 	if (!bridge)
 		return;
 
-	drm_bridge_pre_enable(bridge->next);
-
-	if (bridge->funcs->pre_enable)
-		bridge->funcs->pre_enable(bridge);
+	encoder = bridge->encoder;
+	list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) {
+		if (iter->funcs->pre_enable)
+			iter->funcs->pre_enable(iter);
+	}
 }
-EXPORT_SYMBOL(drm_bridge_pre_enable);
+EXPORT_SYMBOL(drm_bridge_chain_pre_enable);
 
 /**
- * drm_bridge_enable - enables all bridges in the encoder chain
+ * drm_bridge_chain_enable - enables all bridges in the encoder chain
  * @bridge: bridge control structure
  *
  * Calls &drm_bridge_funcs.enable op for all the bridges in the encoder
@@ -340,22 +371,25 @@ EXPORT_SYMBOL(drm_bridge_pre_enable);
  *
  * Note that the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_enable(struct drm_bridge *bridge)
+void drm_bridge_chain_enable(struct drm_bridge *bridge)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->enable)
-		bridge->funcs->enable(bridge);
-
-	drm_bridge_enable(bridge->next);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->enable)
+			bridge->funcs->enable(bridge);
+	}
 }
-EXPORT_SYMBOL(drm_bridge_enable);
+EXPORT_SYMBOL(drm_bridge_chain_enable);
 
 /**
- * drm_atomic_bridge_disable - disables all bridges in the encoder chain
+ * drm_atomic_bridge_chain_disable - disables all bridges in the encoder chain
  * @bridge: bridge control structure
- * @state: atomic state being committed
+ * @old_state: old atomic state
  *
  * Calls &drm_bridge_funcs.atomic_disable (falls back on
  * &drm_bridge_funcs.disable) op for all the bridges in the encoder chain,
@@ -364,26 +398,33 @@ EXPORT_SYMBOL(drm_bridge_enable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_atomic_bridge_disable(struct drm_bridge *bridge,
-			       struct drm_atomic_state *state)
+void drm_atomic_bridge_chain_disable(struct drm_bridge *bridge,
+				     struct drm_atomic_state *old_state)
 {
+	struct drm_encoder *encoder;
+	struct drm_bridge *iter;
+
 	if (!bridge)
 		return;
 
-	drm_atomic_bridge_disable(bridge->next, state);
+	encoder = bridge->encoder;
+	list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) {
+		if (iter->funcs->atomic_disable)
+			iter->funcs->atomic_disable(iter, old_state);
+		else if (iter->funcs->disable)
+			iter->funcs->disable(iter);
 
-	if (bridge->funcs->atomic_disable)
-		bridge->funcs->atomic_disable(bridge, state);
-	else if (bridge->funcs->disable)
-		bridge->funcs->disable(bridge);
+		if (iter == bridge)
+			break;
+	}
 }
-EXPORT_SYMBOL(drm_atomic_bridge_disable);
+EXPORT_SYMBOL(drm_atomic_bridge_chain_disable);
 
 /**
- * drm_atomic_bridge_post_disable - cleans up after disabling all bridges in the
- *				    encoder chain
+ * drm_atomic_bridge_chain_post_disable - cleans up after disabling all bridges
+ *					  in the encoder chain
  * @bridge: bridge control structure
- * @state: atomic state being committed
+ * @old_state: old atomic state
  *
  * Calls &drm_bridge_funcs.atomic_post_disable (falls back on
  * &drm_bridge_funcs.post_disable) op for all the bridges in the encoder chain,
@@ -392,26 +433,29 @@ EXPORT_SYMBOL(drm_atomic_bridge_disable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_atomic_bridge_post_disable(struct drm_bridge *bridge,
-				    struct drm_atomic_state *state)
+void drm_atomic_bridge_chain_post_disable(struct drm_bridge *bridge,
+					  struct drm_atomic_state *old_state)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->atomic_post_disable)
-		bridge->funcs->atomic_post_disable(bridge, state);
-	else if (bridge->funcs->post_disable)
-		bridge->funcs->post_disable(bridge);
-
-	drm_atomic_bridge_post_disable(bridge->next, state);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->atomic_post_disable)
+			bridge->funcs->atomic_post_disable(bridge, old_state);
+		else if (bridge->funcs->post_disable)
+			bridge->funcs->post_disable(bridge);
+	}
 }
-EXPORT_SYMBOL(drm_atomic_bridge_post_disable);
+EXPORT_SYMBOL(drm_atomic_bridge_chain_post_disable);
 
 /**
- * drm_atomic_bridge_pre_enable - prepares for enabling all bridges in the
- *				  encoder chain
+ * drm_atomic_bridge_chain_pre_enable - prepares for enabling all bridges in
+ *					the encoder chain
  * @bridge: bridge control structure
- * @state: atomic state being committed
+ * @old_state: old atomic state
  *
  * Calls &drm_bridge_funcs.atomic_pre_enable (falls back on
  * &drm_bridge_funcs.pre_enable) op for all the bridges in the encoder chain,
@@ -420,25 +464,32 @@ EXPORT_SYMBOL(drm_atomic_bridge_post_disable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_atomic_bridge_pre_enable(struct drm_bridge *bridge,
-				  struct drm_atomic_state *state)
+void drm_atomic_bridge_chain_pre_enable(struct drm_bridge *bridge,
+					struct drm_atomic_state *old_state)
 {
+	struct drm_encoder *encoder;
+	struct drm_bridge *iter;
+
 	if (!bridge)
 		return;
 
-	drm_atomic_bridge_pre_enable(bridge->next, state);
+	encoder = bridge->encoder;
+	list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) {
+		if (iter->funcs->atomic_pre_enable)
+			iter->funcs->atomic_pre_enable(iter, old_state);
+		else if (iter->funcs->pre_enable)
+			iter->funcs->pre_enable(iter);
 
-	if (bridge->funcs->atomic_pre_enable)
-		bridge->funcs->atomic_pre_enable(bridge, state);
-	else if (bridge->funcs->pre_enable)
-		bridge->funcs->pre_enable(bridge);
+		if (iter == bridge)
+			break;
+	}
 }
-EXPORT_SYMBOL(drm_atomic_bridge_pre_enable);
+EXPORT_SYMBOL(drm_atomic_bridge_chain_pre_enable);
 
 /**
- * drm_atomic_bridge_enable - enables all bridges in the encoder chain
+ * drm_atomic_bridge_chain_enable - enables all bridges in the encoder chain
  * @bridge: bridge control structure
- * @state: atomic state being committed
+ * @old_state: old atomic state
  *
  * Calls &drm_bridge_funcs.atomic_enable (falls back on
  * &drm_bridge_funcs.enable) op for all the bridges in the encoder chain,
@@ -447,20 +498,23 @@ EXPORT_SYMBOL(drm_atomic_bridge_pre_enable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_atomic_bridge_enable(struct drm_bridge *bridge,
-			      struct drm_atomic_state *state)
+void drm_atomic_bridge_chain_enable(struct drm_bridge *bridge,
+				    struct drm_atomic_state *old_state)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->atomic_enable)
-		bridge->funcs->atomic_enable(bridge, state);
-	else if (bridge->funcs->enable)
-		bridge->funcs->enable(bridge);
-
-	drm_atomic_bridge_enable(bridge->next, state);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->atomic_enable)
+			bridge->funcs->atomic_enable(bridge, old_state);
+		else if (bridge->funcs->enable)
+			bridge->funcs->enable(bridge);
+	}
 }
-EXPORT_SYMBOL(drm_atomic_bridge_enable);
+EXPORT_SYMBOL(drm_atomic_bridge_chain_enable);
 
 #ifdef CONFIG_OF
 /**
diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
index d9a2e3695525..b031b45aa8ef 100644
--- a/drivers/gpu/drm/drm_client.c
+++ b/drivers/gpu/drm/drm_client.c
@@ -150,7 +150,7 @@ void drm_client_release(struct drm_client_dev *client)
 {
 	struct drm_device *dev = client->dev;
 
-	DRM_DEV_DEBUG_KMS(dev->dev, "%s\n", client->name);
+	drm_dbg_kms(dev, "%s\n", client->name);
 
 	drm_client_modeset_free(client);
 	drm_client_close(client);
@@ -203,7 +203,7 @@ void drm_client_dev_hotplug(struct drm_device *dev)
 			continue;
 
 		ret = client->funcs->hotplug(client);
-		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+		drm_dbg_kms(dev, "%s: ret=%d\n", client->name, ret);
 	}
 	mutex_unlock(&dev->clientlist_mutex);
 }
@@ -223,7 +223,7 @@ void drm_client_dev_restore(struct drm_device *dev)
 			continue;
 
 		ret = client->funcs->restore(client);
-		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+		drm_dbg_kms(dev, "%s: ret=%d\n", client->name, ret);
 		if (!ret) /* The first one to return zero gets the privilege to restore */
 			break;
 	}
@@ -351,8 +351,8 @@ static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer)
 
 	ret = drm_mode_rmfb(buffer->client->dev, buffer->fb->base.id, buffer->client->file);
 	if (ret)
-		DRM_DEV_ERROR(buffer->client->dev->dev,
-			      "Error removing FB:%u (%d)\n", buffer->fb->base.id, ret);
+		drm_err(buffer->client->dev,
+			"Error removing FB:%u (%d)\n", buffer->fb->base.id, ret);
 
 	buffer->fb = NULL;
 }
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 895b73f23079..6d4a29e99ae2 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -115,6 +115,33 @@ drm_client_find_modeset(struct drm_client_dev *client, struct drm_crtc *crtc)
 }
 
 static struct drm_display_mode *
+drm_connector_get_tiled_mode(struct drm_connector *connector)
+{
+	struct drm_display_mode *mode;
+
+	list_for_each_entry(mode, &connector->modes, head) {
+		if (mode->hdisplay == connector->tile_h_size &&
+		    mode->vdisplay == connector->tile_v_size)
+			return mode;
+	}
+	return NULL;
+}
+
+static struct drm_display_mode *
+drm_connector_fallback_non_tiled_mode(struct drm_connector *connector)
+{
+	struct drm_display_mode *mode;
+
+	list_for_each_entry(mode, &connector->modes, head) {
+		if (mode->hdisplay == connector->tile_h_size &&
+		    mode->vdisplay == connector->tile_v_size)
+			continue;
+		return mode;
+	}
+	return NULL;
+}
+
+static struct drm_display_mode *
 drm_connector_has_preferred_mode(struct drm_connector *connector, int width, int height)
 {
 	struct drm_display_mode *mode;
@@ -348,8 +375,15 @@ static bool drm_client_target_preferred(struct drm_connector **connectors,
 	struct drm_connector *connector;
 	u64 conn_configured = 0;
 	int tile_pass = 0;
+	int num_tiled_conns = 0;
 	int i;
 
+	for (i = 0; i < connector_count; i++) {
+		if (connectors[i]->has_tile &&
+		    connectors[i]->status == connector_status_connected)
+			num_tiled_conns++;
+	}
+
 retry:
 	for (i = 0; i < connector_count; i++) {
 		connector = connectors[i];
@@ -399,6 +433,28 @@ retry:
 			list_for_each_entry(modes[i], &connector->modes, head)
 				break;
 		}
+		/*
+		 * In case of tiled mode if all tiles not present fallback to
+		 * first available non tiled mode.
+		 * After all tiles are present, try to find the tiled mode
+		 * for all and if tiled mode not present due to fbcon size
+		 * limitations, use first non tiled mode only for
+		 * tile 0,0 and set to no mode for all other tiles.
+		 */
+		if (connector->has_tile) {
+			if (num_tiled_conns <
+			    connector->num_h_tile * connector->num_v_tile ||
+			    (connector->tile_h_loc == 0 &&
+			     connector->tile_v_loc == 0 &&
+			     !drm_connector_get_tiled_mode(connector))) {
+				DRM_DEBUG_KMS("Falling back to non tiled mode on Connector %d\n",
+					      connector->base.id);
+				modes[i] = drm_connector_fallback_non_tiled_mode(connector);
+			} else {
+				modes[i] = drm_connector_get_tiled_mode(connector);
+			}
+		}
+
 		DRM_DEBUG_KMS("found mode %s\n", modes[i] ? modes[i]->name :
 			  "none");
 		conn_configured |= BIT_ULL(i);
@@ -515,6 +571,7 @@ static bool drm_client_firmware_config(struct drm_client_dev *client,
 	bool fallback = true, ret = true;
 	int num_connectors_enabled = 0;
 	int num_connectors_detected = 0;
+	int num_tiled_conns = 0;
 	struct drm_modeset_acquire_ctx ctx;
 
 	if (!drm_drv_uses_atomic_modeset(dev))
@@ -532,6 +589,11 @@ static bool drm_client_firmware_config(struct drm_client_dev *client,
 	memcpy(save_enabled, enabled, count);
 	mask = GENMASK(count - 1, 0);
 	conn_configured = 0;
+	for (i = 0; i < count; i++) {
+		if (connectors[i]->has_tile &&
+		    connectors[i]->status == connector_status_connected)
+			num_tiled_conns++;
+	}
 retry:
 	conn_seq = conn_configured;
 	for (i = 0; i < count; i++) {
@@ -631,6 +693,16 @@ retry:
 				      connector->name);
 			modes[i] = &connector->state->crtc->mode;
 		}
+		/*
+		 * In case of tiled modes, if all tiles are not present
+		 * then fallback to a non tiled mode.
+		 */
+		if (connector->has_tile &&
+		    num_tiled_conns < connector->num_h_tile * connector->num_v_tile) {
+			DRM_DEBUG_KMS("Falling back to non tiled mode on Connector %d\n",
+				      connector->base.id);
+			modes[i] = drm_connector_fallback_non_tiled_mode(connector);
+		}
 		crtcs[i] = new_crtc;
 
 		DRM_DEBUG_KMS("connector %s on [CRTC:%d:%s]: %dx%d%s\n",
diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c
index 4ce5c6d8de99..c93123ff7c21 100644
--- a/drivers/gpu/drm/drm_color_mgmt.c
+++ b/drivers/gpu/drm/drm_color_mgmt.c
@@ -109,28 +109,38 @@
  */
 
 /**
- * drm_color_lut_extract - clamp and round LUT entries
+ * drm_color_ctm_s31_32_to_qm_n
+ *
  * @user_input: input value
- * @bit_precision: number of bits the hw LUT supports
+ * @m: number of integer bits, only support m <= 32, include the sign-bit
+ * @n: number of fractional bits, only support n <= 32
+ *
+ * Convert and clamp S31.32 sign-magnitude to Qm.n (signed 2's complement).
+ * The sign-bit BIT(m+n-1) and above are 0 for positive value and 1 for negative
+ * the range of value is [-2^(m-1), 2^(m-1) - 2^-n]
+ *
+ * For example
+ * A Q3.12 format number:
+ * - required bit: 3 + 12 = 15bits
+ * - range: [-2^2, 2^2 - 2^−15]
  *
- * Extract a degamma/gamma LUT value provided by user (in the form of
- * &drm_color_lut entries) and round it to the precision supported by the
- * hardware.
+ * NOTE: the m can be zero if all bit_precision are used to present fractional
+ *       bits like Q0.32
  */
-uint32_t drm_color_lut_extract(uint32_t user_input, uint32_t bit_precision)
+u64 drm_color_ctm_s31_32_to_qm_n(u64 user_input, u32 m, u32 n)
 {
-	uint32_t val = user_input;
-	uint32_t max = 0xffff >> (16 - bit_precision);
+	u64 mag = (user_input & ~BIT_ULL(63)) >> (32 - n);
+	bool negative = !!(user_input & BIT_ULL(63));
+	s64 val;
 
-	/* Round only if we're not using full precision. */
-	if (bit_precision < 16) {
-		val += 1UL << (16 - bit_precision - 1);
-		val >>= 16 - bit_precision;
-	}
+	WARN_ON(m > 32 || n > 32);
+
+	val = clamp_val(mag, 0, negative ?
+				BIT_ULL(n + m - 1) : BIT_ULL(n + m - 1) - 1);
 
-	return clamp_val(val, 0, max);
+	return negative ? -val : val;
 }
-EXPORT_SYMBOL(drm_color_lut_extract);
+EXPORT_SYMBOL(drm_color_ctm_s31_32_to_qm_n);
 
 /**
  * drm_crtc_enable_color_mgmt - enable color management properties
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 499b05aaccfc..93a4eec429e8 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -48,6 +48,8 @@
 #include <drm/drm_print.h>
 #include <drm/drm_vblank.h>
 
+#include "drm_crtc_helper_internal.h"
+
 /**
  * DOC: overview
  *
diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index ca3c55c6b815..e22b812c4b80 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -140,8 +140,8 @@ static ssize_t crc_control_write(struct file *file, const char __user *ubuf,
 	if (IS_ERR(source))
 		return PTR_ERR(source);
 
-	if (source[len] == '\n')
-		source[len] = '\0';
+	if (source[len - 1] == '\n')
+		source[len - 1] = '\0';
 
 	ret = crtc->funcs->verify_crc_source(crtc, source, &values_cnt);
 	if (ret)
@@ -258,6 +258,11 @@ static int crtc_crc_release(struct inode *inode, struct file *filep)
 	struct drm_crtc *crtc = filep->f_inode->i_private;
 	struct drm_crtc_crc *crc = &crtc->crc;
 
+	/* terminate the infinite while loop if 'drm_dp_aux_crc_work' running */
+	spin_lock_irq(&crc->lock);
+	crc->opened = false;
+	spin_unlock_irq(&crc->lock);
+
 	crtc->funcs->set_crc_source(crtc, NULL);
 
 	spin_lock_irq(&crc->lock);
diff --git a/drivers/gpu/drm/drm_dp_aux_dev.c b/drivers/gpu/drm/drm_dp_aux_dev.c
index 0cfb386754c3..2510717d5a08 100644
--- a/drivers/gpu/drm/drm_dp_aux_dev.c
+++ b/drivers/gpu/drm/drm_dp_aux_dev.c
@@ -163,11 +163,7 @@ static ssize_t auxdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			break;
 		}
 
-		if (aux_dev->aux->is_remote)
-			res = drm_dp_mst_dpcd_read(aux_dev->aux, pos, buf,
-						   todo);
-		else
-			res = drm_dp_dpcd_read(aux_dev->aux, pos, buf, todo);
+		res = drm_dp_dpcd_read(aux_dev->aux, pos, buf, todo);
 
 		if (res <= 0)
 			break;
@@ -215,11 +211,7 @@ static ssize_t auxdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			break;
 		}
 
-		if (aux_dev->aux->is_remote)
-			res = drm_dp_mst_dpcd_write(aux_dev->aux, pos, buf,
-						    todo);
-		else
-			res = drm_dp_dpcd_write(aux_dev->aux, pos, buf, todo);
+		res = drm_dp_dpcd_write(aux_dev->aux, pos, buf, todo);
 
 		if (res <= 0)
 			break;
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 2c7870aef469..a5364b5192b8 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -32,6 +32,7 @@
 #include <drm/drm_dp_helper.h>
 #include <drm/drm_print.h>
 #include <drm/drm_vblank.h>
+#include <drm/drm_dp_mst_helper.h>
 
 #include "drm_crtc_helper_internal.h"
 
@@ -266,7 +267,7 @@ unlock:
 
 /**
  * drm_dp_dpcd_read() - read a series of bytes from the DPCD
- * @aux: DisplayPort AUX channel
+ * @aux: DisplayPort AUX channel (SST or MST)
  * @offset: address of the (first) register to read
  * @buffer: buffer to store the register values
  * @size: number of bytes in @buffer
@@ -295,13 +296,18 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
 	 * We just have to do it before any DPCD access and hope that the
 	 * monitor doesn't power down exactly after the throw away read.
 	 */
-	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV, buffer,
-				 1);
-	if (ret != 1)
-		goto out;
+	if (!aux->is_remote) {
+		ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV,
+					 buffer, 1);
+		if (ret != 1)
+			goto out;
+	}
 
-	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer,
-				 size);
+	if (aux->is_remote)
+		ret = drm_dp_mst_dpcd_read(aux, offset, buffer, size);
+	else
+		ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset,
+					 buffer, size);
 
 out:
 	drm_dp_dump_access(aux, DP_AUX_NATIVE_READ, offset, buffer, ret);
@@ -311,7 +317,7 @@ EXPORT_SYMBOL(drm_dp_dpcd_read);
 
 /**
  * drm_dp_dpcd_write() - write a series of bytes to the DPCD
- * @aux: DisplayPort AUX channel
+ * @aux: DisplayPort AUX channel (SST or MST)
  * @offset: address of the (first) register to write
  * @buffer: buffer containing the values to write
  * @size: number of bytes in @buffer
@@ -328,8 +334,12 @@ ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset,
 {
 	int ret;
 
-	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer,
-				 size);
+	if (aux->is_remote)
+		ret = drm_dp_mst_dpcd_write(aux, offset, buffer, size);
+	else
+		ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset,
+					 buffer, size);
+
 	drm_dp_dump_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer, ret);
 	return ret;
 }
@@ -969,6 +979,19 @@ static void drm_dp_aux_crc_work(struct work_struct *work)
 }
 
 /**
+ * drm_dp_remote_aux_init() - minimally initialise a remote aux channel
+ * @aux: DisplayPort AUX channel
+ *
+ * Used for remote aux channel in general. Merely initialize the crc work
+ * struct.
+ */
+void drm_dp_remote_aux_init(struct drm_dp_aux *aux)
+{
+	INIT_WORK(&aux->crc_work, drm_dp_aux_crc_work);
+}
+EXPORT_SYMBOL(drm_dp_remote_aux_init);
+
+/**
  * drm_dp_aux_init() - minimally initialise an aux channel
  * @aux: DisplayPort AUX channel
  *
@@ -1155,6 +1178,8 @@ static const struct dpcd_quirk dpcd_quirk_list[] = {
 	{ OUI(0x00, 0x10, 0xfa), DEVICE_ID_ANY, false, BIT(DP_DPCD_QUIRK_NO_PSR) },
 	/* CH7511 seems to leave SINK_COUNT zeroed */
 	{ OUI(0x00, 0x00, 0x00), DEVICE_ID('C', 'H', '7', '5', '1', '1'), false, BIT(DP_DPCD_QUIRK_NO_SINK_COUNT) },
+	/* Synaptics DP1.4 MST hubs can support DSC without virtual DPCD */
+	{ OUI(0x90, 0xCC, 0x24), DEVICE_ID_ANY, true, BIT(DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) },
 };
 
 #undef OUI
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index e6afe4faeca6..20cdaf3146b8 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -76,6 +76,11 @@ static int drm_dp_send_dpcd_write(struct drm_dp_mst_topology_mgr *mgr,
 
 static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
 				    struct drm_dp_mst_branch *mstb);
+
+static void
+drm_dp_send_clear_payload_id_table(struct drm_dp_mst_topology_mgr *mgr,
+				   struct drm_dp_mst_branch *mstb);
+
 static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
 					   struct drm_dp_mst_branch *mstb,
 					   struct drm_dp_mst_port *port);
@@ -517,8 +522,10 @@ drm_dp_decode_sideband_req(const struct drm_dp_sideband_msg_tx *raw,
 			}
 
 			if (failed) {
-				for (i = 0; i < r->num_transactions; i++)
+				for (i = 0; i < r->num_transactions; i++) {
+					tx = &r->transactions[i];
 					kfree(tx->bytes);
+				}
 				return -ENOMEM;
 			}
 
@@ -846,6 +853,7 @@ static bool drm_dp_sideband_parse_enum_path_resources_ack(struct drm_dp_sideband
 {
 	int idx = 1;
 	repmsg->u.path_resources.port_number = (raw->msg[idx] >> 4) & 0xf;
+	repmsg->u.path_resources.fec_capable = raw->msg[idx] & 0x1;
 	idx++;
 	if (idx > raw->curlen)
 		goto fail_len;
@@ -950,6 +958,8 @@ static bool drm_dp_sideband_parse_reply(struct drm_dp_sideband_msg_rx *raw,
 	case DP_POWER_DOWN_PHY:
 	case DP_POWER_UP_PHY:
 		return drm_dp_sideband_parse_power_updown_phy_ack(raw, msg);
+	case DP_CLEAR_PAYLOAD_ID_TABLE:
+		return true; /* since there's nothing to parse */
 	default:
 		DRM_ERROR("Got unknown reply 0x%02x (%s)\n", msg->req_type,
 			  drm_dp_mst_req_type_str(msg->req_type));
@@ -1048,6 +1058,15 @@ static int build_link_address(struct drm_dp_sideband_msg_tx *msg)
 	return 0;
 }
 
+static int build_clear_payload_id_table(struct drm_dp_sideband_msg_tx *msg)
+{
+	struct drm_dp_sideband_msg_req_body req;
+
+	req.req_type = DP_CLEAR_PAYLOAD_ID_TABLE;
+	drm_dp_encode_sideband_req(&req, msg);
+	return 0;
+}
+
 static int build_enum_path_resources(struct drm_dp_sideband_msg_tx *msg, int port_num)
 {
 	struct drm_dp_sideband_msg_req_body req;
@@ -2175,6 +2194,7 @@ drm_dp_mst_topology_unlink_port(struct drm_dp_mst_topology_mgr *mgr,
 				struct drm_dp_mst_port *port)
 {
 	mutex_lock(&mgr->lock);
+	port->parent->num_ports--;
 	list_del(&port->next);
 	mutex_unlock(&mgr->lock);
 	drm_dp_mst_topology_put_port(port);
@@ -2199,6 +2219,9 @@ drm_dp_mst_add_port(struct drm_device *dev,
 	port->aux.dev = dev->dev;
 	port->aux.is_remote = true;
 
+	/* initialize the MST downstream port's AUX crc work queue */
+	drm_dp_remote_aux_init(&port->aux);
+
 	/*
 	 * Make sure the memory allocation for our parent branch stays
 	 * around until our own memory allocation is released
@@ -2275,6 +2298,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb,
 		mutex_lock(&mgr->lock);
 		drm_dp_mst_topology_get_port(port);
 		list_add(&port->next, &mstb->ports);
+		mstb->num_ports++;
 		mutex_unlock(&mgr->lock);
 	}
 
@@ -2564,10 +2588,14 @@ static void drm_dp_mst_link_probe_work(struct work_struct *work)
 	struct drm_device *dev = mgr->dev;
 	struct drm_dp_mst_branch *mstb;
 	int ret;
+	bool clear_payload_id_table;
 
 	mutex_lock(&mgr->probe_lock);
 
 	mutex_lock(&mgr->lock);
+	clear_payload_id_table = !mgr->payload_id_table_cleared;
+	mgr->payload_id_table_cleared = true;
+
 	mstb = mgr->mst_primary;
 	if (mstb) {
 		ret = drm_dp_mst_topology_try_get_mstb(mstb);
@@ -2580,6 +2608,19 @@ static void drm_dp_mst_link_probe_work(struct work_struct *work)
 		return;
 	}
 
+	/*
+	 * Certain branch devices seem to incorrectly report an available_pbn
+	 * of 0 on downstream sinks, even after clearing the
+	 * DP_PAYLOAD_ALLOCATE_* registers in
+	 * drm_dp_mst_topology_mgr_set_mst(). Namely, the CableMatters USB-C
+	 * 2x DP hub. Sending a CLEAR_PAYLOAD_ID_TABLE message seems to make
+	 * things work again.
+	 */
+	if (clear_payload_id_table) {
+		DRM_DEBUG_KMS("Clearing payload ID table\n");
+		drm_dp_send_clear_payload_id_table(mgr, mstb);
+	}
+
 	ret = drm_dp_check_and_send_link_address(mgr, mstb);
 	drm_dp_mst_topology_put_mstb(mstb);
 
@@ -2906,6 +2947,28 @@ out:
 	return ret < 0 ? ret : changed;
 }
 
+void drm_dp_send_clear_payload_id_table(struct drm_dp_mst_topology_mgr *mgr,
+					struct drm_dp_mst_branch *mstb)
+{
+	struct drm_dp_sideband_msg_tx *txmsg;
+	int len, ret;
+
+	txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL);
+	if (!txmsg)
+		return;
+
+	txmsg->dst = mstb;
+	len = build_clear_payload_id_table(txmsg);
+
+	drm_dp_queue_down_tx(mgr, txmsg);
+
+	ret = drm_dp_mst_wait_tx_reply(mstb, txmsg);
+	if (ret > 0 && txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK)
+		DRM_DEBUG_KMS("clear payload table id nak received\n");
+
+	kfree(txmsg);
+}
+
 static int
 drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
 				struct drm_dp_mst_branch *mstb,
@@ -2941,6 +3004,7 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
 				      path_res->avail_payload_bw_number);
 			port->available_pbn =
 				path_res->avail_payload_bw_number;
+			port->fec_capable = path_res->fec_capable;
 		}
 	}
 
@@ -3435,6 +3499,7 @@ static int drm_dp_get_vc_payload_bw(u8 dp_link_bw, u8  dp_link_count)
 int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state)
 {
 	int ret = 0;
+	int i = 0;
 	struct drm_dp_mst_branch *mstb = NULL;
 
 	mutex_lock(&mgr->lock);
@@ -3495,10 +3560,23 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 		/* this can fail if the device is gone */
 		drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, 0);
 		ret = 0;
+		mutex_lock(&mgr->payload_lock);
 		memset(mgr->payloads, 0, mgr->max_payloads * sizeof(struct drm_dp_payload));
 		mgr->payload_mask = 0;
 		set_bit(0, &mgr->payload_mask);
+		for (i = 0; i < mgr->max_payloads; i++) {
+			struct drm_dp_vcpi *vcpi = mgr->proposed_vcpis[i];
+
+			if (vcpi) {
+				vcpi->vcpi = 0;
+				vcpi->num_slots = 0;
+			}
+			mgr->proposed_vcpis[i] = NULL;
+		}
 		mgr->vcpi_mask = 0;
+		mutex_unlock(&mgr->payload_lock);
+
+		mgr->payload_id_table_cleared = false;
 	}
 
 out_unlock:
@@ -4071,6 +4149,7 @@ static int drm_dp_init_vcpi(struct drm_dp_mst_topology_mgr *mgr,
  * @mgr: MST topology manager for the port
  * @port: port to find vcpi slots for
  * @pbn: bandwidth required for the mode in PBN
+ * @pbn_div: divider for DSC mode that takes FEC into account
  *
  * Allocates VCPI slots to @port, replacing any previous VCPI allocations it
  * may have had. Any atomic drivers which support MST must call this function
@@ -4097,11 +4176,12 @@ static int drm_dp_init_vcpi(struct drm_dp_mst_topology_mgr *mgr,
  */
 int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 				  struct drm_dp_mst_topology_mgr *mgr,
-				  struct drm_dp_mst_port *port, int pbn)
+				  struct drm_dp_mst_port *port, int pbn,
+				  int pbn_div)
 {
 	struct drm_dp_mst_topology_state *topology_state;
 	struct drm_dp_vcpi_allocation *pos, *vcpi = NULL;
-	int prev_slots, req_slots;
+	int prev_slots, prev_bw, req_slots;
 
 	topology_state = drm_atomic_get_mst_topology_state(state, mgr);
 	if (IS_ERR(topology_state))
@@ -4112,6 +4192,7 @@ int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 		if (pos->port == port) {
 			vcpi = pos;
 			prev_slots = vcpi->vcpi;
+			prev_bw = vcpi->pbn;
 
 			/*
 			 * This should never happen, unless the driver tries
@@ -4127,14 +4208,22 @@ int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 			break;
 		}
 	}
-	if (!vcpi)
+	if (!vcpi) {
 		prev_slots = 0;
+		prev_bw = 0;
+	}
+
+	if (pbn_div <= 0)
+		pbn_div = mgr->pbn_div;
 
-	req_slots = DIV_ROUND_UP(pbn, mgr->pbn_div);
+	req_slots = DIV_ROUND_UP(pbn, pbn_div);
 
 	DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] [MST PORT:%p] VCPI %d -> %d\n",
 			 port->connector->base.id, port->connector->name,
 			 port, prev_slots, req_slots);
+	DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] [MST PORT:%p] PBN %d -> %d\n",
+			 port->connector->base.id, port->connector->name,
+			 port, prev_bw, pbn);
 
 	/* Add the new allocation to the state */
 	if (!vcpi) {
@@ -4147,6 +4236,7 @@ int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 		list_add(&vcpi->next, &topology_state->vcpis);
 	}
 	vcpi->vcpi = req_slots;
+	vcpi->pbn = pbn;
 
 	return req_slots;
 }
@@ -4397,10 +4487,11 @@ EXPORT_SYMBOL(drm_dp_check_act_status);
  * drm_dp_calc_pbn_mode() - Calculate the PBN for a mode.
  * @clock: dot clock for the mode
  * @bpp: bpp for the mode.
+ * @dsc: DSC mode. If true, bpp has units of 1/16 of a bit per pixel
  *
  * This uses the formula in the spec to calculate the PBN value for a mode.
  */
-int drm_dp_calc_pbn_mode(int clock, int bpp)
+int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc)
 {
 	/*
 	 * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006
@@ -4411,7 +4502,16 @@ int drm_dp_calc_pbn_mode(int clock, int bpp)
 	 * peak_kbps *= (1006/1000)
 	 * peak_kbps *= (64/54)
 	 * peak_kbps *= 8    convert to bytes
+	 *
+	 * If the bpp is in units of 1/16, further divide by 16. Put this
+	 * factor in the numerator rather than the denominator to avoid
+	 * integer overflow
 	 */
+
+	if (dsc)
+		return DIV_ROUND_UP_ULL(mul_u32_u32(clock * (bpp / 16), 64 * 1006),
+					8 * 54 * 1000 * 1000);
+
 	return DIV_ROUND_UP_ULL(mul_u32_u32(clock * bpp, 64 * 1006),
 				8 * 54 * 1000 * 1000);
 }
@@ -4713,9 +4813,61 @@ static void drm_dp_mst_destroy_state(struct drm_private_obj *obj,
 	kfree(mst_state);
 }
 
+static bool drm_dp_mst_port_downstream_of_branch(struct drm_dp_mst_port *port,
+						 struct drm_dp_mst_branch *branch)
+{
+	while (port->parent) {
+		if (port->parent == branch)
+			return true;
+
+		if (port->parent->port_parent)
+			port = port->parent->port_parent;
+		else
+			break;
+	}
+	return false;
+}
+
+static inline
+int drm_dp_mst_atomic_check_bw_limit(struct drm_dp_mst_branch *branch,
+				     struct drm_dp_mst_topology_state *mst_state)
+{
+	struct drm_dp_mst_port *port;
+	struct drm_dp_vcpi_allocation *vcpi;
+	int pbn_limit = 0, pbn_used = 0;
+
+	list_for_each_entry(port, &branch->ports, next) {
+		if (port->mstb)
+			if (drm_dp_mst_atomic_check_bw_limit(port->mstb, mst_state))
+				return -ENOSPC;
+
+		if (port->available_pbn > 0)
+			pbn_limit = port->available_pbn;
+	}
+	DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch has %d PBN available\n",
+			 branch, pbn_limit);
+
+	list_for_each_entry(vcpi, &mst_state->vcpis, next) {
+		if (!vcpi->pbn)
+			continue;
+
+		if (drm_dp_mst_port_downstream_of_branch(vcpi->port, branch))
+			pbn_used += vcpi->pbn;
+	}
+	DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch used %d PBN\n",
+			 branch, pbn_used);
+
+	if (pbn_used > pbn_limit) {
+		DRM_DEBUG_ATOMIC("[MST BRANCH:%p] No available bandwidth\n",
+				 branch);
+		return -ENOSPC;
+	}
+	return 0;
+}
+
 static inline int
-drm_dp_mst_atomic_check_topology_state(struct drm_dp_mst_topology_mgr *mgr,
-				       struct drm_dp_mst_topology_state *mst_state)
+drm_dp_mst_atomic_check_vcpi_alloc_limit(struct drm_dp_mst_topology_mgr *mgr,
+					 struct drm_dp_mst_topology_state *mst_state)
 {
 	struct drm_dp_vcpi_allocation *vcpi;
 	int avail_slots = 63, payload_count = 0;
@@ -4753,6 +4905,128 @@ drm_dp_mst_atomic_check_topology_state(struct drm_dp_mst_topology_mgr *mgr,
 }
 
 /**
+ * drm_dp_mst_add_affected_dsc_crtcs
+ * @state: Pointer to the new struct drm_dp_mst_topology_state
+ * @mgr: MST topology manager
+ *
+ * Whenever there is a change in mst topology
+ * DSC configuration would have to be recalculated
+ * therefore we need to trigger modeset on all affected
+ * CRTCs in that topology
+ *
+ * See also:
+ * drm_dp_mst_atomic_enable_dsc()
+ */
+int drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, struct drm_dp_mst_topology_mgr *mgr)
+{
+	struct drm_dp_mst_topology_state *mst_state;
+	struct drm_dp_vcpi_allocation *pos;
+	struct drm_connector *connector;
+	struct drm_connector_state *conn_state;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+
+	mst_state = drm_atomic_get_mst_topology_state(state, mgr);
+
+	if (IS_ERR(mst_state))
+		return -EINVAL;
+
+	list_for_each_entry(pos, &mst_state->vcpis, next) {
+
+		connector = pos->port->connector;
+
+		if (!connector)
+			return -EINVAL;
+
+		conn_state = drm_atomic_get_connector_state(state, connector);
+
+		if (IS_ERR(conn_state))
+			return PTR_ERR(conn_state);
+
+		crtc = conn_state->crtc;
+
+		if (WARN_ON(!crtc))
+			return -EINVAL;
+
+		if (!drm_dp_mst_dsc_aux_for_port(pos->port))
+			continue;
+
+		crtc_state = drm_atomic_get_crtc_state(mst_state->base.state, crtc);
+
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+
+		DRM_DEBUG_ATOMIC("[MST MGR:%p] Setting mode_changed flag on CRTC %p\n",
+				 mgr, crtc);
+
+		crtc_state->mode_changed = true;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(drm_dp_mst_add_affected_dsc_crtcs);
+
+/**
+ * drm_dp_mst_atomic_enable_dsc - Set DSC Enable Flag to On/Off
+ * @state: Pointer to the new drm_atomic_state
+ * @port: Pointer to the affected MST Port
+ * @pbn: Newly recalculated bw required for link with DSC enabled
+ * @pbn_div: Divider to calculate correct number of pbn per slot
+ * @enable: Boolean flag to enable or disable DSC on the port
+ *
+ * This function enables DSC on the given Port
+ * by recalculating its vcpi from pbn provided
+ * and sets dsc_enable flag to keep track of which
+ * ports have DSC enabled
+ *
+ */
+int drm_dp_mst_atomic_enable_dsc(struct drm_atomic_state *state,
+				 struct drm_dp_mst_port *port,
+				 int pbn, int pbn_div,
+				 bool enable)
+{
+	struct drm_dp_mst_topology_state *mst_state;
+	struct drm_dp_vcpi_allocation *pos;
+	bool found = false;
+	int vcpi = 0;
+
+	mst_state = drm_atomic_get_mst_topology_state(state, port->mgr);
+
+	if (IS_ERR(mst_state))
+		return PTR_ERR(mst_state);
+
+	list_for_each_entry(pos, &mst_state->vcpis, next) {
+		if (pos->port == port) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		DRM_DEBUG_ATOMIC("[MST PORT:%p] Couldn't find VCPI allocation in mst state %p\n",
+				 port, mst_state);
+		return -EINVAL;
+	}
+
+	if (pos->dsc_enabled == enable) {
+		DRM_DEBUG_ATOMIC("[MST PORT:%p] DSC flag is already set to %d, returning %d VCPI slots\n",
+				 port, enable, pos->vcpi);
+		vcpi = pos->vcpi;
+	}
+
+	if (enable) {
+		vcpi = drm_dp_atomic_find_vcpi_slots(state, port->mgr, port, pbn, pbn_div);
+		DRM_DEBUG_ATOMIC("[MST PORT:%p] Enabling DSC flag, reallocating %d VCPI slots on the port\n",
+				 port, vcpi);
+		if (vcpi < 0)
+			return -EINVAL;
+	}
+
+	pos->dsc_enabled = enable;
+
+	return vcpi;
+}
+EXPORT_SYMBOL(drm_dp_mst_atomic_enable_dsc);
+/**
  * drm_dp_mst_atomic_check - Check that the new state of an MST topology in an
  * atomic update is valid
  * @state: Pointer to the new &struct drm_dp_mst_topology_state
@@ -4780,7 +5054,13 @@ int drm_dp_mst_atomic_check(struct drm_atomic_state *state)
 	int i, ret = 0;
 
 	for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) {
-		ret = drm_dp_mst_atomic_check_topology_state(mgr, mst_state);
+		if (!mgr->mst_state)
+			continue;
+
+		ret = drm_dp_mst_atomic_check_vcpi_alloc_limit(mgr, mst_state);
+		if (ret)
+			break;
+		ret = drm_dp_mst_atomic_check_bw_limit(mgr->mst_primary, mst_state);
 		if (ret)
 			break;
 	}
@@ -5044,3 +5324,173 @@ static void drm_dp_mst_unregister_i2c_bus(struct drm_dp_aux *aux)
 {
 	i2c_del_adapter(&aux->ddc);
 }
+
+/**
+ * drm_dp_mst_is_virtual_dpcd() - Is the given port a virtual DP Peer Device
+ * @port: The port to check
+ *
+ * A single physical MST hub object can be represented in the topology
+ * by multiple branches, with virtual ports between those branches.
+ *
+ * As of DP1.4, An MST hub with internal (virtual) ports must expose
+ * certain DPCD registers over those ports. See sections 2.6.1.1.1
+ * and 2.6.1.1.2 of Display Port specification v1.4 for details.
+ *
+ * May acquire mgr->lock
+ *
+ * Returns:
+ * true if the port is a virtual DP peer device, false otherwise
+ */
+static bool drm_dp_mst_is_virtual_dpcd(struct drm_dp_mst_port *port)
+{
+	struct drm_dp_mst_port *downstream_port;
+
+	if (!port || port->dpcd_rev < DP_DPCD_REV_14)
+		return false;
+
+	/* Virtual DP Sink (Internal Display Panel) */
+	if (port->port_num >= 8)
+		return true;
+
+	/* DP-to-HDMI Protocol Converter */
+	if (port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV &&
+	    !port->mcs &&
+	    port->ldps)
+		return true;
+
+	/* DP-to-DP */
+	mutex_lock(&port->mgr->lock);
+	if (port->pdt == DP_PEER_DEVICE_MST_BRANCHING &&
+	    port->mstb &&
+	    port->mstb->num_ports == 2) {
+		list_for_each_entry(downstream_port, &port->mstb->ports, next) {
+			if (downstream_port->pdt == DP_PEER_DEVICE_SST_SINK &&
+			    !downstream_port->input) {
+				mutex_unlock(&port->mgr->lock);
+				return true;
+			}
+		}
+	}
+	mutex_unlock(&port->mgr->lock);
+
+	return false;
+}
+
+/**
+ * drm_dp_mst_dsc_aux_for_port() - Find the correct aux for DSC
+ * @port: The port to check. A leaf of the MST tree with an attached display.
+ *
+ * Depending on the situation, DSC may be enabled via the endpoint aux,
+ * the immediately upstream aux, or the connector's physical aux.
+ *
+ * This is both the correct aux to read DSC_CAPABILITY and the
+ * correct aux to write DSC_ENABLED.
+ *
+ * This operation can be expensive (up to four aux reads), so
+ * the caller should cache the return.
+ *
+ * Returns:
+ * NULL if DSC cannot be enabled on this port, otherwise the aux device
+ */
+struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port)
+{
+	struct drm_dp_mst_port *immediate_upstream_port;
+	struct drm_dp_mst_port *fec_port;
+	struct drm_dp_desc desc = { 0 };
+	u8 endpoint_fec;
+	u8 endpoint_dsc;
+
+	if (!port)
+		return NULL;
+
+	if (port->parent->port_parent)
+		immediate_upstream_port = port->parent->port_parent;
+	else
+		immediate_upstream_port = NULL;
+
+	fec_port = immediate_upstream_port;
+	while (fec_port) {
+		/*
+		 * Each physical link (i.e. not a virtual port) between the
+		 * output and the primary device must support FEC
+		 */
+		if (!drm_dp_mst_is_virtual_dpcd(fec_port) &&
+		    !fec_port->fec_capable)
+			return NULL;
+
+		fec_port = fec_port->parent->port_parent;
+	}
+
+	/* DP-to-DP peer device */
+	if (drm_dp_mst_is_virtual_dpcd(immediate_upstream_port)) {
+		u8 upstream_dsc;
+
+		if (drm_dp_dpcd_read(&port->aux,
+				     DP_DSC_SUPPORT, &endpoint_dsc, 1) != 1)
+			return NULL;
+		if (drm_dp_dpcd_read(&port->aux,
+				     DP_FEC_CAPABILITY, &endpoint_fec, 1) != 1)
+			return NULL;
+		if (drm_dp_dpcd_read(&immediate_upstream_port->aux,
+				     DP_DSC_SUPPORT, &upstream_dsc, 1) != 1)
+			return NULL;
+
+		/* Enpoint decompression with DP-to-DP peer device */
+		if ((endpoint_dsc & DP_DSC_DECOMPRESSION_IS_SUPPORTED) &&
+		    (endpoint_fec & DP_FEC_CAPABLE) &&
+		    (upstream_dsc & 0x2) /* DSC passthrough */)
+			return &port->aux;
+
+		/* Virtual DPCD decompression with DP-to-DP peer device */
+		return &immediate_upstream_port->aux;
+	}
+
+	/* Virtual DPCD decompression with DP-to-HDMI or Virtual DP Sink */
+	if (drm_dp_mst_is_virtual_dpcd(port))
+		return &port->aux;
+
+	/*
+	 * Synaptics quirk
+	 * Applies to ports for which:
+	 * - Physical aux has Synaptics OUI
+	 * - DPv1.4 or higher
+	 * - Port is on primary branch device
+	 * - Not a VGA adapter (DP_DWN_STRM_PORT_TYPE_ANALOG)
+	 */
+	if (drm_dp_read_desc(port->mgr->aux, &desc, true))
+		return NULL;
+
+	if (drm_dp_has_quirk(&desc, DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) &&
+	    port->mgr->dpcd[DP_DPCD_REV] >= DP_DPCD_REV_14 &&
+	    port->parent == port->mgr->mst_primary) {
+		u8 downstreamport;
+
+		if (drm_dp_dpcd_read(&port->aux, DP_DOWNSTREAMPORT_PRESENT,
+				     &downstreamport, 1) < 0)
+			return NULL;
+
+		if ((downstreamport & DP_DWN_STRM_PORT_PRESENT) &&
+		   ((downstreamport & DP_DWN_STRM_PORT_TYPE_MASK)
+		     != DP_DWN_STRM_PORT_TYPE_ANALOG))
+			return port->mgr->aux;
+	}
+
+	/*
+	 * The check below verifies if the MST sink
+	 * connected to the GPU is capable of DSC -
+	 * therefore the endpoint needs to be
+	 * both DSC and FEC capable.
+	 */
+	if (drm_dp_dpcd_read(&port->aux,
+	   DP_DSC_SUPPORT, &endpoint_dsc, 1) != 1)
+		return NULL;
+	if (drm_dp_dpcd_read(&port->aux,
+	   DP_FEC_CAPABILITY, &endpoint_fec, 1) != 1)
+		return NULL;
+	if ((endpoint_dsc & DP_DSC_DECOMPRESSION_IS_SUPPORTED) &&
+	   (endpoint_fec & DP_FEC_CAPABLE))
+		return &port->aux;
+
+	return NULL;
+}
+EXPORT_SYMBOL(drm_dp_mst_dsc_aux_for_port);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 1b9b40a1c7c9..7c18a980cd4b 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -622,7 +622,8 @@ int drm_dev_init(struct drm_device *dev,
 		return -ENODEV;
 	}
 
-	BUG_ON(!parent);
+	if (WARN_ON(!parent))
+		return -EINVAL;
 
 	kref_init(&dev->ref);
 	dev->dev = get_device(parent);
@@ -725,7 +726,7 @@ int devm_drm_dev_init(struct device *parent,
 {
 	int ret;
 
-	if (WARN_ON(!parent || !driver->release))
+	if (WARN_ON(!driver->release))
 		return -EINVAL;
 
 	ret = drm_dev_init(dev, driver, parent);
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 474ac04d5600..99769d6c9f84 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -710,14 +710,11 @@ static const struct minimode extra_modes[] = {
 };
 
 /*
- * Probably taken from CEA-861 spec.
- * This table is converted from xorg's hw/xfree86/modes/xf86EdidModes.c.
+ * From CEA/CTA-861 spec.
  *
- * Index using the VIC.
+ * Do not access directly, instead always use cea_mode_for_vic().
  */
-static const struct drm_display_mode edid_cea_modes[] = {
-	/* 0 - dummy, VICs start at 1 */
-	{ },
+static const struct drm_display_mode edid_cea_modes_1[] = {
 	/* 1 - 640x480@60Hz 4:3 */
 	{ DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656,
 		   752, 800, 0, 480, 490, 492, 525, 0,
@@ -1381,6 +1378,149 @@ static const struct drm_display_mode edid_cea_modes[] = {
 };
 
 /*
+ * From CEA/CTA-861 spec.
+ *
+ * Do not access directly, instead always use cea_mode_for_vic().
+ */
+static const struct drm_display_mode edid_cea_modes_193[] = {
+	/* 193 - 5120x2160@120Hz 64:27 */
+	{ DRM_MODE("5120x2160", DRM_MODE_TYPE_DRIVER, 1485000, 5120, 5284,
+		   5372, 5500, 0, 2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 194 - 7680x4320@24Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 10232,
+		   10408, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 195 - 7680x4320@25Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 10032,
+		   10208, 10800, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 196 - 7680x4320@30Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 8232,
+		   8408, 9000, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 197 - 7680x4320@48Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 10232,
+		   10408, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 48, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 198 - 7680x4320@50Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 10032,
+		   10208, 10800, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 199 - 7680x4320@60Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 8232,
+		   8408, 9000, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 200 - 7680x4320@100Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 4752000, 7680, 9792,
+		   9968, 10560, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 201 - 7680x4320@120Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 4752000, 7680, 8032,
+		   8208, 8800, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 202 - 7680x4320@24Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 10232,
+		   10408, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 203 - 7680x4320@25Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 10032,
+		   10208, 10800, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 204 - 7680x4320@30Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 8232,
+		   8408, 9000, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 205 - 7680x4320@48Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 10232,
+		   10408, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 48, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 206 - 7680x4320@50Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 10032,
+		   10208, 10800, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 207 - 7680x4320@60Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 8232,
+		   8408, 9000, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 208 - 7680x4320@100Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 4752000, 7680, 9792,
+		   9968, 10560, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 209 - 7680x4320@120Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 4752000, 7680, 8032,
+		   8208, 8800, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 210 - 10240x4320@24Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 1485000, 10240, 11732,
+		   11908, 12500, 0, 4320, 4336, 4356, 4950, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 211 - 10240x4320@25Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 1485000, 10240, 12732,
+		   12908, 13500, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 212 - 10240x4320@30Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 1485000, 10240, 10528,
+		   10704, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 213 - 10240x4320@48Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 2970000, 10240, 11732,
+		   11908, 12500, 0, 4320, 4336, 4356, 4950, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 48, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 214 - 10240x4320@50Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 2970000, 10240, 12732,
+		   12908, 13500, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 215 - 10240x4320@60Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 2970000, 10240, 10528,
+		   10704, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 216 - 10240x4320@100Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 5940000, 10240, 12432,
+		   12608, 13200, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 217 - 10240x4320@120Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 5940000, 10240, 10528,
+		   10704, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 218 - 4096x2160@100Hz 256:135 */
+	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 1188000, 4096, 4896,
+		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
+	/* 219 - 4096x2160@120Hz 256:135 */
+	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 1188000, 4096, 4184,
+		   4272, 4400, 0, 2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
+};
+
+/*
  * HDMI 1.4 4k modes. Index using the VIC.
  */
 static const struct drm_display_mode edid_4k_modes[] = {
@@ -1391,25 +1531,25 @@ static const struct drm_display_mode edid_4k_modes[] = {
 		   3840, 4016, 4104, 4400, 0,
 		   2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	  .vrefresh = 30, },
+	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
 	/* 2 - 3840x2160@25Hz */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000,
 		   3840, 4896, 4984, 5280, 0,
 		   2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	  .vrefresh = 25, },
+	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
 	/* 3 - 3840x2160@24Hz */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000,
 		   3840, 5116, 5204, 5500, 0,
 		   2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	  .vrefresh = 24, },
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
 	/* 4 - 4096x2160@24Hz (SMPTE) */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000,
 		   4096, 5116, 5204, 5500, 0,
 		   2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	  .vrefresh = 24, },
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
 };
 
 /*** DDC fetch and block validation ***/
@@ -3071,6 +3211,30 @@ static u8 *drm_find_cea_extension(const struct edid *edid)
 	return cea;
 }
 
+static const struct drm_display_mode *cea_mode_for_vic(u8 vic)
+{
+	BUILD_BUG_ON(1 + ARRAY_SIZE(edid_cea_modes_1) - 1 != 127);
+	BUILD_BUG_ON(193 + ARRAY_SIZE(edid_cea_modes_193) - 1 != 219);
+
+	if (vic >= 1 && vic < 1 + ARRAY_SIZE(edid_cea_modes_1))
+		return &edid_cea_modes_1[vic - 1];
+	if (vic >= 193 && vic < 193 + ARRAY_SIZE(edid_cea_modes_193))
+		return &edid_cea_modes_193[vic - 193];
+	return NULL;
+}
+
+static u8 cea_num_vics(void)
+{
+	return 193 + ARRAY_SIZE(edid_cea_modes_193);
+}
+
+static u8 cea_next_vic(u8 vic)
+{
+	if (++vic == 1 + ARRAY_SIZE(edid_cea_modes_1))
+		vic = 193;
+	return vic;
+}
+
 /*
  * Calculate the alternate clock for the CEA mode
  * (60Hz vs. 59.94Hz etc.)
@@ -3108,14 +3272,14 @@ cea_mode_alternate_timings(u8 vic, struct drm_display_mode *mode)
 	 * get the other variants by simply increasing the
 	 * vertical front porch length.
 	 */
-	BUILD_BUG_ON(edid_cea_modes[8].vtotal != 262 ||
-		     edid_cea_modes[9].vtotal != 262 ||
-		     edid_cea_modes[12].vtotal != 262 ||
-		     edid_cea_modes[13].vtotal != 262 ||
-		     edid_cea_modes[23].vtotal != 312 ||
-		     edid_cea_modes[24].vtotal != 312 ||
-		     edid_cea_modes[27].vtotal != 312 ||
-		     edid_cea_modes[28].vtotal != 312);
+	BUILD_BUG_ON(cea_mode_for_vic(8)->vtotal != 262 ||
+		     cea_mode_for_vic(9)->vtotal != 262 ||
+		     cea_mode_for_vic(12)->vtotal != 262 ||
+		     cea_mode_for_vic(13)->vtotal != 262 ||
+		     cea_mode_for_vic(23)->vtotal != 312 ||
+		     cea_mode_for_vic(24)->vtotal != 312 ||
+		     cea_mode_for_vic(27)->vtotal != 312 ||
+		     cea_mode_for_vic(28)->vtotal != 312);
 
 	if (((vic == 8 || vic == 9 ||
 	      vic == 12 || vic == 13) && mode->vtotal < 263) ||
@@ -3143,8 +3307,8 @@ static u8 drm_match_cea_mode_clock_tolerance(const struct drm_display_mode *to_m
 	if (to_match->picture_aspect_ratio)
 		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
 
-	for (vic = 1; vic < ARRAY_SIZE(edid_cea_modes); vic++) {
-		struct drm_display_mode cea_mode = edid_cea_modes[vic];
+	for (vic = 1; vic < cea_num_vics(); vic = cea_next_vic(vic)) {
+		struct drm_display_mode cea_mode = *cea_mode_for_vic(vic);
 		unsigned int clock1, clock2;
 
 		/* Check both 60Hz and 59.94Hz */
@@ -3182,8 +3346,8 @@ u8 drm_match_cea_mode(const struct drm_display_mode *to_match)
 	if (to_match->picture_aspect_ratio)
 		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
 
-	for (vic = 1; vic < ARRAY_SIZE(edid_cea_modes); vic++) {
-		struct drm_display_mode cea_mode = edid_cea_modes[vic];
+	for (vic = 1; vic < cea_num_vics(); vic = cea_next_vic(vic)) {
+		struct drm_display_mode cea_mode = *cea_mode_for_vic(vic);
 		unsigned int clock1, clock2;
 
 		/* Check both 60Hz and 59.94Hz */
@@ -3206,28 +3370,31 @@ EXPORT_SYMBOL(drm_match_cea_mode);
 
 static bool drm_valid_cea_vic(u8 vic)
 {
-	return vic > 0 && vic < ARRAY_SIZE(edid_cea_modes);
+	return cea_mode_for_vic(vic) != NULL;
 }
 
 static enum hdmi_picture_aspect drm_get_cea_aspect_ratio(const u8 video_code)
 {
-	return edid_cea_modes[video_code].picture_aspect_ratio;
+	const struct drm_display_mode *mode = cea_mode_for_vic(video_code);
+
+	if (mode)
+		return mode->picture_aspect_ratio;
+
+	return HDMI_PICTURE_ASPECT_NONE;
+}
+
+static enum hdmi_picture_aspect drm_get_hdmi_aspect_ratio(const u8 video_code)
+{
+	return edid_4k_modes[video_code].picture_aspect_ratio;
 }
 
 /*
  * Calculate the alternate clock for HDMI modes (those from the HDMI vendor
  * specific block).
- *
- * It's almost like cea_mode_alternate_clock(), we just need to add an
- * exception for the VIC 4 mode (4096x2160@24Hz): no alternate clock for this
- * one.
  */
 static unsigned int
 hdmi_mode_alternate_clock(const struct drm_display_mode *hdmi_mode)
 {
-	if (hdmi_mode->vdisplay == 4096 && hdmi_mode->hdisplay == 2160)
-		return hdmi_mode->clock;
-
 	return cea_mode_alternate_clock(hdmi_mode);
 }
 
@@ -3240,6 +3407,9 @@ static u8 drm_match_hdmi_mode_clock_tolerance(const struct drm_display_mode *to_
 	if (!to_match->clock)
 		return 0;
 
+	if (to_match->picture_aspect_ratio)
+		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
+
 	for (vic = 1; vic < ARRAY_SIZE(edid_4k_modes); vic++) {
 		const struct drm_display_mode *hdmi_mode = &edid_4k_modes[vic];
 		unsigned int clock1, clock2;
@@ -3275,6 +3445,9 @@ static u8 drm_match_hdmi_mode(const struct drm_display_mode *to_match)
 	if (!to_match->clock)
 		return 0;
 
+	if (to_match->picture_aspect_ratio)
+		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
+
 	for (vic = 1; vic < ARRAY_SIZE(edid_4k_modes); vic++) {
 		const struct drm_display_mode *hdmi_mode = &edid_4k_modes[vic];
 		unsigned int clock1, clock2;
@@ -3319,7 +3492,7 @@ add_alternate_cea_modes(struct drm_connector *connector, struct edid *edid)
 		unsigned int clock1, clock2;
 
 		if (drm_valid_cea_vic(vic)) {
-			cea_mode = &edid_cea_modes[vic];
+			cea_mode = cea_mode_for_vic(vic);
 			clock2 = cea_mode_alternate_clock(cea_mode);
 		} else {
 			vic = drm_match_hdmi_mode(mode);
@@ -3394,7 +3567,7 @@ drm_display_mode_from_vic_index(struct drm_connector *connector,
 	if (!drm_valid_cea_vic(vic))
 		return NULL;
 
-	newmode = drm_mode_duplicate(dev, &edid_cea_modes[vic]);
+	newmode = drm_mode_duplicate(dev, cea_mode_for_vic(vic));
 	if (!newmode)
 		return NULL;
 
@@ -3428,7 +3601,7 @@ static int do_y420vdb_modes(struct drm_connector *connector,
 		if (!drm_valid_cea_vic(vic))
 			continue;
 
-		newmode = drm_mode_duplicate(dev, &edid_cea_modes[vic]);
+		newmode = drm_mode_duplicate(dev, cea_mode_for_vic(vic));
 		if (!newmode)
 			break;
 		bitmap_set(hdmi->y420_vdb_modes, vic, 1);
@@ -3997,7 +4170,7 @@ static void fixup_detailed_cea_mode_clock(struct drm_display_mode *mode)
 	vic = drm_match_cea_mode_clock_tolerance(mode, 5);
 	if (drm_valid_cea_vic(vic)) {
 		type = "CEA";
-		cea_mode = &edid_cea_modes[vic];
+		cea_mode = cea_mode_for_vic(vic);
 		clock1 = cea_mode->clock;
 		clock2 = cea_mode_alternate_clock(cea_mode);
 	} else {
@@ -4279,12 +4452,12 @@ int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads)
 	cea = drm_find_cea_extension(edid);
 	if (!cea) {
 		DRM_DEBUG_KMS("SAD: no CEA Extension found\n");
-		return -ENOENT;
+		return 0;
 	}
 
 	if (cea_revision(cea) < 3) {
 		DRM_DEBUG_KMS("SAD: wrong CEA revision\n");
-		return -EOPNOTSUPP;
+		return 0;
 	}
 
 	if (cea_db_offsets(cea, &start, &end)) {
@@ -4340,12 +4513,12 @@ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb)
 	cea = drm_find_cea_extension(edid);
 	if (!cea) {
 		DRM_DEBUG_KMS("SAD: no CEA Extension found\n");
-		return -ENOENT;
+		return 0;
 	}
 
 	if (cea_revision(cea) < 3) {
 		DRM_DEBUG_KMS("SAD: wrong CEA revision\n");
-		return -EOPNOTSUPP;
+		return 0;
 	}
 
 	if (cea_db_offsets(cea, &start, &end)) {
@@ -4573,7 +4746,7 @@ static void drm_parse_hdmi_forum_vsdb(struct drm_connector *connector,
 		if (scdc->supported) {
 			scdc->scrambling.supported = true;
 
-			/* Few sinks support scrambling for cloks < 340M */
+			/* Few sinks support scrambling for clocks < 340M */
 			if ((hf_vsdb[6] & 0x8))
 				scdc->scrambling.low_rates = true;
 		}
@@ -5222,6 +5395,7 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 					 const struct drm_display_mode *mode)
 {
 	enum hdmi_picture_aspect picture_aspect;
+	u8 vic, hdmi_vic;
 	int err;
 
 	if (!frame || !mode)
@@ -5234,7 +5408,8 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		frame->pixel_repeat = 1;
 
-	frame->video_code = drm_mode_cea_vic(connector, mode);
+	vic = drm_mode_cea_vic(connector, mode);
+	hdmi_vic = drm_mode_hdmi_vic(connector, mode);
 
 	frame->picture_aspect = HDMI_PICTURE_ASPECT_NONE;
 
@@ -5248,11 +5423,15 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 
 	/*
 	 * Populate picture aspect ratio from either
-	 * user input (if specified) or from the CEA mode list.
+	 * user input (if specified) or from the CEA/HDMI mode lists.
 	 */
 	picture_aspect = mode->picture_aspect_ratio;
-	if (picture_aspect == HDMI_PICTURE_ASPECT_NONE)
-		picture_aspect = drm_get_cea_aspect_ratio(frame->video_code);
+	if (picture_aspect == HDMI_PICTURE_ASPECT_NONE) {
+		if (vic)
+			picture_aspect = drm_get_cea_aspect_ratio(vic);
+		else if (hdmi_vic)
+			picture_aspect = drm_get_hdmi_aspect_ratio(hdmi_vic);
+	}
 
 	/*
 	 * The infoframe can't convey anything but none, 4:3
@@ -5260,12 +5439,20 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	 * we can only satisfy it by specifying the right VIC.
 	 */
 	if (picture_aspect > HDMI_PICTURE_ASPECT_16_9) {
-		if (picture_aspect !=
-		    drm_get_cea_aspect_ratio(frame->video_code))
+		if (vic) {
+			if (picture_aspect != drm_get_cea_aspect_ratio(vic))
+				return -EINVAL;
+		} else if (hdmi_vic) {
+			if (picture_aspect != drm_get_hdmi_aspect_ratio(hdmi_vic))
+				return -EINVAL;
+		} else {
 			return -EINVAL;
+		}
+
 		picture_aspect = HDMI_PICTURE_ASPECT_NONE;
 	}
 
+	frame->video_code = vic;
 	frame->picture_aspect = picture_aspect;
 	frame->active_aspect = HDMI_ACTIVE_ASPECT_PICTURE;
 	frame->scan_mode = HDMI_SCAN_MODE_UNDERSCAN;
diff --git a/drivers/gpu/drm/drm_encoder.c b/drivers/gpu/drm/drm_encoder.c
index 80d88a55302e..e555281f43d4 100644
--- a/drivers/gpu/drm/drm_encoder.c
+++ b/drivers/gpu/drm/drm_encoder.c
@@ -140,6 +140,7 @@ int drm_encoder_init(struct drm_device *dev,
 		goto out_put;
 	}
 
+	INIT_LIST_HEAD(&encoder->bridge_chain);
 	list_add_tail(&encoder->head, &dev->mode_config.encoder_list);
 	encoder->index = dev->mode_config.num_encoder++;
 
@@ -160,22 +161,16 @@ EXPORT_SYMBOL(drm_encoder_init);
 void drm_encoder_cleanup(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
+	struct drm_bridge *bridge, *next;
 
 	/* Note that the encoder_list is considered to be static; should we
 	 * remove the drm_encoder at runtime we would have to decrement all
 	 * the indices on the drm_encoder after us in the encoder_list.
 	 */
 
-	if (encoder->bridge) {
-		struct drm_bridge *bridge = encoder->bridge;
-		struct drm_bridge *next;
-
-		while (bridge) {
-			next = bridge->next;
-			drm_bridge_detach(bridge);
-			bridge = next;
-		}
-	}
+	list_for_each_entry_safe(bridge, next, &encoder->bridge_chain,
+				 chain_node)
+		drm_bridge_detach(bridge);
 
 	drm_mode_object_unregister(dev, &encoder->base);
 	kfree(encoder->name);
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index c0b0f603af63..9801c0333eca 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -9,6 +9,7 @@
  *  Copyright (C) 2012 Red Hat
  */
 
+#include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_cma_helper.h>
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index d8e8f3960f4d..4c7cbce7bae7 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -95,10 +95,6 @@ static DEFINE_MUTEX(kernel_fb_helper_lock);
  * It will automatically set up deferred I/O if the driver requires a shadow
  * buffer.
  *
- * For other drivers, setup fbdev emulation by calling
- * drm_fb_helper_fbdev_setup() and tear it down by calling
- * drm_fb_helper_fbdev_teardown().
- *
  * At runtime drivers should restore the fbdev console by using
  * drm_fb_helper_lastclose() as their &drm_driver.lastclose callback.
  * They should also notify the fb helper code from updates to the output
@@ -195,6 +191,7 @@ int drm_fb_helper_debug_leave(struct fb_info *info)
 {
 	struct drm_fb_helper *helper = info->par;
 	struct drm_client_dev *client = &helper->client;
+	struct drm_device *dev = helper->dev;
 	struct drm_crtc *crtc;
 	const struct drm_crtc_helper_funcs *funcs;
 	struct drm_mode_set *mode_set;
@@ -213,7 +210,7 @@ int drm_fb_helper_debug_leave(struct fb_info *info)
 			continue;
 
 		if (!fb) {
-			DRM_ERROR("no fb to restore??\n");
+			drm_err(dev, "no fb to restore?\n");
 			continue;
 		}
 
@@ -567,8 +564,7 @@ EXPORT_SYMBOL(drm_fb_helper_unregister_fbi);
  * drm_fb_helper_fini - finialize a &struct drm_fb_helper
  * @fb_helper: driver-allocated fbdev helper, can be NULL
  *
- * This cleans up all remaining resources associated with @fb_helper. Must be
- * called after drm_fb_helper_unlink_fbi() was called.
+ * This cleans up all remaining resources associated with @fb_helper.
  */
 void drm_fb_helper_fini(struct drm_fb_helper *fb_helper)
 {
@@ -608,19 +604,6 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper)
 }
 EXPORT_SYMBOL(drm_fb_helper_fini);
 
-/**
- * drm_fb_helper_unlink_fbi - wrapper around unlink_framebuffer
- * @fb_helper: driver-allocated fbdev helper, can be NULL
- *
- * A wrapper around unlink_framebuffer implemented by fbdev core
- */
-void drm_fb_helper_unlink_fbi(struct drm_fb_helper *fb_helper)
-{
-	if (fb_helper && fb_helper->fbdev)
-		unlink_framebuffer(fb_helper->fbdev);
-}
-EXPORT_SYMBOL(drm_fb_helper_unlink_fbi);
-
 static bool drm_fbdev_use_shadow_fb(struct drm_fb_helper *fb_helper)
 {
 	struct drm_device *dev = fb_helper->dev;
@@ -1266,12 +1249,13 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 {
 	struct drm_fb_helper *fb_helper = info->par;
 	struct drm_framebuffer *fb = fb_helper->fb;
+	struct drm_device *dev = fb_helper->dev;
 
 	if (in_dbg_master())
 		return -EINVAL;
 
 	if (var->pixclock != 0) {
-		DRM_DEBUG("fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n");
+		drm_dbg_kms(dev, "fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n");
 		var->pixclock = 0;
 	}
 
@@ -1286,7 +1270,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	if (var->bits_per_pixel > fb->format->cpp[0] * 8 ||
 	    var->xres > fb->width || var->yres > fb->height ||
 	    var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
-		DRM_DEBUG("fb requested width/height/bpp can't fit in current fb "
+		drm_dbg_kms(dev, "fb requested width/height/bpp can't fit in current fb "
 			  "request %dx%d-%d (virtual %dx%d) > %dx%d-%d\n",
 			  var->xres, var->yres, var->bits_per_pixel,
 			  var->xres_virtual, var->yres_virtual,
@@ -1318,7 +1302,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	 * so reject all pixel format changing requests.
 	 */
 	if (!drm_fb_pixel_format_equal(var, &info->var)) {
-		DRM_DEBUG("fbdev emulation doesn't support changing the pixel format\n");
+		drm_dbg_kms(dev, "fbdev emulation doesn't support changing the pixel format\n");
 		return -EINVAL;
 	}
 
@@ -1343,7 +1327,7 @@ int drm_fb_helper_set_par(struct fb_info *info)
 		return -EBUSY;
 
 	if (var->pixclock != 0) {
-		DRM_ERROR("PIXEL CLOCK SET\n");
+		drm_err(fb_helper->dev, "PIXEL CLOCK SET\n");
 		return -EINVAL;
 	}
 
@@ -1453,6 +1437,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 					 int preferred_bpp)
 {
 	struct drm_client_dev *client = &fb_helper->client;
+	struct drm_device *dev = fb_helper->dev;
 	int ret = 0;
 	int crtc_count = 0;
 	struct drm_connector_list_iter conn_iter;
@@ -1516,7 +1501,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 		struct drm_plane *plane = crtc->primary;
 		int j;
 
-		DRM_DEBUG("test CRTC %u primary plane\n", drm_crtc_index(crtc));
+		drm_dbg_kms(dev, "test CRTC %u primary plane\n", drm_crtc_index(crtc));
 
 		for (j = 0; j < plane->format_count; j++) {
 			const struct drm_format_info *fmt;
@@ -1549,7 +1534,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 		}
 	}
 	if (sizes.surface_depth != best_depth && best_depth) {
-		DRM_INFO("requested bpp %d, scaled depth down to %d",
+		drm_info(dev, "requested bpp %d, scaled depth down to %d",
 			 sizes.surface_bpp, best_depth);
 		sizes.surface_depth = best_depth;
 	}
@@ -1581,7 +1566,9 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 		for (j = 0; j < mode_set->num_connectors; j++) {
 			struct drm_connector *connector = mode_set->connectors[j];
 
-			if (connector->has_tile) {
+			if (connector->has_tile &&
+			    desired_mode->hdisplay == connector->tile_h_size &&
+			    desired_mode->vdisplay == connector->tile_v_size) {
 				lasth = (connector->tile_h_loc == (connector->num_h_tile - 1));
 				lastv = (connector->tile_v_loc == (connector->num_v_tile - 1));
 				/* cloning to multiple tiles is just crazy-talk, so: */
@@ -1597,7 +1584,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 	mutex_unlock(&client->modeset_mutex);
 
 	if (crtc_count == 0 || sizes.fb_width == -1 || sizes.fb_height == -1) {
-		DRM_INFO("Cannot find any crtc or sizes\n");
+		drm_info(dev, "Cannot find any crtc or sizes\n");
 
 		/* First time: disable all crtc's.. */
 		if (!fb_helper->deferred_setup)
@@ -1912,7 +1899,7 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
 
 	drm_master_internal_release(fb_helper->dev);
 
-	DRM_DEBUG_KMS("\n");
+	drm_dbg_kms(fb_helper->dev, "\n");
 
 	drm_client_modeset_probe(&fb_helper->client, fb_helper->fb->width, fb_helper->fb->height);
 	drm_setup_crtcs_fb(fb_helper);
@@ -1925,108 +1912,6 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
 EXPORT_SYMBOL(drm_fb_helper_hotplug_event);
 
 /**
- * drm_fb_helper_fbdev_setup() - Setup fbdev emulation
- * @dev: DRM device
- * @fb_helper: fbdev helper structure to set up
- * @funcs: fbdev helper functions
- * @preferred_bpp: Preferred bits per pixel for the device.
- *                 @dev->mode_config.preferred_depth is used if this is zero.
- * @max_conn_count: Maximum number of connectors (not used)
- *
- * This function sets up fbdev emulation and registers fbdev for access by
- * userspace. If all connectors are disconnected, setup is deferred to the next
- * time drm_fb_helper_hotplug_event() is called.
- * The caller must to provide a &drm_fb_helper_funcs->fb_probe callback
- * function.
- *
- * Use drm_fb_helper_fbdev_teardown() to destroy the fbdev.
- *
- * See also: drm_fb_helper_initial_config(), drm_fbdev_generic_setup().
- *
- * Returns:
- * Zero on success or negative error code on failure.
- */
-int drm_fb_helper_fbdev_setup(struct drm_device *dev,
-			      struct drm_fb_helper *fb_helper,
-			      const struct drm_fb_helper_funcs *funcs,
-			      unsigned int preferred_bpp,
-			      unsigned int max_conn_count)
-{
-	int ret;
-
-	if (!preferred_bpp)
-		preferred_bpp = dev->mode_config.preferred_depth;
-	if (!preferred_bpp)
-		preferred_bpp = 32;
-
-	drm_fb_helper_prepare(dev, fb_helper, funcs);
-
-	ret = drm_fb_helper_init(dev, fb_helper, 0);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "fbdev: Failed to initialize (ret=%d)\n", ret);
-		return ret;
-	}
-
-	if (!drm_drv_uses_atomic_modeset(dev))
-		drm_helper_disable_unused_functions(dev);
-
-	ret = drm_fb_helper_initial_config(fb_helper, preferred_bpp);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "fbdev: Failed to set configuration (ret=%d)\n", ret);
-		goto err_drm_fb_helper_fini;
-	}
-
-	return 0;
-
-err_drm_fb_helper_fini:
-	drm_fb_helper_fbdev_teardown(dev);
-
-	return ret;
-}
-EXPORT_SYMBOL(drm_fb_helper_fbdev_setup);
-
-/**
- * drm_fb_helper_fbdev_teardown - Tear down fbdev emulation
- * @dev: DRM device
- *
- * This function unregisters fbdev if not already done and cleans up the
- * associated resources including the &drm_framebuffer.
- * The driver is responsible for freeing the &drm_fb_helper structure which is
- * stored in &drm_device->fb_helper. Do note that this pointer has been cleared
- * when this function returns.
- *
- * In order to support device removal/unplug while file handles are still open,
- * drm_fb_helper_unregister_fbi() should be called on device removal and
- * drm_fb_helper_fbdev_teardown() in the &drm_driver->release callback when
- * file handles are closed.
- */
-void drm_fb_helper_fbdev_teardown(struct drm_device *dev)
-{
-	struct drm_fb_helper *fb_helper = dev->fb_helper;
-	struct fb_ops *fbops = NULL;
-
-	if (!fb_helper)
-		return;
-
-	/* Unregister if it hasn't been done already */
-	if (fb_helper->fbdev && fb_helper->fbdev->dev)
-		drm_fb_helper_unregister_fbi(fb_helper);
-
-	if (fb_helper->fbdev && fb_helper->fbdev->fbdefio) {
-		fb_deferred_io_cleanup(fb_helper->fbdev);
-		kfree(fb_helper->fbdev->fbdefio);
-		fbops = fb_helper->fbdev->fbops;
-	}
-
-	drm_fb_helper_fini(fb_helper);
-	kfree(fbops);
-
-	if (fb_helper->fb)
-		drm_framebuffer_remove(fb_helper->fb);
-}
-EXPORT_SYMBOL(drm_fb_helper_fbdev_teardown);
-
-/**
  * drm_fb_helper_lastclose - DRM driver lastclose helper for fbdev emulation
  * @dev: DRM device
  *
@@ -2079,7 +1964,6 @@ static int drm_fbdev_fb_release(struct fb_info *info, int user)
 static void drm_fbdev_cleanup(struct drm_fb_helper *fb_helper)
 {
 	struct fb_info *fbi = fb_helper->fbdev;
-	struct fb_ops *fbops = NULL;
 	void *shadow = NULL;
 
 	if (!fb_helper->dev)
@@ -2088,15 +1972,11 @@ static void drm_fbdev_cleanup(struct drm_fb_helper *fb_helper)
 	if (fbi && fbi->fbdefio) {
 		fb_deferred_io_cleanup(fbi);
 		shadow = fbi->screen_buffer;
-		fbops = fbi->fbops;
 	}
 
 	drm_fb_helper_fini(fb_helper);
 
-	if (shadow) {
-		vfree(shadow);
-		kfree(fbops);
-	}
+	vfree(shadow);
 
 	drm_client_framebuffer_delete(fb_helper->buffer);
 }
@@ -2127,7 +2007,7 @@ static int drm_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 		return -ENODEV;
 }
 
-static struct fb_ops drm_fbdev_fb_ops = {
+static const struct fb_ops drm_fbdev_fb_ops = {
 	.owner		= THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open	= drm_fbdev_fb_open,
@@ -2146,32 +2026,26 @@ static struct fb_deferred_io drm_fbdev_defio = {
 	.deferred_io	= drm_fb_helper_deferred_io,
 };
 
-/**
- * drm_fb_helper_generic_probe - Generic fbdev emulation probe helper
- * @fb_helper: fbdev helper structure
- * @sizes: describes fbdev size and scanout surface size
- *
+/*
  * This function uses the client API to create a framebuffer backed by a dumb buffer.
  *
  * The _sys_ versions are used for &fb_ops.fb_read, fb_write, fb_fillrect,
  * fb_copyarea, fb_imageblit.
- *
- * Returns:
- * Zero on success or negative error code on failure.
  */
-int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
-				struct drm_fb_helper_surface_size *sizes)
+static int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
+				       struct drm_fb_helper_surface_size *sizes)
 {
 	struct drm_client_dev *client = &fb_helper->client;
+	struct drm_device *dev = fb_helper->dev;
 	struct drm_client_buffer *buffer;
 	struct drm_framebuffer *fb;
 	struct fb_info *fbi;
 	u32 format;
 	void *vaddr;
 
-	DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n",
-		      sizes->surface_width, sizes->surface_height,
-		      sizes->surface_bpp);
+	drm_dbg_kms(dev, "surface width(%d), height(%d) and bpp(%d)\n",
+		    sizes->surface_width, sizes->surface_height,
+		    sizes->surface_bpp);
 
 	format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth);
 	buffer = drm_client_framebuffer_create(client, sizes->surface_width,
@@ -2194,24 +2068,10 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
 	drm_fb_helper_fill_info(fbi, fb_helper, sizes);
 
 	if (drm_fbdev_use_shadow_fb(fb_helper)) {
-		struct fb_ops *fbops;
-		void *shadow;
-
-		/*
-		 * fb_deferred_io_cleanup() clears &fbops->fb_mmap so a per
-		 * instance version is necessary.
-		 */
-		fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
-		shadow = vzalloc(fbi->screen_size);
-		if (!fbops || !shadow) {
-			kfree(fbops);
-			vfree(shadow);
+		fbi->screen_buffer = vzalloc(fbi->screen_size);
+		if (!fbi->screen_buffer)
 			return -ENOMEM;
-		}
 
-		*fbops = *fbi->fbops;
-		fbi->fbops = fbops;
-		fbi->screen_buffer = shadow;
 		fbi->fbdefio = &drm_fbdev_defio;
 
 		fb_deferred_io_init(fbi);
@@ -2232,7 +2092,6 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
 
 	return 0;
 }
-EXPORT_SYMBOL(drm_fb_helper_generic_probe);
 
 static const struct drm_fb_helper_funcs drm_fb_helper_generic_funcs = {
 	.fb_probe = drm_fb_helper_generic_probe,
@@ -2270,7 +2129,7 @@ static int drm_fbdev_client_hotplug(struct drm_client_dev *client)
 		return drm_fb_helper_hotplug_event(dev->fb_helper);
 
 	if (!dev->mode_config.num_connector) {
-		DRM_DEV_DEBUG(dev->dev, "No connectors found, will not create framebuffer!\n");
+		drm_dbg_kms(dev, "No connectors found, will not create framebuffer!\n");
 		return 0;
 	}
 
@@ -2295,7 +2154,7 @@ err:
 	fb_helper->dev = NULL;
 	fb_helper->fbdev = NULL;
 
-	DRM_DEV_ERROR(dev->dev, "fbdev: Failed to setup generic emulation (ret=%d)\n", ret);
+	drm_err(dev, "fbdev: Failed to setup generic emulation (ret=%d)\n", ret);
 
 	return ret;
 }
@@ -2314,8 +2173,7 @@ static const struct drm_client_funcs drm_fbdev_client_funcs = {
  *                 @dev->mode_config.preferred_depth is used if this is zero.
  *
  * This function sets up generic fbdev emulation for drivers that supports
- * dumb buffers with a virtual address and that can be mmap'ed. If the driver
- * does not support these functions, it could use drm_fb_helper_fbdev_setup().
+ * dumb buffers with a virtual address and that can be mmap'ed.
  *
  * Restore, hotplug events and teardown are all taken care of. Drivers that do
  * suspend/resume need to call drm_fb_helper_set_suspend_unlocked() themselves.
@@ -2353,7 +2211,7 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
 	ret = drm_client_init(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
 	if (ret) {
 		kfree(fb_helper);
-		DRM_DEV_ERROR(dev->dev, "Failed to register client: %d\n", ret);
+		drm_err(dev, "Failed to register client: %d\n", ret);
 		return ret;
 	}
 
@@ -2365,7 +2223,7 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
 
 	ret = drm_fbdev_client_hotplug(&fb_helper->client);
 	if (ret)
-		DRM_DEV_DEBUG(dev->dev, "client hotplug ret=%d\n", ret);
+		drm_dbg_kms(dev, "client hotplug ret=%d\n", ret);
 
 	drm_client_register(&fb_helper->client);
 
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index ea34bc991858..92d16724f949 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -31,7 +31,9 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/anon_inodes.h>
 #include <linux/dma-fence.h>
+#include <linux/file.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/poll.h>
@@ -285,7 +287,7 @@ static int drm_cpu_valid(void)
 }
 
 /*
- * Called whenever a process opens /dev/drm.
+ * Called whenever a process opens a drm node
  *
  * \param filp file pointer.
  * \param minor acquired minor-object.
@@ -754,3 +756,43 @@ void drm_send_event(struct drm_device *dev, struct drm_pending_event *e)
 	spin_unlock_irqrestore(&dev->event_lock, irqflags);
 }
 EXPORT_SYMBOL(drm_send_event);
+
+/**
+ * mock_drm_getfile - Create a new struct file for the drm device
+ * @minor: drm minor to wrap (e.g. #drm_device.primary)
+ * @flags: file creation mode (O_RDWR etc)
+ *
+ * This create a new struct file that wraps a DRM file context around a
+ * DRM minor. This mimicks userspace opening e.g. /dev/dri/card0, but without
+ * invoking userspace. The struct file may be operated on using its f_op
+ * (the drm_device.driver.fops) to mimick userspace operations, or be supplied
+ * to userspace facing functions as an internal/anonymous client.
+ *
+ * RETURNS:
+ * Pointer to newly created struct file, ERR_PTR on failure.
+ */
+struct file *mock_drm_getfile(struct drm_minor *minor, unsigned int flags)
+{
+	struct drm_device *dev = minor->dev;
+	struct drm_file *priv;
+	struct file *file;
+
+	priv = drm_file_alloc(minor);
+	if (IS_ERR(priv))
+		return ERR_CAST(priv);
+
+	file = anon_inode_getfile("drm", dev->driver->fops, priv, flags);
+	if (IS_ERR(file)) {
+		drm_file_free(priv);
+		return file;
+	}
+
+	/* Everyone shares a single global address space */
+	file->f_mapping = dev->anon_inode->i_mapping;
+
+	drm_dev_get(dev);
+	priv->filp = file;
+
+	return file;
+}
+EXPORT_SYMBOL_FOR_TESTS_ONLY(mock_drm_getfile);
diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index c630064ccf41..b234bfaeda06 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -253,17 +253,17 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		  .char_per_block = { 8, 0, 0 }, .block_w = { 2, 0, 0 }, .block_h = { 2, 0, 0 },
 		  .hsub = 2, .vsub = 2, .is_yuv = true },
 		{ .format = DRM_FORMAT_P010,            .depth = 0,  .num_planes = 2,
-		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 0, 0 }, .block_h = { 1, 0, 0 },
+		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 1, 0 }, .block_h = { 1, 1, 0 },
 		  .hsub = 2, .vsub = 2, .is_yuv = true},
 		{ .format = DRM_FORMAT_P012,		.depth = 0,  .num_planes = 2,
-		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 0, 0 }, .block_h = { 1, 0, 0 },
+		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 1, 0 }, .block_h = { 1, 1, 0 },
 		   .hsub = 2, .vsub = 2, .is_yuv = true},
 		{ .format = DRM_FORMAT_P016,		.depth = 0,  .num_planes = 2,
-		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 0, 0 }, .block_h = { 1, 0, 0 },
+		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 1, 0 }, .block_h = { 1, 1, 0 },
 		  .hsub = 2, .vsub = 2, .is_yuv = true},
 		{ .format = DRM_FORMAT_P210,		.depth = 0,
 		  .num_planes = 2, .char_per_block = { 2, 4, 0 },
-		  .block_w = { 1, 0, 0 }, .block_h = { 1, 0, 0 }, .hsub = 2,
+		  .block_w = { 1, 1, 0 }, .block_h = { 1, 1, 0 }, .hsub = 2,
 		  .vsub = 1, .is_yuv = true },
 		{ .format = DRM_FORMAT_VUY101010,	.depth = 0,
 		  .num_planes = 1, .cpp = { 0, 0, 0 }, .hsub = 1, .vsub = 1,
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 000fa4a1899f..a9e4a610445a 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1114,9 +1114,6 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
 	drm_gem_object_get(obj);
 
 	if (obj->funcs && obj->funcs->mmap) {
-		/* Remove the fake offset */
-		vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
-
 		ret = obj->funcs->mmap(obj, vma);
 		if (ret) {
 			drm_gem_object_put_unlocked(obj);
diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
index b9bcd310ca2d..3a7ace19a902 100644
--- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c
+++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
@@ -74,8 +74,7 @@ drm_gem_fb_alloc(struct drm_device *dev,
 
 	ret = drm_framebuffer_init(dev, fb, funcs);
 	if (ret) {
-		DRM_DEV_ERROR(dev->dev, "Failed to init framebuffer: %d\n",
-			      ret);
+		drm_err(dev, "Failed to init framebuffer: %d\n", ret);
 		kfree(fb);
 		return ERR_PTR(ret);
 	}
@@ -160,7 +159,7 @@ drm_gem_fb_create_with_funcs(struct drm_device *dev, struct drm_file *file,
 
 		objs[i] = drm_gem_object_lookup(file, mode_cmd->handles[i]);
 		if (!objs[i]) {
-			DRM_DEBUG_KMS("Failed to lookup GEM object\n");
+			drm_dbg_kms(dev, "Failed to lookup GEM object\n");
 			ret = -ENOENT;
 			goto err_gem_object_put;
 		}
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 0810d3ef6961..a421a2eed48a 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -528,6 +528,9 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	struct drm_gem_shmem_object *shmem;
 	int ret;
 
+	/* Remove the fake offset */
+	vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
+
 	shmem = to_drm_gem_shmem_obj(obj);
 
 	ret = drm_gem_shmem_get_pages(shmem);
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 666cb4c22bb9..a4863326061a 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -2,6 +2,7 @@
 
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_ttm_helper.h>
@@ -92,14 +93,18 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo,
 }
 
 static int drm_gem_vram_init(struct drm_device *dev,
-			     struct ttm_bo_device *bdev,
 			     struct drm_gem_vram_object *gbo,
-			     size_t size, unsigned long pg_align,
-			     bool interruptible)
+			     size_t size, unsigned long pg_align)
 {
+	struct drm_vram_mm *vmm = dev->vram_mm;
+	struct ttm_bo_device *bdev;
 	int ret;
 	size_t acc_size;
 
+	if (WARN_ONCE(!vmm, "VRAM MM not initialized"))
+		return -EINVAL;
+	bdev = &vmm->bdev;
+
 	gbo->bo.base.funcs = &drm_gem_vram_object_funcs;
 
 	ret = drm_gem_object_init(dev, &gbo->bo.base, size);
@@ -112,7 +117,7 @@ static int drm_gem_vram_init(struct drm_device *dev,
 	drm_gem_vram_placement(gbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
 	ret = ttm_bo_init(bdev, &gbo->bo, size, ttm_bo_type_device,
-			  &gbo->placement, pg_align, interruptible, acc_size,
+			  &gbo->placement, pg_align, false, acc_size,
 			  NULL, NULL, ttm_buffer_object_destroy);
 	if (ret)
 		goto err_drm_gem_object_release;
@@ -127,29 +132,33 @@ err_drm_gem_object_release:
 /**
  * drm_gem_vram_create() - Creates a VRAM-backed GEM object
  * @dev:		the DRM device
- * @bdev:		the TTM BO device backing the object
  * @size:		the buffer size in bytes
  * @pg_align:		the buffer's alignment in multiples of the page size
- * @interruptible:	sleep interruptible if waiting for memory
  *
  * Returns:
  * A new instance of &struct drm_gem_vram_object on success, or
  * an ERR_PTR()-encoded error code otherwise.
  */
 struct drm_gem_vram_object *drm_gem_vram_create(struct drm_device *dev,
-						struct ttm_bo_device *bdev,
 						size_t size,
-						unsigned long pg_align,
-						bool interruptible)
+						unsigned long pg_align)
 {
 	struct drm_gem_vram_object *gbo;
 	int ret;
 
-	gbo = kzalloc(sizeof(*gbo), GFP_KERNEL);
-	if (!gbo)
-		return ERR_PTR(-ENOMEM);
+	if (dev->driver->gem_create_object) {
+		struct drm_gem_object *gem =
+			dev->driver->gem_create_object(dev, size);
+		if (!gem)
+			return ERR_PTR(-ENOMEM);
+		gbo = drm_gem_vram_of_gem(gem);
+	} else {
+		gbo = kzalloc(sizeof(*gbo), GFP_KERNEL);
+		if (!gbo)
+			return ERR_PTR(-ENOMEM);
+	}
 
-	ret = drm_gem_vram_init(dev, bdev, gbo, size, pg_align, interruptible);
+	ret = drm_gem_vram_init(dev, gbo, size, pg_align);
 	if (ret < 0)
 		goto err_kfree;
 
@@ -483,9 +492,8 @@ EXPORT_SYMBOL(drm_gem_vram_vunmap);
 	Helper for implementing &struct drm_driver.dumb_create
  * @file:		the DRM file
  * @dev:		the DRM device
- * @bdev:		the TTM BO device managing the buffer object
  * @pg_align:		the buffer's alignment in multiples of the page size
- * @interruptible:	sleep interruptible if waiting for memory
+ * @pitch_align:	the scanline's alignment in powers of 2
  * @args:		the arguments as provided to \
 				&struct drm_driver.dumb_create
  *
@@ -500,9 +508,8 @@ EXPORT_SYMBOL(drm_gem_vram_vunmap);
  */
 int drm_gem_vram_fill_create_dumb(struct drm_file *file,
 				  struct drm_device *dev,
-				  struct ttm_bo_device *bdev,
 				  unsigned long pg_align,
-				  bool interruptible,
+				  unsigned long pitch_align,
 				  struct drm_mode_create_dumb *args)
 {
 	size_t pitch, size;
@@ -510,14 +517,19 @@ int drm_gem_vram_fill_create_dumb(struct drm_file *file,
 	int ret;
 	u32 handle;
 
-	pitch = args->width * ((args->bpp + 7) / 8);
+	pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
+	if (pitch_align) {
+		if (WARN_ON_ONCE(!is_power_of_2(pitch_align)))
+			return -EINVAL;
+		pitch = ALIGN(pitch, pitch_align);
+	}
 	size = pitch * args->height;
 
 	size = roundup(size, PAGE_SIZE);
 	if (!size)
 		return -EINVAL;
 
-	gbo = drm_gem_vram_create(dev, bdev, size, pg_align, interruptible);
+	gbo = drm_gem_vram_create(dev, size, pg_align);
 	if (IS_ERR(gbo))
 		return PTR_ERR(gbo);
 
@@ -612,8 +624,7 @@ int drm_gem_vram_driver_dumb_create(struct drm_file *file,
 	if (WARN_ONCE(!dev->vram_mm, "VRAM MM not initialized"))
 		return -EINVAL;
 
-	return drm_gem_vram_fill_create_dumb(file, dev, &dev->vram_mm->bdev, 0,
-					     false, args);
+	return drm_gem_vram_fill_create_dumb(file, dev, 0, 0, args);
 }
 EXPORT_SYMBOL(drm_gem_vram_driver_dumb_create);
 
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 51a2055c8f18..6937bf923f05 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -45,12 +45,34 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor);
 void drm_file_free(struct drm_file *file);
 void drm_lastclose(struct drm_device *dev);
 
+#ifdef CONFIG_PCI
+
 /* drm_pci.c */
 int drm_irq_by_busid(struct drm_device *dev, void *data,
 		     struct drm_file *file_priv);
 void drm_pci_agp_destroy(struct drm_device *dev);
 int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master);
 
+#else
+
+static inline int drm_irq_by_busid(struct drm_device *dev, void *data,
+				   struct drm_file *file_priv)
+{
+	return -EINVAL;
+}
+
+static inline void drm_pci_agp_destroy(struct drm_device *dev)
+{
+}
+
+static inline int drm_pci_set_busid(struct drm_device *dev,
+				    struct drm_master *master)
+{
+	return -EINVAL;
+}
+
+#endif
+
 /* drm_prime.c */
 int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index fcd728d7cf72..5afb39688b55 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -652,8 +652,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, 0),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_RENDER_ALLOW),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, 0),
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index 2e8ce99d0baa..2c79e8199e3c 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -360,7 +360,8 @@ void drm_legacy_lock_master_cleanup(struct drm_device *dev, struct drm_master *m
 	/*
 	 * Since the master is disappearing, so is the
 	 * possibility to lock.
-	 */	mutex_lock(&dev->struct_mutex);
+	 */
+	mutex_lock(&dev->struct_mutex);
 	if (master->lock.hw_lock) {
 		if (dev->sigdata.lock == master->lock.hw_lock)
 			dev->sigdata.lock = NULL;
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index e34058c721be..16bff1be4b8a 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -367,9 +367,9 @@ static void mipi_dbi_blank(struct mipi_dbi_dev *dbidev)
 	memset(dbidev->tx_buf, 0, len);
 
 	mipi_dbi_command(dbi, MIPI_DCS_SET_COLUMN_ADDRESS, 0, 0,
-			 (width >> 8) & 0xFF, (width - 1) & 0xFF);
+			 ((width - 1) >> 8) & 0xFF, (width - 1) & 0xFF);
 	mipi_dbi_command(dbi, MIPI_DCS_SET_PAGE_ADDRESS, 0, 0,
-			 (height >> 8) & 0xFF, (height - 1) & 0xFF);
+			 ((height - 1) >> 8) & 0xFF, (height - 1) & 0xFF);
 	mipi_dbi_command_buf(dbi, MIPI_DCS_WRITE_MEMORY_START,
 			     (u8 *)dbidev->tx_buf, len);
 
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index bd2498bbd74a..55531895dde6 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -33,6 +33,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 
+#include <drm/drm_dsc.h>
 #include <video/mipi_display.h>
 
 /**
@@ -373,6 +374,7 @@ bool mipi_dsi_packet_format_is_short(u8 type)
 	case MIPI_DSI_V_SYNC_END:
 	case MIPI_DSI_H_SYNC_START:
 	case MIPI_DSI_H_SYNC_END:
+	case MIPI_DSI_COMPRESSION_MODE:
 	case MIPI_DSI_END_OF_TRANSMISSION:
 	case MIPI_DSI_COLOR_MODE_OFF:
 	case MIPI_DSI_COLOR_MODE_ON:
@@ -387,7 +389,7 @@ bool mipi_dsi_packet_format_is_short(u8 type)
 	case MIPI_DSI_DCS_SHORT_WRITE:
 	case MIPI_DSI_DCS_SHORT_WRITE_PARAM:
 	case MIPI_DSI_DCS_READ:
-	case MIPI_DSI_DCS_COMPRESSION_MODE:
+	case MIPI_DSI_EXECUTE_QUEUE:
 	case MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE:
 		return true;
 	}
@@ -406,11 +408,12 @@ EXPORT_SYMBOL(mipi_dsi_packet_format_is_short);
 bool mipi_dsi_packet_format_is_long(u8 type)
 {
 	switch (type) {
-	case MIPI_DSI_PPS_LONG_WRITE:
 	case MIPI_DSI_NULL_PACKET:
 	case MIPI_DSI_BLANKING_PACKET:
 	case MIPI_DSI_GENERIC_LONG_WRITE:
 	case MIPI_DSI_DCS_LONG_WRITE:
+	case MIPI_DSI_PICTURE_PARAMETER_SET:
+	case MIPI_DSI_COMPRESSED_PIXEL_STREAM:
 	case MIPI_DSI_LOOSELY_PACKED_PIXEL_STREAM_YCBCR20:
 	case MIPI_DSI_PACKED_PIXEL_STREAM_YCBCR24:
 	case MIPI_DSI_PACKED_PIXEL_STREAM_YCBCR16:
@@ -547,6 +550,56 @@ int mipi_dsi_set_maximum_return_packet_size(struct mipi_dsi_device *dsi,
 EXPORT_SYMBOL(mipi_dsi_set_maximum_return_packet_size);
 
 /**
+ * mipi_dsi_compression_mode() - enable/disable DSC on the peripheral
+ * @dsi: DSI peripheral device
+ * @enable: Whether to enable or disable the DSC
+ *
+ * Enable or disable Display Stream Compression on the peripheral using the
+ * default Picture Parameter Set and VESA DSC 1.1 algorithm.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+ssize_t mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable)
+{
+	/* Note: Needs updating for non-default PPS or algorithm */
+	u8 tx[2] = { enable << 0, 0 };
+	struct mipi_dsi_msg msg = {
+		.channel = dsi->channel,
+		.type = MIPI_DSI_COMPRESSION_MODE,
+		.tx_len = sizeof(tx),
+		.tx_buf = tx,
+	};
+	int ret = mipi_dsi_device_transfer(dsi, &msg);
+
+	return (ret < 0) ? ret : 0;
+}
+EXPORT_SYMBOL(mipi_dsi_compression_mode);
+
+/**
+ * mipi_dsi_picture_parameter_set() - transmit the DSC PPS to the peripheral
+ * @dsi: DSI peripheral device
+ * @pps: VESA DSC 1.1 Picture Parameter Set
+ *
+ * Transmit the VESA DSC 1.1 Picture Parameter Set to the peripheral.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+ssize_t mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi,
+				       const struct drm_dsc_picture_parameter_set *pps)
+{
+	struct mipi_dsi_msg msg = {
+		.channel = dsi->channel,
+		.type = MIPI_DSI_PICTURE_PARAMETER_SET,
+		.tx_len = sizeof(*pps),
+		.tx_buf = pps,
+	};
+	int ret = mipi_dsi_device_transfer(dsi, &msg);
+
+	return (ret < 0) ? ret : 0;
+}
+EXPORT_SYMBOL(mipi_dsi_picture_parameter_set);
+
+/**
  * mipi_dsi_generic_write() - transmit data using a generic write packet
  * @dsi: DSI peripheral device
  * @payload: buffer containing the payload
diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c
index 3b570a404933..08e6eff6a179 100644
--- a/drivers/gpu/drm/drm_mode_config.c
+++ b/drivers/gpu/drm/drm_mode_config.c
@@ -27,6 +27,7 @@
 #include <drm/drm_file.h>
 #include <drm/drm_mode_config.h>
 #include <drm/drm_print.h>
+#include <linux/dma-resv.h>
 
 #include "drm_crtc_internal.h"
 #include "drm_internal.h"
@@ -415,6 +416,33 @@ void drm_mode_config_init(struct drm_device *dev)
 	dev->mode_config.num_crtc = 0;
 	dev->mode_config.num_encoder = 0;
 	dev->mode_config.num_total_plane = 0;
+
+	if (IS_ENABLED(CONFIG_LOCKDEP)) {
+		struct drm_modeset_acquire_ctx modeset_ctx;
+		struct ww_acquire_ctx resv_ctx;
+		struct dma_resv resv;
+		int ret;
+
+		dma_resv_init(&resv);
+
+		drm_modeset_acquire_init(&modeset_ctx, 0);
+		ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
+				       &modeset_ctx);
+		if (ret == -EDEADLK)
+			ret = drm_modeset_backoff(&modeset_ctx);
+
+		ww_acquire_init(&resv_ctx, &reservation_ww_class);
+		ret = dma_resv_lock(&resv, &resv_ctx);
+		if (ret == -EDEADLK)
+			dma_resv_lock_slow(&resv, &resv_ctx);
+
+		dma_resv_unlock(&resv);
+		ww_acquire_fini(&resv_ctx);
+
+		drm_modeset_drop_locks(&modeset_ctx);
+		drm_modeset_acquire_fini(&modeset_ctx);
+		dma_resv_fini(&resv);
+	}
 }
 EXPORT_SYMBOL(drm_mode_config_init);
 
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index 6a23e36ed4fe..35c2719407a8 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -224,12 +224,26 @@ EXPORT_SYMBOL(drm_mode_object_get);
  * This attaches the given property to the modeset object with the given initial
  * value. Currently this function cannot fail since the properties are stored in
  * a statically sized array.
+ *
+ * Note that all properties must be attached before the object itself is
+ * registered and accessible from userspace.
  */
 void drm_object_attach_property(struct drm_mode_object *obj,
 				struct drm_property *property,
 				uint64_t init_val)
 {
 	int count = obj->properties->count;
+	struct drm_device *dev = property->dev;
+
+
+	if (obj->type == DRM_MODE_OBJECT_CONNECTOR) {
+		struct drm_connector *connector = obj_to_connector(obj);
+
+		WARN_ON(!dev->driver->load &&
+			connector->registration_state == DRM_CONNECTOR_REGISTERED);
+	} else {
+		WARN_ON(!dev->driver->load && dev->registered);
+	}
 
 	if (count == DRM_OBJECT_MAX_PROPERTY) {
 		WARN(1, "Failed to attach object property (type: 0x%x). Please "
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 88232698d7a0..10336b144c72 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -233,7 +233,7 @@ struct drm_display_mode *drm_cvt_mode(struct drm_device *dev, int hdisplay,
 		/* 3) Nominal HSync width (% of line period) - default 8 */
 #define CVT_HSYNC_PERCENTAGE	8
 		unsigned int hblank_percentage;
-		int vsyncandback_porch, vback_porch, hblank;
+		int vsyncandback_porch, __maybe_unused vback_porch, hblank;
 
 		/* estimated the horizontal period */
 		tmp1 = HV_FACTOR * 1000000  -
@@ -386,9 +386,10 @@ drm_gtf_mode_complex(struct drm_device *dev, int hdisplay, int vdisplay,
 	int top_margin, bottom_margin;
 	int interlace;
 	unsigned int hfreq_est;
-	int vsync_plus_bp, vback_porch;
-	unsigned int vtotal_lines, vfieldrate_est, hperiod;
-	unsigned int vfield_rate, vframe_rate;
+	int vsync_plus_bp, __maybe_unused vback_porch;
+	unsigned int vtotal_lines, __maybe_unused vfieldrate_est;
+	unsigned int __maybe_unused hperiod;
+	unsigned int vfield_rate, __maybe_unused vframe_rate;
 	int left_margin, right_margin;
 	unsigned int total_active_pixels, ideal_duty_cycle;
 	unsigned int hblank, total_pixels, pixel_freq;
@@ -1568,33 +1569,76 @@ static int drm_mode_parse_cmdline_res_mode(const char *str, unsigned int length,
 	return 0;
 }
 
-static int drm_mode_parse_cmdline_options(char *str, size_t len,
+static int drm_mode_parse_cmdline_int(const char *delim, unsigned int *int_ret)
+{
+	const char *value;
+	char *endp;
+
+	/*
+	 * delim must point to the '=', otherwise it is a syntax error and
+	 * if delim points to the terminating zero, then delim + 1 wil point
+	 * past the end of the string.
+	 */
+	if (*delim != '=')
+		return -EINVAL;
+
+	value = delim + 1;
+	*int_ret = simple_strtol(value, &endp, 10);
+
+	/* Make sure we have parsed something */
+	if (endp == value)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int drm_mode_parse_panel_orientation(const char *delim,
+					    struct drm_cmdline_mode *mode)
+{
+	const char *value;
+
+	if (*delim != '=')
+		return -EINVAL;
+
+	value = delim + 1;
+	delim = strchr(value, ',');
+	if (!delim)
+		delim = value + strlen(value);
+
+	if (!strncmp(value, "normal", delim - value))
+		mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
+	else if (!strncmp(value, "upside_down", delim - value))
+		mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP;
+	else if (!strncmp(value, "left_side_up", delim - value))
+		mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP;
+	else if (!strncmp(value, "right_side_up", delim - value))
+		mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int drm_mode_parse_cmdline_options(const char *str,
+					  bool freestanding,
 					  const struct drm_connector *connector,
 					  struct drm_cmdline_mode *mode)
 {
-	unsigned int rotation = 0;
-	char *sep = str;
+	unsigned int deg, margin, rotation = 0;
+	const char *delim, *option, *sep;
 
-	while ((sep = strchr(sep, ','))) {
-		char *delim, *option;
-
-		option = sep + 1;
+	option = str;
+	do {
 		delim = strchr(option, '=');
 		if (!delim) {
 			delim = strchr(option, ',');
 
 			if (!delim)
-				delim = str + len;
+				delim = option + strlen(option);
 		}
 
 		if (!strncmp(option, "rotate", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int deg;
-
-			deg = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &deg))
 				return -EINVAL;
 
 			switch (deg) {
@@ -1619,58 +1663,40 @@ static int drm_mode_parse_cmdline_options(char *str, size_t len,
 			}
 		} else if (!strncmp(option, "reflect_x", delim - option)) {
 			rotation |= DRM_MODE_REFLECT_X;
-			sep = delim;
 		} else if (!strncmp(option, "reflect_y", delim - option)) {
 			rotation |= DRM_MODE_REFLECT_Y;
-			sep = delim;
 		} else if (!strncmp(option, "margin_right", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int margin;
-
-			margin = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &margin))
 				return -EINVAL;
 
 			mode->tv_margins.right = margin;
 		} else if (!strncmp(option, "margin_left", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int margin;
-
-			margin = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &margin))
 				return -EINVAL;
 
 			mode->tv_margins.left = margin;
 		} else if (!strncmp(option, "margin_top", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int margin;
-
-			margin = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &margin))
 				return -EINVAL;
 
 			mode->tv_margins.top = margin;
 		} else if (!strncmp(option, "margin_bottom", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int margin;
-
-			margin = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &margin))
 				return -EINVAL;
 
 			mode->tv_margins.bottom = margin;
+		} else if (!strncmp(option, "panel_orientation", delim - option)) {
+			if (drm_mode_parse_panel_orientation(delim, mode))
+				return -EINVAL;
 		} else {
 			return -EINVAL;
 		}
-	}
+		sep = strchr(delim, ',');
+		option = sep + 1;
+	} while (sep);
+
+	if (rotation && freestanding)
+		return -EINVAL;
 
 	mode->rotation_reflection = rotation;
 
@@ -1682,17 +1708,6 @@ static const char * const drm_named_modes_whitelist[] = {
 	"PAL",
 };
 
-static bool drm_named_mode_is_in_whitelist(const char *mode, unsigned int size)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(drm_named_modes_whitelist); i++)
-		if (!strncmp(mode, drm_named_modes_whitelist[i], size))
-			return true;
-
-	return false;
-}
-
 /**
  * drm_mode_parse_command_line_for_connector - parse command line modeline for connector
  * @mode_option: optional per connector mode option
@@ -1723,72 +1738,30 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 					       struct drm_cmdline_mode *mode)
 {
 	const char *name;
-	bool named_mode = false, parse_extras = false;
+	bool freestanding = false, parse_extras = false;
 	unsigned int bpp_off = 0, refresh_off = 0, options_off = 0;
 	unsigned int mode_end = 0;
-	char *bpp_ptr = NULL, *refresh_ptr = NULL, *extra_ptr = NULL;
-	char *options_ptr = NULL;
+	const char *bpp_ptr = NULL, *refresh_ptr = NULL, *extra_ptr = NULL;
+	const char *options_ptr = NULL;
 	char *bpp_end_ptr = NULL, *refresh_end_ptr = NULL;
-	int ret;
+	int i, len, ret;
 
-#ifdef CONFIG_FB
-	if (!mode_option)
-		mode_option = fb_mode_option;
-#endif
+	memset(mode, 0, sizeof(*mode));
+	mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_UNKNOWN;
 
-	if (!mode_option) {
-		mode->specified = false;
+	if (!mode_option)
 		return false;
-	}
 
 	name = mode_option;
 
-	/*
-	 * This is a bit convoluted. To differentiate between the
-	 * named modes and poorly formatted resolutions, we need a
-	 * bunch of things:
-	 *   - We need to make sure that the first character (which
-	 *     would be our resolution in X) is a digit.
-	 *   - If not, then it's either a named mode or a force on/off.
-	 *     To distinguish between the two, we need to run the
-	 *     extra parsing function, and if not, then we consider it
-	 *     a named mode.
-	 *
-	 * If this isn't enough, we should add more heuristics here,
-	 * and matching unit-tests.
-	 */
-	if (!isdigit(name[0]) && name[0] != 'x') {
-		unsigned int namelen = strlen(name);
-
-		/*
-		 * Only the force on/off options can be in that case,
-		 * and they all take a single character.
-		 */
-		if (namelen == 1) {
-			ret = drm_mode_parse_cmdline_extra(name, namelen, true,
-							   connector, mode);
-			if (!ret)
-				return true;
-		}
-
-		named_mode = true;
-	}
-
 	/* Try to locate the bpp and refresh specifiers, if any */
 	bpp_ptr = strchr(name, '-');
-	if (bpp_ptr) {
+	if (bpp_ptr)
 		bpp_off = bpp_ptr - name;
-		mode->bpp_specified = true;
-	}
 
 	refresh_ptr = strchr(name, '@');
-	if (refresh_ptr) {
-		if (named_mode)
-			return false;
-
+	if (refresh_ptr)
 		refresh_off = refresh_ptr - name;
-		mode->refresh_specified = true;
-	}
 
 	/* Locate the start of named options */
 	options_ptr = strchr(name, ',');
@@ -1802,33 +1775,58 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 		mode_end = refresh_off;
 	} else if (options_ptr) {
 		mode_end = options_off;
+		parse_extras = true;
 	} else {
 		mode_end = strlen(name);
 		parse_extras = true;
 	}
 
-	if (named_mode) {
-		if (mode_end + 1 > DRM_DISPLAY_MODE_LEN)
-			return false;
+	/* First check for a named mode */
+	for (i = 0; i < ARRAY_SIZE(drm_named_modes_whitelist); i++) {
+		ret = str_has_prefix(name, drm_named_modes_whitelist[i]);
+		if (ret == mode_end) {
+			if (refresh_ptr)
+				return false; /* named + refresh is invalid */
 
-		if (!drm_named_mode_is_in_whitelist(name, mode_end))
-			return false;
+			strcpy(mode->name, drm_named_modes_whitelist[i]);
+			mode->specified = true;
+			break;
+		}
+	}
 
-		strscpy(mode->name, name, mode_end + 1);
-	} else {
+	/* No named mode? Check for a normal mode argument, e.g. 1024x768 */
+	if (!mode->specified && isdigit(name[0])) {
 		ret = drm_mode_parse_cmdline_res_mode(name, mode_end,
 						      parse_extras,
 						      connector,
 						      mode);
 		if (ret)
 			return false;
+
+		mode->specified = true;
+	}
+
+	/* No mode? Check for freestanding extras and/or options */
+	if (!mode->specified) {
+		unsigned int len = strlen(mode_option);
+
+		if (bpp_ptr || refresh_ptr)
+			return false; /* syntax error */
+
+		if (len == 1 || (len >= 2 && mode_option[1] == ','))
+			extra_ptr = mode_option;
+		else
+			options_ptr = mode_option - 1;
+
+		freestanding = true;
 	}
-	mode->specified = true;
 
 	if (bpp_ptr) {
 		ret = drm_mode_parse_cmdline_bpp(bpp_ptr, &bpp_end_ptr, mode);
 		if (ret)
 			return false;
+
+		mode->bpp_specified = true;
 	}
 
 	if (refresh_ptr) {
@@ -1836,6 +1834,8 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 						     &refresh_end_ptr, mode);
 		if (ret)
 			return false;
+
+		mode->refresh_specified = true;
 	}
 
 	/*
@@ -1849,20 +1849,21 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 	else if (refresh_ptr)
 		extra_ptr = refresh_end_ptr;
 
-	if (extra_ptr &&
-	    extra_ptr != options_ptr) {
-		int len = strlen(name) - (extra_ptr - name);
+	if (extra_ptr) {
+		if (options_ptr)
+			len = options_ptr - extra_ptr;
+		else
+			len = strlen(extra_ptr);
 
-		ret = drm_mode_parse_cmdline_extra(extra_ptr, len, false,
+		ret = drm_mode_parse_cmdline_extra(extra_ptr, len, freestanding,
 						   connector, mode);
 		if (ret)
 			return false;
 	}
 
 	if (options_ptr) {
-		int len = strlen(name) - (options_ptr - name);
-
-		ret = drm_mode_parse_cmdline_options(options_ptr, len,
+		ret = drm_mode_parse_cmdline_options(options_ptr + 1,
+						     freestanding,
 						     connector, mode);
 		if (ret)
 			return false;
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 0ca58803ba46..b50b44e76279 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -274,3 +274,119 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(drm_of_find_panel_or_bridge);
+
+enum drm_of_lvds_pixels {
+	DRM_OF_LVDS_EVEN = BIT(0),
+	DRM_OF_LVDS_ODD = BIT(1),
+};
+
+static int drm_of_lvds_get_port_pixels_type(struct device_node *port_node)
+{
+	bool even_pixels =
+		of_property_read_bool(port_node, "dual-lvds-even-pixels");
+	bool odd_pixels =
+		of_property_read_bool(port_node, "dual-lvds-odd-pixels");
+
+	return (even_pixels ? DRM_OF_LVDS_EVEN : 0) |
+	       (odd_pixels ? DRM_OF_LVDS_ODD : 0);
+}
+
+static int drm_of_lvds_get_remote_pixels_type(
+			const struct device_node *port_node)
+{
+	struct device_node *endpoint = NULL;
+	int pixels_type = -EPIPE;
+
+	for_each_child_of_node(port_node, endpoint) {
+		struct device_node *remote_port;
+		int current_pt;
+
+		if (!of_node_name_eq(endpoint, "endpoint"))
+			continue;
+
+		remote_port = of_graph_get_remote_port(endpoint);
+		if (!remote_port) {
+			of_node_put(remote_port);
+			return -EPIPE;
+		}
+
+		current_pt = drm_of_lvds_get_port_pixels_type(remote_port);
+		of_node_put(remote_port);
+		if (pixels_type < 0)
+			pixels_type = current_pt;
+
+		/*
+		 * Sanity check, ensure that all remote endpoints have the same
+		 * pixel type. We may lift this restriction later if we need to
+		 * support multiple sinks with different dual-link
+		 * configurations by passing the endpoints explicitly to
+		 * drm_of_lvds_get_dual_link_pixel_order().
+		 */
+		if (!current_pt || pixels_type != current_pt) {
+			of_node_put(remote_port);
+			return -EINVAL;
+		}
+	}
+
+	return pixels_type;
+}
+
+/**
+ * drm_of_lvds_get_dual_link_pixel_order - Get LVDS dual-link pixel order
+ * @port1: First DT port node of the Dual-link LVDS source
+ * @port2: Second DT port node of the Dual-link LVDS source
+ *
+ * An LVDS dual-link connection is made of two links, with even pixels
+ * transitting on one link, and odd pixels on the other link. This function
+ * returns, for two ports of an LVDS dual-link source, which port shall transmit
+ * the even and odd pixels, based on the requirements of the connected sink.
+ *
+ * The pixel order is determined from the dual-lvds-even-pixels and
+ * dual-lvds-odd-pixels properties in the sink's DT port nodes. If those
+ * properties are not present, or if their usage is not valid, this function
+ * returns -EINVAL.
+ *
+ * If either port is not connected, this function returns -EPIPE.
+ *
+ * @port1 and @port2 are typically DT sibling nodes, but may have different
+ * parents when, for instance, two separate LVDS encoders carry the even and odd
+ * pixels.
+ *
+ * Return:
+ * * DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS - @port1 carries even pixels and @port2
+ *   carries odd pixels
+ * * DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS - @port1 carries odd pixels and @port2
+ *   carries even pixels
+ * * -EINVAL - @port1 and @port2 are not connected to a dual-link LVDS sink, or
+ *   the sink configuration is invalid
+ * * -EPIPE - when @port1 or @port2 are not connected
+ */
+int drm_of_lvds_get_dual_link_pixel_order(const struct device_node *port1,
+					  const struct device_node *port2)
+{
+	int remote_p1_pt, remote_p2_pt;
+
+	if (!port1 || !port2)
+		return -EINVAL;
+
+	remote_p1_pt = drm_of_lvds_get_remote_pixels_type(port1);
+	if (remote_p1_pt < 0)
+		return remote_p1_pt;
+
+	remote_p2_pt = drm_of_lvds_get_remote_pixels_type(port2);
+	if (remote_p2_pt < 0)
+		return remote_p2_pt;
+
+	/*
+	 * A valid dual-lVDS bus is found when one remote port is marked with
+	 * "dual-lvds-even-pixels", and the other remote port is marked with
+	 * "dual-lvds-odd-pixels", bail out if the markers are not right.
+	 */
+	if (remote_p1_pt + remote_p2_pt != DRM_OF_LVDS_EVEN + DRM_OF_LVDS_ODD)
+		return -EINVAL;
+
+	return remote_p1_pt == DRM_OF_LVDS_EVEN ?
+		DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS :
+		DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS;
+}
+EXPORT_SYMBOL_GPL(drm_of_lvds_get_dual_link_pixel_order);
diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index ed7985c0535a..8c7bac85a793 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -21,11 +21,13 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/backlight.h>
 #include <linux/err.h>
 #include <linux/module.h>
 
 #include <drm/drm_crtc.h>
 #include <drm/drm_panel.h>
+#include <drm/drm_print.h>
 
 static DEFINE_MUTEX(panel_lock);
 static LIST_HEAD(panel_list);
@@ -112,12 +114,6 @@ EXPORT_SYMBOL(drm_panel_remove);
  */
 int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector)
 {
-	if (panel->connector)
-		return -EBUSY;
-
-	panel->connector = connector;
-	panel->drm = connector->dev;
-
 	return 0;
 }
 EXPORT_SYMBOL(drm_panel_attach);
@@ -134,8 +130,6 @@ EXPORT_SYMBOL(drm_panel_attach);
  */
 void drm_panel_detach(struct drm_panel *panel)
 {
-	panel->connector = NULL;
-	panel->drm = NULL;
 }
 EXPORT_SYMBOL(drm_panel_detach);
 
@@ -151,10 +145,13 @@ EXPORT_SYMBOL(drm_panel_detach);
  */
 int drm_panel_prepare(struct drm_panel *panel)
 {
-	if (panel && panel->funcs && panel->funcs->prepare)
+	if (!panel)
+		return -EINVAL;
+
+	if (panel->funcs && panel->funcs->prepare)
 		return panel->funcs->prepare(panel);
 
-	return panel ? -ENOSYS : -EINVAL;
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_prepare);
 
@@ -171,10 +168,13 @@ EXPORT_SYMBOL(drm_panel_prepare);
  */
 int drm_panel_unprepare(struct drm_panel *panel)
 {
-	if (panel && panel->funcs && panel->funcs->unprepare)
+	if (!panel)
+		return -EINVAL;
+
+	if (panel->funcs && panel->funcs->unprepare)
 		return panel->funcs->unprepare(panel);
 
-	return panel ? -ENOSYS : -EINVAL;
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_unprepare);
 
@@ -190,10 +190,23 @@ EXPORT_SYMBOL(drm_panel_unprepare);
  */
 int drm_panel_enable(struct drm_panel *panel)
 {
-	if (panel && panel->funcs && panel->funcs->enable)
-		return panel->funcs->enable(panel);
+	int ret;
+
+	if (!panel)
+		return -EINVAL;
+
+	if (panel->funcs && panel->funcs->enable) {
+		ret = panel->funcs->enable(panel);
+		if (ret < 0)
+			return ret;
+	}
 
-	return panel ? -ENOSYS : -EINVAL;
+	ret = backlight_enable(panel->backlight);
+	if (ret < 0)
+		DRM_DEV_INFO(panel->dev, "failed to enable backlight: %d\n",
+			     ret);
+
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_enable);
 
@@ -209,16 +222,27 @@ EXPORT_SYMBOL(drm_panel_enable);
  */
 int drm_panel_disable(struct drm_panel *panel)
 {
-	if (panel && panel->funcs && panel->funcs->disable)
+	int ret;
+
+	if (!panel)
+		return -EINVAL;
+
+	ret = backlight_disable(panel->backlight);
+	if (ret < 0)
+		DRM_DEV_INFO(panel->dev, "failed to disable backlight: %d\n",
+			     ret);
+
+	if (panel->funcs && panel->funcs->disable)
 		return panel->funcs->disable(panel);
 
-	return panel ? -ENOSYS : -EINVAL;
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_disable);
 
 /**
  * drm_panel_get_modes - probe the available display modes of a panel
  * @panel: DRM panel
+ * @connector: DRM connector
  *
  * The modes probed from the panel are automatically added to the connector
  * that the panel is attached to.
@@ -226,12 +250,16 @@ EXPORT_SYMBOL(drm_panel_disable);
  * Return: The number of modes available from the panel on success or a
  * negative error code on failure.
  */
-int drm_panel_get_modes(struct drm_panel *panel)
+int drm_panel_get_modes(struct drm_panel *panel,
+			struct drm_connector *connector)
 {
-	if (panel && panel->funcs && panel->funcs->get_modes)
-		return panel->funcs->get_modes(panel);
+	if (!panel)
+		return -EINVAL;
 
-	return panel ? -ENOSYS : -EINVAL;
+	if (panel->funcs && panel->funcs->get_modes)
+		return panel->funcs->get_modes(panel, connector);
+
+	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL(drm_panel_get_modes);
 
@@ -274,6 +302,45 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np)
 EXPORT_SYMBOL(of_drm_find_panel);
 #endif
 
+#if IS_REACHABLE(CONFIG_BACKLIGHT_CLASS_DEVICE)
+/**
+ * drm_panel_of_backlight - use backlight device node for backlight
+ * @panel: DRM panel
+ *
+ * Use this function to enable backlight handling if your panel
+ * uses device tree and has a backlight phandle.
+ *
+ * When the panel is enabled backlight will be enabled after a
+ * successful call to &drm_panel_funcs.enable()
+ *
+ * When the panel is disabled backlight will be disabled before the
+ * call to &drm_panel_funcs.disable().
+ *
+ * A typical implementation for a panel driver supporting device tree
+ * will call this function at probe time. Backlight will then be handled
+ * transparently without requiring any intervention from the driver.
+ * drm_panel_of_backlight() must be called after the call to drm_panel_init().
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int drm_panel_of_backlight(struct drm_panel *panel)
+{
+	struct backlight_device *backlight;
+
+	if (!panel || !panel->dev)
+		return -EINVAL;
+
+	backlight = devm_of_find_backlight(panel->dev);
+
+	if (IS_ERR(backlight))
+		return PTR_ERR(backlight);
+
+	panel->backlight = backlight;
+	return 0;
+}
+EXPORT_SYMBOL(drm_panel_of_backlight);
+#endif
+
 MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>");
 MODULE_DESCRIPTION("DRM panel infrastructure");
 MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index a86a3ab2771c..f2e43d341980 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -125,8 +125,6 @@ void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 
 EXPORT_SYMBOL(drm_pci_free);
 
-#ifdef CONFIG_PCI
-
 static int drm_get_pci_domain(struct drm_device *dev)
 {
 #ifndef __alpha__
@@ -284,6 +282,8 @@ err_free:
 }
 EXPORT_SYMBOL(drm_get_pci_dev);
 
+#ifdef CONFIG_DRM_LEGACY
+
 /**
  * drm_legacy_pci_init - shadow-attach a legacy DRM PCI driver
  * @driver: DRM device driver
@@ -331,17 +331,6 @@ int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 }
 EXPORT_SYMBOL(drm_legacy_pci_init);
 
-#else
-
-void drm_pci_agp_destroy(struct drm_device *dev) {}
-
-int drm_irq_by_busid(struct drm_device *dev, void *data,
-		     struct drm_file *file_priv)
-{
-	return -EINVAL;
-}
-#endif
-
 /**
  * drm_legacy_pci_exit - unregister shadow-attach legacy DRM driver
  * @driver: DRM device driver
@@ -367,3 +356,5 @@ void drm_legacy_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver)
 	DRM_INFO("Module unloaded\n");
 }
 EXPORT_SYMBOL(drm_legacy_pci_exit);
+
+#endif
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 0814211b0f3f..86d9b0e45c8c 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -240,6 +240,7 @@ void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv)
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info)
 {
+	struct drm_gem_object *obj = exp_info->priv;
 	struct dma_buf *dma_buf;
 
 	dma_buf = dma_buf_export(exp_info);
@@ -247,7 +248,8 @@ struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 		return dma_buf;
 
 	drm_dev_get(dev);
-	drm_gem_object_get(exp_info->priv);
+	drm_gem_object_get(obj);
+	dma_buf->file->f_mapping = obj->dev->anon_inode->i_mapping;
 
 	return dma_buf;
 }
@@ -713,6 +715,9 @@ int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	struct file *fil;
 	int ret;
 
+	/* Add the fake offset */
+	vma->vm_pgoff += drm_vma_node_start(&obj->vma_node);
+
 	if (obj->funcs && obj->funcs->mmap) {
 		ret = obj->funcs->mmap(obj, vma);
 		if (ret)
@@ -737,8 +742,6 @@ int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	if (ret)
 		goto out;
 
-	vma->vm_pgoff += drm_vma_node_start(&obj->vma_node);
-
 	ret = obj->dev->driver->fops->mmap(fil, vma);
 
 	drm_vma_node_revoke(&obj->vma_node, priv);
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index 9a25d73c155c..111b932cf2a9 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -37,11 +37,11 @@
 #include <drm/drm_print.h>
 
 /*
- * drm_debug: Enable debug output.
+ * __drm_debug: Enable debug output.
  * Bitmask of DRM_UT_x. See include/drm/drm_print.h for details.
  */
-unsigned int drm_debug;
-EXPORT_SYMBOL(drm_debug);
+unsigned int __drm_debug;
+EXPORT_SYMBOL(__drm_debug);
 
 MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug category.\n"
 "\t\tBit 0 (0x01)  will enable CORE messages (drm core code)\n"
@@ -52,7 +52,7 @@ MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug cat
 "\t\tBit 5 (0x20)  will enable VBL messages (vblank code)\n"
 "\t\tBit 7 (0x80)  will enable LEASE messages (leasing code)\n"
 "\t\tBit 8 (0x100) will enable DP messages (displayport code)");
-module_param_named(debug, drm_debug, int, 0600);
+module_param_named(debug, __drm_debug, int, 0600);
 
 void __drm_puts_coredump(struct drm_printer *p, const char *str)
 {
@@ -256,7 +256,7 @@ void drm_dev_printk(const struct device *dev, const char *level,
 }
 EXPORT_SYMBOL(drm_dev_printk);
 
-void drm_dev_dbg(const struct device *dev, unsigned int category,
+void drm_dev_dbg(const struct device *dev, enum drm_debug_category category,
 		 const char *format, ...)
 {
 	struct va_format vaf;
@@ -280,7 +280,7 @@ void drm_dev_dbg(const struct device *dev, unsigned int category,
 }
 EXPORT_SYMBOL(drm_dev_dbg);
 
-void drm_dbg(unsigned int category, const char *format, ...)
+void __drm_dbg(enum drm_debug_category category, const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
@@ -297,9 +297,9 @@ void drm_dbg(unsigned int category, const char *format, ...)
 
 	va_end(args);
 }
-EXPORT_SYMBOL(drm_dbg);
+EXPORT_SYMBOL(__drm_dbg);
 
-void drm_err(const char *format, ...)
+void __drm_err(const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
@@ -313,7 +313,7 @@ void drm_err(const char *format, ...)
 
 	va_end(args);
 }
-EXPORT_SYMBOL(drm_err);
+EXPORT_SYMBOL(__drm_err);
 
 /**
  * drm_print_regset32 - print the contents of registers to a
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index a7c87abe88d0..576b4b7dcd89 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -101,6 +101,7 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 
 	/* Step 2: Validate against encoders and crtcs */
 	drm_connector_for_each_possible_encoder(connector, encoder) {
+		struct drm_bridge *bridge;
 		struct drm_crtc *crtc;
 
 		ret = drm_encoder_mode_valid(encoder, mode);
@@ -112,7 +113,8 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 			continue;
 		}
 
-		ret = drm_bridge_mode_valid(encoder->bridge, mode);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		ret = drm_bridge_chain_mode_valid(bridge, mode);
 		if (ret != MODE_OK) {
 			/* There is also no point in continuing for crtc check
 			 * here. */
diff --git a/drivers/gpu/drm/drm_rect.c b/drivers/gpu/drm/drm_rect.c
index b8363aaa9032..0460e874896e 100644
--- a/drivers/gpu/drm/drm_rect.c
+++ b/drivers/gpu/drm/drm_rect.c
@@ -52,9 +52,17 @@ bool drm_rect_intersect(struct drm_rect *r1, const struct drm_rect *r2)
 }
 EXPORT_SYMBOL(drm_rect_intersect);
 
-static u32 clip_scaled(u32 src, u32 dst, u32 clip)
+static u32 clip_scaled(int src, int dst, int *clip)
 {
-	u64 tmp = mul_u32_u32(src, dst - clip);
+	u64 tmp;
+
+	if (dst == 0)
+		return 0;
+
+	/* Only clip what we have. Keeps the result bounded. */
+	*clip = min(*clip, dst);
+
+	tmp = mul_u32_u32(src, dst - *clip);
 
 	/*
 	 * Round toward 1.0 when clipping so that we don't accidentally
@@ -73,11 +81,13 @@ static u32 clip_scaled(u32 src, u32 dst, u32 clip)
  * @clip: clip rectangle
  *
  * Clip rectangle @dst by rectangle @clip. Clip rectangle @src by the
- * same amounts multiplied by @hscale and @vscale.
+ * the corresponding amounts, retaining the vertical and horizontal scaling
+ * factors from @src to @dst.
  *
  * RETURNS:
+ *
  * %true if rectangle @dst is still visible after being clipped,
- * %false otherwise
+ * %false otherwise.
  */
 bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst,
 			  const struct drm_rect *clip)
@@ -87,34 +97,34 @@ bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst,
 	diff = clip->x1 - dst->x1;
 	if (diff > 0) {
 		u32 new_src_w = clip_scaled(drm_rect_width(src),
-					    drm_rect_width(dst), diff);
+					    drm_rect_width(dst), &diff);
 
-		src->x1 = clamp_t(int64_t, src->x2 - new_src_w, INT_MIN, INT_MAX);
-		dst->x1 = clip->x1;
+		src->x1 = src->x2 - new_src_w;
+		dst->x1 += diff;
 	}
 	diff = clip->y1 - dst->y1;
 	if (diff > 0) {
 		u32 new_src_h = clip_scaled(drm_rect_height(src),
-					    drm_rect_height(dst), diff);
+					    drm_rect_height(dst), &diff);
 
-		src->y1 = clamp_t(int64_t, src->y2 - new_src_h, INT_MIN, INT_MAX);
-		dst->y1 = clip->y1;
+		src->y1 = src->y2 - new_src_h;
+		dst->y1 += diff;
 	}
 	diff = dst->x2 - clip->x2;
 	if (diff > 0) {
 		u32 new_src_w = clip_scaled(drm_rect_width(src),
-					    drm_rect_width(dst), diff);
+					    drm_rect_width(dst), &diff);
 
-		src->x2 = clamp_t(int64_t, src->x1 + new_src_w, INT_MIN, INT_MAX);
-		dst->x2 = clip->x2;
+		src->x2 = src->x1 + new_src_w;
+		dst->x2 -= diff;
 	}
 	diff = dst->y2 - clip->y2;
 	if (diff > 0) {
 		u32 new_src_h = clip_scaled(drm_rect_height(src),
-					    drm_rect_height(dst), diff);
+					    drm_rect_height(dst), &diff);
 
-		src->y2 = clamp_t(int64_t, src->y1 + new_src_h, INT_MIN, INT_MAX);
-		dst->y2 = clip->y2;
+		src->y2 = src->y1 + new_src_h;
+		dst->y2 -= diff;
 	}
 
 	return drm_rect_visible(dst);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index ac26c084f30d..6b43c1c94e8f 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -65,12 +65,13 @@ static int etnaviv_open(struct drm_device *dev, struct drm_file *file)
 
 	for (i = 0; i < ETNA_MAX_PIPES; i++) {
 		struct etnaviv_gpu *gpu = priv->gpu[i];
-		struct drm_sched_rq *rq;
+		struct drm_gpu_scheduler *sched;
 
 		if (gpu) {
-			rq = &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+			sched = &gpu->sched;
 			drm_sched_entity_init(&ctx->sched_entity[i],
-					      &rq, 1, NULL);
+					      DRM_SCHED_PRIORITY_NORMAL, &sched,
+					      1, NULL);
 			}
 	}
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index aa3e4c3b063a..3b0afa156d92 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -113,7 +113,7 @@ static void submit_unlock_object(struct etnaviv_gem_submit *submit, int i)
 	if (submit->bos[i].flags & BO_LOCKED) {
 		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 
-		ww_mutex_unlock(&obj->resv->lock);
+		dma_resv_unlock(obj->resv);
 		submit->bos[i].flags &= ~BO_LOCKED;
 	}
 }
@@ -133,8 +133,7 @@ retry:
 		contended = i;
 
 		if (!(submit->bos[i].flags & BO_LOCKED)) {
-			ret = ww_mutex_lock_interruptible(&obj->resv->lock,
-							  ticket);
+			ret = dma_resv_lock_interruptible(obj->resv, ticket);
 			if (ret == -EALREADY)
 				DRM_ERROR("BO at index %u already on submit list\n",
 					  i);
@@ -161,8 +160,7 @@ fail:
 		obj = &submit->bos[contended].obj->base;
 
 		/* we lost out in a seqno race, lock and retry.. */
-		ret = ww_mutex_lock_slow_interruptible(&obj->resv->lock,
-						       ticket);
+		ret = dma_resv_lock_slow_interruptible(obj->resv, ticket);
 		if (!ret) {
 			submit->bos[contended].flags |= BO_LOCKED;
 			slow_locked = contended;
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 6f7d3b3b3628..6417f374b923 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -1,13 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_EXYNOS
-	tristate "DRM Support for Samsung SoC EXYNOS Series"
+	tristate "DRM Support for Samsung SoC Exynos Series"
 	depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST)
 	depends on MMU
 	select DRM_KMS_HELPER
 	select VIDEOMODE_HELPERS
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	help
-	  Choose this option if you have a Samsung SoC EXYNOS chipset.
+	  Choose this option if you have a Samsung SoC Exynos chipset.
 	  If M is selected the module will be called exynosdrm.
 
 if DRM_EXYNOS
@@ -62,7 +62,7 @@ config DRM_EXYNOS_DSI
 	  This enables support for Exynos MIPI-DSI device.
 
 config DRM_EXYNOS_DP
-	bool "EXYNOS specific extensions for Analogix DP driver"
+	bool "Exynos specific extensions for Analogix DP driver"
 	depends on DRM_EXYNOS_FIMD || DRM_EXYNOS7_DECON
 	select DRM_ANALOGIX_DP
 	default DRM_EXYNOS
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 2d5cbfda3ca7..8428ae12dfa5 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -510,7 +510,7 @@ static void decon_swreset(struct decon_context *ctx)
 	       ctx->addr + DECON_CRCCTRL);
 }
 
-static void decon_enable(struct exynos_drm_crtc *crtc)
+static void decon_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
 
@@ -523,7 +523,7 @@ static void decon_enable(struct exynos_drm_crtc *crtc)
 	decon_commit(ctx->crtc);
 }
 
-static void decon_disable(struct exynos_drm_crtc *crtc)
+static void decon_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
 	int i;
@@ -599,8 +599,8 @@ static enum drm_mode_status decon_mode_valid(struct exynos_drm_crtc *crtc,
 }
 
 static const struct exynos_drm_crtc_ops decon_crtc_ops = {
-	.enable			= decon_enable,
-	.disable		= decon_disable,
+	.atomic_enable		= decon_atomic_enable,
+	.atomic_disable		= decon_atomic_disable,
 	.enable_vblank		= decon_enable_vblank,
 	.disable_vblank		= decon_disable_vblank,
 	.atomic_begin		= decon_atomic_begin,
@@ -651,7 +651,7 @@ static void decon_unbind(struct device *dev, struct device *master, void *data)
 {
 	struct decon_context *ctx = dev_get_drvdata(dev);
 
-	decon_disable(ctx->crtc);
+	decon_atomic_disable(ctx->crtc);
 
 	/* detach this sub driver from iommu mapping if supported. */
 	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f0640950bd46..ff59c641fa80 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -526,7 +526,7 @@ static void decon_init(struct decon_context *ctx)
 		writel(VIDCON1_VCLK_HOLD, ctx->regs + VIDCON1(0));
 }
 
-static void decon_enable(struct exynos_drm_crtc *crtc)
+static void decon_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
 
@@ -546,7 +546,7 @@ static void decon_enable(struct exynos_drm_crtc *crtc)
 	ctx->suspended = false;
 }
 
-static void decon_disable(struct exynos_drm_crtc *crtc)
+static void decon_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
 	int i;
@@ -568,8 +568,8 @@ static void decon_disable(struct exynos_drm_crtc *crtc)
 }
 
 static const struct exynos_drm_crtc_ops decon_crtc_ops = {
-	.enable = decon_enable,
-	.disable = decon_disable,
+	.atomic_enable = decon_atomic_enable,
+	.atomic_disable = decon_atomic_disable,
 	.enable_vblank = decon_enable_vblank,
 	.disable_vblank = decon_disable_vblank,
 	.atomic_begin = decon_atomic_begin,
@@ -653,7 +653,7 @@ static void decon_unbind(struct device *dev, struct device *master,
 {
 	struct decon_context *ctx = dev_get_drvdata(dev);
 
-	decon_disable(ctx->crtc);
+	decon_atomic_disable(ctx->crtc);
 
 	if (ctx->encoder)
 		exynos_dpi_remove(ctx->encoder);
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 1e6aa24bf45e..4785885c0f4f 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -110,7 +110,6 @@ static int exynos_dp_bridge_attach(struct analogix_dp_plat_data *plat_data,
 		if (ret) {
 			DRM_DEV_ERROR(dp->dev,
 				      "Failed to attach bridge to drm\n");
-			bridge->next = NULL;
 			return ret;
 		}
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 77ce78986408..1c03485676ef 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -23,8 +23,8 @@ static void exynos_drm_crtc_atomic_enable(struct drm_crtc *crtc,
 {
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
 
-	if (exynos_crtc->ops->enable)
-		exynos_crtc->ops->enable(exynos_crtc);
+	if (exynos_crtc->ops->atomic_enable)
+		exynos_crtc->ops->atomic_enable(exynos_crtc);
 
 	drm_crtc_vblank_on(crtc);
 }
@@ -36,8 +36,8 @@ static void exynos_drm_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	drm_crtc_vblank_off(crtc);
 
-	if (exynos_crtc->ops->disable)
-		exynos_crtc->ops->disable(exynos_crtc);
+	if (exynos_crtc->ops->atomic_disable)
+		exynos_crtc->ops->atomic_disable(exynos_crtc);
 
 	if (crtc->state->event && !crtc->state->active) {
 		spin_lock_irq(&crtc->dev->event_lock);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 3cebb19ec1c4..43fa0f26c052 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -43,7 +43,7 @@ exynos_dpi_detect(struct drm_connector *connector, bool force)
 {
 	struct exynos_dpi *ctx = connector_to_dpi(connector);
 
-	if (ctx->panel && !ctx->panel->connector)
+	if (ctx->panel)
 		drm_panel_attach(ctx->panel, &ctx->connector);
 
 	return connector_status_connected;
@@ -85,7 +85,7 @@ static int exynos_dpi_get_modes(struct drm_connector *connector)
 	}
 
 	if (ctx->panel)
-		return ctx->panel->funcs->get_modes(ctx->panel);
+		return drm_panel_get_modes(ctx->panel, connector);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index d4014ba592fd..d4d21d8cfb90 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -118,8 +118,8 @@ struct exynos_drm_plane_config {
 /*
  * Exynos drm crtc ops
  *
- * @enable: enable the device
- * @disable: disable the device
+ * @atomic_enable: enable the device
+ * @atomic_disable: disable the device
  * @enable_vblank: specific driver callback for enabling vblank interrupt.
  * @disable_vblank: specific driver callback for disabling vblank interrupt.
  * @mode_valid: specific driver callback for mode validation
@@ -133,8 +133,8 @@ struct exynos_drm_plane_config {
  */
 struct exynos_drm_crtc;
 struct exynos_drm_crtc_ops {
-	void (*enable)(struct exynos_drm_crtc *crtc);
-	void (*disable)(struct exynos_drm_crtc *crtc);
+	void (*atomic_enable)(struct exynos_drm_crtc *crtc);
+	void (*atomic_disable)(struct exynos_drm_crtc *crtc);
 	int (*enable_vblank)(struct exynos_drm_crtc *crtc);
 	void (*disable_vblank)(struct exynos_drm_crtc *crtc);
 	enum drm_mode_status (*mode_valid)(struct exynos_drm_crtc *crtc,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 72726f2c7a9f..33628d85edad 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -255,6 +255,7 @@ struct exynos_dsi {
 	struct mipi_dsi_host dsi_host;
 	struct drm_connector connector;
 	struct drm_panel *panel;
+	struct list_head bridge_chain;
 	struct drm_bridge *out_bridge;
 	struct device *dev;
 
@@ -1377,6 +1378,7 @@ static void exynos_dsi_unregister_te_irq(struct exynos_dsi *dsi)
 static void exynos_dsi_enable(struct drm_encoder *encoder)
 {
 	struct exynos_dsi *dsi = encoder_to_dsi(encoder);
+	struct drm_bridge *iter;
 	int ret;
 
 	if (dsi->state & DSIM_STATE_ENABLED)
@@ -1390,7 +1392,11 @@ static void exynos_dsi_enable(struct drm_encoder *encoder)
 		if (ret < 0)
 			goto err_put_sync;
 	} else {
-		drm_bridge_pre_enable(dsi->out_bridge);
+		list_for_each_entry_reverse(iter, &dsi->bridge_chain,
+					    chain_node) {
+			if (iter->funcs->pre_enable)
+				iter->funcs->pre_enable(iter);
+		}
 	}
 
 	exynos_dsi_set_display_mode(dsi);
@@ -1401,7 +1407,10 @@ static void exynos_dsi_enable(struct drm_encoder *encoder)
 		if (ret < 0)
 			goto err_display_disable;
 	} else {
-		drm_bridge_enable(dsi->out_bridge);
+		list_for_each_entry(iter, &dsi->bridge_chain, chain_node) {
+			if (iter->funcs->enable)
+				iter->funcs->enable(iter);
+		}
 	}
 
 	dsi->state |= DSIM_STATE_VIDOUT_AVAILABLE;
@@ -1419,6 +1428,7 @@ err_put_sync:
 static void exynos_dsi_disable(struct drm_encoder *encoder)
 {
 	struct exynos_dsi *dsi = encoder_to_dsi(encoder);
+	struct drm_bridge *iter;
 
 	if (!(dsi->state & DSIM_STATE_ENABLED))
 		return;
@@ -1426,10 +1436,20 @@ static void exynos_dsi_disable(struct drm_encoder *encoder)
 	dsi->state &= ~DSIM_STATE_VIDOUT_AVAILABLE;
 
 	drm_panel_disable(dsi->panel);
-	drm_bridge_disable(dsi->out_bridge);
+
+	list_for_each_entry_reverse(iter, &dsi->bridge_chain, chain_node) {
+		if (iter->funcs->disable)
+			iter->funcs->disable(iter);
+	}
+
 	exynos_dsi_set_display_enable(dsi, false);
 	drm_panel_unprepare(dsi->panel);
-	drm_bridge_post_disable(dsi->out_bridge);
+
+	list_for_each_entry(iter, &dsi->bridge_chain, chain_node) {
+		if (iter->funcs->post_disable)
+			iter->funcs->post_disable(iter);
+	}
+
 	dsi->state &= ~DSIM_STATE_ENABLED;
 	pm_runtime_put_sync(dsi->dev);
 }
@@ -1461,7 +1481,7 @@ static int exynos_dsi_get_modes(struct drm_connector *connector)
 	struct exynos_dsi *dsi = connector_to_dsi(connector);
 
 	if (dsi->panel)
-		return dsi->panel->funcs->get_modes(dsi->panel);
+		return drm_panel_get_modes(dsi->panel, connector);
 
 	return 0;
 }
@@ -1522,7 +1542,7 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host,
 	if (out_bridge) {
 		drm_bridge_attach(encoder, out_bridge, NULL);
 		dsi->out_bridge = out_bridge;
-		encoder->bridge = NULL;
+		list_splice_init(&encoder->bridge_chain, &dsi->bridge_chain);
 	} else {
 		int ret = exynos_dsi_create_connector(encoder);
 
@@ -1588,6 +1608,7 @@ static int exynos_dsi_host_detach(struct mipi_dsi_host *host,
 		if (dsi->out_bridge->funcs->detach)
 			dsi->out_bridge->funcs->detach(dsi->out_bridge);
 		dsi->out_bridge = NULL;
+		INIT_LIST_HEAD(&dsi->bridge_chain);
 	}
 
 	if (drm->mode_config.poll_enabled)
@@ -1735,6 +1756,7 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 	init_completion(&dsi->completed);
 	spin_lock_init(&dsi->transfer_lock);
 	INIT_LIST_HEAD(&dsi->transfer_list);
+	INIT_LIST_HEAD(&dsi->bridge_chain);
 
 	dsi->dsi_host.ops = &exynos_dsi_ops;
 	dsi->dsi_host.dev = dev;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index b0877b97291c..647a1fd1d815 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -60,7 +60,7 @@ static int exynos_drm_fb_mmap(struct fb_info *info,
 	return 0;
 }
 
-static struct fb_ops exynos_drm_fb_ops = {
+static const struct fb_ops exynos_drm_fb_ops = {
 	.owner		= THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_mmap        = exynos_drm_fb_mmap,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 8d0a929104e5..21aec38702fc 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -894,7 +894,7 @@ static void fimd_disable_plane(struct exynos_drm_crtc *crtc,
 		fimd_enable_shadow_channel_path(ctx, win, false);
 }
 
-static void fimd_enable(struct exynos_drm_crtc *crtc)
+static void fimd_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct fimd_context *ctx = crtc->ctx;
 
@@ -912,7 +912,7 @@ static void fimd_enable(struct exynos_drm_crtc *crtc)
 	fimd_commit(ctx->crtc);
 }
 
-static void fimd_disable(struct exynos_drm_crtc *crtc)
+static void fimd_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct fimd_context *ctx = crtc->ctx;
 	int i;
@@ -1006,8 +1006,8 @@ static void fimd_dp_clock_enable(struct exynos_drm_clk *clk, bool enable)
 }
 
 static const struct exynos_drm_crtc_ops fimd_crtc_ops = {
-	.enable = fimd_enable,
-	.disable = fimd_disable,
+	.atomic_enable = fimd_atomic_enable,
+	.atomic_disable = fimd_atomic_disable,
 	.enable_vblank = fimd_enable_vblank,
 	.disable_vblank = fimd_disable_vblank,
 	.atomic_begin = fimd_atomic_begin,
@@ -1098,7 +1098,7 @@ static void fimd_unbind(struct device *dev, struct device *master,
 {
 	struct fimd_context *ctx = dev_get_drvdata(dev);
 
-	fimd_disable(ctx->crtc);
+	fimd_atomic_disable(ctx->crtc);
 
 	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 65b891cb9c50..b320b3a21ad4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -120,7 +120,7 @@ static void vidi_update_plane(struct exynos_drm_crtc *crtc,
 	DRM_DEV_DEBUG_KMS(ctx->dev, "dma_addr = %pad\n", &addr);
 }
 
-static void vidi_enable(struct exynos_drm_crtc *crtc)
+static void vidi_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct vidi_context *ctx = crtc->ctx;
 
@@ -133,7 +133,7 @@ static void vidi_enable(struct exynos_drm_crtc *crtc)
 	drm_crtc_vblank_on(&crtc->base);
 }
 
-static void vidi_disable(struct exynos_drm_crtc *crtc)
+static void vidi_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct vidi_context *ctx = crtc->ctx;
 
@@ -147,8 +147,8 @@ static void vidi_disable(struct exynos_drm_crtc *crtc)
 }
 
 static const struct exynos_drm_crtc_ops vidi_crtc_ops = {
-	.enable = vidi_enable,
-	.disable = vidi_disable,
+	.atomic_enable = vidi_atomic_enable,
+	.atomic_disable = vidi_atomic_disable,
 	.enable_vblank = vidi_enable_vblank,
 	.disable_vblank = vidi_disable_vblank,
 	.update_plane = vidi_update_plane,
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 48159d5d2214..9ff921f43a93 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -946,8 +946,10 @@ static int hdmi_create_connector(struct drm_encoder *encoder)
 	connector->interlace_allowed = true;
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
 
-	ret = drm_connector_init(hdata->drm_dev, connector,
-			&hdmi_connector_funcs, DRM_MODE_CONNECTOR_HDMIA);
+	ret = drm_connector_init_with_ddc(hdata->drm_dev, connector,
+					  &hdmi_connector_funcs,
+					  DRM_MODE_CONNECTOR_HDMIA,
+					  hdata->ddc_adpt);
 	if (ret) {
 		DRM_DEV_ERROR(hdata->dev,
 			      "Failed to initialize connector with drm\n");
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 6cfdb95fef2f..38ae9c32feef 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -986,7 +986,7 @@ static void mixer_atomic_flush(struct exynos_drm_crtc *crtc)
 	exynos_crtc_handle_event(crtc);
 }
 
-static void mixer_enable(struct exynos_drm_crtc *crtc)
+static void mixer_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct mixer_context *ctx = crtc->ctx;
 
@@ -1015,7 +1015,7 @@ static void mixer_enable(struct exynos_drm_crtc *crtc)
 	set_bit(MXR_BIT_POWERED, &ctx->flags);
 }
 
-static void mixer_disable(struct exynos_drm_crtc *crtc)
+static void mixer_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct mixer_context *ctx = crtc->ctx;
 	int i;
@@ -1109,8 +1109,8 @@ static bool mixer_mode_fixup(struct exynos_drm_crtc *crtc,
 }
 
 static const struct exynos_drm_crtc_ops mixer_crtc_ops = {
-	.enable			= mixer_enable,
-	.disable		= mixer_disable,
+	.atomic_enable		= mixer_atomic_enable,
+	.atomic_disable		= mixer_atomic_disable,
 	.enable_vblank		= mixer_enable_vblank,
 	.disable_vblank		= mixer_disable_vblank,
 	.atomic_begin		= mixer_atomic_begin,
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index 82c972e9c024..9598ee3cc4d2 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -68,7 +68,7 @@ static int fsl_dcu_drm_connector_get_modes(struct drm_connector *connector)
 	struct fsl_dcu_drm_connector *fsl_connector;
 
 	fsl_connector = to_fsl_dcu_connector(connector);
-	return drm_panel_get_modes(fsl_connector->panel);
+	return drm_panel_get_modes(fsl_connector->panel, connector);
 }
 
 static int fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector,
diff --git a/drivers/gpu/drm/gma500/accel_2d.c b/drivers/gpu/drm/gma500/accel_2d.c
index 45ad5ffedc93..adc0507545bf 100644
--- a/drivers/gpu/drm/gma500/accel_2d.c
+++ b/drivers/gpu/drm/gma500/accel_2d.c
@@ -21,9 +21,9 @@
 
 #include <drm/drm.h>
 #include <drm/drm_crtc.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_fourcc.h>
 
-#include "framebuffer.h"
 #include "psb_drv.h"
 #include "psb_reg.h"
 
@@ -226,11 +226,10 @@ static int psb_accel_2d_copy(struct drm_psb_private *dev_priv,
 static void psbfb_copyarea_accel(struct fb_info *info,
 				 const struct fb_copyarea *a)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
-	struct drm_device *dev = psbfb->base.dev;
-	struct drm_framebuffer *fb = fbdev->psb_fb_helper.fb;
-	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct drm_device *dev;
+	struct drm_psb_private *dev_priv;
 	uint32_t offset;
 	uint32_t stride;
 	uint32_t src_format;
@@ -239,6 +238,8 @@ static void psbfb_copyarea_accel(struct fb_info *info,
 	if (!fb)
 		return;
 
+	dev = fb->dev;
+	dev_priv = dev->dev_private;
 	offset = to_gtt_range(fb->obj[0])->offset;
 	stride = fb->pitches[0];
 
@@ -309,9 +310,9 @@ void psbfb_copyarea(struct fb_info *info,
  */
 int psbfb_sync(struct fb_info *info)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
-	struct drm_device *dev = psbfb->base.dev;
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct drm_device *dev = fb->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long _end = jiffies + HZ;
 	int busy = 0;
diff --git a/drivers/gpu/drm/gma500/cdv_intel_display.c b/drivers/gpu/drm/gma500/cdv_intel_display.c
index 8b784947ed3b..1ed854f498b7 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_display.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_display.c
@@ -582,8 +582,8 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc,
 	struct gma_clock_t clock;
 	u32 dpll = 0, dspcntr, pipeconf;
 	bool ok;
-	bool is_crt = false, is_lvds = false, is_tv = false;
-	bool is_hdmi = false, is_dp = false;
+	bool is_lvds = false, is_tv = false;
+	bool is_dp = false;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
 	const struct gma_limit_t *limit;
@@ -607,10 +607,7 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc,
 			is_tv = true;
 			break;
 		case INTEL_OUTPUT_ANALOG:
-			is_crt = true;
-			break;
 		case INTEL_OUTPUT_HDMI:
-			is_hdmi = true;
 			break;
 		case INTEL_OUTPUT_DISPLAYPORT:
 			is_dp = true;
@@ -979,6 +976,7 @@ const struct drm_crtc_funcs cdv_intel_crtc_funcs = {
 	.gamma_set = gma_crtc_gamma_set,
 	.set_config = gma_crtc_set_config,
 	.destroy = gma_crtc_destroy,
+	.page_flip = gma_crtc_page_flip,
 };
 
 const struct gma_clock_funcs cdv_clock_funcs = {
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 570b59520fd1..5772b2dce0d6 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -1594,7 +1594,6 @@ cdv_intel_dp_complete_link_train(struct gma_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
-	bool channel_eq = false;
 	int tries, cr_tries;
 	u32 reg;
 	uint32_t DP = intel_dp->DP;
@@ -1602,7 +1601,6 @@ cdv_intel_dp_complete_link_train(struct gma_encoder *encoder)
 	/* channel equalization */
 	tries = 0;
 	cr_tries = 0;
-	channel_eq = false;
 
 	DRM_DEBUG_KMS("\n");
 		reg = DP | DP_LINK_TRAIN_PAT_2;
@@ -1648,7 +1646,6 @@ cdv_intel_dp_complete_link_train(struct gma_encoder *encoder)
 
 		if (cdv_intel_channel_eq_ok(encoder)) {
 			DRM_DEBUG_KMS("PT2 train is done\n");
-			channel_eq = true;
 			break;
 		}
 
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index 218f3bb15276..1459076d1980 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -40,8 +40,8 @@ static int psbfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 			   unsigned blue, unsigned transp,
 			   struct fb_info *info)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct drm_framebuffer *fb = fbdev->psb_fb_helper.fb;
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
 	uint32_t v;
 
 	if (!fb)
@@ -77,10 +77,10 @@ static int psbfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 
 static int psbfb_pan(struct fb_var_screeninfo *var, struct fb_info *info)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
-	struct drm_device *dev = psbfb->base.dev;
-	struct gtt_range *gtt = to_gtt_range(psbfb->base.obj[0]);
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct drm_device *dev = fb->dev;
+	struct gtt_range *gtt = to_gtt_range(fb->obj[0]);
 
 	/*
 	 *	We have to poke our nose in here. The core fb code assumes
@@ -99,10 +99,10 @@ static int psbfb_pan(struct fb_var_screeninfo *var, struct fb_info *info)
 static vm_fault_t psbfb_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct psb_framebuffer *psbfb = vma->vm_private_data;
-	struct drm_device *dev = psbfb->base.dev;
+	struct drm_framebuffer *fb = vma->vm_private_data;
+	struct drm_device *dev = fb->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct gtt_range *gtt = to_gtt_range(psbfb->base.obj[0]);
+	struct gtt_range *gtt = to_gtt_range(fb->obj[0]);
 	int page_num;
 	int i;
 	unsigned long address;
@@ -145,23 +145,21 @@ static const struct vm_operations_struct psbfb_vm_ops = {
 
 static int psbfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
 
 	if (vma->vm_pgoff != 0)
 		return -EINVAL;
 	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
 		return -EINVAL;
 
-	if (!psbfb->addr_space)
-		psbfb->addr_space = vma->vm_file->f_mapping;
 	/*
 	 * If this is a GEM object then info->screen_base is the virtual
 	 * kernel remapping of the object. FIXME: Review if this is
 	 * suitable for our mmap work
 	 */
 	vma->vm_ops = &psbfb_vm_ops;
-	vma->vm_private_data = (void *)psbfb;
+	vma->vm_private_data = (void *)fb;
 	vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP;
 	return 0;
 }
@@ -209,9 +207,9 @@ static struct fb_ops psbfb_unaccel_ops = {
  *	0 on success or an error code if we fail.
  */
 static int psb_framebuffer_init(struct drm_device *dev,
-					struct psb_framebuffer *fb,
+					struct drm_framebuffer *fb,
 					const struct drm_mode_fb_cmd2 *mode_cmd,
-					struct gtt_range *gt)
+					struct drm_gem_object *obj)
 {
 	const struct drm_format_info *info;
 	int ret;
@@ -227,9 +225,9 @@ static int psb_framebuffer_init(struct drm_device *dev,
 	if (mode_cmd->pitches[0] & 63)
 		return -EINVAL;
 
-	drm_helper_mode_fill_fb_struct(dev, &fb->base, mode_cmd);
-	fb->base.obj[0] = &gt->gem;
-	ret = drm_framebuffer_init(dev, &fb->base, &psb_fb_funcs);
+	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
+	fb->obj[0] = obj;
+	ret = drm_framebuffer_init(dev, fb, &psb_fb_funcs);
 	if (ret) {
 		dev_err(dev->dev, "framebuffer init failed: %d\n", ret);
 		return ret;
@@ -252,21 +250,21 @@ static int psb_framebuffer_init(struct drm_device *dev,
 static struct drm_framebuffer *psb_framebuffer_create
 			(struct drm_device *dev,
 			 const struct drm_mode_fb_cmd2 *mode_cmd,
-			 struct gtt_range *gt)
+			 struct drm_gem_object *obj)
 {
-	struct psb_framebuffer *fb;
+	struct drm_framebuffer *fb;
 	int ret;
 
 	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
 	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
-	ret = psb_framebuffer_init(dev, fb, mode_cmd, gt);
+	ret = psb_framebuffer_init(dev, fb, mode_cmd, obj);
 	if (ret) {
 		kfree(fb);
 		return ERR_PTR(ret);
 	}
-	return &fb->base;
+	return fb;
 }
 
 /**
@@ -300,14 +298,13 @@ static struct gtt_range *psbfb_alloc(struct drm_device *dev, int aligned_size)
  *
  *	Create a framebuffer to the specifications provided
  */
-static int psbfb_create(struct psb_fbdev *fbdev,
+static int psbfb_create(struct drm_fb_helper *fb_helper,
 				struct drm_fb_helper_surface_size *sizes)
 {
-	struct drm_device *dev = fbdev->psb_fb_helper.dev;
+	struct drm_device *dev = fb_helper->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct fb_info *info;
 	struct drm_framebuffer *fb;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
 	struct drm_mode_fb_cmd2 mode_cmd;
 	int size;
 	int ret;
@@ -372,7 +369,7 @@ static int psbfb_create(struct psb_fbdev *fbdev,
 
 	memset(dev_priv->vram_addr + backing->offset, 0, size);
 
-	info = drm_fb_helper_alloc_fbi(&fbdev->psb_fb_helper);
+	info = drm_fb_helper_alloc_fbi(fb_helper);
 	if (IS_ERR(info)) {
 		ret = PTR_ERR(info);
 		goto out;
@@ -380,14 +377,13 @@ static int psbfb_create(struct psb_fbdev *fbdev,
 
 	mode_cmd.pixel_format = drm_mode_legacy_fb_format(bpp, depth);
 
-	ret = psb_framebuffer_init(dev, psbfb, &mode_cmd, backing);
-	if (ret)
+	fb = psb_framebuffer_create(dev, &mode_cmd, &backing->gem);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
 		goto out;
+	}
 
-	fb = &psbfb->base;
-	psbfb->fbdev = info;
-
-	fbdev->psb_fb_helper.fb = fb;
+	fb_helper->fb = fb;
 
 	if (dev_priv->ops->accel_2d && pitch_lines > 8)	/* 2D engine */
 		info->fbops = &psbfb_ops;
@@ -411,15 +407,14 @@ static int psbfb_create(struct psb_fbdev *fbdev,
 		info->apertures->ranges[0].size = dev_priv->gtt.stolen_size;
 	}
 
-	drm_fb_helper_fill_info(info, &fbdev->psb_fb_helper, sizes);
+	drm_fb_helper_fill_info(info, fb_helper, sizes);
 
 	info->fix.mmio_start = pci_resource_start(dev->pdev, 0);
 	info->fix.mmio_len = pci_resource_len(dev->pdev, 0);
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	dev_dbg(dev->dev, "allocated %dx%d fb\n",
-					psbfb->base.width, psbfb->base.height);
+	dev_dbg(dev->dev, "allocated %dx%d fb\n", fb->width, fb->height);
 
 	return 0;
 out:
@@ -439,7 +434,6 @@ static struct drm_framebuffer *psb_user_framebuffer_create
 			(struct drm_device *dev, struct drm_file *filp,
 			 const struct drm_mode_fb_cmd2 *cmd)
 {
-	struct gtt_range *r;
 	struct drm_gem_object *obj;
 
 	/*
@@ -451,17 +445,15 @@ static struct drm_framebuffer *psb_user_framebuffer_create
 		return ERR_PTR(-ENOENT);
 
 	/* Let the core code do all the work */
-	r = container_of(obj, struct gtt_range, gem);
-	return psb_framebuffer_create(dev, cmd, r);
+	return psb_framebuffer_create(dev, cmd, obj);
 }
 
-static int psbfb_probe(struct drm_fb_helper *helper,
+static int psbfb_probe(struct drm_fb_helper *fb_helper,
 				struct drm_fb_helper_surface_size *sizes)
 {
-	struct psb_fbdev *psb_fbdev =
-		container_of(helper, struct psb_fbdev, psb_fb_helper);
-	struct drm_device *dev = psb_fbdev->psb_fb_helper.dev;
+	struct drm_device *dev = fb_helper->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
+	unsigned int fb_size;
 	int bytespp;
 
 	bytespp = sizes->surface_bpp / 8;
@@ -471,72 +463,77 @@ static int psbfb_probe(struct drm_fb_helper *helper,
 	/* If the mode will not fit in 32bit then switch to 16bit to get
 	   a console on full resolution. The X mode setting server will
 	   allocate its own 32bit GEM framebuffer */
-	if (ALIGN(sizes->fb_width * bytespp, 64) * sizes->fb_height >
-	                dev_priv->vram_stolen_size) {
+	fb_size = ALIGN(sizes->surface_width * bytespp, 64) *
+		  sizes->surface_height;
+	fb_size = ALIGN(fb_size, PAGE_SIZE);
+
+	if (fb_size > dev_priv->vram_stolen_size) {
                 sizes->surface_bpp = 16;
                 sizes->surface_depth = 16;
         }
 
-	return psbfb_create(psb_fbdev, sizes);
+	return psbfb_create(fb_helper, sizes);
 }
 
 static const struct drm_fb_helper_funcs psb_fb_helper_funcs = {
 	.fb_probe = psbfb_probe,
 };
 
-static int psb_fbdev_destroy(struct drm_device *dev, struct psb_fbdev *fbdev)
+static int psb_fbdev_destroy(struct drm_device *dev,
+			     struct drm_fb_helper *fb_helper)
 {
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
+	struct drm_framebuffer *fb = fb_helper->fb;
+
+	drm_fb_helper_unregister_fbi(fb_helper);
 
-	drm_fb_helper_unregister_fbi(&fbdev->psb_fb_helper);
+	drm_fb_helper_fini(fb_helper);
+	drm_framebuffer_unregister_private(fb);
+	drm_framebuffer_cleanup(fb);
 
-	drm_fb_helper_fini(&fbdev->psb_fb_helper);
-	drm_framebuffer_unregister_private(&psbfb->base);
-	drm_framebuffer_cleanup(&psbfb->base);
+	if (fb->obj[0])
+		drm_gem_object_put_unlocked(fb->obj[0]);
+	kfree(fb);
 
-	if (psbfb->base.obj[0])
-		drm_gem_object_put_unlocked(psbfb->base.obj[0]);
 	return 0;
 }
 
 int psb_fbdev_init(struct drm_device *dev)
 {
-	struct psb_fbdev *fbdev;
+	struct drm_fb_helper *fb_helper;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	int ret;
 
-	fbdev = kzalloc(sizeof(struct psb_fbdev), GFP_KERNEL);
-	if (!fbdev) {
+	fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL);
+	if (!fb_helper) {
 		dev_err(dev->dev, "no memory\n");
 		return -ENOMEM;
 	}
 
-	dev_priv->fbdev = fbdev;
+	dev_priv->fb_helper = fb_helper;
 
-	drm_fb_helper_prepare(dev, &fbdev->psb_fb_helper, &psb_fb_helper_funcs);
+	drm_fb_helper_prepare(dev, fb_helper, &psb_fb_helper_funcs);
 
-	ret = drm_fb_helper_init(dev, &fbdev->psb_fb_helper,
-				 INTELFB_CONN_LIMIT);
+	ret = drm_fb_helper_init(dev, fb_helper, INTELFB_CONN_LIMIT);
 	if (ret)
 		goto free;
 
-	ret = drm_fb_helper_single_add_all_connectors(&fbdev->psb_fb_helper);
+	ret = drm_fb_helper_single_add_all_connectors(fb_helper);
 	if (ret)
 		goto fini;
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
 	drm_helper_disable_unused_functions(dev);
 
-	ret = drm_fb_helper_initial_config(&fbdev->psb_fb_helper, 32);
+	ret = drm_fb_helper_initial_config(fb_helper, 32);
 	if (ret)
 		goto fini;
 
 	return 0;
 
 fini:
-	drm_fb_helper_fini(&fbdev->psb_fb_helper);
+	drm_fb_helper_fini(fb_helper);
 free:
-	kfree(fbdev);
+	kfree(fb_helper);
 	return ret;
 }
 
@@ -544,12 +541,12 @@ static void psb_fbdev_fini(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 
-	if (!dev_priv->fbdev)
+	if (!dev_priv->fb_helper)
 		return;
 
-	psb_fbdev_destroy(dev, dev_priv->fbdev);
-	kfree(dev_priv->fbdev);
-	dev_priv->fbdev = NULL;
+	psb_fbdev_destroy(dev, dev_priv->fb_helper);
+	kfree(dev_priv->fb_helper);
+	dev_priv->fb_helper = NULL;
 }
 
 static const struct drm_mode_config_funcs psb_mode_funcs = {
diff --git a/drivers/gpu/drm/gma500/framebuffer.h b/drivers/gpu/drm/gma500/framebuffer.h
index ae8a02639fd9..2fbba4b48841 100644
--- a/drivers/gpu/drm/gma500/framebuffer.h
+++ b/drivers/gpu/drm/gma500/framebuffer.h
@@ -9,23 +9,8 @@
 #ifndef _FRAMEBUFFER_H_
 #define _FRAMEBUFFER_H_
 
-#include <drm/drm_fb_helper.h>
-
 #include "psb_drv.h"
 
-struct psb_framebuffer {
-	struct drm_framebuffer base;
-	struct address_space *addr_space;
-	struct fb_info *fbdev;
-};
-
-struct psb_fbdev {
-	struct drm_fb_helper psb_fb_helper; /* must be first */
-	struct psb_framebuffer pfb;
-};
-
-#define to_psb_fb(x) container_of(x, struct psb_framebuffer, base)
-
 extern int gma_connector_clones(struct drm_device *dev, int type_mask);
 
 #endif
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index e20ccb5d10fd..17f136985d21 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -255,6 +255,8 @@ void gma_crtc_dpms(struct drm_crtc *crtc, int mode)
 		/* Give the overlay scaler a chance to enable
 		 * if it's on this pipe */
 		/* psb_intel_crtc_dpms_video(crtc, true); TODO */
+
+		drm_crtc_vblank_on(crtc);
 		break;
 	case DRM_MODE_DPMS_OFF:
 		if (!gma_crtc->active)
@@ -501,6 +503,52 @@ void gma_crtc_destroy(struct drm_crtc *crtc)
 	kfree(gma_crtc);
 }
 
+int gma_crtc_page_flip(struct drm_crtc *crtc,
+		       struct drm_framebuffer *fb,
+		       struct drm_pending_vblank_event *event,
+		       uint32_t page_flip_flags,
+		       struct drm_modeset_acquire_ctx *ctx)
+{
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	struct drm_framebuffer *current_fb = crtc->primary->fb;
+	struct drm_framebuffer *old_fb = crtc->primary->old_fb;
+	const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+	int ret;
+
+	if (!crtc_funcs->mode_set_base)
+		return -EINVAL;
+
+	/* Using mode_set_base requires the new fb to be set already. */
+	crtc->primary->fb = fb;
+
+	if (event) {
+		spin_lock_irqsave(&dev->event_lock, flags);
+
+		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
+		gma_crtc->page_flip_event = event;
+
+		/* Call this locked if we want an event at vblank interrupt. */
+		ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb);
+		if (ret) {
+			gma_crtc->page_flip_event = NULL;
+			drm_crtc_vblank_put(crtc);
+		}
+
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	} else {
+		ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb);
+	}
+
+	/* Restore previous fb in case of failure. */
+	if (ret)
+		crtc->primary->fb = current_fb;
+
+	return ret;
+}
+
 int gma_crtc_set_config(struct drm_mode_set *set,
 			struct drm_modeset_acquire_ctx *ctx)
 {
diff --git a/drivers/gpu/drm/gma500/gma_display.h b/drivers/gpu/drm/gma500/gma_display.h
index fdbd7ecaa59c..7bd6c1ee8b21 100644
--- a/drivers/gpu/drm/gma500/gma_display.h
+++ b/drivers/gpu/drm/gma500/gma_display.h
@@ -11,6 +11,7 @@
 #define _GMA_DISPLAY_H_
 
 #include <linux/pm_runtime.h>
+#include <drm/drm_vblank.h>
 
 struct drm_encoder;
 struct drm_mode_set;
@@ -71,6 +72,11 @@ extern void gma_crtc_prepare(struct drm_crtc *crtc);
 extern void gma_crtc_commit(struct drm_crtc *crtc);
 extern void gma_crtc_disable(struct drm_crtc *crtc);
 extern void gma_crtc_destroy(struct drm_crtc *crtc);
+extern int gma_crtc_page_flip(struct drm_crtc *crtc,
+			      struct drm_framebuffer *fb,
+			      struct drm_pending_vblank_event *event,
+			      uint32_t page_flip_flags,
+			      struct drm_modeset_acquire_ctx *ctx);
 extern int gma_crtc_set_config(struct drm_mode_set *set,
 			       struct drm_modeset_acquire_ctx *ctx);
 
diff --git a/drivers/gpu/drm/gma500/mdfld_intel_display.c b/drivers/gpu/drm/gma500/mdfld_intel_display.c
index b8bfb96008b8..4fff110c4921 100644
--- a/drivers/gpu/drm/gma500/mdfld_intel_display.c
+++ b/drivers/gpu/drm/gma500/mdfld_intel_display.c
@@ -113,27 +113,6 @@ static int psb_intel_panel_fitter_pipe(struct drm_device *dev)
 	return (pfit_control >> 29) & 0x3;
 }
 
-static struct drm_device globle_dev;
-
-void mdfld__intel_plane_set_alpha(int enable)
-{
-	struct drm_device *dev = &globle_dev;
-	int dspcntr_reg = DSPACNTR;
-	u32 dspcntr;
-
-	dspcntr = REG_READ(dspcntr_reg);
-
-	if (enable) {
-		dspcntr &= ~DISPPLANE_32BPP_NO_ALPHA;
-		dspcntr |= DISPPLANE_32BPP;
-	} else {
-		dspcntr &= ~DISPPLANE_32BPP;
-		dspcntr |= DISPPLANE_32BPP_NO_ALPHA;
-	}
-
-	REG_WRITE(dspcntr_reg, dspcntr);
-}
-
 static int check_fb(struct drm_framebuffer *fb)
 {
 	if (!fb)
@@ -164,8 +143,6 @@ static int mdfld__intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	u32 dspcntr;
 	int ret;
 
-	memcpy(&globle_dev, dev, sizeof(struct drm_device));
-
 	dev_dbg(dev->dev, "pipe = 0x%x.\n", pipe);
 
 	/* no fb bound */
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index f4c520893ceb..f4370232767d 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -159,9 +159,7 @@ static void oaktrail_hdmi_audio_disable(struct drm_device *dev)
 
 static unsigned int htotal_calculate(struct drm_display_mode *mode)
 {
-	u32 htotal, new_crtc_htotal;
-
-	htotal = (mode->crtc_hdisplay - 1) | ((mode->crtc_htotal - 1) << 16);
+	u32 new_crtc_htotal;
 
 	/*
 	 * 1024 x 768  new_crtc_htotal = 0x1024;
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index 7390403ea1b7..582e09597500 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -117,6 +117,7 @@ static void oaktrail_lvds_mode_set(struct drm_encoder *encoder,
 
 	if (!connector) {
 		DRM_ERROR("Couldn't find connector when setting mode");
+		gma_power_end(dev);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 0900052fc484..6956c8e7501c 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -19,10 +19,10 @@
 
 #include <drm/drm.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_irq.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 #include <drm/drm_vblank.h>
 
@@ -426,14 +426,48 @@ static long psb_unlocked_ioctl(struct file *filp, unsigned int cmd,
 
 static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	return drm_get_pci_dev(pdev, ent, &driver);
-}
+	struct drm_device *dev;
+	int ret;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	dev = drm_dev_alloc(&driver, &pdev->dev);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto err_pci_disable_device;
+	}
+
+	dev->pdev = pdev;
+	pci_set_drvdata(pdev, dev);
+
+	ret = psb_driver_load(dev, ent->driver_data);
+	if (ret)
+		goto err_drm_dev_put;
 
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_psb_driver_unload;
+
+	return 0;
+
+err_psb_driver_unload:
+	psb_driver_unload(dev);
+err_drm_dev_put:
+	drm_dev_put(dev);
+err_pci_disable_device:
+	pci_disable_device(pdev);
+	return ret;
+}
 
 static void psb_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	drm_put_dev(dev);
+
+	drm_dev_unregister(dev);
+	psb_driver_unload(dev);
+	drm_dev_put(dev);
 }
 
 static const struct dev_pm_ops psb_pm_ops = {
@@ -466,8 +500,6 @@ static const struct file_operations psb_gem_fops = {
 
 static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM,
-	.load = psb_driver_load,
-	.unload = psb_driver_unload,
 	.lastclose = drm_fb_helper_lastclose,
 
 	.num_ioctls = ARRAY_SIZE(psb_ioctls),
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 9b3c03f4a38d..3d4ef3071d45 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -229,6 +229,8 @@ enum {
 #define KSEL_BYPASS_25 6
 #define KSEL_BYPASS_83_100 7
 
+struct drm_fb_helper;
+
 struct opregion_header;
 struct opregion_acpi;
 struct opregion_swsci;
@@ -432,7 +434,7 @@ struct drm_psb_private {
 	struct pci_dev *lpc_pdev; /* Currently only used by mrst */
 	const struct psb_ops *ops;
 	const struct psb_offset *regmap;
-	
+
 	struct child_device_config *child_dev;
 	int child_dev_num;
 
@@ -540,7 +542,7 @@ struct drm_psb_private {
 
 	/* Oaktrail HDMI state */
 	struct oaktrail_hdmi_dev *hdmi_priv;
-	
+
 	/* Register state */
 	struct psb_save_area regs;
 
@@ -572,7 +574,7 @@ struct drm_psb_private {
 	uint32_t blc_adj1;
 	uint32_t blc_adj2;
 
-	void *fbdev;
+	struct drm_fb_helper *fb_helper;
 
 	/* 2D acceleration */
 	spinlock_t lock_2d;
diff --git a/drivers/gpu/drm/gma500/psb_intel_display.c b/drivers/gpu/drm/gma500/psb_intel_display.c
index 4256410535f0..fed3b563e62e 100644
--- a/drivers/gpu/drm/gma500/psb_intel_display.c
+++ b/drivers/gpu/drm/gma500/psb_intel_display.c
@@ -432,6 +432,7 @@ const struct drm_crtc_funcs psb_intel_crtc_funcs = {
 	.gamma_set = gma_crtc_gamma_set,
 	.set_config = gma_crtc_set_config,
 	.destroy = gma_crtc_destroy,
+	.page_flip = gma_crtc_page_flip,
 };
 
 const struct gma_clock_funcs psb_clock_funcs = {
diff --git a/drivers/gpu/drm/gma500/psb_intel_drv.h b/drivers/gpu/drm/gma500/psb_intel_drv.h
index cdf10333d1c2..16c6136f778b 100644
--- a/drivers/gpu/drm/gma500/psb_intel_drv.h
+++ b/drivers/gpu/drm/gma500/psb_intel_drv.h
@@ -12,6 +12,7 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_probe_helper.h>
+#include <drm/drm_vblank.h>
 #include <linux/gpio.h>
 #include "gma_display.h"
 
@@ -182,6 +183,8 @@ struct gma_crtc {
 	struct psb_intel_crtc_state *crtc_state;
 
 	const struct gma_clock_funcs *clock_funcs;
+
+	struct drm_pending_vblank_event *page_flip_event;
 };
 
 #define to_gma_crtc(x)	\
diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c
index e6265fb85626..91f90016dba9 100644
--- a/drivers/gpu/drm/gma500/psb_irq.c
+++ b/drivers/gpu/drm/gma500/psb_irq.c
@@ -165,11 +165,23 @@ static void mid_pipe_event_handler(struct drm_device *dev, int pipe)
 		"%s, can't clear status bits for pipe %d, its value = 0x%x.\n",
 		__func__, pipe, PSB_RVDC32(pipe_stat_reg));
 
-	if (pipe_stat_val & PIPE_VBLANK_STATUS)
-		drm_handle_vblank(dev, pipe);
+	if (pipe_stat_val & PIPE_VBLANK_STATUS ||
+	    (IS_MFLD(dev) && pipe_stat_val & PIPE_TE_STATUS)) {
+		struct drm_crtc *crtc = drm_crtc_from_index(dev, pipe);
+		struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+		unsigned long flags;
 
-	if (pipe_stat_val & PIPE_TE_STATUS)
 		drm_handle_vblank(dev, pipe);
+
+		spin_lock_irqsave(&dev->event_lock, flags);
+		if (gma_crtc->page_flip_event) {
+			drm_crtc_send_vblank_event(crtc,
+						   gma_crtc->page_flip_event);
+			gma_crtc->page_flip_event = NULL;
+			drm_crtc_vblank_put(crtc);
+		}
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
 }
 
 /*
@@ -194,7 +206,6 @@ static void psb_sgx_interrupt(struct drm_device *dev, u32 stat_1, u32 stat_2)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	u32 val, addr;
-	int error = false;
 
 	if (stat_1 & _PSB_CE_TWOD_COMPLETE)
 		val = PSB_RSGX32(PSB_CR_2D_BLIT_STATUS);
@@ -229,7 +240,6 @@ static void psb_sgx_interrupt(struct drm_device *dev, u32 stat_1, u32 stat_2)
 
 			DRM_ERROR("\tMMU failing address is 0x%08x.\n",
 				  (unsigned int)addr);
-			error = true;
 		}
 	}
 
@@ -460,12 +470,11 @@ void psb_irq_turn_off_dpst(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv =
 	    (struct drm_psb_private *) dev->dev_private;
-	u32 hist_reg;
 	u32 pwm_reg;
 
 	if (gma_power_begin(dev, false)) {
 		PSB_WVDC32(0x00000000, HISTOGRAM_INT_CONTROL);
-		hist_reg = PSB_RVDC32(HISTOGRAM_INT_CONTROL);
+		PSB_RVDC32(HISTOGRAM_INT_CONTROL);
 
 		psb_disable_pipestat(dev_priv, 0, PIPE_DPST_EVENT_ENABLE);
 
diff --git a/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c b/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c
index 7de3ce637c7f..9e8224456ea2 100644
--- a/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c
+++ b/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c
@@ -25,7 +25,7 @@
 #include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/platform_data/tc35876x.h>
+#include <linux/gpio/consumer.h>
 
 #include <asm/intel_scu_ipc.h>
 
@@ -36,6 +36,11 @@
 
 static struct i2c_client *tc35876x_client;
 static struct i2c_client *cmi_lcd_i2c_client;
+/* Panel GPIOs */
+static struct gpio_desc *bridge_reset;
+static struct gpio_desc *bridge_bl_enable;
+static struct gpio_desc *backlight_voltage;
+
 
 #define FLD_MASK(start, end)	(((1 << ((start) - (end) + 1)) - 1) << (end))
 #define FLD_VAL(val, start, end) (((val) << (end)) & FLD_MASK(start, end))
@@ -316,27 +321,23 @@ static int tc35876x_regr(struct i2c_client *client, u16 reg, u32 *value)
 
 void tc35876x_set_bridge_reset_state(struct drm_device *dev, int state)
 {
-	struct tc35876x_platform_data *pdata;
-
 	if (WARN(!tc35876x_client, "%s called before probe", __func__))
 		return;
 
 	dev_dbg(&tc35876x_client->dev, "%s: state %d\n", __func__, state);
 
-	pdata = dev_get_platdata(&tc35876x_client->dev);
-
-	if (pdata->gpio_bridge_reset == -1)
+	if (!bridge_reset)
 		return;
 
 	if (state) {
-		gpio_set_value_cansleep(pdata->gpio_bridge_reset, 0);
+		gpiod_set_value_cansleep(bridge_reset, 0);
 		mdelay(10);
 	} else {
 		/* Pull MIPI Bridge reset pin to Low */
-		gpio_set_value_cansleep(pdata->gpio_bridge_reset, 0);
+		gpiod_set_value_cansleep(bridge_reset, 0);
 		mdelay(20);
 		/* Pull MIPI Bridge reset pin to High */
-		gpio_set_value_cansleep(pdata->gpio_bridge_reset, 1);
+		gpiod_set_value_cansleep(bridge_reset, 1);
 		mdelay(40);
 	}
 }
@@ -510,25 +511,20 @@ void tc35876x_brightness_control(struct drm_device *dev, int level)
 
 void tc35876x_toshiba_bridge_panel_off(struct drm_device *dev)
 {
-	struct tc35876x_platform_data *pdata;
-
 	if (WARN(!tc35876x_client, "%s called before probe", __func__))
 		return;
 
 	dev_dbg(&tc35876x_client->dev, "%s\n", __func__);
 
-	pdata = dev_get_platdata(&tc35876x_client->dev);
-
-	if (pdata->gpio_panel_bl_en != -1)
-		gpio_set_value_cansleep(pdata->gpio_panel_bl_en, 0);
+	if (bridge_bl_enable)
+		gpiod_set_value_cansleep(bridge_bl_enable, 0);
 
-	if (pdata->gpio_panel_vadd != -1)
-		gpio_set_value_cansleep(pdata->gpio_panel_vadd, 0);
+	if (backlight_voltage)
+		gpiod_set_value_cansleep(backlight_voltage, 0);
 }
 
 void tc35876x_toshiba_bridge_panel_on(struct drm_device *dev)
 {
-	struct tc35876x_platform_data *pdata;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 
 	if (WARN(!tc35876x_client, "%s called before probe", __func__))
@@ -536,10 +532,8 @@ void tc35876x_toshiba_bridge_panel_on(struct drm_device *dev)
 
 	dev_dbg(&tc35876x_client->dev, "%s\n", __func__);
 
-	pdata = dev_get_platdata(&tc35876x_client->dev);
-
-	if (pdata->gpio_panel_vadd != -1) {
-		gpio_set_value_cansleep(pdata->gpio_panel_vadd, 1);
+	if (backlight_voltage) {
+		gpiod_set_value_cansleep(backlight_voltage, 1);
 		msleep(260);
 	}
 
@@ -571,8 +565,8 @@ void tc35876x_toshiba_bridge_panel_on(struct drm_device *dev)
 				"i2c write failed (%d)\n", ret);
 	}
 
-	if (pdata->gpio_panel_bl_en != -1)
-		gpio_set_value_cansleep(pdata->gpio_panel_bl_en, 1);
+	if (bridge_bl_enable)
+		gpiod_set_value_cansleep(bridge_bl_enable, 1);
 
 	tc35876x_brightness_control(dev, dev_priv->brightness_adjusted);
 }
@@ -635,8 +629,6 @@ static int tc35876x_get_panel_info(struct drm_device *dev, int pipe,
 static int tc35876x_bridge_probe(struct i2c_client *client,
 				const struct i2c_device_id *id)
 {
-	struct tc35876x_platform_data *pdata;
-
 	dev_info(&client->dev, "%s\n", __func__);
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
@@ -645,26 +637,23 @@ static int tc35876x_bridge_probe(struct i2c_client *client,
 		return -ENODEV;
 	}
 
-	pdata = dev_get_platdata(&client->dev);
-	if (!pdata) {
-		dev_err(&client->dev, "%s: no platform data\n", __func__);
-		return -ENODEV;
-	}
+	bridge_reset = devm_gpiod_get_optional(&client->dev, "bridge-reset", GPIOD_OUT_LOW);
+	if (IS_ERR(bridge_reset))
+		return PTR_ERR(bridge_reset);
+	if (bridge_reset)
+		gpiod_set_consumer_name(bridge_reset, "tc35876x bridge reset");
 
-	if (pdata->gpio_bridge_reset != -1) {
-		gpio_request(pdata->gpio_bridge_reset, "tc35876x bridge reset");
-		gpio_direction_output(pdata->gpio_bridge_reset, 0);
-	}
-
-	if (pdata->gpio_panel_bl_en != -1) {
-		gpio_request(pdata->gpio_panel_bl_en, "tc35876x panel bl en");
-		gpio_direction_output(pdata->gpio_panel_bl_en, 0);
-	}
+	bridge_bl_enable = devm_gpiod_get_optional(&client->dev, "bl-en", GPIOD_OUT_LOW);
+	if (IS_ERR(bridge_bl_enable))
+		return PTR_ERR(bridge_bl_enable);
+	if (bridge_bl_enable)
+		gpiod_set_consumer_name(bridge_bl_enable, "tc35876x panel bl en");
 
-	if (pdata->gpio_panel_vadd != -1) {
-		gpio_request(pdata->gpio_panel_vadd, "tc35876x panel vadd");
-		gpio_direction_output(pdata->gpio_panel_vadd, 0);
-	}
+	backlight_voltage = devm_gpiod_get_optional(&client->dev, "vadd", GPIOD_OUT_LOW);
+	if (IS_ERR(backlight_voltage))
+		return PTR_ERR(backlight_voltage);
+	if (backlight_voltage)
+		gpiod_set_consumer_name(backlight_voltage, "tc35876x panel vadd");
 
 	tc35876x_client = client;
 
@@ -673,19 +662,8 @@ static int tc35876x_bridge_probe(struct i2c_client *client,
 
 static int tc35876x_bridge_remove(struct i2c_client *client)
 {
-	struct tc35876x_platform_data *pdata = dev_get_platdata(&client->dev);
-
 	dev_dbg(&client->dev, "%s\n", __func__);
 
-	if (pdata->gpio_bridge_reset != -1)
-		gpio_free(pdata->gpio_bridge_reset);
-
-	if (pdata->gpio_panel_bl_en != -1)
-		gpio_free(pdata->gpio_panel_bl_en);
-
-	if (pdata->gpio_panel_vadd != -1)
-		gpio_free(pdata->gpio_panel_vadd);
-
 	tc35876x_client = NULL;
 
 	return 0;
diff --git a/drivers/gpu/drm/hisilicon/hibmc/Makefile b/drivers/gpu/drm/hisilicon/hibmc/Makefile
index 0c2d4296bccd..f99132715597 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/Makefile
+++ b/drivers/gpu/drm/hisilicon/hibmc/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_drm_fbdev.o hibmc_ttm.o
+hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_ttm.o
 
 obj-$(CONFIG_DRM_HISI_HIBMC) += hibmc-drm.o
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index 6527a97f68a3..7fa7d4933f60 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -99,14 +99,12 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
 	s64 gpu_addr = 0;
 	unsigned int line_l;
 	struct hibmc_drm_private *priv = plane->dev->dev_private;
-	struct hibmc_framebuffer *hibmc_fb;
 	struct drm_gem_vram_object *gbo;
 
 	if (!state->fb)
 		return;
 
-	hibmc_fb = to_hibmc_framebuffer(state->fb);
-	gbo = drm_gem_vram_of_gem(hibmc_fb->obj);
+	gbo = drm_gem_vram_of_gem(state->fb->obj[0]);
 
 	gpu_addr = drm_gem_vram_offset(gbo);
 	if (WARN_ON_ONCE(gpu_addr < 0))
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index 8dd5a43e5486..4a8a4cfb4b75 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -17,6 +17,7 @@
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_vram_helper.h>
 #include <drm/drm_irq.h>
 #include <drm/drm_print.h>
@@ -54,6 +55,7 @@ static struct drm_driver hibmc_driver = {
 	.desc			= "hibmc drm driver",
 	.major			= 1,
 	.minor			= 0,
+	.debugfs_init		= drm_vram_mm_debugfs_init,
 	.dumb_create            = hibmc_dumb_create,
 	.dumb_map_offset        = drm_gem_vram_driver_dumb_mmap_offset,
 	.gem_prime_mmap		= drm_gem_prime_mmap,
@@ -247,8 +249,6 @@ static int hibmc_unload(struct drm_device *dev)
 {
 	struct hibmc_drm_private *priv = dev->dev_private;
 
-	hibmc_fbdev_fini(priv);
-
 	drm_atomic_helper_shutdown(dev);
 
 	if (dev->irq_enabled)
@@ -307,7 +307,7 @@ static int hibmc_load(struct drm_device *dev)
 	/* reset all the states of crtc/plane/encoder/connector */
 	drm_mode_config_reset(dev);
 
-	ret = hibmc_fbdev_init(priv);
+	ret = drm_fbdev_generic_setup(dev, 16);
 	if (ret) {
 		DRM_ERROR("failed to initialize fbdev: %d\n", ret);
 		goto err;
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
index e58ecd7edcf8..50a0c1f9d211 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
@@ -18,18 +18,6 @@
 #include <drm/drm_framebuffer.h>
 
 struct drm_device;
-struct drm_gem_object;
-
-struct hibmc_framebuffer {
-	struct drm_framebuffer fb;
-	struct drm_gem_object *obj;
-};
-
-struct hibmc_fbdev {
-	struct drm_fb_helper helper; /* must be first */
-	struct hibmc_framebuffer *fb;
-	int size;
-};
 
 struct hibmc_drm_private {
 	/* hw */
@@ -42,13 +30,8 @@ struct hibmc_drm_private {
 	/* drm */
 	struct drm_device  *dev;
 	bool mode_config_initialized;
-
-	/* fbdev */
-	struct hibmc_fbdev *fbdev;
 };
 
-#define to_hibmc_framebuffer(x) container_of(x, struct hibmc_framebuffer, fb)
-
 void hibmc_set_power_mode(struct hibmc_drm_private *priv,
 			  unsigned int power_mode);
 void hibmc_set_current_gate(struct hibmc_drm_private *priv,
@@ -56,15 +39,6 @@ void hibmc_set_current_gate(struct hibmc_drm_private *priv,
 
 int hibmc_de_init(struct hibmc_drm_private *priv);
 int hibmc_vdac_init(struct hibmc_drm_private *priv);
-int hibmc_fbdev_init(struct hibmc_drm_private *priv);
-void hibmc_fbdev_fini(struct hibmc_drm_private *priv);
-
-int hibmc_gem_create(struct drm_device *dev, u32 size, bool iskernel,
-		     struct drm_gem_object **obj);
-struct hibmc_framebuffer *
-hibmc_framebuffer_init(struct drm_device *dev,
-		       const struct drm_mode_fb_cmd2 *mode_cmd,
-		       struct drm_gem_object *obj);
 
 int hibmc_mm_init(struct hibmc_drm_private *hibmc);
 void hibmc_mm_fini(struct hibmc_drm_private *hibmc);
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_fbdev.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_fbdev.c
deleted file mode 100644
index b4c1cea051e8..000000000000
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_fbdev.c
+++ /dev/null
@@ -1,240 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* Hisilicon Hibmc SoC drm driver
- *
- * Based on the bochs drm driver.
- *
- * Copyright (c) 2016 Huawei Limited.
- *
- * Author:
- *	Rongrong Zou <zourongrong@huawei.com>
- *	Rongrong Zou <zourongrong@gmail.com>
- *	Jianhua Li <lijianhua@huawei.com>
- */
-
-#include <drm/drm_crtc.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_gem_vram_helper.h>
-#include <drm/drm_probe_helper.h>
-
-#include "hibmc_drm_drv.h"
-
-static int hibmcfb_create_object(
-				struct hibmc_drm_private *priv,
-				const struct drm_mode_fb_cmd2 *mode_cmd,
-				struct drm_gem_object **gobj_p)
-{
-	struct drm_gem_object *gobj;
-	struct drm_device *dev = priv->dev;
-	u32 size;
-	int ret = 0;
-
-	size = mode_cmd->pitches[0] * mode_cmd->height;
-	ret = hibmc_gem_create(dev, size, true, &gobj);
-	if (ret)
-		return ret;
-
-	*gobj_p = gobj;
-	return ret;
-}
-
-static struct fb_ops hibmc_drm_fb_ops = {
-	.owner = THIS_MODULE,
-	.fb_check_var = drm_fb_helper_check_var,
-	.fb_set_par = drm_fb_helper_set_par,
-	.fb_fillrect = drm_fb_helper_sys_fillrect,
-	.fb_copyarea = drm_fb_helper_sys_copyarea,
-	.fb_imageblit = drm_fb_helper_sys_imageblit,
-	.fb_pan_display = drm_fb_helper_pan_display,
-	.fb_blank = drm_fb_helper_blank,
-	.fb_setcmap = drm_fb_helper_setcmap,
-};
-
-static int hibmc_drm_fb_create(struct drm_fb_helper *helper,
-			       struct drm_fb_helper_surface_size *sizes)
-{
-	struct hibmc_fbdev *hi_fbdev =
-		container_of(helper, struct hibmc_fbdev, helper);
-	struct hibmc_drm_private *priv = helper->dev->dev_private;
-	struct fb_info *info;
-	struct drm_mode_fb_cmd2 mode_cmd;
-	struct drm_gem_object *gobj = NULL;
-	int ret = 0;
-	size_t size;
-	unsigned int bytes_per_pixel;
-	struct drm_gem_vram_object *gbo = NULL;
-	void *base;
-
-	DRM_DEBUG_DRIVER("surface width(%d), height(%d) and bpp(%d)\n",
-			 sizes->surface_width, sizes->surface_height,
-			 sizes->surface_bpp);
-
-	bytes_per_pixel = DIV_ROUND_UP(sizes->surface_bpp, 8);
-
-	mode_cmd.width = sizes->surface_width;
-	mode_cmd.height = sizes->surface_height;
-	mode_cmd.pitches[0] = mode_cmd.width * bytes_per_pixel;
-	mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp,
-							  sizes->surface_depth);
-
-	size = PAGE_ALIGN(mode_cmd.pitches[0] * mode_cmd.height);
-
-	ret = hibmcfb_create_object(priv, &mode_cmd, &gobj);
-	if (ret) {
-		DRM_ERROR("failed to create fbcon backing object: %d\n", ret);
-		return -ENOMEM;
-	}
-
-	gbo = drm_gem_vram_of_gem(gobj);
-
-	ret = drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM);
-	if (ret) {
-		DRM_ERROR("failed to pin fbcon: %d\n", ret);
-		goto out_unref_gem;
-	}
-
-	base = drm_gem_vram_kmap(gbo, true, NULL);
-	if (IS_ERR(base)) {
-		ret = PTR_ERR(base);
-		DRM_ERROR("failed to kmap fbcon: %d\n", ret);
-		goto out_unpin_bo;
-	}
-
-	info = drm_fb_helper_alloc_fbi(helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		DRM_ERROR("failed to allocate fbi: %d\n", ret);
-		goto out_release_fbi;
-	}
-
-	hi_fbdev->fb = hibmc_framebuffer_init(priv->dev, &mode_cmd, gobj);
-	if (IS_ERR(hi_fbdev->fb)) {
-		ret = PTR_ERR(hi_fbdev->fb);
-		hi_fbdev->fb = NULL;
-		DRM_ERROR("failed to initialize framebuffer: %d\n", ret);
-		goto out_release_fbi;
-	}
-
-	priv->fbdev->size = size;
-	hi_fbdev->helper.fb = &hi_fbdev->fb->fb;
-
-	info->fbops = &hibmc_drm_fb_ops;
-
-	drm_fb_helper_fill_info(info, &priv->fbdev->helper, sizes);
-
-	info->screen_base = base;
-	info->screen_size = size;
-
-	info->fix.smem_start = gbo->bo.mem.bus.offset + gbo->bo.mem.bus.base;
-	info->fix.smem_len = size;
-	return 0;
-
-out_release_fbi:
-	drm_gem_vram_kunmap(gbo);
-out_unpin_bo:
-	drm_gem_vram_unpin(gbo);
-out_unref_gem:
-	drm_gem_object_put_unlocked(gobj);
-
-	return ret;
-}
-
-static void hibmc_fbdev_destroy(struct hibmc_fbdev *fbdev)
-{
-	struct hibmc_framebuffer *gfb = fbdev->fb;
-	struct drm_fb_helper *fbh = &fbdev->helper;
-
-	drm_fb_helper_unregister_fbi(fbh);
-
-	drm_fb_helper_fini(fbh);
-
-	if (gfb)
-		drm_framebuffer_put(&gfb->fb);
-}
-
-static const struct drm_fb_helper_funcs hibmc_fbdev_helper_funcs = {
-	.fb_probe = hibmc_drm_fb_create,
-};
-
-int hibmc_fbdev_init(struct hibmc_drm_private *priv)
-{
-	int ret;
-	struct fb_var_screeninfo *var;
-	struct fb_fix_screeninfo *fix;
-	struct hibmc_fbdev *hifbdev;
-
-	hifbdev = devm_kzalloc(priv->dev->dev, sizeof(*hifbdev), GFP_KERNEL);
-	if (!hifbdev) {
-		DRM_ERROR("failed to allocate hibmc_fbdev\n");
-		return -ENOMEM;
-	}
-
-	priv->fbdev = hifbdev;
-	drm_fb_helper_prepare(priv->dev, &hifbdev->helper,
-			      &hibmc_fbdev_helper_funcs);
-
-	/* Now just one crtc and one channel */
-	ret = drm_fb_helper_init(priv->dev, &hifbdev->helper, 1);
-	if (ret) {
-		DRM_ERROR("failed to initialize fb helper: %d\n", ret);
-		return ret;
-	}
-
-	ret = drm_fb_helper_single_add_all_connectors(&hifbdev->helper);
-	if (ret) {
-		DRM_ERROR("failed to add all connectors: %d\n", ret);
-		goto fini;
-	}
-
-	ret = drm_fb_helper_initial_config(&hifbdev->helper, 16);
-	if (ret) {
-		DRM_ERROR("failed to setup initial conn config: %d\n", ret);
-		goto fini;
-	}
-
-	var = &hifbdev->helper.fbdev->var;
-	fix = &hifbdev->helper.fbdev->fix;
-
-	DRM_DEBUG_DRIVER("Member of info->var is :\n"
-			 "xres=%d\n"
-			 "yres=%d\n"
-			 "xres_virtual=%d\n"
-			 "yres_virtual=%d\n"
-			 "xoffset=%d\n"
-			 "yoffset=%d\n"
-			 "bits_per_pixel=%d\n"
-			 "...\n", var->xres, var->yres, var->xres_virtual,
-			 var->yres_virtual, var->xoffset, var->yoffset,
-			 var->bits_per_pixel);
-	DRM_DEBUG_DRIVER("Member of info->fix is :\n"
-			 "smem_start=%lx\n"
-			 "smem_len=%d\n"
-			 "type=%d\n"
-			 "type_aux=%d\n"
-			 "visual=%d\n"
-			 "xpanstep=%d\n"
-			 "ypanstep=%d\n"
-			 "ywrapstep=%d\n"
-			 "line_length=%d\n"
-			 "accel=%d\n"
-			 "capabilities=%d\n"
-			 "...\n", fix->smem_start, fix->smem_len, fix->type,
-			 fix->type_aux, fix->visual, fix->xpanstep,
-			 fix->ypanstep, fix->ywrapstep, fix->line_length,
-			 fix->accel, fix->capabilities);
-
-	return 0;
-
-fini:
-	drm_fb_helper_fini(&hifbdev->helper);
-	return ret;
-}
-
-void hibmc_fbdev_fini(struct hibmc_drm_private *priv)
-{
-	if (!priv->fbdev)
-		return;
-
-	hibmc_fbdev_destroy(priv->fbdev);
-	priv->fbdev = NULL;
-}
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
index 21b684eab5c9..50b988fdd5cc 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
@@ -15,6 +15,7 @@
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_gem_vram_helper.h>
 #include <drm/drm_print.h>
 
@@ -46,125 +47,14 @@ void hibmc_mm_fini(struct hibmc_drm_private *hibmc)
 	drm_vram_helper_release_mm(hibmc->dev);
 }
 
-int hibmc_gem_create(struct drm_device *dev, u32 size, bool iskernel,
-		     struct drm_gem_object **obj)
-{
-	struct drm_gem_vram_object *gbo;
-	int ret;
-
-	*obj = NULL;
-
-	size = roundup(size, PAGE_SIZE);
-	if (size == 0)
-		return -EINVAL;
-
-	gbo = drm_gem_vram_create(dev, &dev->vram_mm->bdev, size, 0, false);
-	if (IS_ERR(gbo)) {
-		ret = PTR_ERR(gbo);
-		if (ret != -ERESTARTSYS)
-			DRM_ERROR("failed to allocate GEM object: %d\n", ret);
-		return ret;
-	}
-	*obj = &gbo->bo.base;
-	return 0;
-}
-
 int hibmc_dumb_create(struct drm_file *file, struct drm_device *dev,
 		      struct drm_mode_create_dumb *args)
 {
-	struct drm_gem_object *gobj;
-	u32 handle;
-	int ret;
-
-	args->pitch = ALIGN(args->width * DIV_ROUND_UP(args->bpp, 8), 16);
-	args->size = args->pitch * args->height;
-
-	ret = hibmc_gem_create(dev, args->size, false,
-			       &gobj);
-	if (ret) {
-		DRM_ERROR("failed to create GEM object: %d\n", ret);
-		return ret;
-	}
-
-	ret = drm_gem_handle_create(file, gobj, &handle);
-	drm_gem_object_put_unlocked(gobj);
-	if (ret) {
-		DRM_ERROR("failed to unreference GEM object: %d\n", ret);
-		return ret;
-	}
-
-	args->handle = handle;
-	return 0;
-}
-
-static void hibmc_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct hibmc_framebuffer *hibmc_fb = to_hibmc_framebuffer(fb);
-
-	drm_gem_object_put_unlocked(hibmc_fb->obj);
-	drm_framebuffer_cleanup(fb);
-	kfree(hibmc_fb);
-}
-
-static const struct drm_framebuffer_funcs hibmc_fb_funcs = {
-	.destroy = hibmc_user_framebuffer_destroy,
-};
-
-struct hibmc_framebuffer *
-hibmc_framebuffer_init(struct drm_device *dev,
-		       const struct drm_mode_fb_cmd2 *mode_cmd,
-		       struct drm_gem_object *obj)
-{
-	struct hibmc_framebuffer *hibmc_fb;
-	int ret;
-
-	hibmc_fb = kzalloc(sizeof(*hibmc_fb), GFP_KERNEL);
-	if (!hibmc_fb) {
-		DRM_ERROR("failed to allocate hibmc_fb\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	drm_helper_mode_fill_fb_struct(dev, &hibmc_fb->fb, mode_cmd);
-	hibmc_fb->obj = obj;
-	ret = drm_framebuffer_init(dev, &hibmc_fb->fb, &hibmc_fb_funcs);
-	if (ret) {
-		DRM_ERROR("drm_framebuffer_init failed: %d\n", ret);
-		kfree(hibmc_fb);
-		return ERR_PTR(ret);
-	}
-
-	return hibmc_fb;
-}
-
-static struct drm_framebuffer *
-hibmc_user_framebuffer_create(struct drm_device *dev,
-			      struct drm_file *filp,
-			      const struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	struct drm_gem_object *obj;
-	struct hibmc_framebuffer *hibmc_fb;
-
-	DRM_DEBUG_DRIVER("%dx%d, format %c%c%c%c\n",
-			 mode_cmd->width, mode_cmd->height,
-			 (mode_cmd->pixel_format) & 0xff,
-			 (mode_cmd->pixel_format >> 8)  & 0xff,
-			 (mode_cmd->pixel_format >> 16) & 0xff,
-			 (mode_cmd->pixel_format >> 24) & 0xff);
-
-	obj = drm_gem_object_lookup(filp, mode_cmd->handles[0]);
-	if (!obj)
-		return ERR_PTR(-ENOENT);
-
-	hibmc_fb = hibmc_framebuffer_init(dev, mode_cmd, obj);
-	if (IS_ERR(hibmc_fb)) {
-		drm_gem_object_put_unlocked(obj);
-		return ERR_PTR((long)hibmc_fb);
-	}
-	return &hibmc_fb->fb;
+	return drm_gem_vram_fill_create_dumb(file, dev, 0, 16, args);
 }
 
 const struct drm_mode_config_funcs hibmc_mode_funcs = {
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
-	.fb_create = hibmc_user_framebuffer_create,
+	.fb_create = drm_gem_fb_create,
 };
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index e66c38332df4..b88c3d5f92b4 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -32,6 +32,7 @@
 
 #include <linux/delay.h>
 #include <linux/mman.h>
+#include <linux/pci.h>
 
 #include <drm/drm_agpsupport.h>
 #include <drm/drm_device.h>
@@ -39,7 +40,6 @@
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_irq.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_print.h>
 #include <drm/i810_drm.h>
 
diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c
index 5dd26a06ee0e..0e53a066d4db 100644
--- a/drivers/gpu/drm/i810/i810_drv.c
+++ b/drivers/gpu/drm/i810/i810_drv.c
@@ -31,11 +31,12 @@
  */
 
 #include "i810_drv.h"
+
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 #include <drm/i810_drm.h>
 
diff --git a/drivers/gpu/drm/i915/.gitignore b/drivers/gpu/drm/i915/.gitignore
new file mode 100644
index 000000000000..d9a77f3b59b2
--- /dev/null
+++ b/drivers/gpu/drm/i915/.gitignore
@@ -0,0 +1 @@
+*.hdrtest
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 438040ff0179..1cb28c20807c 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -27,6 +27,7 @@ config DRM_I915_DEBUG
 	select X86_MSR # used by igt/pm_rpm
 	select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
 	select DRM_DEBUG_MM if DRM=y
+	select DRM_EXPORT_FOR_TESTS if m
 	select DRM_DEBUG_SELFTEST
 	select DMABUF_SELFTESTS
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
@@ -149,6 +150,7 @@ config DRM_I915_SELFTEST
 	bool "Enable selftests upon driver load"
 	depends on DRM_I915
 	default n
+	select DRM_EXPORT_FOR_TESTS if m
 	select FAULT_INJECTION
 	select PRIME_NUMBERS
 	help
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 90dcf09f52cc..b8c5f8934dbd 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -31,9 +31,6 @@ CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init)
 subdir-ccflags-y += \
 	$(call as-instr,movntdqa (%eax)$(comma)%xmm0,-DCONFIG_AS_MOVNTDQA)
 
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
-
 subdir-ccflags-y += -I$(srctree)/$(src)
 
 # Please keep these build lists sorted!
@@ -73,8 +70,12 @@ i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o display/intel_pipe_crc.o
 i915-$(CONFIG_PERF_EVENTS) += i915_pmu.o
 
 # "Graphics Technology" (aka we talk to the gpu)
-obj-y += gt/
 gt-y += \
+	gt/debugfs_engines.o \
+	gt/debugfs_gt.o \
+	gt/debugfs_gt_pm.o \
+	gt/gen6_ppgtt.o \
+	gt/gen8_ppgtt.o \
 	gt/intel_breadcrumbs.o \
 	gt/intel_context.o \
 	gt/intel_engine_cs.o \
@@ -82,14 +83,17 @@ gt-y += \
 	gt/intel_engine_pm.o \
 	gt/intel_engine_pool.o \
 	gt/intel_engine_user.o \
+	gt/intel_ggtt.o \
 	gt/intel_gt.o \
 	gt/intel_gt_irq.o \
 	gt/intel_gt_pm.o \
 	gt/intel_gt_pm_irq.o \
 	gt/intel_gt_requests.o \
+	gt/intel_gtt.o \
 	gt/intel_llc.o \
 	gt/intel_lrc.o \
 	gt/intel_mocs.o \
+	gt/intel_ppgtt.o \
 	gt/intel_rc6.o \
 	gt/intel_renderstate.o \
 	gt/intel_reset.o \
@@ -108,7 +112,6 @@ gt-y += \
 i915-y += $(gt-y)
 
 # GEM (Graphics Execution Management) code
-obj-y += gem/
 gem-y += \
 	gem/i915_gem_busy.o \
 	gem/i915_gem_clflush.o \
@@ -154,7 +157,6 @@ i915-y += \
 	  intel_wopcm.o
 
 # general-purpose microcontroller (GuC) support
-obj-y += gt/uc/
 i915-y += gt/uc/intel_uc.o \
 	  gt/uc/intel_uc_fw.o \
 	  gt/uc/intel_guc.o \
@@ -167,7 +169,6 @@ i915-y += gt/uc/intel_uc.o \
 	  gt/uc/intel_huc_fw.o
 
 # modesetting core code
-obj-y += display/
 i915-y += \
 	display/intel_atomic.o \
 	display/intel_atomic_plane.o \
@@ -232,7 +233,6 @@ i915-y += \
 	display/vlv_dsi_pll.o
 
 # perf code
-obj-y += oa/
 i915-y += \
 	oa/i915_oa_hsw.o \
 	oa/i915_oa_bdw.o \
@@ -257,8 +257,10 @@ i915-$(CONFIG_DRM_I915_SELFTEST) += \
 	gem/selftests/igt_gem_utils.o \
 	selftests/i915_random.o \
 	selftests/i915_selftest.o \
+	selftests/igt_atomic.o \
 	selftests/igt_flush_test.o \
 	selftests/igt_live_test.o \
+	selftests/igt_mmap.o \
 	selftests/igt_reset.o \
 	selftests/igt_spinner.o
 
@@ -272,3 +274,27 @@ endif
 
 obj-$(CONFIG_DRM_I915) += i915.o
 obj-$(CONFIG_DRM_I915_GVT_KVMGT) += gvt/kvmgt.o
+
+# header test
+
+# exclude some broken headers from the test coverage
+no-header-test := \
+	display/intel_vbt_defs.h \
+	gvt/execlist.h \
+	gvt/fb_decoder.h \
+	gvt/gtt.h \
+	gvt/gvt.h \
+	gvt/interrupt.h \
+	gvt/mmio_context.h \
+	gvt/mpt.h \
+	gvt/scheduler.h
+
+extra-$(CONFIG_DRM_I915_WERROR) += \
+	$(patsubst %.h,%.hdrtest, $(filter-out $(no-header-test), \
+		$(shell cd $(srctree)/$(src) && find * -name '*.h')))
+
+quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
+      cmd_hdrtest = $(CC) $(c_flags) -S -o /dev/null -x c /dev/null -include $<; touch $@
+
+$(obj)/%.hdrtest: $(src)/%.h FORCE
+	$(call if_changed_dep,hdrtest)
diff --git a/drivers/gpu/drm/i915/display/Makefile b/drivers/gpu/drm/i915/display/Makefile
deleted file mode 100644
index 173c305d7866..000000000000
--- a/drivers/gpu/drm/i915/display/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
-header-test- := intel_vbt_defs.h
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 325df29b0447..f8e882101396 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -34,6 +34,7 @@
 #include "intel_ddi.h"
 #include "intel_dsi.h"
 #include "intel_panel.h"
+#include "intel_vdsc.h"
 
 static inline int header_credits_available(struct drm_i915_private *dev_priv,
 					   enum transcoder dsi_trans)
@@ -76,7 +77,7 @@ static enum transcoder dsi_port_to_transcoder(enum port port)
 static void wait_for_cmds_dispatched_to_panel(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct mipi_dsi_device *dsi;
 	enum port port;
 	enum transcoder dsi_trans;
@@ -201,7 +202,7 @@ static int dsi_send_pkt_payld(struct intel_dsi_host *host,
 static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum phy phy;
 	u32 tmp;
 	int lane;
@@ -266,7 +267,7 @@ static void configure_dual_link_mode(struct intel_encoder *encoder,
 				     const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 dss_ctl1;
 
 	dss_ctl1 = I915_READ(DSS_CTL1);
@@ -276,7 +277,7 @@ static void configure_dual_link_mode(struct intel_encoder *encoder,
 
 	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
 		const struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+					&pipe_config->hw.adjusted_mode;
 		u32 dss_ctl2;
 		u16 hactive = adjusted_mode->crtc_hdisplay;
 		u16 dl_buffer_depth;
@@ -301,18 +302,31 @@ static void configure_dual_link_mode(struct intel_encoder *encoder,
 	I915_WRITE(DSS_CTL1, dss_ctl1);
 }
 
-static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder)
+/* aka DSI 8X clock */
+static int afe_clk(struct intel_encoder *encoder,
+		   const struct intel_crtc_state *crtc_state)
+{
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	int bpp;
+
+	if (crtc_state->dsc.compression_enable)
+		bpp = crtc_state->dsc.compressed_bpp;
+	else
+		bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+
+	return DIV_ROUND_CLOSEST(intel_dsi->pclk * bpp, intel_dsi->lane_count);
+}
+
+static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder,
+					  const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
-	u32 bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
-	u32 afe_clk_khz; /* 8X Clock */
+	int afe_clk_khz;
 	u32 esc_clk_div_m;
 
-	afe_clk_khz = DIV_ROUND_CLOSEST(intel_dsi->pclk * bpp,
-					intel_dsi->lane_count);
-
+	afe_clk_khz = afe_clk(encoder, crtc_state);
 	esc_clk_div_m = DIV_ROUND_UP(afe_clk_khz, DSI_MAX_ESC_CLK);
 
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -346,7 +360,7 @@ static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv,
 static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 tmp;
 
@@ -362,7 +376,7 @@ static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum phy phy;
 
 	for_each_dsi_phy(phy, intel_dsi->phys)
@@ -373,7 +387,7 @@ static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
 static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum phy phy;
 	u32 tmp;
 	int lane;
@@ -422,7 +436,7 @@ static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder)
 static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
@@ -474,7 +488,7 @@ static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder)
 static void gen11_dsi_enable_ddi_buffer(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum port port;
 
@@ -490,10 +504,12 @@ static void gen11_dsi_enable_ddi_buffer(struct intel_encoder *encoder)
 	}
 }
 
-static void gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder)
+static void
+gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder,
+			     const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum port port;
 	enum phy phy;
@@ -531,7 +547,7 @@ static void gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder)
 	 * leave all fields at HW default values.
 	 */
 	if (IS_GEN(dev_priv, 11)) {
-		if (intel_dsi_bitrate(intel_dsi) <= 800000) {
+		if (afe_clk(encoder, crtc_state) <= 800000) {
 			for_each_dsi_port(port, intel_dsi->ports) {
 				tmp = I915_READ(DPHY_TA_TIMING_PARAM(port));
 				tmp &= ~TA_SURE_MASK;
@@ -559,7 +575,7 @@ static void gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder)
 static void gen11_dsi_gate_clocks(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
@@ -575,7 +591,7 @@ static void gen11_dsi_gate_clocks(struct intel_encoder *encoder)
 static void gen11_dsi_ungate_clocks(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
@@ -592,7 +608,7 @@ static void gen11_dsi_map_pll(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 	enum phy phy;
 	u32 val;
@@ -624,8 +640,8 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			       const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	u32 tmp;
 	enum port port;
@@ -641,7 +657,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			tmp |= EOTP_DISABLED;
 
 		/* enable link calibration if freq > 1.5Gbps */
-		if (intel_dsi_bitrate(intel_dsi) >= 1500 * 1000) {
+		if (afe_clk(encoder, pipe_config) >= 1500 * 1000) {
 			tmp &= ~LINK_CALIBRATION_MASK;
 			tmp |= CALIBRATION_ENABLED_INITIAL_ONLY;
 		}
@@ -667,22 +683,26 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 
 		/* select pixel format */
 		tmp &= ~PIX_FMT_MASK;
-		switch (intel_dsi->pixel_format) {
-		default:
-			MISSING_CASE(intel_dsi->pixel_format);
-			/* fallthrough */
-		case MIPI_DSI_FMT_RGB565:
-			tmp |= PIX_FMT_RGB565;
-			break;
-		case MIPI_DSI_FMT_RGB666_PACKED:
-			tmp |= PIX_FMT_RGB666_PACKED;
-			break;
-		case MIPI_DSI_FMT_RGB666:
-			tmp |= PIX_FMT_RGB666_LOOSE;
-			break;
-		case MIPI_DSI_FMT_RGB888:
-			tmp |= PIX_FMT_RGB888;
-			break;
+		if (pipe_config->dsc.compression_enable) {
+			tmp |= PIX_FMT_COMPRESSED;
+		} else {
+			switch (intel_dsi->pixel_format) {
+			default:
+				MISSING_CASE(intel_dsi->pixel_format);
+				/* fallthrough */
+			case MIPI_DSI_FMT_RGB565:
+				tmp |= PIX_FMT_RGB565;
+				break;
+			case MIPI_DSI_FMT_RGB666_PACKED:
+				tmp |= PIX_FMT_RGB666_PACKED;
+				break;
+			case MIPI_DSI_FMT_RGB666:
+				tmp |= PIX_FMT_RGB666_LOOSE;
+				break;
+			case MIPI_DSI_FMT_RGB888:
+				tmp |= PIX_FMT_RGB888;
+				break;
+			}
 		}
 
 		if (INTEL_GEN(dev_priv) >= 12) {
@@ -745,6 +765,9 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 		case PIPE_C:
 			tmp |= TRANS_DDI_EDP_INPUT_C_ONOFF;
 			break;
+		case PIPE_D:
+			tmp |= TRANS_DDI_EDP_INPUT_D_ONOFF;
+			break;
 		}
 
 		/* enable DDI buffer */
@@ -763,12 +786,12 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 
 static void
 gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
-				 const struct intel_crtc_state *pipe_config)
+				 const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	const struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	enum port port;
 	enum transcoder dsi_trans;
 	/* horizontal timings */
@@ -776,11 +799,25 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 	u16 hback_porch;
 	/* vertical timings */
 	u16 vtotal, vactive, vsync_start, vsync_end, vsync_shift;
+	int mul = 1, div = 1;
+
+	/*
+	 * Adjust horizontal timings (htotal, hsync_start, hsync_end) to account
+	 * for slower link speed if DSC is enabled.
+	 *
+	 * The compression frequency ratio is the ratio between compressed and
+	 * non-compressed link speeds, and simplifies down to the ratio between
+	 * compressed and non-compressed bpp.
+	 */
+	if (crtc_state->dsc.compression_enable) {
+		mul = crtc_state->dsc.compressed_bpp;
+		div = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+	}
 
 	hactive = adjusted_mode->crtc_hdisplay;
-	htotal = adjusted_mode->crtc_htotal;
-	hsync_start = adjusted_mode->crtc_hsync_start;
-	hsync_end = adjusted_mode->crtc_hsync_end;
+	htotal = DIV_ROUND_UP(adjusted_mode->crtc_htotal * mul, div);
+	hsync_start = DIV_ROUND_UP(adjusted_mode->crtc_hsync_start * mul, div);
+	hsync_end = DIV_ROUND_UP(adjusted_mode->crtc_hsync_end * mul, div);
 	hsync_size  = hsync_end - hsync_start;
 	hback_porch = (adjusted_mode->crtc_htotal -
 		       adjusted_mode->crtc_hsync_end);
@@ -886,7 +923,7 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 static void gen11_dsi_enable_transcoder(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp;
@@ -904,10 +941,11 @@ static void gen11_dsi_enable_transcoder(struct intel_encoder *encoder)
 	}
 }
 
-static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder)
+static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder,
+				     const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp, hs_tx_timeout, lp_rx_timeout, ta_timeout, divisor, mul;
@@ -919,7 +957,7 @@ static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder)
 	 * TIME_NS = (BYTE_CLK_COUNT * 8 * 10^6)/ Bitrate
 	 * ESCAPE_CLK_COUNT  = TIME_NS/ESC_CLK_NS
 	 */
-	divisor = intel_dsi_tlpx_ns(intel_dsi) * intel_dsi_bitrate(intel_dsi) * 1000;
+	divisor = intel_dsi_tlpx_ns(intel_dsi) * afe_clk(encoder, crtc_state) * 1000;
 	mul = 8 * 1000000;
 	hs_tx_timeout = DIV_ROUND_UP(intel_dsi->hs_tx_timeout * mul,
 				     divisor);
@@ -955,7 +993,7 @@ static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder)
 
 static void
 gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
-			      const struct intel_crtc_state *pipe_config)
+			      const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
@@ -972,13 +1010,13 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 	gen11_dsi_enable_ddi_buffer(encoder);
 
 	/* setup D-PHY timings */
-	gen11_dsi_setup_dphy_timings(encoder);
+	gen11_dsi_setup_dphy_timings(encoder, crtc_state);
 
 	/* step 4h: setup DSI protocol timeouts */
-	gen11_dsi_setup_timeouts(encoder);
+	gen11_dsi_setup_timeouts(encoder, crtc_state);
 
 	/* Step (4h, 4i, 4j, 4k): Configure transcoder */
-	gen11_dsi_configure_transcoder(encoder, pipe_config);
+	gen11_dsi_configure_transcoder(encoder, crtc_state);
 
 	/* Step 4l: Gate DDI clocks */
 	if (IS_GEN(dev_priv, 11))
@@ -988,7 +1026,7 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct mipi_dsi_device *dsi;
 	enum port port;
 	enum transcoder dsi_trans;
@@ -1025,21 +1063,21 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 }
 
 static void gen11_dsi_pre_pll_enable(struct intel_encoder *encoder,
-				     const struct intel_crtc_state *pipe_config,
+				     const struct intel_crtc_state *crtc_state,
 				     const struct drm_connector_state *conn_state)
 {
 	/* step2: enable IO power */
 	gen11_dsi_enable_io_power(encoder);
 
 	/* step3: enable DSI PLL */
-	gen11_dsi_program_esc_clk_div(encoder);
+	gen11_dsi_program_esc_clk_div(encoder, crtc_state);
 }
 
 static void gen11_dsi_pre_enable(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *pipe_config,
 				 const struct drm_connector_state *conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
 	/* step3b */
 	gen11_dsi_map_pll(encoder, pipe_config);
@@ -1050,6 +1088,8 @@ static void gen11_dsi_pre_enable(struct intel_encoder *encoder,
 	/* step5: program and powerup panel */
 	gen11_dsi_powerup_panel(encoder);
 
+	intel_dsc_enable(encoder, pipe_config);
+
 	/* step6c: configure transcoder timings */
 	gen11_dsi_set_transcoder_timings(encoder, pipe_config);
 
@@ -1064,7 +1104,7 @@ static void gen11_dsi_pre_enable(struct intel_encoder *encoder,
 static void gen11_dsi_disable_transcoder(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp;
@@ -1086,7 +1126,7 @@ static void gen11_dsi_disable_transcoder(struct intel_encoder *encoder)
 
 static void gen11_dsi_powerdown_panel(struct intel_encoder *encoder)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_OFF);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET);
@@ -1099,7 +1139,7 @@ static void gen11_dsi_powerdown_panel(struct intel_encoder *encoder)
 static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp;
@@ -1140,7 +1180,7 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum port port;
 
@@ -1162,7 +1202,7 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 tmp;
 
@@ -1189,7 +1229,7 @@ static void gen11_dsi_disable(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
 	/* step1: turn off backlight */
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_OFF);
@@ -1211,12 +1251,42 @@ static void gen11_dsi_disable(struct intel_encoder *encoder,
 	gen11_dsi_disable_io_power(encoder);
 }
 
+static void gen11_dsi_post_disable(struct intel_encoder *encoder,
+				   const struct intel_crtc_state *old_crtc_state,
+				   const struct drm_connector_state *old_conn_state)
+{
+	intel_crtc_vblank_off(old_crtc_state);
+
+	intel_dsc_disable(old_crtc_state);
+
+	skl_scaler_disable(old_crtc_state);
+}
+
+static enum drm_mode_status gen11_dsi_mode_valid(struct drm_connector *connector,
+						 struct drm_display_mode *mode)
+{
+	/* FIXME: DSC? */
+	return intel_dsi_mode_valid(connector, mode);
+}
+
 static void gen11_dsi_get_timings(struct intel_encoder *encoder,
 				  struct intel_crtc_state *pipe_config)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+					&pipe_config->hw.adjusted_mode;
+
+	if (pipe_config->dsc.compressed_bpp) {
+		int div = pipe_config->dsc.compressed_bpp;
+		int mul = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+
+		adjusted_mode->crtc_htotal =
+			DIV_ROUND_UP(adjusted_mode->crtc_htotal * mul, div);
+		adjusted_mode->crtc_hsync_start =
+			DIV_ROUND_UP(adjusted_mode->crtc_hsync_start * mul, div);
+		adjusted_mode->crtc_hsync_end =
+			DIV_ROUND_UP(adjusted_mode->crtc_hsync_end * mul, div);
+	}
 
 	if (intel_dsi->dual_link) {
 		adjusted_mode->crtc_hdisplay *= 2;
@@ -1242,22 +1312,66 @@ static void gen11_dsi_get_config(struct intel_encoder *encoder,
 				 struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+
+	intel_dsc_get_config(encoder, pipe_config);
 
 	/* FIXME: adapt icl_ddi_clock_get() for DSI and use that? */
 	pipe_config->port_clock =
 		cnl_calc_wrpll_link(dev_priv, &pipe_config->dpll_hw_state);
 
-	pipe_config->base.adjusted_mode.crtc_clock = intel_dsi->pclk;
+	pipe_config->hw.adjusted_mode.crtc_clock = intel_dsi->pclk;
 	if (intel_dsi->dual_link)
-		pipe_config->base.adjusted_mode.crtc_clock *= 2;
+		pipe_config->hw.adjusted_mode.crtc_clock *= 2;
 
 	gen11_dsi_get_timings(encoder, pipe_config);
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI);
 	pipe_config->pipe_bpp = bdw_get_pipemisc_bpp(crtc);
 }
 
+static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder,
+					struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	int dsc_max_bpc = INTEL_GEN(dev_priv) >= 12 ? 12 : 10;
+	bool use_dsc;
+	int ret;
+
+	use_dsc = intel_bios_get_dsc_params(encoder, crtc_state, dsc_max_bpc);
+	if (!use_dsc)
+		return 0;
+
+	if (crtc_state->pipe_bpp < 8 * 3)
+		return -EINVAL;
+
+	/* FIXME: split only when necessary */
+	if (crtc_state->dsc.slice_count > 1)
+		crtc_state->dsc.dsc_split = true;
+
+	vdsc_cfg->convert_rgb = true;
+
+	ret = intel_dsc_compute_params(encoder, crtc_state);
+	if (ret)
+		return ret;
+
+	/* DSI specific sanity checks on the common code */
+	WARN_ON(vdsc_cfg->vbr_enable);
+	WARN_ON(vdsc_cfg->simple_422);
+	WARN_ON(vdsc_cfg->pic_width % vdsc_cfg->slice_width);
+	WARN_ON(vdsc_cfg->slice_height < 8);
+	WARN_ON(vdsc_cfg->pic_height % vdsc_cfg->slice_height);
+
+	ret = drm_dsc_compute_rc_parameters(vdsc_cfg);
+	if (ret)
+		return ret;
+
+	crtc_state->dsc.compression_enable = true;
+
+	return 0;
+}
+
 static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config,
 				    struct drm_connector_state *conn_state)
@@ -1265,11 +1379,11 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
 						   base);
 	struct intel_connector *intel_connector = intel_dsi->attached_connector;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	const struct drm_display_mode *fixed_mode =
 					intel_connector->panel.fixed_mode;
 	struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+					&pipe_config->hw.adjusted_mode;
 
 	pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
 	intel_fixed_panel_mode(fixed_mode, adjusted_mode);
@@ -1283,8 +1397,17 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 	else
 		pipe_config->cpu_transcoder = TRANSCODER_DSI_0;
 
+	if (intel_dsi->pixel_format == MIPI_DSI_FMT_RGB888)
+		pipe_config->pipe_bpp = 24;
+	else
+		pipe_config->pipe_bpp = 18;
+
 	pipe_config->clock_set = true;
-	pipe_config->port_clock = intel_dsi_bitrate(intel_dsi) / 5;
+
+	if (gen11_dsi_dsc_compute_config(encoder, pipe_config))
+		DRM_DEBUG_KMS("Attempting to use DSC failed\n");
+
+	pipe_config->port_clock = afe_clk(encoder, pipe_config) / 5;
 
 	return 0;
 }
@@ -1292,15 +1415,21 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
 					struct intel_crtc_state *crtc_state)
 {
-	get_dsi_io_power_domains(to_i915(encoder->base.dev),
-				 enc_to_intel_dsi(&encoder->base));
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+
+	get_dsi_io_power_domains(i915,
+				 enc_to_intel_dsi(encoder));
+
+	if (crtc_state->dsc.compression_enable)
+		intel_display_power_get(i915,
+					intel_dsc_power_domain(crtc_state));
 }
 
 static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum transcoder dsi_trans;
 	intel_wakeref_t wakeref;
 	enum port port;
@@ -1325,6 +1454,9 @@ static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 		case TRANS_DDI_EDP_INPUT_C_ONOFF:
 			*pipe = PIPE_C;
 			break;
+		case TRANS_DDI_EDP_INPUT_D_ONOFF:
+			*pipe = PIPE_D;
+			break;
 		default:
 			DRM_ERROR("Invalid PIPE input\n");
 			goto out;
@@ -1360,7 +1492,7 @@ static const struct drm_connector_funcs gen11_dsi_connector_funcs = {
 
 static const struct drm_connector_helper_funcs gen11_dsi_connector_helper_funcs = {
 	.get_modes = intel_dsi_get_modes,
-	.mode_valid = intel_dsi_mode_valid,
+	.mode_valid = gen11_dsi_mode_valid,
 	.atomic_check = intel_digital_connector_atomic_check,
 };
 
@@ -1577,6 +1709,7 @@ void icl_dsi_init(struct drm_i915_private *dev_priv)
 	encoder->pre_pll_enable = gen11_dsi_pre_pll_enable;
 	encoder->pre_enable = gen11_dsi_pre_enable;
 	encoder->disable = gen11_dsi_disable;
+	encoder->post_disable = gen11_dsi_post_disable;
 	encoder->port = port;
 	encoder->get_config = gen11_dsi_get_config;
 	encoder->update_pipe = intel_panel_update_backlight;
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index c2875b10adf9..c362eecdd414 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -37,6 +37,7 @@
 #include "intel_atomic.h"
 #include "intel_display_types.h"
 #include "intel_hdcp.h"
+#include "intel_psr.h"
 #include "intel_sprite.h"
 
 /**
@@ -129,6 +130,7 @@ int intel_digital_connector_atomic_check(struct drm_connector *conn,
 	struct drm_crtc_state *crtc_state;
 
 	intel_hdcp_atomic_check(conn, old_state, new_state);
+	intel_psr_atomic_check(conn, old_state, new_state);
 
 	if (!new_state->crtc)
 		return 0;
@@ -175,6 +177,38 @@ intel_digital_connector_duplicate_state(struct drm_connector *connector)
 }
 
 /**
+ * intel_connector_needs_modeset - check if connector needs a modeset
+ */
+bool
+intel_connector_needs_modeset(struct intel_atomic_state *state,
+			      struct drm_connector *connector)
+{
+	const struct drm_connector_state *old_conn_state, *new_conn_state;
+
+	old_conn_state = drm_atomic_get_old_connector_state(&state->base, connector);
+	new_conn_state = drm_atomic_get_new_connector_state(&state->base, connector);
+
+	return old_conn_state->crtc != new_conn_state->crtc ||
+	       (new_conn_state->crtc &&
+		drm_atomic_crtc_needs_modeset(drm_atomic_get_new_crtc_state(&state->base,
+									    new_conn_state->crtc)));
+}
+
+struct intel_digital_connector_state *
+intel_atomic_get_digital_connector_state(struct intel_atomic_state *state,
+					 struct intel_connector *connector)
+{
+	struct drm_connector_state *conn_state;
+
+	conn_state = drm_atomic_get_connector_state(&state->base,
+						    &connector->base);
+	if (IS_ERR(conn_state))
+		return ERR_CAST(conn_state);
+
+	return to_intel_digital_connector_state(conn_state);
+}
+
+/**
  * intel_crtc_duplicate_state - duplicate crtc state
  * @crtc: drm crtc
  *
@@ -186,13 +220,22 @@ intel_digital_connector_duplicate_state(struct drm_connector *connector)
 struct drm_crtc_state *
 intel_crtc_duplicate_state(struct drm_crtc *crtc)
 {
+	const struct intel_crtc_state *old_crtc_state = to_intel_crtc_state(crtc->state);
 	struct intel_crtc_state *crtc_state;
 
-	crtc_state = kmemdup(crtc->state, sizeof(*crtc_state), GFP_KERNEL);
+	crtc_state = kmemdup(old_crtc_state, sizeof(*crtc_state), GFP_KERNEL);
 	if (!crtc_state)
 		return NULL;
 
-	__drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->base);
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->uapi);
+
+	/* copy color blobs */
+	if (crtc_state->hw.degamma_lut)
+		drm_property_blob_get(crtc_state->hw.degamma_lut);
+	if (crtc_state->hw.ctm)
+		drm_property_blob_get(crtc_state->hw.ctm);
+	if (crtc_state->hw.gamma_lut)
+		drm_property_blob_get(crtc_state->hw.gamma_lut);
 
 	crtc_state->update_pipe = false;
 	crtc_state->disable_lp_wm = false;
@@ -205,7 +248,29 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	crtc_state->fb_bits = 0;
 	crtc_state->update_planes = 0;
 
-	return &crtc_state->base;
+	return &crtc_state->uapi;
+}
+
+static void intel_crtc_put_color_blobs(struct intel_crtc_state *crtc_state)
+{
+	drm_property_blob_put(crtc_state->hw.degamma_lut);
+	drm_property_blob_put(crtc_state->hw.gamma_lut);
+	drm_property_blob_put(crtc_state->hw.ctm);
+}
+
+void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state)
+{
+	intel_crtc_put_color_blobs(crtc_state);
+}
+
+void intel_crtc_copy_color_blobs(struct intel_crtc_state *crtc_state)
+{
+	drm_property_replace_blob(&crtc_state->hw.degamma_lut,
+				  crtc_state->uapi.degamma_lut);
+	drm_property_replace_blob(&crtc_state->hw.gamma_lut,
+				  crtc_state->uapi.gamma_lut);
+	drm_property_replace_blob(&crtc_state->hw.ctm,
+				  crtc_state->uapi.ctm);
 }
 
 /**
@@ -220,7 +285,11 @@ void
 intel_crtc_destroy_state(struct drm_crtc *crtc,
 			 struct drm_crtc_state *state)
 {
-	drm_atomic_helper_crtc_destroy_state(crtc, state);
+	struct intel_crtc_state *crtc_state = to_intel_crtc_state(state);
+
+	__drm_atomic_helper_crtc_destroy_state(&crtc_state->uapi);
+	intel_crtc_free_hw_state(crtc_state);
+	kfree(crtc_state);
 }
 
 static void intel_atomic_setup_scaler(struct intel_crtc_scaler_state *scaler_state,
@@ -249,10 +318,10 @@ static void intel_atomic_setup_scaler(struct intel_crtc_scaler_state *scaler_sta
 		return;
 
 	/* set scaler mode */
-	if (plane_state && plane_state->base.fb &&
-	    plane_state->base.fb->format->is_yuv &&
-	    plane_state->base.fb->format->num_planes > 1) {
-		struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	if (plane_state && plane_state->hw.fb &&
+	    plane_state->hw.fb->format->is_yuv &&
+	    plane_state->hw.fb->format->num_planes > 1) {
+		struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 		if (IS_GEN(dev_priv, 9) &&
 		    !IS_GEMINILAKE(dev_priv)) {
 			mode = SKL_PS_SCALER_MODE_NV12;
@@ -319,7 +388,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 	struct intel_plane_state *plane_state = NULL;
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
-	struct drm_atomic_state *drm_state = crtc_state->base.state;
+	struct drm_atomic_state *drm_state = crtc_state->uapi.state;
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(drm_state);
 	int num_scalers_need;
 	int i;
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.h b/drivers/gpu/drm/i915/display/intel_atomic.h
index 49d5cb1b9e0a..74c749dbfb4f 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic.h
@@ -17,6 +17,7 @@ struct drm_device;
 struct drm_i915_private;
 struct drm_property;
 struct intel_atomic_state;
+struct intel_connector;
 struct intel_crtc;
 struct intel_crtc_state;
 
@@ -32,10 +33,17 @@ int intel_digital_connector_atomic_check(struct drm_connector *conn,
 					 struct drm_atomic_state *state);
 struct drm_connector_state *
 intel_digital_connector_duplicate_state(struct drm_connector *connector);
+bool intel_connector_needs_modeset(struct intel_atomic_state *state,
+				   struct drm_connector *connector);
+struct intel_digital_connector_state *
+intel_atomic_get_digital_connector_state(struct intel_atomic_state *state,
+					 struct intel_connector *connector);
 
 struct drm_crtc_state *intel_crtc_duplicate_state(struct drm_crtc *crtc);
 void intel_crtc_destroy_state(struct drm_crtc *crtc,
 			       struct drm_crtc_state *state);
+void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state);
+void intel_crtc_copy_color_blobs(struct intel_crtc_state *crtc_state);
 struct drm_atomic_state *intel_atomic_state_alloc(struct drm_device *dev);
 void intel_atomic_state_clear(struct drm_atomic_state *state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index 98f557a9f8ee..3e97af682b1b 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -41,6 +41,16 @@
 #include "intel_pm.h"
 #include "intel_sprite.h"
 
+static void intel_plane_state_reset(struct intel_plane_state *plane_state,
+				    struct intel_plane *plane)
+{
+	memset(plane_state, 0, sizeof(*plane_state));
+
+	__drm_atomic_helper_plane_state_reset(&plane_state->uapi, &plane->base);
+
+	plane_state->scaler_id = -1;
+}
+
 struct intel_plane *intel_plane_alloc(void)
 {
 	struct intel_plane_state *plane_state;
@@ -56,8 +66,9 @@ struct intel_plane *intel_plane_alloc(void)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	__drm_atomic_helper_plane_reset(&plane->base, &plane_state->base);
-	plane_state->scaler_id = -1;
+	intel_plane_state_reset(plane_state, plane);
+
+	plane->base.state = &plane_state->uapi;
 
 	return plane;
 }
@@ -80,22 +91,24 @@ void intel_plane_free(struct intel_plane *plane)
 struct drm_plane_state *
 intel_plane_duplicate_state(struct drm_plane *plane)
 {
-	struct drm_plane_state *state;
 	struct intel_plane_state *intel_state;
 
-	intel_state = kmemdup(plane->state, sizeof(*intel_state), GFP_KERNEL);
+	intel_state = to_intel_plane_state(plane->state);
+	intel_state = kmemdup(intel_state, sizeof(*intel_state), GFP_KERNEL);
 
 	if (!intel_state)
 		return NULL;
 
-	state = &intel_state->base;
-
-	__drm_atomic_helper_plane_duplicate_state(plane, state);
+	__drm_atomic_helper_plane_duplicate_state(plane, &intel_state->uapi);
 
 	intel_state->vma = NULL;
 	intel_state->flags = 0;
 
-	return state;
+	/* add reference to fb */
+	if (intel_state->hw.fb)
+		drm_framebuffer_get(intel_state->hw.fb);
+
+	return &intel_state->uapi;
 }
 
 /**
@@ -110,18 +123,22 @@ void
 intel_plane_destroy_state(struct drm_plane *plane,
 			  struct drm_plane_state *state)
 {
-	WARN_ON(to_intel_plane_state(state)->vma);
+	struct intel_plane_state *plane_state = to_intel_plane_state(state);
+	WARN_ON(plane_state->vma);
 
-	drm_atomic_helper_plane_destroy_state(plane, state);
+	__drm_atomic_helper_plane_destroy_state(&plane_state->uapi);
+	if (plane_state->hw.fb)
+		drm_framebuffer_put(plane_state->hw.fb);
+	kfree(plane_state);
 }
 
 unsigned int intel_plane_data_rate(const struct intel_crtc_state *crtc_state,
 				   const struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	cpp = fb->format->cpp[0];
@@ -144,10 +161,10 @@ bool intel_plane_calc_min_cdclk(struct intel_atomic_state *state,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	const struct intel_plane_state *plane_state =
 		intel_atomic_get_new_plane_state(state, plane);
-	struct intel_crtc *crtc = to_intel_crtc(plane_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc);
 	struct intel_crtc_state *crtc_state;
 
-	if (!plane_state->base.visible || !plane->min_cdclk)
+	if (!plane_state->uapi.visible || !plane->min_cdclk)
 		return false;
 
 	crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
@@ -176,23 +193,52 @@ bool intel_plane_calc_min_cdclk(struct intel_atomic_state *state,
 	return false;
 }
 
+static void intel_plane_clear_hw_state(struct intel_plane_state *plane_state)
+{
+	if (plane_state->hw.fb)
+		drm_framebuffer_put(plane_state->hw.fb);
+
+	memset(&plane_state->hw, 0, sizeof(plane_state->hw));
+}
+
+void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state,
+				       const struct intel_plane_state *from_plane_state)
+{
+	intel_plane_clear_hw_state(plane_state);
+
+	plane_state->hw.crtc = from_plane_state->uapi.crtc;
+	plane_state->hw.fb = from_plane_state->uapi.fb;
+	if (plane_state->hw.fb)
+		drm_framebuffer_get(plane_state->hw.fb);
+
+	plane_state->hw.alpha = from_plane_state->uapi.alpha;
+	plane_state->hw.pixel_blend_mode =
+		from_plane_state->uapi.pixel_blend_mode;
+	plane_state->hw.rotation = from_plane_state->uapi.rotation;
+	plane_state->hw.color_encoding = from_plane_state->uapi.color_encoding;
+	plane_state->hw.color_range = from_plane_state->uapi.color_range;
+}
+
 int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state,
 					struct intel_crtc_state *new_crtc_state,
 					const struct intel_plane_state *old_plane_state,
 					struct intel_plane_state *new_plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(new_plane_state->base.plane);
-	const struct drm_framebuffer *fb = new_plane_state->base.fb;
+	struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane);
+	const struct drm_framebuffer *fb;
 	int ret;
 
+	intel_plane_copy_uapi_to_hw_state(new_plane_state, new_plane_state);
+	fb = new_plane_state->hw.fb;
+
 	new_crtc_state->active_planes &= ~BIT(plane->id);
 	new_crtc_state->nv12_planes &= ~BIT(plane->id);
 	new_crtc_state->c8_planes &= ~BIT(plane->id);
 	new_crtc_state->data_rate[plane->id] = 0;
 	new_crtc_state->min_cdclk[plane->id] = 0;
-	new_plane_state->base.visible = false;
+	new_plane_state->uapi.visible = false;
 
-	if (!new_plane_state->base.crtc && !old_plane_state->base.crtc)
+	if (!new_plane_state->hw.crtc && !old_plane_state->hw.crtc)
 		return 0;
 
 	ret = plane->check_plane(new_crtc_state, new_plane_state);
@@ -200,18 +246,18 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 		return ret;
 
 	/* FIXME pre-g4x don't work like this */
-	if (new_plane_state->base.visible)
+	if (new_plane_state->uapi.visible)
 		new_crtc_state->active_planes |= BIT(plane->id);
 
-	if (new_plane_state->base.visible &&
-	    drm_format_info_is_yuv_semiplanar(fb->format))
+	if (new_plane_state->uapi.visible &&
+	    intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		new_crtc_state->nv12_planes |= BIT(plane->id);
 
-	if (new_plane_state->base.visible &&
+	if (new_plane_state->uapi.visible &&
 	    fb->format->format == DRM_FORMAT_C8)
 		new_crtc_state->c8_planes |= BIT(plane->id);
 
-	if (new_plane_state->base.visible || old_plane_state->base.visible)
+	if (new_plane_state->uapi.visible || old_plane_state->uapi.visible)
 		new_crtc_state->update_planes |= BIT(plane->id);
 
 	new_crtc_state->data_rate[plane->id] =
@@ -225,11 +271,11 @@ static struct intel_crtc *
 get_crtc_from_states(const struct intel_plane_state *old_plane_state,
 		     const struct intel_plane_state *new_plane_state)
 {
-	if (new_plane_state->base.crtc)
-		return to_intel_crtc(new_plane_state->base.crtc);
+	if (new_plane_state->uapi.crtc)
+		return to_intel_crtc(new_plane_state->uapi.crtc);
 
-	if (old_plane_state->base.crtc)
-		return to_intel_crtc(old_plane_state->base.crtc);
+	if (old_plane_state->uapi.crtc)
+		return to_intel_crtc(old_plane_state->uapi.crtc);
 
 	return NULL;
 }
@@ -246,7 +292,7 @@ int intel_plane_atomic_check(struct intel_atomic_state *state,
 	const struct intel_crtc_state *old_crtc_state;
 	struct intel_crtc_state *new_crtc_state;
 
-	new_plane_state->base.visible = false;
+	new_plane_state->uapi.visible = false;
 	if (!crtc)
 		return 0;
 
@@ -307,26 +353,16 @@ void intel_update_plane(struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	trace_intel_update_plane(&plane->base, crtc);
 	plane->update_plane(plane, crtc_state, plane_state);
 }
 
-void intel_update_slave(struct intel_plane *plane,
-			const struct intel_crtc_state *crtc_state,
-			const struct intel_plane_state *plane_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-
-	trace_intel_update_plane(&plane->base, crtc);
-	plane->update_slave(plane, crtc_state, plane_state);
-}
-
 void intel_disable_plane(struct intel_plane *plane,
 			 const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	trace_intel_disable_plane(&plane->base, crtc);
 	plane->disable_plane(plane, crtc_state);
@@ -355,25 +391,9 @@ void skl_update_planes_on_crtc(struct intel_atomic_state *state,
 		struct intel_plane_state *new_plane_state =
 			intel_atomic_get_new_plane_state(state, plane);
 
-		if (new_plane_state->base.visible) {
+		if (new_plane_state->uapi.visible ||
+		    new_plane_state->planar_slave) {
 			intel_update_plane(plane, new_crtc_state, new_plane_state);
-		} else if (new_plane_state->planar_slave) {
-			struct intel_plane *master =
-				new_plane_state->planar_linked_plane;
-
-			/*
-			 * We update the slave plane from this function because
-			 * programming it from the master plane's update_plane
-			 * callback runs into issues when the Y plane is
-			 * reassigned, disabled or used by a different plane.
-			 *
-			 * The slave plane is updated with the master plane's
-			 * plane_state.
-			 */
-			new_plane_state =
-				intel_atomic_get_new_plane_state(state, master);
-
-			intel_update_slave(plane, new_crtc_state, new_plane_state);
 		} else {
 			intel_disable_plane(plane, new_crtc_state);
 		}
@@ -395,7 +415,7 @@ void i9xx_update_planes_on_crtc(struct intel_atomic_state *state,
 		    !(update_mask & BIT(plane->id)))
 			continue;
 
-		if (new_plane_state->base.visible)
+		if (new_plane_state->uapi.visible)
 			intel_update_plane(plane, new_crtc_state, new_plane_state);
 		else
 			intel_disable_plane(plane, new_crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
index e61e9a82aadf..5cedafdddb55 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
@@ -20,12 +20,11 @@ extern const struct drm_plane_helper_funcs intel_plane_helper_funcs;
 
 unsigned int intel_plane_data_rate(const struct intel_crtc_state *crtc_state,
 				   const struct intel_plane_state *plane_state);
+void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state,
+				       const struct intel_plane_state *from_plane_state);
 void intel_update_plane(struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state);
-void intel_update_slave(struct intel_plane *plane,
-			const struct intel_crtc_state *crtc_state,
-			const struct intel_plane_state *plane_state);
 void intel_disable_plane(struct intel_plane *plane,
 			 const struct intel_crtc_state *crtc_state);
 struct intel_plane *intel_plane_alloc(void);
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 3a5ac13d5801..b18040793d9e 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -234,7 +234,7 @@ static const struct hdmi_aud_ncts hdmi_aud_ncts_36bpp[] = {
 static u32 audio_config_hdmi_pixel_clock(const struct intel_crtc_state *crtc_state)
 {
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(hdmi_audio_clock); i++) {
@@ -555,7 +555,7 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder,
 				    const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
 	u32 tmp, eldv;
@@ -602,7 +602,7 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 				   const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_connector *connector = conn_state->connector;
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
@@ -692,10 +692,10 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct i915_audio_component *acomp = dev_priv->audio_component;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_connector *connector = conn_state->connector;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	enum port port = encoder->port;
 	enum pipe pipe = crtc->pipe;
 
@@ -707,8 +707,8 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 	DRM_DEBUG_DRIVER("ELD on [CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
 			 connector->base.id,
 			 connector->name,
-			 connector->encoder->base.id,
-			 connector->encoder->name);
+			 encoder->base.base.id,
+			 encoder->base.name);
 
 	connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2;
 
@@ -753,7 +753,7 @@ void intel_audio_codec_disable(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct i915_audio_component *acomp = dev_priv->audio_component;
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum port port = encoder->port;
 	enum pipe pipe = crtc->pipe;
 
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 63c1bd4c2954..8beac06e3f10 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -29,6 +29,7 @@
 #include <drm/i915_drm.h>
 
 #include "display/intel_display.h"
+#include "display/intel_display_types.h"
 #include "display/intel_gmbus.h"
 
 #include "i915_drv.h"
@@ -58,6 +59,13 @@
  * that.
  */
 
+/* Wrapper for VBT child device config */
+struct display_device_data {
+	struct child_device_config child;
+	struct dsc_compression_parameters_entry *dsc;
+	struct list_head node;
+};
+
 #define	SLAVE_ADDR1	0x70
 #define	SLAVE_ADDR2	0x72
 
@@ -202,17 +210,12 @@ get_lvds_fp_timing(const struct bdb_header *bdb,
 	return (const struct lvds_fp_timing *)((const u8 *)bdb + ofs);
 }
 
-/* Try to find integrated panel data */
+/* Parse general panel options */
 static void
-parse_lfp_panel_data(struct drm_i915_private *dev_priv,
-		     const struct bdb_header *bdb)
+parse_panel_options(struct drm_i915_private *dev_priv,
+		    const struct bdb_header *bdb)
 {
 	const struct bdb_lvds_options *lvds_options;
-	const struct bdb_lvds_lfp_data *lvds_lfp_data;
-	const struct bdb_lvds_lfp_data_ptrs *lvds_lfp_data_ptrs;
-	const struct lvds_dvo_timing *panel_dvo_timing;
-	const struct lvds_fp_timing *fp_timing;
-	struct drm_display_mode *panel_fixed_mode;
 	int panel_type;
 	int drrs_mode;
 	int ret;
@@ -261,6 +264,19 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("DRRS not supported (VBT input)\n");
 		break;
 	}
+}
+
+/* Try to find integrated panel timing data */
+static void
+parse_lfp_panel_dtd(struct drm_i915_private *dev_priv,
+		    const struct bdb_header *bdb)
+{
+	const struct bdb_lvds_lfp_data *lvds_lfp_data;
+	const struct bdb_lvds_lfp_data_ptrs *lvds_lfp_data_ptrs;
+	const struct lvds_dvo_timing *panel_dvo_timing;
+	const struct lvds_fp_timing *fp_timing;
+	struct drm_display_mode *panel_fixed_mode;
+	int panel_type = dev_priv->vbt.panel_type;
 
 	lvds_lfp_data = find_section(bdb, BDB_LVDS_LFP_DATA);
 	if (!lvds_lfp_data)
@@ -282,7 +298,7 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 
 	dev_priv->vbt.lfp_lvds_vbt_mode = panel_fixed_mode;
 
-	DRM_DEBUG_KMS("Found panel mode in BIOS VBT tables:\n");
+	DRM_DEBUG_KMS("Found panel mode in BIOS VBT legacy lfp table:\n");
 	drm_mode_debug_printmodeline(panel_fixed_mode);
 
 	fp_timing = get_lvds_fp_timing(bdb, lvds_lfp_data,
@@ -300,6 +316,98 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 }
 
 static void
+parse_generic_dtd(struct drm_i915_private *dev_priv,
+		  const struct bdb_header *bdb)
+{
+	const struct bdb_generic_dtd *generic_dtd;
+	const struct generic_dtd_entry *dtd;
+	struct drm_display_mode *panel_fixed_mode;
+	int num_dtd;
+
+	generic_dtd = find_section(bdb, BDB_GENERIC_DTD);
+	if (!generic_dtd)
+		return;
+
+	if (generic_dtd->gdtd_size < sizeof(struct generic_dtd_entry)) {
+		DRM_ERROR("GDTD size %u is too small.\n",
+			  generic_dtd->gdtd_size);
+		return;
+	} else if (generic_dtd->gdtd_size !=
+		   sizeof(struct generic_dtd_entry)) {
+		DRM_ERROR("Unexpected GDTD size %u\n", generic_dtd->gdtd_size);
+		/* DTD has unknown fields, but keep going */
+	}
+
+	num_dtd = (get_blocksize(generic_dtd) -
+		   sizeof(struct bdb_generic_dtd)) / generic_dtd->gdtd_size;
+	if (dev_priv->vbt.panel_type >= num_dtd) {
+		DRM_ERROR("Panel type %d not found in table of %d DTD's\n",
+			  dev_priv->vbt.panel_type, num_dtd);
+		return;
+	}
+
+	dtd = &generic_dtd->dtd[dev_priv->vbt.panel_type];
+
+	panel_fixed_mode = kzalloc(sizeof(*panel_fixed_mode), GFP_KERNEL);
+	if (!panel_fixed_mode)
+		return;
+
+	panel_fixed_mode->hdisplay = dtd->hactive;
+	panel_fixed_mode->hsync_start =
+		panel_fixed_mode->hdisplay + dtd->hfront_porch;
+	panel_fixed_mode->hsync_end =
+		panel_fixed_mode->hsync_start + dtd->hsync;
+	panel_fixed_mode->htotal = panel_fixed_mode->hsync_end;
+
+	panel_fixed_mode->vdisplay = dtd->vactive;
+	panel_fixed_mode->vsync_start =
+		panel_fixed_mode->vdisplay + dtd->vfront_porch;
+	panel_fixed_mode->vsync_end =
+		panel_fixed_mode->vsync_start + dtd->vsync;
+	panel_fixed_mode->vtotal = panel_fixed_mode->vsync_end;
+
+	panel_fixed_mode->clock = dtd->pixel_clock;
+	panel_fixed_mode->width_mm = dtd->width_mm;
+	panel_fixed_mode->height_mm = dtd->height_mm;
+
+	panel_fixed_mode->type = DRM_MODE_TYPE_PREFERRED;
+	drm_mode_set_name(panel_fixed_mode);
+
+	if (dtd->hsync_positive_polarity)
+		panel_fixed_mode->flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		panel_fixed_mode->flags |= DRM_MODE_FLAG_NHSYNC;
+
+	if (dtd->vsync_positive_polarity)
+		panel_fixed_mode->flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		panel_fixed_mode->flags |= DRM_MODE_FLAG_NVSYNC;
+
+	DRM_DEBUG_KMS("Found panel mode in BIOS VBT generic dtd table:\n");
+	drm_mode_debug_printmodeline(panel_fixed_mode);
+
+	dev_priv->vbt.lfp_lvds_vbt_mode = panel_fixed_mode;
+}
+
+static void
+parse_panel_dtd(struct drm_i915_private *dev_priv,
+		const struct bdb_header *bdb)
+{
+	/*
+	 * Older VBTs provided provided DTD information for internal displays
+	 * through the "LFP panel DTD" block (42).  As of VBT revision 229,
+	 * that block is now deprecated and DTD information should be provided
+	 * via a newer "generic DTD" block (58).  Just to be safe, we'll
+	 * try the new generic DTD block first on VBT >= 229, but still fall
+	 * back to trying the old LFP block if that fails.
+	 */
+	if (bdb->version >= 229)
+		parse_generic_dtd(dev_priv, bdb);
+	if (!dev_priv->vbt.lfp_lvds_vbt_mode)
+		parse_lfp_panel_dtd(dev_priv, bdb);
+}
+
+static void
 parse_lfp_backlight(struct drm_i915_private *dev_priv,
 		    const struct bdb_header *bdb)
 {
@@ -449,8 +557,9 @@ static void
 parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, u8 bdb_version)
 {
 	struct sdvo_device_mapping *mapping;
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
-	int i, count = 0;
+	int count = 0;
 
 	/*
 	 * Only parse SDVO mappings on gens that could have SDVO. This isn't
@@ -461,8 +570,8 @@ parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, u8 bdb_version)
 		return;
 	}
 
-	for (i = 0, count = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		if (child->slave_addr != SLAVE_ADDR1 &&
 		    child->slave_addr != SLAVE_ADDR2) {
@@ -552,16 +661,45 @@ parse_driver_features(struct drm_i915_private *dev_priv,
 			dev_priv->vbt.int_lvds_support = 0;
 	}
 
-	DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled);
+	if (bdb->version < 228) {
+		DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled);
+		/*
+		 * If DRRS is not supported, drrs_type has to be set to 0.
+		 * This is because, VBT is configured in such a way that
+		 * static DRRS is 0 and DRRS not supported is represented by
+		 * driver->drrs_enabled=false
+		 */
+		if (!driver->drrs_enabled)
+			dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED;
+
+		dev_priv->vbt.psr.enable = driver->psr_enabled;
+	}
+}
+
+static void
+parse_power_conservation_features(struct drm_i915_private *dev_priv,
+				  const struct bdb_header *bdb)
+{
+	const struct bdb_lfp_power *power;
+	u8 panel_type = dev_priv->vbt.panel_type;
+
+	if (bdb->version < 228)
+		return;
+
+	power = find_section(bdb, BDB_LVDS_POWER);
+	if (!power)
+		return;
+
+	dev_priv->vbt.psr.enable = power->psr & BIT(panel_type);
+
 	/*
 	 * If DRRS is not supported, drrs_type has to be set to 0.
 	 * This is because, VBT is configured in such a way that
 	 * static DRRS is 0 and DRRS not supported is represented by
-	 * driver->drrs_enabled=false
+	 * power->drrs & BIT(panel_type)=false
 	 */
-	if (!driver->drrs_enabled)
+	if (!(power->drrs & BIT(panel_type)))
 		dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED;
-	dev_priv->vbt.psr.enable = driver->psr_enabled;
 }
 
 static void
@@ -1230,6 +1368,57 @@ err:
 	memset(dev_priv->vbt.dsi.sequence, 0, sizeof(dev_priv->vbt.dsi.sequence));
 }
 
+static void
+parse_compression_parameters(struct drm_i915_private *i915,
+			     const struct bdb_header *bdb)
+{
+	const struct bdb_compression_parameters *params;
+	struct display_device_data *devdata;
+	const struct child_device_config *child;
+	u16 block_size;
+	int index;
+
+	if (bdb->version < 198)
+		return;
+
+	params = find_section(bdb, BDB_COMPRESSION_PARAMETERS);
+	if (params) {
+		/* Sanity checks */
+		if (params->entry_size != sizeof(params->data[0])) {
+			DRM_DEBUG_KMS("VBT: unsupported compression param entry size\n");
+			return;
+		}
+
+		block_size = get_blocksize(params);
+		if (block_size < sizeof(*params)) {
+			DRM_DEBUG_KMS("VBT: expected 16 compression param entries\n");
+			return;
+		}
+	}
+
+	list_for_each_entry(devdata, &i915->vbt.display_devices, node) {
+		child = &devdata->child;
+
+		if (!child->compression_enable)
+			continue;
+
+		if (!params) {
+			DRM_DEBUG_KMS("VBT: compression params not available\n");
+			continue;
+		}
+
+		if (child->compression_method_cps) {
+			DRM_DEBUG_KMS("VBT: CPS compression not supported\n");
+			continue;
+		}
+
+		index = child->compression_structure_index;
+
+		devdata->dsc = kmemdup(&params->data[index],
+				       sizeof(*devdata->dsc), GFP_KERNEL);
+	}
+}
+
 static u8 translate_iboost(u8 val)
 {
 	static const u8 mapping[] = { 1, 3, 7 }; /* See VBT spec */
@@ -1246,7 +1435,7 @@ static enum port get_port_by_ddc_pin(struct drm_i915_private *i915, u8 ddc_pin)
 	const struct ddi_vbt_port_info *info;
 	enum port port;
 
-	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
+	for_each_port(port) {
 		info = &i915->vbt.ddi_port_info[port];
 
 		if (info->child && ddc_pin == info->alternate_ddc_pin)
@@ -1297,7 +1486,7 @@ static enum port get_port_by_aux_ch(struct drm_i915_private *i915, u8 aux_ch)
 	const struct ddi_vbt_port_info *info;
 	enum port port;
 
-	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
+	for_each_port(port) {
 		info = &i915->vbt.ddi_port_info[port];
 
 		if (info->child && aux_ch == info->alternate_aux_channel)
@@ -1418,9 +1607,10 @@ static enum port dvo_port_to_port(u8 dvo_port)
 }
 
 static void parse_ddi_port(struct drm_i915_private *dev_priv,
-			   const struct child_device_config *child,
+			   struct display_device_data *devdata,
 			   u8 bdb_version)
 {
+	const struct child_device_config *child = &devdata->child;
 	struct ddi_vbt_port_info *info;
 	bool is_dvi, is_hdmi, is_dp, is_edp, is_crt;
 	enum port port;
@@ -1443,7 +1633,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 	is_hdmi = is_dvi && (child->device_type & DEVICE_TYPE_NOT_HDMI_OUTPUT) == 0;
 	is_edp = is_dp && (child->device_type & DEVICE_TYPE_INTERNAL_CONNECTOR);
 
-	if (port == PORT_A && is_dvi) {
+	if (port == PORT_A && is_dvi && INTEL_GEN(dev_priv) < 12) {
 		DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n",
 			      is_hdmi ? "/HDMI" : "");
 		is_dvi = false;
@@ -1461,26 +1651,11 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 	if (bdb_version >= 209)
 		info->supports_tbt = child->tbt;
 
-	DRM_DEBUG_KMS("Port %c VBT info: CRT:%d DVI:%d HDMI:%d DP:%d eDP:%d LSPCON:%d USB-Type-C:%d TBT:%d\n",
+	DRM_DEBUG_KMS("Port %c VBT info: CRT:%d DVI:%d HDMI:%d DP:%d eDP:%d LSPCON:%d USB-Type-C:%d TBT:%d DSC:%d\n",
 		      port_name(port), is_crt, is_dvi, is_hdmi, is_dp, is_edp,
 		      HAS_LSPCON(dev_priv) && child->lspcon,
-		      info->supports_typec_usb, info->supports_tbt);
-
-	if (is_edp && is_dvi)
-		DRM_DEBUG_KMS("Internal DP port %c is TMDS compatible\n",
-			      port_name(port));
-	if (is_crt && port != PORT_E)
-		DRM_DEBUG_KMS("Port %c is analog\n", port_name(port));
-	if (is_crt && (is_dvi || is_dp))
-		DRM_DEBUG_KMS("Analog port %c is also DP or TMDS compatible\n",
-			      port_name(port));
-	if (is_dvi && (port == PORT_A || port == PORT_E))
-		DRM_DEBUG_KMS("Port %c is TMDS compatible\n", port_name(port));
-	if (!is_dvi && !is_dp && !is_crt)
-		DRM_DEBUG_KMS("Port %c is not DP/TMDS/CRT compatible\n",
-			      port_name(port));
-	if (is_edp && (port == PORT_B || port == PORT_C || port == PORT_E))
-		DRM_DEBUG_KMS("Port %c is internal DP\n", port_name(port));
+		      info->supports_typec_usb, info->supports_tbt,
+		      devdata->dsc != NULL);
 
 	if (is_dvi) {
 		u8 ddc_pin;
@@ -1509,6 +1684,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 			      port_name(port),
 			      hdmi_level_shift);
 		info->hdmi_level_shift = hdmi_level_shift;
+		info->hdmi_level_shift_set = true;
 	}
 
 	if (bdb_version >= 204) {
@@ -1571,8 +1747,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 
 static void parse_ddi_ports(struct drm_i915_private *dev_priv, u8 bdb_version)
 {
-	const struct child_device_config *child;
-	int i;
+	struct display_device_data *devdata;
 
 	if (!HAS_DDI(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		return;
@@ -1580,11 +1755,8 @@ static void parse_ddi_ports(struct drm_i915_private *dev_priv, u8 bdb_version)
 	if (bdb_version < 155)
 		return;
 
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
-
-		parse_ddi_port(dev_priv, child, bdb_version);
-	}
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node)
+		parse_ddi_port(dev_priv, devdata, bdb_version);
 }
 
 static void
@@ -1592,8 +1764,9 @@ parse_general_definitions(struct drm_i915_private *dev_priv,
 			  const struct bdb_header *bdb)
 {
 	const struct bdb_general_definitions *defs;
+	struct display_device_data *devdata;
 	const struct child_device_config *child;
-	int i, child_device_num, count;
+	int i, child_device_num;
 	u8 expected_size;
 	u16 block_size;
 	int bus_pin;
@@ -1649,26 +1822,7 @@ parse_general_definitions(struct drm_i915_private *dev_priv,
 
 	/* get the number of child device */
 	child_device_num = (block_size - sizeof(*defs)) / defs->child_dev_size;
-	count = 0;
-	/* get the number of child device that is present */
-	for (i = 0; i < child_device_num; i++) {
-		child = child_device_ptr(defs, i);
-		if (!child->device_type)
-			continue;
-		count++;
-	}
-	if (!count) {
-		DRM_DEBUG_KMS("no child dev is parsed from VBT\n");
-		return;
-	}
-	dev_priv->vbt.child_dev = kcalloc(count, sizeof(*child), GFP_KERNEL);
-	if (!dev_priv->vbt.child_dev) {
-		DRM_DEBUG_KMS("No memory space for child device\n");
-		return;
-	}
 
-	dev_priv->vbt.child_dev_num = count;
-	count = 0;
 	for (i = 0; i < child_device_num; i++) {
 		child = child_device_ptr(defs, i);
 		if (!child->device_type)
@@ -1677,23 +1831,29 @@ parse_general_definitions(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("Found VBT child device with type 0x%x\n",
 			      child->device_type);
 
+		devdata = kzalloc(sizeof(*devdata), GFP_KERNEL);
+		if (!devdata)
+			break;
+
 		/*
 		 * Copy as much as we know (sizeof) and is available
-		 * (child_dev_size) of the child device. Accessing the data must
-		 * depend on VBT version.
+		 * (child_dev_size) of the child device config. Accessing the
+		 * data must depend on VBT version.
 		 */
-		memcpy(dev_priv->vbt.child_dev + count, child,
+		memcpy(&devdata->child, child,
 		       min_t(size_t, defs->child_dev_size, sizeof(*child)));
-		count++;
+
+		list_add_tail(&devdata->node, &dev_priv->vbt.display_devices);
 	}
+
+	if (list_empty(&dev_priv->vbt.display_devices))
+		DRM_DEBUG_KMS("no child dev is parsed from VBT\n");
 }
 
 /* Common defaults which may be overridden by VBT. */
 static void
 init_vbt_defaults(struct drm_i915_private *dev_priv)
 {
-	enum port port;
-
 	dev_priv->vbt.crt_ddc_pin = GMBUS_PIN_VGADDC;
 
 	/* Default to having backlight */
@@ -1721,13 +1881,6 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	dev_priv->vbt.lvds_ssc_freq = intel_bios_ssc_frequency(dev_priv,
 			!HAS_PCH_SPLIT(dev_priv));
 	DRM_DEBUG_KMS("Set default to SSC at %d kHz\n", dev_priv->vbt.lvds_ssc_freq);
-
-	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
-		struct ddi_vbt_port_info *info =
-			&dev_priv->vbt.ddi_port_info[port];
-
-		info->hdmi_level_shift = HDMI_LEVEL_SHIFT_UNKNOWN;
-	}
 }
 
 /* Defaults to initialize only if there is no VBT. */
@@ -1736,7 +1889,7 @@ init_vbt_missing_defaults(struct drm_i915_private *dev_priv)
 {
 	enum port port;
 
-	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
+	for_each_port(port) {
 		struct ddi_vbt_port_info *info =
 			&dev_priv->vbt.ddi_port_info[port];
 		enum phy phy = intel_port_to_phy(dev_priv, port);
@@ -1787,6 +1940,13 @@ bool intel_bios_is_valid_vbt(const void *buf, size_t size)
 		return false;
 	}
 
+	if (vbt->vbt_size > size) {
+		DRM_DEBUG_DRIVER("VBT incomplete (vbt_size overflows)\n");
+		return false;
+	}
+
+	size = vbt->vbt_size;
+
 	if (range_overflows_t(size_t,
 			      vbt->bdb_offset,
 			      sizeof(struct bdb_header),
@@ -1804,28 +1964,61 @@ bool intel_bios_is_valid_vbt(const void *buf, size_t size)
 	return vbt;
 }
 
-static const struct vbt_header *find_vbt(void __iomem *bios, size_t size)
+static struct vbt_header *oprom_get_vbt(struct drm_i915_private *dev_priv)
 {
-	size_t i;
+	struct pci_dev *pdev = dev_priv->drm.pdev;
+	void __iomem *p = NULL, *oprom;
+	struct vbt_header *vbt;
+	u16 vbt_size;
+	size_t i, size;
 
-	/* Scour memory looking for the VBT signature. */
-	for (i = 0; i + 4 < size; i++) {
-		void *vbt;
+	oprom = pci_map_rom(pdev, &size);
+	if (!oprom)
+		return NULL;
 
-		if (ioread32(bios + i) != *((const u32 *) "$VBT"))
+	/* Scour memory looking for the VBT signature. */
+	for (i = 0; i + 4 < size; i += 4) {
+		if (ioread32(oprom + i) != *((const u32 *)"$VBT"))
 			continue;
 
-		/*
-		 * This is the one place where we explicitly discard the address
-		 * space (__iomem) of the BIOS/VBT.
-		 */
-		vbt = (void __force *) bios + i;
-		if (intel_bios_is_valid_vbt(vbt, size - i))
-			return vbt;
-
+		p = oprom + i;
+		size -= i;
 		break;
 	}
 
+	if (!p)
+		goto err_unmap_oprom;
+
+	if (sizeof(struct vbt_header) > size) {
+		DRM_DEBUG_DRIVER("VBT header incomplete\n");
+		goto err_unmap_oprom;
+	}
+
+	vbt_size = ioread16(p + offsetof(struct vbt_header, vbt_size));
+	if (vbt_size > size) {
+		DRM_DEBUG_DRIVER("VBT incomplete (vbt_size overflows)\n");
+		goto err_unmap_oprom;
+	}
+
+	/* The rest will be validated by intel_bios_is_valid_vbt() */
+	vbt = kmalloc(vbt_size, GFP_KERNEL);
+	if (!vbt)
+		goto err_unmap_oprom;
+
+	memcpy_fromio(vbt, p, vbt_size);
+
+	if (!intel_bios_is_valid_vbt(vbt, vbt_size))
+		goto err_free_vbt;
+
+	pci_unmap_rom(pdev, oprom);
+
+	return vbt;
+
+err_free_vbt:
+	kfree(vbt);
+err_unmap_oprom:
+	pci_unmap_rom(pdev, oprom);
+
 	return NULL;
 }
 
@@ -1839,10 +2032,11 @@ static const struct vbt_header *find_vbt(void __iomem *bios, size_t size)
  */
 void intel_bios_init(struct drm_i915_private *dev_priv)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
 	const struct vbt_header *vbt = dev_priv->opregion.vbt;
+	struct vbt_header *oprom_vbt = NULL;
 	const struct bdb_header *bdb;
-	u8 __iomem *bios = NULL;
+
+	INIT_LIST_HEAD(&dev_priv->vbt.display_devices);
 
 	if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv)) {
 		DRM_DEBUG_KMS("Skipping VBT init due to disabled display.\n");
@@ -1853,15 +2047,11 @@ void intel_bios_init(struct drm_i915_private *dev_priv)
 
 	/* If the OpRegion does not have VBT, look in PCI ROM. */
 	if (!vbt) {
-		size_t size;
-
-		bios = pci_map_rom(pdev, &size);
-		if (!bios)
+		oprom_vbt = oprom_get_vbt(dev_priv);
+		if (!oprom_vbt)
 			goto out;
 
-		vbt = find_vbt(bios, size);
-		if (!vbt)
-			goto out;
+		vbt = oprom_vbt;
 
 		DRM_DEBUG_KMS("Found valid VBT in PCI ROM\n");
 	}
@@ -1874,15 +2064,20 @@ void intel_bios_init(struct drm_i915_private *dev_priv)
 	/* Grab useful general definitions */
 	parse_general_features(dev_priv, bdb);
 	parse_general_definitions(dev_priv, bdb);
-	parse_lfp_panel_data(dev_priv, bdb);
+	parse_panel_options(dev_priv, bdb);
+	parse_panel_dtd(dev_priv, bdb);
 	parse_lfp_backlight(dev_priv, bdb);
 	parse_sdvo_panel_data(dev_priv, bdb);
 	parse_driver_features(dev_priv, bdb);
+	parse_power_conservation_features(dev_priv, bdb);
 	parse_edp(dev_priv, bdb);
 	parse_psr(dev_priv, bdb);
 	parse_mipi_config(dev_priv, bdb);
 	parse_mipi_sequence(dev_priv, bdb);
 
+	/* Depends on child device list */
+	parse_compression_parameters(dev_priv, bdb);
+
 	/* Further processing on pre-parsed data */
 	parse_sdvo_device_mapping(dev_priv, bdb->version);
 	parse_ddi_ports(dev_priv, bdb->version);
@@ -1893,8 +2088,7 @@ out:
 		init_vbt_missing_defaults(dev_priv);
 	}
 
-	if (bios)
-		pci_unmap_rom(pdev, bios);
+	kfree(oprom_vbt);
 }
 
 /**
@@ -1903,9 +2097,14 @@ out:
  */
 void intel_bios_driver_remove(struct drm_i915_private *dev_priv)
 {
-	kfree(dev_priv->vbt.child_dev);
-	dev_priv->vbt.child_dev = NULL;
-	dev_priv->vbt.child_dev_num = 0;
+	struct display_device_data *devdata, *n;
+
+	list_for_each_entry_safe(devdata, n, &dev_priv->vbt.display_devices, node) {
+		list_del(&devdata->node);
+		kfree(devdata->dsc);
+		kfree(devdata);
+	}
+
 	kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
 	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
 	kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
@@ -1929,17 +2128,18 @@ void intel_bios_driver_remove(struct drm_i915_private *dev_priv)
  */
 bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
-	int i;
 
 	if (!dev_priv->vbt.int_tv_support)
 		return false;
 
-	if (!dev_priv->vbt.child_dev_num)
+	if (list_empty(&dev_priv->vbt.display_devices))
 		return true;
 
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
+
 		/*
 		 * If the device type is not TV, continue.
 		 */
@@ -1971,14 +2171,14 @@ bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv)
  */
 bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
-	int i;
 
-	if (!dev_priv->vbt.child_dev_num)
+	if (list_empty(&dev_priv->vbt.display_devices))
 		return true;
 
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		/* If the device type is not LFP, continue.
 		 * We have to check both the new identifiers as well as the
@@ -2020,6 +2220,7 @@ bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin)
  */
 bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
 	static const struct {
 		u16 dp, hdmi;
@@ -2030,7 +2231,6 @@ bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port por
 		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
 		[PORT_F] = { DVO_PORT_DPF, DVO_PORT_HDMIF, },
 	};
-	int i;
 
 	if (HAS_DDI(dev_priv)) {
 		const struct ddi_vbt_port_info *port_info =
@@ -2045,11 +2245,8 @@ bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port por
 	if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping))
 		return false;
 
-	if (!dev_priv->vbt.child_dev_num)
-		return false;
-
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		if ((child->dvo_port == port_mapping[port].dp ||
 		     child->dvo_port == port_mapping[port].hdmi) &&
@@ -2070,6 +2267,7 @@ bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port por
  */
 bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
 	static const short port_mapping[] = {
 		[PORT_B] = DVO_PORT_DPB,
@@ -2078,16 +2276,12 @@ bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port)
 		[PORT_E] = DVO_PORT_DPE,
 		[PORT_F] = DVO_PORT_DPF,
 	};
-	int i;
 
 	if (HAS_DDI(dev_priv))
 		return dev_priv->vbt.ddi_port_info[port].supports_edp;
 
-	if (!dev_priv->vbt.child_dev_num)
-		return false;
-
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		if (child->dvo_port == port_mapping[port] &&
 		    (child->device_type & DEVICE_TYPE_eDP_BITS) ==
@@ -2136,13 +2330,10 @@ static bool child_dev_is_dp_dual_mode(const struct child_device_config *child,
 bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv,
 				     enum port port)
 {
-	const struct child_device_config *child;
-	int i;
-
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	const struct display_device_data *devdata;
 
-		if (child_dev_is_dp_dual_mode(child, port))
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		if (child_dev_is_dp_dual_mode(&devdata->child, port))
 			return true;
 	}
 
@@ -2159,12 +2350,12 @@ bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv,
 bool intel_bios_is_dsi_present(struct drm_i915_private *dev_priv,
 			       enum port *port)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
 	u8 dvo_port;
-	int i;
 
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		if (!(child->device_type & DEVICE_TYPE_MIPI_OUTPUT))
 			continue;
@@ -2188,6 +2379,104 @@ bool intel_bios_is_dsi_present(struct drm_i915_private *dev_priv,
 	return false;
 }
 
+static void fill_dsc(struct intel_crtc_state *crtc_state,
+		     struct dsc_compression_parameters_entry *dsc,
+		     int dsc_max_bpc)
+{
+	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	int bpc = 8;
+
+	vdsc_cfg->dsc_version_major = dsc->version_major;
+	vdsc_cfg->dsc_version_minor = dsc->version_minor;
+
+	if (dsc->support_12bpc && dsc_max_bpc >= 12)
+		bpc = 12;
+	else if (dsc->support_10bpc && dsc_max_bpc >= 10)
+		bpc = 10;
+	else if (dsc->support_8bpc && dsc_max_bpc >= 8)
+		bpc = 8;
+	else
+		DRM_DEBUG_KMS("VBT: Unsupported BPC %d for DCS\n",
+			      dsc_max_bpc);
+
+	crtc_state->pipe_bpp = bpc * 3;
+
+	crtc_state->dsc.compressed_bpp = min(crtc_state->pipe_bpp,
+					     VBT_DSC_MAX_BPP(dsc->max_bpp));
+
+	/*
+	 * FIXME: This is ugly, and slice count should take DSC engine
+	 * throughput etc. into account.
+	 *
+	 * Also, per spec DSI supports 1, 2, 3 or 4 horizontal slices.
+	 */
+	if (dsc->slices_per_line & BIT(2)) {
+		crtc_state->dsc.slice_count = 4;
+	} else if (dsc->slices_per_line & BIT(1)) {
+		crtc_state->dsc.slice_count = 2;
+	} else {
+		/* FIXME */
+		if (!(dsc->slices_per_line & BIT(0)))
+			DRM_DEBUG_KMS("VBT: Unsupported DSC slice count for DSI\n");
+
+		crtc_state->dsc.slice_count = 1;
+	}
+
+	if (crtc_state->hw.adjusted_mode.crtc_hdisplay %
+	    crtc_state->dsc.slice_count != 0)
+		DRM_DEBUG_KMS("VBT: DSC hdisplay %d not divisible by slice count %d\n",
+			      crtc_state->hw.adjusted_mode.crtc_hdisplay,
+			      crtc_state->dsc.slice_count);
+
+	/*
+	 * FIXME: Use VBT rc_buffer_block_size and rc_buffer_size for the
+	 * implementation specific physical rate buffer size. Currently we use
+	 * the required rate buffer model size calculated in
+	 * drm_dsc_compute_rc_parameters() according to VESA DSC Annex E.
+	 *
+	 * The VBT rc_buffer_block_size and rc_buffer_size definitions
+	 * correspond to DP 1.4 DPCD offsets 0x62 and 0x63. The DP DSC
+	 * implementation should also use the DPCD (or perhaps VBT for eDP)
+	 * provided value for the buffer size.
+	 */
+
+	/* FIXME: DSI spec says bpc + 1 for this one */
+	vdsc_cfg->line_buf_depth = VBT_DSC_LINE_BUFFER_DEPTH(dsc->line_buffer_depth);
+
+	vdsc_cfg->block_pred_enable = dsc->block_prediction_enable;
+
+	vdsc_cfg->slice_height = dsc->slice_height;
+}
+
+/* FIXME: initially DSI specific */
+bool intel_bios_get_dsc_params(struct intel_encoder *encoder,
+			       struct intel_crtc_state *crtc_state,
+			       int dsc_max_bpc)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	const struct display_device_data *devdata;
+	const struct child_device_config *child;
+
+	list_for_each_entry(devdata, &i915->vbt.display_devices, node) {
+		child = &devdata->child;
+
+		if (!(child->device_type & DEVICE_TYPE_MIPI_OUTPUT))
+			continue;
+
+		if (child->dvo_port - DVO_PORT_MIPIA == encoder->port) {
+			if (!devdata->dsc)
+				return false;
+
+			if (crtc_state)
+				fill_dsc(crtc_state, devdata->dsc, dsc_max_bpc);
+
+			return true;
+		}
+	}
+
+	return false;
+}
+
 /**
  * intel_bios_is_port_hpd_inverted - is HPD inverted for %port
  * @i915:	i915 device instance
diff --git a/drivers/gpu/drm/i915/display/intel_bios.h b/drivers/gpu/drm/i915/display/intel_bios.h
index 98f064828a57..d6a0c29d37ac 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.h
+++ b/drivers/gpu/drm/i915/display/intel_bios.h
@@ -35,6 +35,8 @@
 #include <drm/i915_drm.h>
 
 struct drm_i915_private;
+struct intel_crtc_state;
+struct intel_encoder;
 enum port;
 
 enum intel_backlight_type {
@@ -242,5 +244,8 @@ bool intel_bios_is_port_hpd_inverted(const struct drm_i915_private *i915,
 bool intel_bios_is_lspcon_present(const struct drm_i915_private *i915,
 				  enum port port);
 enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *dev_priv, enum port port);
+bool intel_bios_get_dsc_params(struct intel_encoder *encoder,
+			       struct intel_crtc_state *crtc_state,
+			       int dsc_max_bpc);
 
 #endif /* _INTEL_BIOS_H_ */
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index 22e83f857de8..b228671d5a5d 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -15,7 +15,7 @@ struct intel_qgv_point {
 };
 
 struct intel_qgv_info {
-	struct intel_qgv_point points[3];
+	struct intel_qgv_point points[I915_NUM_QGV_POINTS];
 	u8 num_points;
 	u8 num_channels;
 	u8 t_bl;
@@ -264,6 +264,9 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv,
 
 void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 {
+	if (!HAS_DISPLAY(dev_priv))
+		return;
+
 	if (IS_GEN(dev_priv, 12))
 		icl_get_bw_info(dev_priv, &tgl_sa_info);
 	else if (IS_GEN(dev_priv, 11))
@@ -273,17 +276,29 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 static unsigned int intel_max_data_rate(struct drm_i915_private *dev_priv,
 					int num_planes)
 {
-	if (INTEL_GEN(dev_priv) >= 11)
+	if (INTEL_GEN(dev_priv) >= 11) {
+		/*
+		 * Any bw group has same amount of QGV points
+		 */
+		const struct intel_bw_info *bi =
+			&dev_priv->max_bw[0];
+		unsigned int min_bw = UINT_MAX;
+		int i;
+
 		/*
 		 * FIXME with SAGV disabled maybe we can assume
 		 * point 1 will always be used? Seems to match
 		 * the behaviour observed in the wild.
 		 */
-		return min3(icl_max_bw(dev_priv, num_planes, 0),
-			    icl_max_bw(dev_priv, num_planes, 1),
-			    icl_max_bw(dev_priv, num_planes, 2));
-	else
+		for (i = 0; i < bi->num_qgv_points; i++) {
+			unsigned int bw = icl_max_bw(dev_priv, num_planes, i);
+
+			min_bw = min(bw, min_bw);
+		}
+		return min_bw;
+	} else {
 		return UINT_MAX;
+	}
 }
 
 static unsigned int intel_bw_crtc_num_active_planes(const struct intel_crtc_state *crtc_state)
@@ -297,7 +312,7 @@ static unsigned int intel_bw_crtc_num_active_planes(const struct intel_crtc_stat
 
 static unsigned int intel_bw_crtc_data_rate(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	unsigned int data_rate = 0;
 	enum plane_id plane_id;
 
@@ -318,7 +333,7 @@ static unsigned int intel_bw_crtc_data_rate(const struct intel_crtc_state *crtc_
 void intel_bw_crtc_update(struct intel_bw_state *bw_state,
 			  const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	bw_state->data_rate[crtc->pipe] =
 		intel_bw_crtc_data_rate(crtc_state);
@@ -471,3 +486,8 @@ int intel_bw_init(struct drm_i915_private *dev_priv)
 
 	return 0;
 }
+
+void intel_bw_cleanup(struct drm_i915_private *dev_priv)
+{
+	drm_atomic_private_obj_fini(&dev_priv->bw_obj);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h
index 9db10af012f4..20b9ad241802 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.h
+++ b/drivers/gpu/drm/i915/display/intel_bw.h
@@ -25,6 +25,7 @@ struct intel_bw_state {
 
 void intel_bw_init_hw(struct drm_i915_private *dev_priv);
 int intel_bw_init(struct drm_i915_private *dev_priv);
+void intel_bw_cleanup(struct drm_i915_private *dev_priv);
 int intel_bw_atomic_check(struct intel_atomic_state *state);
 void intel_bw_crtc_update(struct intel_bw_state *bw_state,
 			  const struct intel_crtc_state *crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index ed8c7ce62119..0ce5926006ca 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1904,7 +1904,7 @@ intel_set_cdclk_post_plane_update(struct drm_i915_private *dev_priv,
 
 static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int pixel_rate = crtc_state->pixel_rate;
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
@@ -1922,7 +1922,7 @@ static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state)
 
 static int intel_planes_min_cdclk(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_plane *plane;
 	int min_cdclk = 0;
@@ -1936,10 +1936,10 @@ static int intel_planes_min_cdclk(const struct intel_crtc_state *crtc_state)
 int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->base.crtc->dev);
+		to_i915(crtc_state->uapi.crtc->dev);
 	int min_cdclk;
 
-	if (!crtc_state->base.enable)
+	if (!crtc_state->hw.enable)
 		return 0;
 
 	min_cdclk = intel_pixel_rate_to_cdclk(crtc_state);
@@ -2004,6 +2004,18 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	/* Account for additional needs from the planes */
 	min_cdclk = max(intel_planes_min_cdclk(crtc_state), min_cdclk);
 
+	/*
+	 * HACK. Currently for TGL platforms we calculate
+	 * min_cdclk initially based on pixel_rate divided
+	 * by 2, accounting for also plane requirements,
+	 * however in some cases the lowest possible CDCLK
+	 * doesn't work and causing the underruns.
+	 * Explicitly stating here that this seems to be currently
+	 * rather a Hack, than final solution.
+	 */
+	if (IS_TIGERLAKE(dev_priv))
+		min_cdclk = max(min_cdclk, (int)crtc_state->pixel_rate);
+
 	if (min_cdclk > dev_priv->max_cdclk_freq) {
 		DRM_DEBUG_KMS("required cdclk (%d kHz) exceeds max (%d kHz)\n",
 			      min_cdclk, dev_priv->max_cdclk_freq);
@@ -2076,7 +2088,7 @@ static int bxt_compute_min_voltage_level(struct intel_atomic_state *state)
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
 		int ret;
 
-		if (crtc_state->base.enable)
+		if (crtc_state->hw.enable)
 			min_voltage_level = crtc_state->min_voltage_level;
 		else
 			min_voltage_level = 0;
@@ -2170,7 +2182,7 @@ static int skl_dpll0_vco(struct intel_atomic_state *state)
 		vco = dev_priv->skl_preferred_vco_freq;
 
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
-		if (!crtc_state->base.enable)
+		if (!crtc_state->hw.enable)
 			continue;
 
 		if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
@@ -2283,11 +2295,11 @@ static int intel_modeset_all_pipes(struct intel_atomic_state *state)
 		if (IS_ERR(crtc_state))
 			return PTR_ERR(crtc_state);
 
-		if (!crtc_state->base.active ||
-		    drm_atomic_crtc_needs_modeset(&crtc_state->base))
+		if (!crtc_state->hw.active ||
+		    drm_atomic_crtc_needs_modeset(&crtc_state->uapi))
 			continue;
 
-		crtc_state->base.mode_changed = true;
+		crtc_state->uapi.mode_changed = true;
 
 		ret = drm_atomic_add_affected_connectors(&state->base,
 							 &crtc->base);
@@ -2368,7 +2380,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state)
 		if (IS_ERR(crtc_state))
 			return PTR_ERR(crtc_state);
 
-		if (drm_atomic_crtc_needs_modeset(&crtc_state->base))
+		if (drm_atomic_crtc_needs_modeset(&crtc_state->uapi))
 			pipe = INVALID_PIPE;
 	} else {
 		pipe = INVALID_PIPE;
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index aa3a063549c3..3980e8b50c28 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -117,10 +117,10 @@ static bool lut_is_legacy(const struct drm_property_blob *lut)
 
 static bool crtc_state_is_legacy_gamma(const struct intel_crtc_state *crtc_state)
 {
-	return !crtc_state->base.degamma_lut &&
-		!crtc_state->base.ctm &&
-		crtc_state->base.gamma_lut &&
-		lut_is_legacy(crtc_state->base.gamma_lut);
+	return !crtc_state->hw.degamma_lut &&
+		!crtc_state->hw.ctm &&
+		crtc_state->hw.gamma_lut &&
+		lut_is_legacy(crtc_state->hw.gamma_lut);
 }
 
 /*
@@ -205,7 +205,7 @@ static void icl_update_output_csc(struct intel_crtc *crtc,
 
 static bool ilk_csc_limited_range(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	/*
 	 * FIXME if there's a gamma LUT after the CSC, we should
@@ -219,7 +219,7 @@ static bool ilk_csc_limited_range(const struct intel_crtc_state *crtc_state)
 static void ilk_csc_convert_ctm(const struct intel_crtc_state *crtc_state,
 				u16 coeffs[9])
 {
-	const struct drm_color_ctm *ctm = crtc_state->base.ctm->data;
+	const struct drm_color_ctm *ctm = crtc_state->hw.ctm->data;
 	const u64 *input;
 	u64 temp[9];
 	int i;
@@ -270,11 +270,11 @@ static void ilk_csc_convert_ctm(const struct intel_crtc_state *crtc_state,
 
 static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	bool limited_color_range = ilk_csc_limited_range(crtc_state);
 
-	if (crtc_state->base.ctm) {
+	if (crtc_state->hw.ctm) {
 		u16 coeff[9];
 
 		ilk_csc_convert_ctm(crtc_state, coeff);
@@ -309,10 +309,10 @@ static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 
 static void icl_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	if (crtc_state->base.ctm) {
+	if (crtc_state->hw.ctm) {
 		u16 coeff[9];
 
 		ilk_csc_convert_ctm(crtc_state, coeff);
@@ -338,12 +338,12 @@ static void icl_load_csc_matrix(const struct intel_crtc_state *crtc_state)
  */
 static void cherryview_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	if (crtc_state->base.ctm) {
-		const struct drm_color_ctm *ctm = crtc_state->base.ctm->data;
+	if (crtc_state->hw.ctm) {
+		const struct drm_color_ctm *ctm = crtc_state->hw.ctm->data;
 		u16 coeffs[9] = {};
 		int i;
 
@@ -404,7 +404,7 @@ static u32 ilk_lut_10(const struct drm_color_lut *color)
 static void i9xx_load_luts_internal(const struct intel_crtc_state *crtc_state,
 				    const struct drm_property_blob *blob)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	int i;
@@ -435,12 +435,12 @@ static void i9xx_load_luts_internal(const struct intel_crtc_state *crtc_state,
 
 static void i9xx_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	i9xx_load_luts_internal(crtc_state, crtc_state->base.gamma_lut);
+	i9xx_load_luts_internal(crtc_state, crtc_state->hw.gamma_lut);
 }
 
 static void i9xx_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
@@ -453,7 +453,7 @@ static void i9xx_color_commit(const struct intel_crtc_state *crtc_state)
 
 static void ilk_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
@@ -468,7 +468,7 @@ static void ilk_color_commit(const struct intel_crtc_state *crtc_state)
 
 static void hsw_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	I915_WRITE(GAMMA_MODE(crtc->pipe), crtc_state->gamma_mode);
@@ -478,7 +478,7 @@ static void hsw_color_commit(const struct intel_crtc_state *crtc_state)
 
 static void skl_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val = 0;
@@ -524,8 +524,8 @@ static void i965_load_lut_10p6(struct intel_crtc *crtc,
 
 static void i965_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
 		i9xx_load_luts(crtc_state);
@@ -547,8 +547,8 @@ static void ilk_load_lut_10(struct intel_crtc *crtc,
 
 static void ilk_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
 		i9xx_load_luts(crtc_state);
@@ -654,9 +654,9 @@ static void ivb_load_lut_ext_max(struct intel_crtc *crtc)
 
 static void ivb_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT) {
 		i9xx_load_luts(crtc_state);
@@ -677,9 +677,9 @@ static void ivb_load_luts(const struct intel_crtc_state *crtc_state)
 
 static void bdw_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT) {
 		i9xx_load_luts(crtc_state);
@@ -700,11 +700,11 @@ static void bdw_load_luts(const struct intel_crtc_state *crtc_state)
 
 static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	const u32 lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size;
-	const struct drm_color_lut *lut = crtc_state->base.degamma_lut->data;
+	const struct drm_color_lut *lut = crtc_state->hw.degamma_lut->data;
 	u32 i;
 
 	/*
@@ -739,7 +739,7 @@ static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state)
 
 static void glk_load_degamma_lut_linear(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	const u32 lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size;
@@ -766,8 +766,8 @@ static void glk_load_degamma_lut_linear(const struct intel_crtc_state *crtc_stat
 
 static void glk_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	/*
 	 * On GLK+ both pipe CSC and degamma LUT are controlled
@@ -777,7 +777,7 @@ static void glk_load_luts(const struct intel_crtc_state *crtc_state)
 	 * the degama LUT so that we don't have to reload
 	 * it every time the pipe CSC is being enabled.
 	 */
-	if (crtc_state->base.degamma_lut)
+	if (crtc_state->hw.degamma_lut)
 		glk_load_degamma_lut(crtc_state);
 	else
 		glk_load_degamma_lut_linear(crtc_state);
@@ -808,7 +808,7 @@ static void
 icl_load_gcmax(const struct intel_crtc_state *crtc_state,
 	       const struct drm_color_lut *color)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_dsb *dsb = intel_dsb_get(crtc);
 	enum pipe pipe = crtc->pipe;
 
@@ -822,8 +822,8 @@ icl_load_gcmax(const struct intel_crtc_state *crtc_state,
 static void
 icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *blob = crtc_state->base.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *blob = crtc_state->hw.gamma_lut;
 	const struct drm_color_lut *lut = blob->data;
 	struct intel_dsb *dsb = intel_dsb_get(crtc);
 	enum pipe pipe = crtc->pipe;
@@ -854,8 +854,8 @@ icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 static void
 icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *blob = crtc_state->base.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *blob = crtc_state->hw.gamma_lut;
 	const struct drm_color_lut *lut = blob->data;
 	const struct drm_color_lut *entry;
 	struct intel_dsb *dsb = intel_dsb_get(crtc);
@@ -910,11 +910,11 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 
 static void icl_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_dsb *dsb = intel_dsb_get(crtc);
 
-	if (crtc_state->base.degamma_lut)
+	if (crtc_state->hw.degamma_lut)
 		glk_load_degamma_lut(crtc_state);
 
 	switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) {
@@ -990,9 +990,9 @@ static void chv_load_cgm_gamma(struct intel_crtc *crtc,
 
 static void chv_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
 
 	cherryview_load_csc_matrix(crtc_state);
 
@@ -1010,35 +1010,35 @@ static void chv_load_luts(const struct intel_crtc_state *crtc_state)
 
 void intel_color_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	dev_priv->display.load_luts(crtc_state);
 }
 
 void intel_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	dev_priv->display.color_commit(crtc_state);
 }
 
 static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
-	return !old_crtc_state->base.gamma_lut &&
-		!old_crtc_state->base.degamma_lut;
+	return !old_crtc_state->hw.gamma_lut &&
+		!old_crtc_state->hw.degamma_lut;
 }
 
 static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
@@ -1050,14 +1050,14 @@ static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 	if (old_crtc_state->cgm_mode || new_crtc_state->cgm_mode)
 		return false;
 
-	return !old_crtc_state->base.gamma_lut;
+	return !old_crtc_state->hw.gamma_lut;
 }
 
 static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
@@ -1068,19 +1068,19 @@ static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 	 * linear hardware degamma mid scanout.
 	 */
 	return !old_crtc_state->csc_enable &&
-		!old_crtc_state->base.gamma_lut;
+		!old_crtc_state->hw.gamma_lut;
 }
 
 int intel_color_check(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	return dev_priv->display.color_check(crtc_state);
 }
 
 void intel_color_get_config(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (dev_priv->display.read_luts)
 		dev_priv->display.read_luts(crtc_state);
@@ -1104,16 +1104,16 @@ static bool need_plane_update(struct intel_plane *plane,
 static int
 intel_color_add_affected_planes(struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 	struct intel_plane *plane;
 
-	if (!new_crtc_state->base.active ||
-	    drm_atomic_crtc_needs_modeset(&new_crtc_state->base))
+	if (!new_crtc_state->hw.active ||
+	    drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi))
 		return 0;
 
 	if (new_crtc_state->gamma_enable == old_crtc_state->gamma_enable &&
@@ -1155,9 +1155,9 @@ static int check_lut_size(const struct drm_property_blob *lut, int expected)
 
 static int check_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
 	int gamma_length, degamma_length;
 	u32 gamma_tests, degamma_tests;
 
@@ -1205,7 +1205,7 @@ static int i9xx_color_check(struct intel_crtc_state *crtc_state)
 		return ret;
 
 	crtc_state->gamma_enable =
-		crtc_state->base.gamma_lut &&
+		crtc_state->hw.gamma_lut &&
 		!crtc_state->c8_planes;
 
 	crtc_state->gamma_mode = i9xx_gamma_mode(crtc_state);
@@ -1226,11 +1226,11 @@ static u32 chv_cgm_mode(const struct intel_crtc_state *crtc_state)
 	if (crtc_state_is_legacy_gamma(crtc_state))
 		return 0;
 
-	if (crtc_state->base.degamma_lut)
+	if (crtc_state->hw.degamma_lut)
 		cgm_mode |= CGM_PIPE_MODE_DEGAMMA;
-	if (crtc_state->base.ctm)
+	if (crtc_state->hw.ctm)
 		cgm_mode |= CGM_PIPE_MODE_CSC;
-	if (crtc_state->base.gamma_lut)
+	if (crtc_state->hw.gamma_lut)
 		cgm_mode |= CGM_PIPE_MODE_GAMMA;
 
 	return cgm_mode;
@@ -1306,7 +1306,7 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state)
 		return ret;
 
 	crtc_state->gamma_enable =
-		crtc_state->base.gamma_lut &&
+		crtc_state->hw.gamma_lut &&
 		!crtc_state->c8_planes;
 
 	/*
@@ -1334,8 +1334,8 @@ static u32 ivb_gamma_mode(const struct intel_crtc_state *crtc_state)
 	if (!crtc_state->gamma_enable ||
 	    crtc_state_is_legacy_gamma(crtc_state))
 		return GAMMA_MODE_MODE_8BIT;
-	else if (crtc_state->base.gamma_lut &&
-		 crtc_state->base.degamma_lut)
+	else if (crtc_state->hw.gamma_lut &&
+		 crtc_state->hw.degamma_lut)
 		return GAMMA_MODE_MODE_SPLIT;
 	else
 		return GAMMA_MODE_MODE_10BIT;
@@ -1349,7 +1349,7 @@ static u32 ivb_csc_mode(const struct intel_crtc_state *crtc_state)
 	 * CSC comes after the LUT in degamma, RGB->YCbCr,
 	 * and RGB full->limited range mode.
 	 */
-	if (crtc_state->base.degamma_lut ||
+	if (crtc_state->hw.degamma_lut ||
 	    crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB ||
 	    limited_color_range)
 		return 0;
@@ -1367,13 +1367,13 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state)
 		return ret;
 
 	crtc_state->gamma_enable =
-		(crtc_state->base.gamma_lut ||
-		 crtc_state->base.degamma_lut) &&
+		(crtc_state->hw.gamma_lut ||
+		 crtc_state->hw.degamma_lut) &&
 		!crtc_state->c8_planes;
 
 	crtc_state->csc_enable =
 		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB ||
-		crtc_state->base.ctm || limited_color_range;
+		crtc_state->hw.ctm || limited_color_range;
 
 	crtc_state->gamma_mode = ivb_gamma_mode(crtc_state);
 
@@ -1406,14 +1406,14 @@ static int glk_color_check(struct intel_crtc_state *crtc_state)
 		return ret;
 
 	crtc_state->gamma_enable =
-		crtc_state->base.gamma_lut &&
+		crtc_state->hw.gamma_lut &&
 		!crtc_state->c8_planes;
 
 	/* On GLK+ degamma LUT is controlled by csc_enable */
 	crtc_state->csc_enable =
-		crtc_state->base.degamma_lut ||
+		crtc_state->hw.degamma_lut ||
 		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB ||
-		crtc_state->base.ctm || crtc_state->limited_color_range;
+		crtc_state->hw.ctm || crtc_state->limited_color_range;
 
 	crtc_state->gamma_mode = glk_gamma_mode(crtc_state);
 
@@ -1432,14 +1432,14 @@ static u32 icl_gamma_mode(const struct intel_crtc_state *crtc_state)
 {
 	u32 gamma_mode = 0;
 
-	if (crtc_state->base.degamma_lut)
+	if (crtc_state->hw.degamma_lut)
 		gamma_mode |= PRE_CSC_GAMMA_ENABLE;
 
-	if (crtc_state->base.gamma_lut &&
+	if (crtc_state->hw.gamma_lut &&
 	    !crtc_state->c8_planes)
 		gamma_mode |= POST_CSC_GAMMA_ENABLE;
 
-	if (!crtc_state->base.gamma_lut ||
+	if (!crtc_state->hw.gamma_lut ||
 	    crtc_state_is_legacy_gamma(crtc_state))
 		gamma_mode |= GAMMA_MODE_MODE_8BIT;
 	else
@@ -1452,7 +1452,7 @@ static u32 icl_csc_mode(const struct intel_crtc_state *crtc_state)
 {
 	u32 csc_mode = 0;
 
-	if (crtc_state->base.ctm)
+	if (crtc_state->hw.ctm)
 		csc_mode |= ICL_CSC_ENABLE;
 
 	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB ||
@@ -1540,7 +1540,7 @@ static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (HAS_GMCH(dev_priv)) {
@@ -1646,7 +1646,7 @@ static u32 intel_color_lut_pack(u32 val, u32 bit_precision)
 static struct drm_property_blob *
 i9xx_read_lut_8(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	struct drm_property_blob *blob;
@@ -1683,13 +1683,13 @@ static void i9xx_read_luts(struct intel_crtc_state *crtc_state)
 	if (!crtc_state->gamma_enable)
 		return;
 
-	crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+	crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc_state);
 }
 
 static struct drm_property_blob *
 i965_read_lut_10p6(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
 	enum pipe pipe = crtc->pipe;
@@ -1733,15 +1733,15 @@ static void i965_read_luts(struct intel_crtc_state *crtc_state)
 		return;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+		crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
-		crtc_state->base.gamma_lut = i965_read_lut_10p6(crtc_state);
+		crtc_state->hw.gamma_lut = i965_read_lut_10p6(crtc_state);
 }
 
 static struct drm_property_blob *
 chv_read_cgm_lut(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
 	enum pipe pipe = crtc->pipe;
@@ -1775,7 +1775,7 @@ chv_read_cgm_lut(const struct intel_crtc_state *crtc_state)
 static void chv_read_luts(struct intel_crtc_state *crtc_state)
 {
 	if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA)
-		crtc_state->base.gamma_lut = chv_read_cgm_lut(crtc_state);
+		crtc_state->hw.gamma_lut = chv_read_cgm_lut(crtc_state);
 	else
 		i965_read_luts(crtc_state);
 }
@@ -1783,7 +1783,7 @@ static void chv_read_luts(struct intel_crtc_state *crtc_state)
 static struct drm_property_blob *
 ilk_read_lut_10(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
 	enum pipe pipe = crtc->pipe;
@@ -1822,15 +1822,15 @@ static void ilk_read_luts(struct intel_crtc_state *crtc_state)
 		return;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+		crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
-		crtc_state->base.gamma_lut = ilk_read_lut_10(crtc_state);
+		crtc_state->hw.gamma_lut = ilk_read_lut_10(crtc_state);
 }
 
 static struct drm_property_blob *
 glk_read_lut_10(const struct intel_crtc_state *crtc_state, u32 prec_index)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	int hw_lut_size = ivb_lut_10_size(prec_index);
 	enum pipe pipe = crtc->pipe;
@@ -1871,9 +1871,9 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state)
 		return;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+		crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
-		crtc_state->base.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
+		crtc_state->hw.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
 }
 
 void intel_color_init(struct intel_crtc *crtc)
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index 39cc6d79dc85..f976b800b245 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -65,7 +65,7 @@ static struct intel_crt *intel_encoder_to_crt(struct intel_encoder *encoder)
 	return container_of(encoder, struct intel_crt, base);
 }
 
-static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
+static struct intel_crt *intel_attached_crt(struct intel_connector *connector)
 {
 	return intel_encoder_to_crt(intel_attached_encoder(connector));
 }
@@ -132,9 +132,9 @@ static void intel_crt_get_config(struct intel_encoder *encoder,
 {
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_ANALOG);
 
-	pipe_config->base.adjusted_mode.flags |= intel_crt_get_flags(encoder);
+	pipe_config->hw.adjusted_mode.flags |= intel_crt_get_flags(encoder);
 
-	pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock;
+	pipe_config->hw.adjusted_mode.crtc_clock = pipe_config->port_clock;
 }
 
 static void hsw_crt_get_config(struct intel_encoder *encoder,
@@ -144,13 +144,13 @@ static void hsw_crt_get_config(struct intel_encoder *encoder,
 
 	intel_ddi_get_config(encoder, pipe_config);
 
-	pipe_config->base.adjusted_mode.flags &= ~(DRM_MODE_FLAG_PHSYNC |
+	pipe_config->hw.adjusted_mode.flags &= ~(DRM_MODE_FLAG_PHSYNC |
 					      DRM_MODE_FLAG_NHSYNC |
 					      DRM_MODE_FLAG_PVSYNC |
 					      DRM_MODE_FLAG_NVSYNC);
-	pipe_config->base.adjusted_mode.flags |= intel_crt_get_flags(encoder);
+	pipe_config->hw.adjusted_mode.flags |= intel_crt_get_flags(encoder);
 
-	pipe_config->base.adjusted_mode.crtc_clock = lpt_get_iclkip(dev_priv);
+	pipe_config->hw.adjusted_mode.crtc_clock = lpt_get_iclkip(dev_priv);
 }
 
 /* Note: The caller is required to filter out dpms modes not supported by the
@@ -161,8 +161,8 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	u32 adpa;
 
 	if (INTEL_GEN(dev_priv) >= 5)
@@ -241,6 +241,14 @@ static void hsw_post_disable_crt(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
+	intel_crtc_vblank_off(old_crtc_state);
+
+	intel_disable_pipe(old_crtc_state);
+
+	intel_ddi_disable_transcoder_func(old_crtc_state);
+
+	ilk_pfit_disable(old_crtc_state);
+
 	intel_ddi_disable_pipe_clock(old_crtc_state);
 
 	pch_post_disable_crt(encoder, old_crtc_state, old_conn_state);
@@ -271,14 +279,14 @@ static void hsw_pre_enable_crt(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 
 	WARN_ON(!crtc_state->has_pch_encoder);
 
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 
-	dev_priv->display.fdi_link_train(crtc, crtc_state);
+	hsw_fdi_link_train(encoder, crtc_state);
 
 	intel_ddi_enable_pipe_clock(crtc_state);
 }
@@ -288,7 +296,7 @@ static void hsw_enable_crt(struct intel_encoder *encoder,
 			   const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 
 	WARN_ON(!crtc_state->has_pch_encoder);
@@ -343,7 +351,7 @@ intel_crt_mode_valid(struct drm_connector *connector,
 
 	/* The FDI receiver on LPT only supports 8bpc and only has 2 lanes. */
 	if (HAS_PCH_LPT(dev_priv) &&
-	    (ironlake_get_lanes_required(mode->clock, 270000, 24) > 2))
+	    ilk_get_lanes_required(mode->clock, 270000, 24) > 2)
 		return MODE_CLOCK_HIGH;
 
 	/* HSW/BDW FDI limited to 4k */
@@ -358,7 +366,7 @@ static int intel_crt_compute_config(struct intel_encoder *encoder,
 				    struct drm_connector_state *conn_state)
 {
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
@@ -373,7 +381,7 @@ static int pch_crt_compute_config(struct intel_encoder *encoder,
 				  struct drm_connector_state *conn_state)
 {
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
@@ -390,7 +398,7 @@ static int hsw_crt_compute_config(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
@@ -419,10 +427,10 @@ static int hsw_crt_compute_config(struct intel_encoder *encoder,
 	return 0;
 }
 
-static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
+static bool ilk_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 adpa;
 	bool ret;
@@ -432,7 +440,7 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 		bool turn_off_dac = HAS_PCH_SPLIT(dev_priv);
 		u32 save_adpa;
 
-		crt->force_hotplug_required = 0;
+		crt->force_hotplug_required = false;
 
 		save_adpa = adpa = I915_READ(crt->adpa_reg);
 		DRM_DEBUG_KMS("trigger hotplug detect cycle: adpa=0x%x\n", adpa);
@@ -469,7 +477,7 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 static bool valleyview_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	bool reenable_hpd;
 	u32 adpa;
@@ -527,7 +535,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 	int i, tries = 0;
 
 	if (HAS_PCH_SPLIT(dev_priv))
-		return intel_ironlake_crt_detect_hotplug(connector);
+		return ilk_crt_detect_hotplug(connector);
 
 	if (IS_VALLEYVIEW(dev_priv))
 		return valleyview_crt_detect_hotplug(connector);
@@ -601,7 +609,7 @@ static int intel_crt_ddc_get_modes(struct drm_connector *connector,
 
 static bool intel_crt_detect_ddc(struct drm_connector *connector)
 {
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(crt->base.base.dev);
 	struct edid *edid;
 	struct i2c_adapter *i2c;
@@ -787,7 +795,7 @@ intel_crt_detect(struct drm_connector *connector,
 		 bool force)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct intel_encoder *intel_encoder = &crt->base;
 	intel_wakeref_t wakeref;
 	int status, ret;
@@ -878,7 +886,7 @@ static int intel_crt_get_modes(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct intel_encoder *intel_encoder = &crt->base;
 	intel_wakeref_t wakeref;
 	struct i2c_adapter *i2c;
@@ -917,7 +925,7 @@ void intel_crt_reset(struct drm_encoder *encoder)
 		POSTING_READ(crt->adpa_reg);
 
 		DRM_DEBUG_KMS("crt adpa set to 0x%x\n", adpa);
-		crt->force_hotplug_required = 1;
+		crt->force_hotplug_required = true;
 	}
 
 }
@@ -1055,7 +1063,7 @@ void intel_crt_init(struct drm_i915_private *dev_priv)
 	/*
 	 * Configure the automatic hotplug detection stuff
 	 */
-	crt->force_hotplug_required = 0;
+	crt->force_hotplug_required = false;
 
 	/*
 	 * TODO: find a proper way to discover whether we need to set the the
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 2a27fb5d7dc6..33f1dc3d7c1a 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -34,6 +34,7 @@
 #include "intel_ddi.h"
 #include "intel_display_types.h"
 #include "intel_dp.h"
+#include "intel_dp_mst.h"
 #include "intel_dp_link_training.h"
 #include "intel_dpio_phy.h"
 #include "intel_dsi.h"
@@ -902,11 +903,10 @@ icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate,
 
 static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port)
 {
+	struct ddi_vbt_port_info *port_info = &dev_priv->vbt.ddi_port_info[port];
 	int n_entries, level, default_entry;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 
-	level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
-
 	if (INTEL_GEN(dev_priv) >= 12) {
 		if (intel_phy_is_combo(dev_priv, phy))
 			icl_get_combo_buf_trans(dev_priv, INTEL_OUTPUT_HDMI,
@@ -941,12 +941,14 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por
 		return 0;
 	}
 
-	/* Choose a good default if VBT is badly populated */
-	if (level == HDMI_LEVEL_SHIFT_UNKNOWN || level >= n_entries)
-		level = default_entry;
-
 	if (WARN_ON_ONCE(n_entries == 0))
 		return 0;
+
+	if (port_info->hdmi_level_shift_set)
+		level = port_info->hdmi_level_shift;
+	else
+		level = default_entry;
+
 	if (WARN_ON_ONCE(level >= n_entries))
 		level = n_entries - 1;
 
@@ -1106,18 +1108,14 @@ static u32 icl_pll_to_ddi_clk_sel(struct intel_encoder *encoder,
  * DDI A (which is used for eDP)
  */
 
-void hsw_fdi_link_train(struct intel_crtc *crtc,
+void hsw_fdi_link_train(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_encoder *encoder;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 temp, i, rx_ctl_val, ddi_pll_sel;
 
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
-		WARN_ON(encoder->type != INTEL_OUTPUT_ANALOG);
-		intel_prepare_dp_ddi_buffers(encoder, crtc_state);
-	}
+	intel_prepare_dp_ddi_buffers(encoder, crtc_state);
 
 	/* Set the FDI_RX_MISC pwrdn lanes and the 2 workarounds listed at the
 	 * mode set "sequence for CRT port" document:
@@ -1240,9 +1238,9 @@ void hsw_fdi_link_train(struct intel_crtc *crtc,
 
 static void intel_ddi_init_dp_buf_reg(struct intel_encoder *encoder)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_digital_port *intel_dig_port =
-		enc_to_dig_port(&encoder->base);
+		enc_to_dig_port(encoder);
 
 	intel_dp->DP = intel_dig_port->saved_port_bits |
 		DDI_BUF_CTL_ENABLE | DDI_BUF_TRANS_SELECT(0);
@@ -1542,7 +1540,7 @@ static void ddi_dotclock_get(struct intel_crtc_state *pipe_config)
 	if (pipe_config->pixel_multiplier)
 		dotclock /= pipe_config->pixel_multiplier;
 
-	pipe_config->base.adjusted_mode.crtc_clock = dotclock;
+	pipe_config->hw.adjusted_mode.crtc_clock = dotclock;
 }
 
 static void icl_ddi_clock_get(struct intel_encoder *encoder,
@@ -1758,7 +1756,7 @@ static void intel_ddi_clock_get(struct intel_encoder *encoder,
 void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 			  const struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 temp;
@@ -1815,22 +1813,6 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 	I915_WRITE(TRANS_MSA_MISC(cpu_transcoder), temp);
 }
 
-void intel_ddi_set_vc_payload_alloc(const struct intel_crtc_state *crtc_state,
-				    bool state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	u32 temp;
-
-	temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
-	if (state == true)
-		temp |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
-	else
-		temp &= ~TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
-	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
-}
-
 /*
  * Returns the TRANS_DDI_FUNC_CTL value based on CRTC state.
  *
@@ -1840,7 +1822,7 @@ void intel_ddi_set_vc_payload_alloc(const struct intel_crtc_state *crtc_state,
 static u32
 intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_encoder *encoder = intel_ddi_get_crtc_encoder(crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
@@ -1872,9 +1854,9 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 		BUG();
 	}
 
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_PVSYNC)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_PVSYNC)
 		temp |= TRANS_DDI_PVSYNC;
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_PHSYNC)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_PHSYNC)
 		temp |= TRANS_DDI_PHSYNC;
 
 	if (cpu_transcoder == TRANSCODER_EDP) {
@@ -1918,8 +1900,13 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 		temp |= TRANS_DDI_MODE_SELECT_DP_MST;
 		temp |= DDI_PORT_WIDTH(crtc_state->lane_count);
 
-		if (INTEL_GEN(dev_priv) >= 12)
-			temp |= TRANS_DDI_MST_TRANSPORT_SELECT(crtc_state->cpu_transcoder);
+		if (INTEL_GEN(dev_priv) >= 12) {
+			enum transcoder master;
+
+			master = crtc_state->mst_master_transcoder;
+			WARN_ON(master == INVALID_TRANSCODER);
+			temp |= TRANS_DDI_MST_TRANSPORT_SELECT(master);
+		}
 	} else {
 		temp |= TRANS_DDI_MODE_SELECT_DP_SST;
 		temp |= DDI_PORT_WIDTH(crtc_state->lane_count);
@@ -1930,12 +1917,14 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 
 void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 temp;
 
 	temp = intel_ddi_transcoder_func_reg_val_get(crtc_state);
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST))
+		temp |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
 	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
 }
 
@@ -1946,7 +1935,7 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 static void
 intel_ddi_config_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 temp;
@@ -1958,20 +1947,21 @@ intel_ddi_config_transcoder_func(const struct intel_crtc_state *crtc_state)
 
 void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder);
-	u32 val = I915_READ(reg);
+	u32 val;
+
+	val = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
+	val &= ~TRANS_DDI_FUNC_ENABLE;
 
 	if (INTEL_GEN(dev_priv) >= 12) {
-		val &= ~(TRANS_DDI_FUNC_ENABLE | TGL_TRANS_DDI_PORT_MASK |
-			 TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
+		if (!intel_dp_mst_is_master_trans(crtc_state))
+			val &= ~TGL_TRANS_DDI_PORT_MASK;
 	} else {
-		val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK |
-			 TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
+		val &= ~TRANS_DDI_PORT_MASK;
 	}
-	I915_WRITE(reg, val);
+	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), val);
 
 	if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME &&
 	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
@@ -2234,7 +2224,7 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
 	if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
 		return;
 
-	dig_port = enc_to_dig_port(&encoder->base);
+	dig_port = enc_to_dig_port(encoder);
 	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
 	/*
@@ -2256,7 +2246,7 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
 
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_encoder *encoder = intel_ddi_get_crtc_encoder(crtc);
 	enum port port = encoder->port;
@@ -2274,7 +2264,7 @@ void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
 
 void intel_ddi_disable_pipe_clock(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
 	if (cpu_transcoder != TRANSCODER_EDP) {
@@ -2304,7 +2294,7 @@ static void _skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
 static void skl_ddi_set_iboost(struct intel_encoder *encoder,
 			       int level, enum intel_output_type type)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 	u8 iboost;
@@ -2375,7 +2365,7 @@ static void bxt_ddi_vswing_sequence(struct intel_encoder *encoder,
 u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 	int n_entries;
@@ -2514,7 +2504,7 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder,
 		width = 4;
 		rate = 0; /* Rate is always < than 6GHz for HDMI */
 	} else {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		width = intel_dp->lane_count;
 		rate = intel_dp->link_rate;
@@ -2640,7 +2630,7 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 		width = 4;
 		/* Rate is always < than 6GHz for HDMI */
 	} else {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		width = intel_dp->lane_count;
 		rate = intel_dp->link_rate;
@@ -3016,11 +3006,38 @@ static void icl_unmap_plls_to_ports(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpll_lock);
 }
 
+static void icl_sanitize_port_clk_off(struct drm_i915_private *dev_priv,
+				      u32 port_mask, bool ddi_clk_needed)
+{
+	enum port port;
+	u32 val;
+
+	val = I915_READ(ICL_DPCLKA_CFGCR0);
+	for_each_port_masked(port, port_mask) {
+		enum phy phy = intel_port_to_phy(dev_priv, port);
+		bool ddi_clk_off = val & icl_dpclka_cfgcr0_clk_off(dev_priv,
+								   phy);
+
+		if (ddi_clk_needed == !ddi_clk_off)
+			continue;
+
+		/*
+		 * Punt on the case now where clock is gated, but it would
+		 * be needed by the port. Something else is really broken then.
+		 */
+		if (WARN_ON(ddi_clk_needed))
+			continue;
+
+		DRM_NOTE("PHY %c is disabled/in DSI mode with an ungated DDI clock, gate it\n",
+			 phy_name(phy));
+		val |= icl_dpclka_cfgcr0_clk_off(dev_priv, phy);
+		I915_WRITE(ICL_DPCLKA_CFGCR0, val);
+	}
+}
+
 void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 val;
-	enum port port;
 	u32 port_mask;
 	bool ddi_clk_needed;
 
@@ -3069,29 +3086,7 @@ void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder)
 		ddi_clk_needed = false;
 	}
 
-	val = I915_READ(ICL_DPCLKA_CFGCR0);
-	for_each_port_masked(port, port_mask) {
-		enum phy phy = intel_port_to_phy(dev_priv, port);
-
-		bool ddi_clk_ungated = !(val &
-					 icl_dpclka_cfgcr0_clk_off(dev_priv,
-								   phy));
-
-		if (ddi_clk_needed == ddi_clk_ungated)
-			continue;
-
-		/*
-		 * Punt on the case now where clock is gated, but it would
-		 * be needed by the port. Something else is really broken then.
-		 */
-		if (WARN_ON(ddi_clk_needed))
-			continue;
-
-		DRM_NOTE("PHY %c is disabled/in DSI mode with an ungated DDI clock, gate it\n",
-			 phy_name(port));
-		val |= icl_dpclka_cfgcr0_clk_off(dev_priv, phy);
-		I915_WRITE(ICL_DPCLKA_CFGCR0, val);
-	}
+	icl_sanitize_port_clk_off(dev_priv, port_mask, ddi_clk_needed);
 }
 
 static void intel_ddi_clk_select(struct intel_encoder *encoder,
@@ -3173,57 +3168,6 @@ static void intel_ddi_clk_disable(struct intel_encoder *encoder)
 }
 
 static void
-icl_phy_set_clock_gating(struct intel_digital_port *dig_port, bool enable)
-{
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	enum tc_port tc_port = intel_port_to_tc(dev_priv, dig_port->base.port);
-	u32 val, bits;
-	int ln;
-
-	if (tc_port == PORT_TC_NONE)
-		return;
-
-	bits = MG_DP_MODE_CFG_TR2PWR_GATING | MG_DP_MODE_CFG_TRPWR_GATING |
-	       MG_DP_MODE_CFG_CLNPWR_GATING | MG_DP_MODE_CFG_DIGPWR_GATING |
-	       MG_DP_MODE_CFG_GAONPWR_GATING;
-
-	for (ln = 0; ln < 2; ln++) {
-		if (INTEL_GEN(dev_priv) >= 12) {
-			I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln));
-			val = I915_READ(DKL_DP_MODE(tc_port));
-		} else {
-			val = I915_READ(MG_DP_MODE(ln, tc_port));
-		}
-
-		if (enable)
-			val |= bits;
-		else
-			val &= ~bits;
-
-		if (INTEL_GEN(dev_priv) >= 12)
-			I915_WRITE(DKL_DP_MODE(tc_port), val);
-		else
-			I915_WRITE(MG_DP_MODE(ln, tc_port), val);
-	}
-
-	if (INTEL_GEN(dev_priv) == 11) {
-		bits = MG_MISC_SUS0_CFG_TR2PWR_GATING |
-		       MG_MISC_SUS0_CFG_CL2PWR_GATING |
-		       MG_MISC_SUS0_CFG_GAONPWR_GATING |
-		       MG_MISC_SUS0_CFG_TRPWR_GATING |
-		       MG_MISC_SUS0_CFG_CL1PWR_GATING |
-		       MG_MISC_SUS0_CFG_DGPWR_GATING;
-
-		val = I915_READ(MG_MISC_SUS0(tc_port));
-		if (enable)
-			val |= (bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE(3));
-		else
-			val &= ~(bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE_MASK);
-		I915_WRITE(MG_MISC_SUS0(tc_port), val);
-	}
-}
-
-static void
 icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 		       const struct intel_crtc_state *crtc_state)
 {
@@ -3329,7 +3273,7 @@ static void intel_ddi_enable_fec(struct intel_encoder *encoder,
 	if (!crtc_state->fec_enable)
 		return;
 
-	intel_dp = enc_to_intel_dp(&encoder->base);
+	intel_dp = enc_to_intel_dp(encoder);
 	val = I915_READ(intel_dp->regs.dp_tp_ctl);
 	val |= DP_TP_CTL_FEC_ENABLE;
 	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
@@ -3349,7 +3293,7 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 	if (!crtc_state->fec_enable)
 		return;
 
-	intel_dp = enc_to_intel_dp(&encoder->base);
+	intel_dp = enc_to_intel_dp(encoder);
 	val = I915_READ(intel_dp->regs.dp_tp_ctl);
 	val &= ~DP_TP_CTL_FEC_ENABLE;
 	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
@@ -3359,7 +3303,7 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 static void
 tgl_clear_psr2_transcoder_exitline(const struct intel_crtc_state *cstate)
 {
-	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(cstate->uapi.crtc->dev);
 	u32 val;
 
 	if (!cstate->dc3co_exitline)
@@ -3374,7 +3318,7 @@ static void
 tgl_set_psr2_transcoder_exitline(const struct intel_crtc_state *cstate)
 {
 	u32 val, exit_scanlines;
-	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(cstate->uapi.crtc->dev);
 
 	if (!cstate->dc3co_exitline)
 		return;
@@ -3392,8 +3336,8 @@ static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
 					      struct intel_crtc_state *cstate)
 {
 	u32 exit_scanlines;
-	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
-	u32 crtc_vdisplay = cstate->base.adjusted_mode.crtc_vdisplay;
+	struct drm_i915_private *dev_priv = to_i915(cstate->uapi.crtc->dev);
+	u32 crtc_vdisplay = cstate->hw.adjusted_mode.crtc_vdisplay;
 
 	cstate->dc3co_exitline = 0;
 
@@ -3401,11 +3345,11 @@ static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
 		return;
 
 	/* B.Specs:49196 DC3CO only works with pipeA and DDIA.*/
-	if (to_intel_crtc(cstate->base.crtc)->pipe != PIPE_A ||
+	if (to_intel_crtc(cstate->uapi.crtc)->pipe != PIPE_A ||
 	    encoder->port != PORT_A)
 		return;
 
-	if (!cstate->has_psr2 || !cstate->base.active)
+	if (!cstate->has_psr2 || !cstate->hw.active)
 		return;
 
 	/*
@@ -3413,7 +3357,7 @@ static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
 	 * PSR2 transcoder Early Exit scanlines = ROUNDUP(200 / line time) + 1
 	 */
 	exit_scanlines =
-		intel_usecs_to_scanlines(&cstate->base.adjusted_mode, 200) + 1;
+		intel_usecs_to_scanlines(&cstate->hw.adjusted_mode, 200) + 1;
 
 	if (WARN_ON(exit_scanlines > crtc_vdisplay))
 		return;
@@ -3425,7 +3369,7 @@ static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
 static void tgl_dc3co_exitline_get_config(struct intel_crtc_state *crtc_state)
 {
 	u32 val;
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (INTEL_GEN(dev_priv) < 12)
 		return;
@@ -3440,10 +3384,10 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	int level = intel_ddi_dp_level(intel_dp);
 	enum transcoder transcoder = crtc_state->cpu_transcoder;
@@ -3455,47 +3399,80 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dp->regs.dp_tp_ctl = TGL_DP_TP_CTL(transcoder);
 	intel_dp->regs.dp_tp_status = TGL_DP_TP_STATUS(transcoder);
 
-	/* 1.a got on intel_atomic_commit_tail() */
+	/*
+	 * 1. Enable Power Wells
+	 *
+	 * This was handled at the beginning of intel_atomic_commit_tail(),
+	 * before we called down into this function.
+	 */
 
-	/* 2. */
+	/* 2. Enable Panel Power if PPS is required */
 	intel_edp_panel_on(intel_dp);
 
 	/*
-	 * 1.b, 3. and 4.a is done before tgl_ddi_pre_enable_dp() by:
-	 * haswell_crtc_enable()->intel_encoders_pre_pll_enable() and
-	 * haswell_crtc_enable()->intel_enable_shared_dpll()
+	 * 3. For non-TBT Type-C ports, set FIA lane count
+	 * (DFLEXDPSP.DPX4TXLATC)
+	 *
+	 * This was done before tgl_ddi_pre_enable_dp by
+	 * hsw_crtc_enable()->intel_encoders_pre_pll_enable().
 	 */
 
-	/* 4.b */
+	/*
+	 * 4. Enable the port PLL.
+	 *
+	 * The PLL enabling itself was already done before this function by
+	 * hsw_crtc_enable()->intel_enable_shared_dpll().  We need only
+	 * configure the PLL to port mapping here.
+	 */
 	intel_ddi_clk_select(encoder, crtc_state);
 
-	/* 5. */
+	/* 5. If IO power is controlled through PWR_WELL_CTL, Enable IO Power */
 	if (!intel_phy_is_tc(dev_priv, phy) ||
 	    dig_port->tc_mode != TC_PORT_TBT_ALT)
 		intel_display_power_get(dev_priv,
 					dig_port->ddi_io_power_domain);
 
-	/* 6. */
+	/* 6. Program DP_MODE */
 	icl_program_mg_dp_mode(dig_port, crtc_state);
 
 	/*
-	 * 7.a - Steps in this function should only be executed over MST
-	 * master, what will be taken in care by MST hook
-	 * intel_mst_pre_enable_dp()
+	 * 7. The rest of the below are substeps under the bspec's "Enable and
+	 * Train Display Port" step.  Note that steps that are specific to
+	 * MST will be handled by intel_mst_pre_enable_dp() before/after it
+	 * calls into this function.  Also intel_mst_pre_enable_dp() only calls
+	 * us when active_mst_links==0, so any steps designated for "single
+	 * stream or multi-stream master transcoder" can just be performed
+	 * unconditionally here.
+	 */
+
+	/*
+	 * 7.a Configure Transcoder Clock Select to direct the Port clock to the
+	 * Transcoder.
 	 */
 	intel_ddi_enable_pipe_clock(crtc_state);
 
-	/* 7.b */
+	/*
+	 * 7.b Configure TRANS_DDI_FUNC_CTL DDI Select, DDI Mode Select & MST
+	 * Transport Select
+	 */
 	intel_ddi_config_transcoder_func(crtc_state);
 
-	/* 7.d */
-	icl_phy_set_clock_gating(dig_port, false);
+	/*
+	 * 7.c Configure & enable DP_TP_CTL with link training pattern 1
+	 * selected
+	 *
+	 * This will be handled by the intel_dp_start_link_train() farther
+	 * down this function.
+	 */
 
-	/* 7.e */
+	/* 7.e Configure voltage swing and related IO settings */
 	tgl_ddi_vswing_sequence(encoder, crtc_state->port_clock, level,
 				encoder->type);
 
-	/* 7.f */
+	/*
+	 * 7.f Combo PHY: Configure PORT_CL_DW10 Static Power Down to power up
+	 * the used lanes of the DDI.
+	 */
 	if (intel_phy_is_combo(dev_priv, phy)) {
 		bool lane_reversal =
 			dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL;
@@ -3505,7 +3482,14 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 					       lane_reversal);
 	}
 
-	/* 7.g */
+	/*
+	 * 7.g Configure and enable DDI_BUF_CTL
+	 * 7.h Wait for DDI_BUF_CTL DDI Idle Status = 0b (Not Idle), timeout
+	 *     after 500 us.
+	 *
+	 * We only configure what the register value will be here.  Actual
+	 * enabling happens during link training farther down.
+	 */
 	intel_ddi_init_dp_buf_reg(encoder);
 
 	if (!is_mst)
@@ -3518,23 +3502,21 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	 * training
 	 */
 	intel_dp_sink_set_fec_ready(intel_dp, crtc_state);
-	/* 7.c, 7.h, 7.i, 7.j */
+
+	/*
+	 * 7.i Follow DisplayPort specification training sequence (see notes for
+	 *     failure handling)
+	 * 7.j If DisplayPort multi-stream - Set DP_TP_CTL link training to Idle
+	 *     Pattern, wait for 5 idle patterns (DP_TP_STATUS Min_Idles_Sent)
+	 *     (timeout after 800 us)
+	 */
 	intel_dp_start_link_train(intel_dp);
 
-	/* 7.k */
+	/* 7.k Set DP_TP_CTL link training to Normal */
 	if (!is_trans_port_sync_mode(crtc_state))
 		intel_dp_stop_link_train(intel_dp);
 
-	/*
-	 * TODO: enable clock gating
-	 *
-	 * It is not written in DP enabling sequence but "PHY Clockgating
-	 * programming" states that clock gating should be enabled after the
-	 * link training but doing so causes all the following trainings to fail
-	 * so not enabling it for now.
-	 */
-
-	/* 7.l */
+	/* 7.l Configure and enable FEC if needed */
 	intel_ddi_enable_fec(encoder, crtc_state);
 	intel_dsc_enable(encoder, crtc_state);
 }
@@ -3543,15 +3525,18 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	int level = intel_ddi_dp_level(intel_dp);
 
-	WARN_ON(is_mst && (port == PORT_A || port == PORT_E));
+	if (INTEL_GEN(dev_priv) < 11)
+		WARN_ON(is_mst && (port == PORT_A || port == PORT_E));
+	else
+		WARN_ON(is_mst && port == PORT_A);
 
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
@@ -3569,7 +3554,6 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 					dig_port->ddi_io_power_domain);
 
 	icl_program_mg_dp_mode(dig_port, crtc_state);
-	icl_phy_set_clock_gating(dig_port, false);
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_ddi_vswing_sequence(encoder, crtc_state->port_clock,
@@ -3603,8 +3587,6 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 
 	intel_ddi_enable_fec(encoder, crtc_state);
 
-	icl_phy_set_clock_gating(dig_port, true);
-
 	if (!is_mst)
 		intel_ddi_enable_pipe_clock(crtc_state);
 
@@ -3633,12 +3615,12 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 				      const struct intel_crtc_state *crtc_state,
 				      const struct drm_connector_state *conn_state)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 	int level = intel_ddi_hdmi_level(dev_priv, port);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 
 	intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
 	intel_ddi_clk_select(encoder, crtc_state);
@@ -3646,7 +3628,6 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
 	icl_program_mg_dp_mode(dig_port, crtc_state);
-	icl_phy_set_clock_gating(dig_port, false);
 
 	if (INTEL_GEN(dev_priv) >= 12)
 		tgl_ddi_vswing_sequence(encoder, crtc_state->port_clock,
@@ -3661,8 +3642,6 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	else
 		intel_prepare_hdmi_ddi_buffers(encoder, level);
 
-	icl_phy_set_clock_gating(dig_port, true);
-
 	if (IS_GEN9_BC(dev_priv))
 		skl_ddi_set_iboost(encoder, level, INTEL_OUTPUT_HDMI);
 
@@ -3677,7 +3656,7 @@ static void intel_ddi_pre_enable(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state,
 				 const struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -3705,12 +3684,12 @@ static void intel_ddi_pre_enable(struct intel_encoder *encoder,
 		intel_ddi_pre_enable_hdmi(encoder, crtc_state, conn_state);
 	} else {
 		struct intel_lspcon *lspcon =
-				enc_to_intel_lspcon(&encoder->base);
+				enc_to_intel_lspcon(encoder);
 
 		intel_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
 		if (lspcon->active) {
 			struct intel_digital_port *dig_port =
-					enc_to_dig_port(&encoder->base);
+					enc_to_dig_port(encoder);
 
 			dig_port->set_infoframes(encoder,
 						 crtc_state->has_infoframe,
@@ -3735,7 +3714,7 @@ static void intel_disable_ddi_buf(struct intel_encoder *encoder,
 	}
 
 	if (intel_crtc_has_dp_encoder(crtc_state)) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		val = I915_READ(intel_dp->regs.dp_tp_ctl);
 		val &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
@@ -3755,23 +3734,42 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 				      const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct intel_dp *intel_dp = &dig_port->dp;
 	bool is_mst = intel_crtc_has_type(old_crtc_state,
 					  INTEL_OUTPUT_DP_MST);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 
-	if (!is_mst) {
-		intel_ddi_disable_pipe_clock(old_crtc_state);
-		/*
-		 * Power down sink before disabling the port, otherwise we end
-		 * up getting interrupts from the sink on detecting link loss.
-		 */
-		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+	/*
+	 * Power down sink before disabling the port, otherwise we end
+	 * up getting interrupts from the sink on detecting link loss.
+	 */
+	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+
+	if (INTEL_GEN(dev_priv) >= 12) {
+		if (is_mst) {
+			enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
+			u32 val;
+
+			val = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
+			val &= ~TGL_TRANS_DDI_PORT_MASK;
+			I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), val);
+		}
+	} else {
+		if (!is_mst)
+			intel_ddi_disable_pipe_clock(old_crtc_state);
 	}
 
 	intel_disable_ddi_buf(encoder, old_crtc_state);
 
+	/*
+	 * From TGL spec: "If single stream or multi-stream master transcoder:
+	 * Configure Transcoder Clock select to direct no clock to the
+	 * transcoder"
+	 */
+	if (INTEL_GEN(dev_priv) >= 12)
+		intel_ddi_disable_pipe_clock(old_crtc_state);
+
 	intel_edp_panel_vdd_on(intel_dp);
 	intel_edp_panel_off(intel_dp);
 
@@ -3789,7 +3787,7 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 					const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &dig_port->hdmi;
 
 	dig_port->set_infoframes(encoder, false,
@@ -3807,11 +3805,46 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 	intel_dp_dual_mode_set_tmds_output(intel_hdmi, false);
 }
 
+static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+	if (old_crtc_state->master_transcoder == INVALID_TRANSCODER)
+		return;
+
+	DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n",
+		      transcoder_name(old_crtc_state->cpu_transcoder));
+
+	I915_WRITE(TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0);
+}
+
 static void intel_ddi_post_disable(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *old_crtc_state,
 				   const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+	bool is_tc_port = intel_phy_is_tc(dev_priv, phy);
+
+	if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST)) {
+		intel_crtc_vblank_off(old_crtc_state);
+
+		intel_disable_pipe(old_crtc_state);
+
+		if (INTEL_GEN(dev_priv) >= 11)
+			icl_disable_transcoder_port_sync(old_crtc_state);
+
+		intel_ddi_disable_transcoder_func(old_crtc_state);
+
+		intel_dsc_disable(old_crtc_state);
+
+		if (INTEL_GEN(dev_priv) >= 9)
+			skl_scaler_disable(old_crtc_state);
+		else
+			ilk_pfit_disable(old_crtc_state);
+	}
 
 	/*
 	 * When called from DP MST code:
@@ -3835,6 +3868,13 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder,
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_unmap_plls_to_ports(encoder);
+
+	if (intel_crtc_has_dp_encoder(old_crtc_state) || is_tc_port)
+		intel_display_power_put_unchecked(dev_priv,
+						  intel_ddi_main_link_aux_domain(dig_port));
+
+	if (is_tc_port)
+		intel_tc_port_put_link(dig_port);
 }
 
 void intel_ddi_fdi_post_disable(struct intel_encoder *encoder,
@@ -3876,7 +3916,7 @@ static void intel_enable_ddi_dp(struct intel_encoder *encoder,
 				const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
 
 	if (port == PORT_A && INTEL_GEN(dev_priv) < 9)
@@ -3917,7 +3957,7 @@ static void intel_enable_ddi_hdmi(struct intel_encoder *encoder,
 				  const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct drm_connector *connector = conn_state->connector;
 	enum port port = encoder->port;
 
@@ -3994,7 +4034,7 @@ static void intel_disable_ddi_dp(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
 				 const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	intel_dp->link_trained = false;
 
@@ -4042,7 +4082,7 @@ static void intel_ddi_update_pipe_dp(struct intel_encoder *encoder,
 				     const struct intel_crtc_state *crtc_state,
 				     const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	intel_ddi_set_dp_msa(crtc_state, conn_state);
 
@@ -4106,8 +4146,9 @@ intel_ddi_update_prepare(struct intel_atomic_state *state,
 
 	WARN_ON(crtc && crtc->active);
 
-	intel_tc_port_get_link(enc_to_dig_port(&encoder->base), required_lanes);
-	if (crtc_state && crtc_state->base.active)
+	intel_tc_port_get_link(enc_to_dig_port(encoder),
+		               required_lanes);
+	if (crtc_state && crtc_state->hw.active)
 		intel_update_active_dpll(state, crtc, encoder);
 }
 
@@ -4116,7 +4157,7 @@ intel_ddi_update_complete(struct intel_atomic_state *state,
 			  struct intel_encoder *encoder,
 			  struct intel_crtc *crtc)
 {
-	intel_tc_port_put_link(enc_to_dig_port(&encoder->base));
+	intel_tc_port_put_link(enc_to_dig_port(encoder));
 }
 
 static void
@@ -4125,7 +4166,7 @@ intel_ddi_pre_pll_enable(struct intel_encoder *encoder,
 			 const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 	bool is_tc_port = intel_phy_is_tc(dev_priv, phy);
 
@@ -4147,61 +4188,44 @@ intel_ddi_pre_pll_enable(struct intel_encoder *encoder,
 						crtc_state->lane_lat_optim_mask);
 }
 
-static void
-intel_ddi_post_pll_disable(struct intel_encoder *encoder,
-			   const struct intel_crtc_state *crtc_state,
-			   const struct drm_connector_state *conn_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
-	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
-	bool is_tc_port = intel_phy_is_tc(dev_priv, phy);
-
-	if (intel_crtc_has_dp_encoder(crtc_state) || is_tc_port)
-		intel_display_power_put_unchecked(dev_priv,
-						  intel_ddi_main_link_aux_domain(dig_port));
-
-	if (is_tc_port)
-		intel_tc_port_put_link(dig_port);
-}
-
 static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv =
 		to_i915(intel_dig_port->base.base.dev);
 	enum port port = intel_dig_port->base.port;
-	u32 val;
+	u32 dp_tp_ctl, ddi_buf_ctl;
 	bool wait = false;
 
-	if (I915_READ(intel_dp->regs.dp_tp_ctl) & DP_TP_CTL_ENABLE) {
-		val = I915_READ(DDI_BUF_CTL(port));
-		if (val & DDI_BUF_CTL_ENABLE) {
-			val &= ~DDI_BUF_CTL_ENABLE;
-			I915_WRITE(DDI_BUF_CTL(port), val);
+	dp_tp_ctl = I915_READ(intel_dp->regs.dp_tp_ctl);
+
+	if (dp_tp_ctl & DP_TP_CTL_ENABLE) {
+		ddi_buf_ctl = I915_READ(DDI_BUF_CTL(port));
+		if (ddi_buf_ctl & DDI_BUF_CTL_ENABLE) {
+			I915_WRITE(DDI_BUF_CTL(port),
+				   ddi_buf_ctl & ~DDI_BUF_CTL_ENABLE);
 			wait = true;
 		}
 
-		val = I915_READ(intel_dp->regs.dp_tp_ctl);
-		val &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
-		val |= DP_TP_CTL_LINK_TRAIN_PAT1;
-		I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
+		dp_tp_ctl &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
+		dp_tp_ctl |= DP_TP_CTL_LINK_TRAIN_PAT1;
+		I915_WRITE(intel_dp->regs.dp_tp_ctl, dp_tp_ctl);
 		POSTING_READ(intel_dp->regs.dp_tp_ctl);
 
 		if (wait)
 			intel_wait_ddi_buf_idle(dev_priv, port);
 	}
 
-	val = DP_TP_CTL_ENABLE |
-	      DP_TP_CTL_LINK_TRAIN_PAT1 | DP_TP_CTL_SCRAMBLE_DISABLE;
+	dp_tp_ctl = DP_TP_CTL_ENABLE |
+		    DP_TP_CTL_LINK_TRAIN_PAT1 | DP_TP_CTL_SCRAMBLE_DISABLE;
 	if (intel_dp->link_mst)
-		val |= DP_TP_CTL_MODE_MST;
+		dp_tp_ctl |= DP_TP_CTL_MODE_MST;
 	else {
-		val |= DP_TP_CTL_MODE_SST;
+		dp_tp_ctl |= DP_TP_CTL_MODE_SST;
 		if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
-			val |= DP_TP_CTL_ENHANCED_FRAME_ENABLE;
+			dp_tp_ctl |= DP_TP_CTL_ENHANCED_FRAME_ENABLE;
 	}
-	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
+	I915_WRITE(intel_dp->regs.dp_tp_ctl, dp_tp_ctl);
 	POSTING_READ(intel_dp->regs.dp_tp_ctl);
 
 	intel_dp->DP |= DDI_BUF_CTL_ENABLE;
@@ -4237,7 +4261,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 			  struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	u32 temp, flags = 0;
 
@@ -4245,6 +4269,8 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	if (WARN_ON(transcoder_is_dsi(cpu_transcoder)))
 		return;
 
+	intel_dsc_get_config(encoder, pipe_config);
+
 	temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
 	if (temp & TRANS_DDI_PHSYNC)
 		flags |= DRM_MODE_FLAG_PHSYNC;
@@ -4255,7 +4281,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	else
 		flags |= DRM_MODE_FLAG_NVSYNC;
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	switch (temp & TRANS_DDI_BPC_MASK) {
 	case TRANS_DDI_BPC_6:
@@ -4326,6 +4352,11 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		pipe_config->output_types |= BIT(INTEL_OUTPUT_DP_MST);
 		pipe_config->lane_count =
 			((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1;
+
+		if (INTEL_GEN(dev_priv) >= 12)
+			pipe_config->mst_master_transcoder =
+					REG_FIELD_GET(TRANS_DDI_MST_TRANSPORT_SELECT_MASK, temp);
+
 		intel_dp_get_m_n(intel_crtc, pipe_config);
 		break;
 	default:
@@ -4404,7 +4435,7 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config,
 				    struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 	int ret;
@@ -4439,7 +4470,7 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder,
 
 static void intel_ddi_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
+	struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder));
 
 	intel_dp_encoder_flush_work(encoder);
 
@@ -4506,7 +4537,7 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder,
 				 struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_hdmi *hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *hdmi = enc_to_intel_hdmi(encoder);
 	struct intel_connector *connector = hdmi->attached_connector;
 	struct i2c_adapter *adapter =
 		intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
@@ -4538,7 +4569,7 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder,
 
 	WARN_ON(!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI));
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return 0;
 
 	if (!crtc_state->hdmi_high_tmds_clock_ratio &&
@@ -4578,7 +4609,7 @@ intel_ddi_hotplug(struct intel_encoder *encoder,
 		  struct intel_connector *connector,
 		  bool irq_received)
 {
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct drm_modeset_acquire_ctx ctx;
 	enum intel_hotplug_state state;
 	int ret;
@@ -4709,8 +4740,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	struct ddi_vbt_port_info *port_info =
 		&dev_priv->vbt.ddi_port_info[port];
 	struct intel_digital_port *intel_dig_port;
-	struct intel_encoder *intel_encoder;
-	struct drm_encoder *encoder;
+	struct intel_encoder *encoder;
 	bool init_hdmi, init_dp, init_lspcon = false;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 
@@ -4739,31 +4769,30 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	if (!intel_dig_port)
 		return;
 
-	intel_encoder = &intel_dig_port->base;
-	encoder = &intel_encoder->base;
+	encoder = &intel_dig_port->base;
 
-	drm_encoder_init(&dev_priv->drm, encoder, &intel_ddi_funcs,
+	drm_encoder_init(&dev_priv->drm, &encoder->base, &intel_ddi_funcs,
 			 DRM_MODE_ENCODER_TMDS, "DDI %c", port_name(port));
 
-	intel_encoder->hotplug = intel_ddi_hotplug;
-	intel_encoder->compute_output_type = intel_ddi_compute_output_type;
-	intel_encoder->compute_config = intel_ddi_compute_config;
-	intel_encoder->enable = intel_enable_ddi;
-	intel_encoder->pre_pll_enable = intel_ddi_pre_pll_enable;
-	intel_encoder->post_pll_disable = intel_ddi_post_pll_disable;
-	intel_encoder->pre_enable = intel_ddi_pre_enable;
-	intel_encoder->disable = intel_disable_ddi;
-	intel_encoder->post_disable = intel_ddi_post_disable;
-	intel_encoder->update_pipe = intel_ddi_update_pipe;
-	intel_encoder->get_hw_state = intel_ddi_get_hw_state;
-	intel_encoder->get_config = intel_ddi_get_config;
-	intel_encoder->suspend = intel_dp_encoder_suspend;
-	intel_encoder->get_power_domains = intel_ddi_get_power_domains;
-	intel_encoder->type = INTEL_OUTPUT_DDI;
-	intel_encoder->power_domain = intel_port_to_power_domain(port);
-	intel_encoder->port = port;
-	intel_encoder->cloneable = 0;
-	intel_encoder->pipe_mask = ~0;
+	encoder->hotplug = intel_ddi_hotplug;
+	encoder->compute_output_type = intel_ddi_compute_output_type;
+	encoder->compute_config = intel_ddi_compute_config;
+	encoder->enable = intel_enable_ddi;
+	encoder->pre_pll_enable = intel_ddi_pre_pll_enable;
+	encoder->pre_enable = intel_ddi_pre_enable;
+	encoder->disable = intel_disable_ddi;
+	encoder->post_disable = intel_ddi_post_disable;
+	encoder->update_pipe = intel_ddi_update_pipe;
+	encoder->get_hw_state = intel_ddi_get_hw_state;
+	encoder->get_config = intel_ddi_get_config;
+	encoder->suspend = intel_dp_encoder_suspend;
+	encoder->get_power_domains = intel_ddi_get_power_domains;
+
+	encoder->type = INTEL_OUTPUT_DDI;
+	encoder->power_domain = intel_port_to_power_domain(port);
+	encoder->port = port;
+	encoder->cloneable = 0;
+	encoder->pipe_mask = ~0;
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
@@ -4771,6 +4800,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	else
 		intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
 			(DDI_BUF_PORT_REVERSAL | DDI_A_4_LANES);
+
 	intel_dig_port->dp.output_reg = INVALID_MMIO_REG;
 	intel_dig_port->max_lanes = intel_ddi_max_lanes(intel_dig_port);
 	intel_dig_port->aux_ch = intel_bios_port_aux_ch(dev_priv, port);
@@ -4781,8 +4811,8 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 
 		intel_tc_port_init(intel_dig_port, is_legacy);
 
-		intel_encoder->update_prepare = intel_ddi_update_prepare;
-		intel_encoder->update_complete = intel_ddi_update_complete;
+		encoder->update_prepare = intel_ddi_update_prepare;
+		encoder->update_complete = intel_ddi_update_complete;
 	}
 
 	WARN_ON(port > PORT_I);
@@ -4798,7 +4828,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 
 	/* In theory we don't need the encoder->type check, but leave it just in
 	 * case we have some really bad VBTs... */
-	if (intel_encoder->type != INTEL_OUTPUT_EDP && init_hdmi) {
+	if (encoder->type != INTEL_OUTPUT_EDP && init_hdmi) {
 		if (!intel_ddi_init_hdmi_connector(intel_dig_port))
 			goto err;
 	}
@@ -4822,6 +4852,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	return;
 
 err:
-	drm_encoder_cleanup(encoder);
+	drm_encoder_cleanup(&encoder->base);
 	kfree(intel_dig_port);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h
index 19aeab1246ee..167c6579d972 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.h
+++ b/drivers/gpu/drm/i915/display/intel_ddi.h
@@ -22,7 +22,7 @@ struct intel_encoder;
 void intel_ddi_fdi_post_disable(struct intel_encoder *intel_encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state);
-void hsw_fdi_link_train(struct intel_crtc *crtc,
+void hsw_fdi_link_train(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state);
 void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port);
 bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 301897791627..19ea842cfd84 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -46,6 +46,7 @@
 #include "display/intel_crt.h"
 #include "display/intel_ddi.h"
 #include "display/intel_dp.h"
+#include "display/intel_dp_mst.h"
 #include "display/intel_dsi.h"
 #include "display/intel_dvo.h"
 #include "display/intel_gmbus.h"
@@ -86,8 +87,8 @@
 /* Primary plane formats for gen <= 3 */
 static const u32 i8xx_primary_formats[] = {
 	DRM_FORMAT_C8,
-	DRM_FORMAT_RGB565,
 	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_RGB565,
 	DRM_FORMAT_XRGB8888,
 };
 
@@ -112,6 +113,21 @@ static const u32 i965_primary_formats[] = {
 	DRM_FORMAT_XBGR16161616F,
 };
 
+/* Primary plane formats for vlv/chv */
+static const u32 vlv_primary_formats[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_XBGR16161616F,
+};
+
 static const u64 i9xx_format_modifiers[] = {
 	I915_FORMAT_MOD_X_TILED,
 	DRM_FORMAT_MOD_LINEAR,
@@ -130,8 +146,8 @@ static const u64 cursor_format_modifiers[] = {
 
 static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
 				struct intel_crtc_state *pipe_config);
-static void ironlake_pch_clock_get(struct intel_crtc *crtc,
-				   struct intel_crtc_state *pipe_config);
+static void ilk_pch_clock_get(struct intel_crtc *crtc,
+			      struct intel_crtc_state *pipe_config);
 
 static int intel_framebuffer_init(struct intel_framebuffer *ifb,
 				  struct drm_i915_gem_object *obj,
@@ -142,21 +158,18 @@ static void intel_cpu_transcoder_set_m_n(const struct intel_crtc_state *crtc_sta
 					 const struct intel_link_m_n *m_n,
 					 const struct intel_link_m_n *m2_n2);
 static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state);
-static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state);
-static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state);
+static void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state);
+static void hsw_set_pipeconf(const struct intel_crtc_state *crtc_state);
 static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state);
 static void vlv_prepare_pll(struct intel_crtc *crtc,
 			    const struct intel_crtc_state *pipe_config);
 static void chv_prepare_pll(struct intel_crtc *crtc,
 			    const struct intel_crtc_state *pipe_config);
-static void intel_crtc_init_scalers(struct intel_crtc *crtc,
-				    struct intel_crtc_state *crtc_state);
-static void skylake_pfit_enable(const struct intel_crtc_state *crtc_state);
-static void ironlake_pfit_disable(const struct intel_crtc_state *old_crtc_state);
-static void ironlake_pfit_enable(const struct intel_crtc_state *crtc_state);
+static void skl_pfit_enable(const struct intel_crtc_state *crtc_state);
+static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state);
 static void intel_modeset_setup_hw_state(struct drm_device *dev,
 					 struct drm_modeset_acquire_ctx *ctx);
-static void intel_pre_disable_primary_noatomic(struct drm_crtc *crtc);
+static struct intel_crtc_state *intel_crtc_state_alloc(struct intel_crtc *crtc);
 
 struct intel_limit {
 	struct {
@@ -357,7 +370,7 @@ static const struct intel_limit intel_limits_g4x_dual_channel_lvds = {
 	},
 };
 
-static const struct intel_limit intel_limits_pineview_sdvo = {
+static const struct intel_limit pnv_limits_sdvo = {
 	.dot = { .min = 20000, .max = 400000},
 	.vco = { .min = 1700000, .max = 3500000 },
 	/* Pineview's Ncounter is a ring counter */
@@ -372,7 +385,7 @@ static const struct intel_limit intel_limits_pineview_sdvo = {
 		.p2_slow = 10, .p2_fast = 5 },
 };
 
-static const struct intel_limit intel_limits_pineview_lvds = {
+static const struct intel_limit pnv_limits_lvds = {
 	.dot = { .min = 20000, .max = 400000 },
 	.vco = { .min = 1700000, .max = 3500000 },
 	.n = { .min = 3, .max = 6 },
@@ -390,7 +403,7 @@ static const struct intel_limit intel_limits_pineview_lvds = {
  * We calculate clock using (register_value + 2) for N/M1/M2, so here
  * the range value for them is (actual_value - 2).
  */
-static const struct intel_limit intel_limits_ironlake_dac = {
+static const struct intel_limit ilk_limits_dac = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 5 },
@@ -403,7 +416,7 @@ static const struct intel_limit intel_limits_ironlake_dac = {
 		.p2_slow = 10, .p2_fast = 5 },
 };
 
-static const struct intel_limit intel_limits_ironlake_single_lvds = {
+static const struct intel_limit ilk_limits_single_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -416,7 +429,7 @@ static const struct intel_limit intel_limits_ironlake_single_lvds = {
 		.p2_slow = 14, .p2_fast = 14 },
 };
 
-static const struct intel_limit intel_limits_ironlake_dual_lvds = {
+static const struct intel_limit ilk_limits_dual_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -430,7 +443,7 @@ static const struct intel_limit intel_limits_ironlake_dual_lvds = {
 };
 
 /* LVDS 100mhz refclk limits. */
-static const struct intel_limit intel_limits_ironlake_single_lvds_100m = {
+static const struct intel_limit ilk_limits_single_lvds_100m = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 2 },
@@ -443,7 +456,7 @@ static const struct intel_limit intel_limits_ironlake_single_lvds_100m = {
 		.p2_slow = 14, .p2_fast = 14 },
 };
 
-static const struct intel_limit intel_limits_ironlake_dual_lvds_100m = {
+static const struct intel_limit ilk_limits_dual_lvds_100m = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -530,7 +543,7 @@ icl_wa_scalerclkgating(struct drm_i915_private *dev_priv, enum pipe pipe,
 static bool
 needs_modeset(const struct intel_crtc_state *state)
 {
-	return drm_atomic_crtc_needs_modeset(&state->base);
+	return drm_atomic_crtc_needs_modeset(&state->uapi);
 }
 
 bool
@@ -541,10 +554,9 @@ is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state)
 }
 
 static bool
-is_trans_port_sync_master(const struct intel_crtc_state *crtc_state)
+is_trans_port_sync_slave(const struct intel_crtc_state *crtc_state)
 {
-	return (crtc_state->master_transcoder == INVALID_TRANSCODER &&
-		crtc_state->sync_mode_slaves_mask);
+	return crtc_state->master_transcoder != INVALID_TRANSCODER;
 }
 
 /*
@@ -658,7 +670,7 @@ i9xx_select_p2_div(const struct intel_limit *limit,
 		   const struct intel_crtc_state *crtc_state,
 		   int target)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		/*
@@ -694,7 +706,7 @@ i9xx_find_best_dpll(const struct intel_limit *limit,
 		    int target, int refclk, struct dpll *match_clock,
 		    struct dpll *best_clock)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_device *dev = crtc_state->uapi.crtc->dev;
 	struct dpll clock;
 	int err = target;
 
@@ -752,7 +764,7 @@ pnv_find_best_dpll(const struct intel_limit *limit,
 		   int target, int refclk, struct dpll *match_clock,
 		   struct dpll *best_clock)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_device *dev = crtc_state->uapi.crtc->dev;
 	struct dpll clock;
 	int err = target;
 
@@ -808,7 +820,7 @@ g4x_find_best_dpll(const struct intel_limit *limit,
 		   int target, int refclk, struct dpll *match_clock,
 		   struct dpll *best_clock)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_device *dev = crtc_state->uapi.crtc->dev;
 	struct dpll clock;
 	int max_n;
 	bool found = false;
@@ -902,7 +914,7 @@ vlv_find_best_dpll(const struct intel_limit *limit,
 		   int target, int refclk, struct dpll *match_clock,
 		   struct dpll *best_clock)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct dpll clock;
 	unsigned int bestppm = 1000000;
@@ -962,7 +974,7 @@ chv_find_best_dpll(const struct intel_limit *limit,
 		   int target, int refclk, struct dpll *match_clock,
 		   struct dpll *best_clock)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	unsigned int best_error_ppm;
 	struct dpll clock;
@@ -1025,33 +1037,6 @@ bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state,
 				  NULL, best_clock);
 }
 
-bool intel_crtc_active(struct intel_crtc *crtc)
-{
-	/* Be paranoid as we can arrive here with only partial
-	 * state retrieved from the hardware during setup.
-	 *
-	 * We can ditch the adjusted_mode.crtc_clock check as soon
-	 * as Haswell has gained clock readout/fastboot support.
-	 *
-	 * We can ditch the crtc->primary->state->fb check as soon as we can
-	 * properly reconstruct framebuffers.
-	 *
-	 * FIXME: The intel_crtc->active here should be switched to
-	 * crtc->state->active once we have proper CRTC states wired up
-	 * for atomic.
-	 */
-	return crtc->active && crtc->base.primary->state->fb &&
-		crtc->config->base.adjusted_mode.crtc_clock;
-}
-
-enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
-					     enum pipe pipe)
-{
-	struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
-
-	return crtc->config->cpu_transcoder;
-}
-
 static bool pipe_scanline_is_moving(struct drm_i915_private *dev_priv,
 				    enum pipe pipe)
 {
@@ -1095,7 +1080,7 @@ static void intel_wait_for_pipe_scanline_moving(struct intel_crtc *crtc)
 static void
 intel_wait_for_pipe_off(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (INTEL_GEN(dev_priv) >= 4) {
@@ -1145,11 +1130,15 @@ static void assert_fdi_tx(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, bool state)
 {
 	bool cur_state;
-	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
-								      pipe);
 
 	if (HAS_DDI(dev_priv)) {
-		/* DDI does not have a specific FDI_TX register */
+		/*
+		 * DDI does not have a specific FDI_TX register.
+		 *
+		 * FDI is never fed from EDP transcoder
+		 * so pipe->transcoder cast is fine here.
+		 */
+		enum transcoder cpu_transcoder = (enum transcoder)pipe;
 		u32 val = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
 		cur_state = !!(val & TRANS_DDI_FUNC_ENABLE);
 	} else {
@@ -1266,11 +1255,9 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 }
 
 void assert_pipe(struct drm_i915_private *dev_priv,
-		 enum pipe pipe, bool state)
+		 enum transcoder cpu_transcoder, bool state)
 {
 	bool cur_state;
-	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
-								      pipe);
 	enum intel_display_power_domain power_domain;
 	intel_wakeref_t wakeref;
 
@@ -1290,8 +1277,9 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 	}
 
 	I915_STATE_WARN(cur_state != state,
-	     "pipe %c assertion failure (expected %s, current %s)\n",
-			pipe_name(pipe), onoff(state), onoff(cur_state));
+			"transcoder %s assertion failure (expected %s, current %s)\n",
+			transcoder_name(cpu_transcoder),
+			onoff(state), onoff(cur_state));
 }
 
 static void assert_plane(struct intel_plane *plane, bool state)
@@ -1418,7 +1406,7 @@ static void vlv_enable_pll(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder);
 
 	/* PLL is protected by panel, make sure we can write it */
 	assert_panel_unlocked(dev_priv, pipe);
@@ -1467,7 +1455,7 @@ static void chv_enable_pll(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder);
 
 	/* PLL is protected by panel, make sure we can write it */
 	assert_panel_unlocked(dev_priv, pipe);
@@ -1514,7 +1502,7 @@ static void i9xx_enable_pll(struct intel_crtc *crtc,
 	u32 dpll = crtc_state->dpll_hw_state.dpll;
 	int i;
 
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder);
 
 	/* PLL is protected by panel, make sure we can write it */
 	if (i9xx_has_pps(dev_priv))
@@ -1554,7 +1542,7 @@ static void i9xx_enable_pll(struct intel_crtc *crtc,
 
 static void i9xx_disable_pll(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -1563,7 +1551,7 @@ static void i9xx_disable_pll(const struct intel_crtc_state *crtc_state)
 		return;
 
 	/* Make sure the pipe isn't still relying on us */
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder);
 
 	I915_WRITE(DPLL(pipe), DPLL_VGA_MODE_DIS);
 	POSTING_READ(DPLL(pipe));
@@ -1574,7 +1562,7 @@ static void vlv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	u32 val;
 
 	/* Make sure the pipe isn't still relying on us */
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, (enum transcoder)pipe);
 
 	val = DPLL_INTEGRATED_REF_CLK_VLV |
 		DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS;
@@ -1591,7 +1579,7 @@ static void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	u32 val;
 
 	/* Make sure the pipe isn't still relying on us */
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, (enum transcoder)pipe);
 
 	val = DPLL_SSC_REF_CLK_CHV |
 		DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS;
@@ -1643,9 +1631,9 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 		     I915_READ(dpll_reg) & port_mask, expected_mask);
 }
 
-static void ironlake_enable_pch_transcoder(const struct intel_crtc_state *crtc_state)
+static void ilk_enable_pch_transcoder(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
@@ -1659,11 +1647,16 @@ static void ironlake_enable_pch_transcoder(const struct intel_crtc_state *crtc_s
 	assert_fdi_rx_enabled(dev_priv, pipe);
 
 	if (HAS_PCH_CPT(dev_priv)) {
-		/* Workaround: Set the timing override bit before enabling the
-		 * pch transcoder. */
 		reg = TRANS_CHICKEN2(pipe);
 		val = I915_READ(reg);
+		/*
+		 * Workaround: Set the timing override bit
+		 * before enabling the pch transcoder.
+		 */
 		val |= TRANS_CHICKEN2_TIMING_OVERRIDE;
+		/* Configure frame start delay to match the CPU */
+		val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
+		val |= TRANS_CHICKEN2_FRAME_START_DELAY(0);
 		I915_WRITE(reg, val);
 	}
 
@@ -1672,6 +1665,10 @@ static void ironlake_enable_pch_transcoder(const struct intel_crtc_state *crtc_s
 	pipeconf_val = I915_READ(PIPECONF(pipe));
 
 	if (HAS_PCH_IBX(dev_priv)) {
+		/* Configure frame start delay to match the CPU */
+		val &= ~TRANS_FRAME_START_DELAY_MASK;
+		val |= TRANS_FRAME_START_DELAY(0);
+
 		/*
 		 * Make the BPC in transcoder be consistent with
 		 * that in pipeconf reg. For HDMI we must use 8bpc
@@ -1709,9 +1706,12 @@ static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 	assert_fdi_tx_enabled(dev_priv, (enum pipe) cpu_transcoder);
 	assert_fdi_rx_enabled(dev_priv, PIPE_A);
 
-	/* Workaround: set timing override bit. */
 	val = I915_READ(TRANS_CHICKEN2(PIPE_A));
+	/* Workaround: set timing override bit. */
 	val |= TRANS_CHICKEN2_TIMING_OVERRIDE;
+	/* Configure frame start delay to match the CPU */
+	val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
+	val |= TRANS_CHICKEN2_FRAME_START_DELAY(0);
 	I915_WRITE(TRANS_CHICKEN2(PIPE_A), val);
 
 	val = TRANS_ENABLE;
@@ -1729,8 +1729,8 @@ static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 		DRM_ERROR("Failed to enable PCH transcoder\n");
 }
 
-static void ironlake_disable_pch_transcoder(struct drm_i915_private *dev_priv,
-					    enum pipe pipe)
+static void ilk_disable_pch_transcoder(struct drm_i915_private *dev_priv,
+				       enum pipe pipe)
 {
 	i915_reg_t reg;
 	u32 val;
@@ -1789,7 +1789,7 @@ enum pipe intel_crtc_pch_transcoder(struct intel_crtc *crtc)
 
 static u32 intel_crtc_max_vblank_count(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	/*
 	 * On i965gm the hardware frame counter reads
@@ -1809,16 +1809,25 @@ static u32 intel_crtc_max_vblank_count(const struct intel_crtc_state *crtc_state
 
 static void intel_crtc_vblank_on(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
+	assert_vblank_disabled(&crtc->base);
 	drm_crtc_set_max_vblank_count(&crtc->base,
 				      intel_crtc_max_vblank_count(crtc_state));
 	drm_crtc_vblank_on(&crtc->base);
 }
 
+void intel_crtc_vblank_off(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+
+	drm_crtc_vblank_off(&crtc->base);
+	assert_vblank_disabled(&crtc->base);
+}
+
 static void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = new_crtc_state->cpu_transcoder;
 	enum pipe pipe = crtc->pipe;
@@ -1874,9 +1883,9 @@ static void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state)
 		intel_wait_for_pipe_scanline_moving(crtc);
 }
 
-static void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state)
+void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
 	enum pipe pipe = crtc->pipe;
@@ -1919,6 +1928,74 @@ static unsigned int intel_tile_size(const struct drm_i915_private *dev_priv)
 	return IS_GEN(dev_priv, 2) ? 2048 : 4096;
 }
 
+static bool is_ccs_plane(const struct drm_framebuffer *fb, int plane)
+{
+	if (!is_ccs_modifier(fb->modifier))
+		return false;
+
+	return plane >= fb->format->num_planes / 2;
+}
+
+static bool is_gen12_ccs_modifier(u64 modifier)
+{
+	return modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+	       modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
+
+}
+
+static bool is_gen12_ccs_plane(const struct drm_framebuffer *fb, int plane)
+{
+	return is_gen12_ccs_modifier(fb->modifier) && is_ccs_plane(fb, plane);
+}
+
+static bool is_aux_plane(const struct drm_framebuffer *fb, int plane)
+{
+	if (is_ccs_modifier(fb->modifier))
+		return is_ccs_plane(fb, plane);
+
+	return plane == 1;
+}
+
+static int main_to_ccs_plane(const struct drm_framebuffer *fb, int main_plane)
+{
+	WARN_ON(!is_ccs_modifier(fb->modifier) ||
+		(main_plane && main_plane >= fb->format->num_planes / 2));
+
+	return fb->format->num_planes / 2 + main_plane;
+}
+
+static int ccs_to_main_plane(const struct drm_framebuffer *fb, int ccs_plane)
+{
+	WARN_ON(!is_ccs_modifier(fb->modifier) ||
+		ccs_plane < fb->format->num_planes / 2);
+
+	return ccs_plane - fb->format->num_planes / 2;
+}
+
+/* Return either the main plane's CCS or - if not a CCS FB - UV plane */
+int intel_main_to_aux_plane(const struct drm_framebuffer *fb, int main_plane)
+{
+	if (is_ccs_modifier(fb->modifier))
+		return main_to_ccs_plane(fb, main_plane);
+
+	return 1;
+}
+
+bool
+intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info,
+				    uint64_t modifier)
+{
+	return info->is_yuv &&
+	       info->num_planes == (is_ccs_modifier(modifier) ? 4 : 2);
+}
+
+static bool is_semiplanar_uv_plane(const struct drm_framebuffer *fb,
+				   int color_plane)
+{
+	return intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
+	       color_plane == 1;
+}
+
 static unsigned int
 intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 {
@@ -1934,16 +2011,21 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 		else
 			return 512;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
-		if (color_plane == 1)
+		if (is_ccs_plane(fb, color_plane))
 			return 128;
 		/* fall through */
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		if (is_ccs_plane(fb, color_plane))
+			return 64;
+		/* fall through */
 	case I915_FORMAT_MOD_Y_TILED:
 		if (IS_GEN(dev_priv, 2) || HAS_128_BYTE_Y_TILING(dev_priv))
 			return 128;
 		else
 			return 512;
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
-		if (color_plane == 1)
+		if (is_ccs_plane(fb, color_plane))
 			return 128;
 		/* fall through */
 	case I915_FORMAT_MOD_Yf_TILED:
@@ -1970,6 +2052,9 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 static unsigned int
 intel_tile_height(const struct drm_framebuffer *fb, int color_plane)
 {
+	if (is_gen12_ccs_plane(fb, color_plane))
+		return 1;
+
 	return intel_tile_size(to_i915(fb->dev)) /
 		intel_tile_width_bytes(fb, color_plane);
 }
@@ -1983,7 +2068,17 @@ static void intel_tile_dims(const struct drm_framebuffer *fb, int color_plane,
 	unsigned int cpp = fb->format->cpp[color_plane];
 
 	*tile_width = tile_width_bytes / cpp;
-	*tile_height = intel_tile_size(to_i915(fb->dev)) / tile_width_bytes;
+	*tile_height = intel_tile_height(fb, color_plane);
+}
+
+static unsigned int intel_tile_row_size(const struct drm_framebuffer *fb,
+					int color_plane)
+{
+	unsigned int tile_width, tile_height;
+
+	intel_tile_dims(fb, color_plane, &tile_width, &tile_height);
+
+	return fb->pitches[color_plane] * tile_height;
 }
 
 unsigned int
@@ -2060,7 +2155,8 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
 
 	/* AUX_DIST needs only 4K alignment */
-	if (color_plane == 1)
+	if ((INTEL_GEN(dev_priv) < 12 && is_aux_plane(fb, color_plane)) ||
+	    is_ccs_plane(fb, color_plane))
 		return 4096;
 
 	switch (fb->modifier) {
@@ -2070,9 +2166,19 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 		if (INTEL_GEN(dev_priv) >= 9)
 			return 256 * 1024;
 		return 0;
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		if (is_semiplanar_uv_plane(fb, color_plane))
+			return intel_tile_row_size(fb, color_plane);
+		/* Fall-through */
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+		return 16 * 1024;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
 	case I915_FORMAT_MOD_Y_TILED:
+		if (INTEL_GEN(dev_priv) >= 12 &&
+		    is_semiplanar_uv_plane(fb, color_plane))
+			return intel_tile_row_size(fb, color_plane);
+		/* Fall-through */
 	case I915_FORMAT_MOD_Yf_TILED:
 		return 1 * 1024 * 1024;
 	default:
@@ -2083,7 +2189,7 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 
 static bool intel_plane_uses_fence(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 
 	return INTEL_GEN(dev_priv) < 4 ||
@@ -2109,6 +2215,8 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 		return ERR_PTR(-EINVAL);
 
 	alignment = intel_surf_alignment(fb, 0);
+	if (WARN_ON(alignment && !is_power_of_2(alignment)))
+		return ERR_PTR(-EINVAL);
 
 	/* Note that the w/a also requires 64 PTE of padding following the
 	 * bo. We currently fill all unused PTE with the shadow page and so
@@ -2126,19 +2234,18 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	 * pin/unpin/fence and not more.
 	 */
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
-	i915_gem_object_lock(obj);
 
 	atomic_inc(&dev_priv->gpu_error.pending_fb_pin);
 
-	pinctl = 0;
-
-	/* Valleyview is definitely limited to scanning out the first
+	/*
+	 * Valleyview is definitely limited to scanning out the first
 	 * 512MiB. Lets presume this behaviour was inherited from the
 	 * g4x display engine and that all earlier gen are similarly
 	 * limited. Testing suggests that it is a little more
 	 * complicated than this. For example, Cherryview appears quite
 	 * happy to scanout from anywhere within its global aperture.
 	 */
+	pinctl = 0;
 	if (HAS_GMCH(dev_priv))
 		pinctl |= PIN_MAPPABLE;
 
@@ -2150,7 +2257,8 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	if (uses_fence && i915_vma_is_map_and_fenceable(vma)) {
 		int ret;
 
-		/* Install a fence for tiled scan-out. Pre-i965 always needs a
+		/*
+		 * Install a fence for tiled scan-out. Pre-i965 always needs a
 		 * fence, whereas 965+ only requires a fence if using
 		 * framebuffer compression.  For simplicity, we always, when
 		 * possible, install a fence as the cost is not that onerous.
@@ -2180,8 +2288,6 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	i915_vma_get(vma);
 err:
 	atomic_dec(&dev_priv->gpu_error.pending_fb_pin);
-
-	i915_gem_object_unlock(obj);
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 	return vma;
 }
@@ -2216,7 +2322,7 @@ u32 intel_fb_xy_to_linear(int x, int y,
 			  const struct intel_plane_state *state,
 			  int color_plane)
 {
-	const struct drm_framebuffer *fb = state->base.fb;
+	const struct drm_framebuffer *fb = state->hw.fb;
 	unsigned int cpp = fb->format->cpp[color_plane];
 	unsigned int pitch = state->color_plane[color_plane].stride;
 
@@ -2264,9 +2370,10 @@ static u32 intel_adjust_tile_offset(int *x, int *y,
 	return new_offset;
 }
 
-static bool is_surface_linear(u64 modifier, int color_plane)
+static bool is_surface_linear(const struct drm_framebuffer *fb, int color_plane)
 {
-	return modifier == DRM_FORMAT_MOD_LINEAR;
+	return fb->modifier == DRM_FORMAT_MOD_LINEAR ||
+	       is_gen12_ccs_plane(fb, color_plane);
 }
 
 static u32 intel_adjust_aligned_offset(int *x, int *y,
@@ -2281,7 +2388,7 @@ static u32 intel_adjust_aligned_offset(int *x, int *y,
 
 	WARN_ON(new_offset > old_offset);
 
-	if (!is_surface_linear(fb->modifier, color_plane)) {
+	if (!is_surface_linear(fb, color_plane)) {
 		unsigned int tile_size, tile_width, tile_height;
 		unsigned int pitch_tiles;
 
@@ -2317,8 +2424,8 @@ static u32 intel_plane_adjust_aligned_offset(int *x, int *y,
 					     int color_plane,
 					     u32 old_offset, u32 new_offset)
 {
-	return intel_adjust_aligned_offset(x, y, state->base.fb, color_plane,
-					   state->base.rotation,
+	return intel_adjust_aligned_offset(x, y, state->hw.fb, color_plane,
+					   state->hw.rotation,
 					   state->color_plane[color_plane].stride,
 					   old_offset, new_offset);
 }
@@ -2348,10 +2455,7 @@ static u32 intel_compute_aligned_offset(struct drm_i915_private *dev_priv,
 	unsigned int cpp = fb->format->cpp[color_plane];
 	u32 offset, offset_aligned;
 
-	if (alignment)
-		alignment--;
-
-	if (!is_surface_linear(fb->modifier, color_plane)) {
+	if (!is_surface_linear(fb, color_plane)) {
 		unsigned int tile_size, tile_width, tile_height;
 		unsigned int tile_rows, tiles, pitch_tiles;
 
@@ -2372,17 +2476,24 @@ static u32 intel_compute_aligned_offset(struct drm_i915_private *dev_priv,
 		*x %= tile_width;
 
 		offset = (tile_rows * pitch_tiles + tiles) * tile_size;
-		offset_aligned = offset & ~alignment;
+
+		offset_aligned = offset;
+		if (alignment)
+			offset_aligned = rounddown(offset_aligned, alignment);
 
 		intel_adjust_tile_offset(x, y, tile_width, tile_height,
 					 tile_size, pitch_tiles,
 					 offset, offset_aligned);
 	} else {
 		offset = *y * pitch + *x * cpp;
-		offset_aligned = offset & ~alignment;
-
-		*y = (offset & alignment) / pitch;
-		*x = ((offset & alignment) - *y * pitch) / cpp;
+		offset_aligned = offset;
+		if (alignment) {
+			offset_aligned = rounddown(offset_aligned, alignment);
+			*y = (offset % alignment) / pitch;
+			*x = ((offset % alignment) - *y * pitch) / cpp;
+		} else {
+			*y = *x = 0;
+		}
 	}
 
 	return offset_aligned;
@@ -2392,10 +2503,10 @@ static u32 intel_plane_compute_aligned_offset(int *x, int *y,
 					      const struct intel_plane_state *state,
 					      int color_plane)
 {
-	struct intel_plane *intel_plane = to_intel_plane(state->base.plane);
+	struct intel_plane *intel_plane = to_intel_plane(state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev);
-	const struct drm_framebuffer *fb = state->base.fb;
-	unsigned int rotation = state->base.rotation;
+	const struct drm_framebuffer *fb = state->hw.fb;
+	unsigned int rotation = state->hw.rotation;
 	int pitch = state->color_plane[color_plane].stride;
 	u32 alignment;
 
@@ -2415,9 +2526,17 @@ static int intel_fb_offset_to_xy(int *x, int *y,
 {
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
 	unsigned int height;
+	u32 alignment;
+
+	if (INTEL_GEN(dev_priv) >= 12 &&
+	    is_semiplanar_uv_plane(fb, color_plane))
+		alignment = intel_tile_row_size(fb, color_plane);
+	else if (fb->modifier != DRM_FORMAT_MOD_LINEAR)
+		alignment = intel_tile_size(dev_priv);
+	else
+		alignment = 0;
 
-	if (fb->modifier != DRM_FORMAT_MOD_LINEAR &&
-	    fb->offsets[color_plane] % intel_tile_size(dev_priv)) {
+	if (alignment != 0 && fb->offsets[color_plane] % alignment) {
 		DRM_DEBUG_KMS("Misaligned offset 0x%08x for color plane %d\n",
 			      fb->offsets[color_plane], color_plane);
 		return -EINVAL;
@@ -2453,6 +2572,8 @@ static unsigned int intel_fb_modifier_to_tiling(u64 fb_modifier)
 		return I915_TILING_X;
 	case I915_FORMAT_MOD_Y_TILED:
 	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
 		return I915_TILING_Y;
 	default:
 		return I915_TILING_NONE;
@@ -2473,7 +2594,7 @@ static unsigned int intel_fb_modifier_to_tiling(u64 fb_modifier)
  * us a ratio of one byte in the CCS for each 8x16 pixels in the
  * main surface.
  */
-static const struct drm_format_info ccs_formats[] = {
+static const struct drm_format_info skl_ccs_formats[] = {
 	{ .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2,
 	  .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, },
 	{ .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2,
@@ -2484,6 +2605,52 @@ static const struct drm_format_info ccs_formats[] = {
 	  .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, .has_alpha = true, },
 };
 
+/*
+ * Gen-12 compression uses 4 bits of CCS data for each cache line pair in the
+ * main surface. And each 64B CCS cache line represents an area of 4x1 Y-tiles
+ * in the main surface. With 4 byte pixels and each Y-tile having dimensions of
+ * 32x32 pixels, the ratio turns out to 1B in the CCS for every 2x32 pixels in
+ * the main surface.
+ */
+static const struct drm_format_info gen12_ccs_formats[] = {
+	{ .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2,
+	  .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 1, .vsub = 1, },
+	{ .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2,
+	  .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 1, .vsub = 1, },
+	{ .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 2,
+	  .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 1, .vsub = 1, .has_alpha = true },
+	{ .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 2,
+	  .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 1, .vsub = 1, .has_alpha = true },
+	{ .format = DRM_FORMAT_YUYV, .num_planes = 2,
+	  .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 2, .vsub = 1, .is_yuv = true },
+	{ .format = DRM_FORMAT_YVYU, .num_planes = 2,
+	  .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 2, .vsub = 1, .is_yuv = true },
+	{ .format = DRM_FORMAT_UYVY, .num_planes = 2,
+	  .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 2, .vsub = 1, .is_yuv = true },
+	{ .format = DRM_FORMAT_VYUY, .num_planes = 2,
+	  .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 2, .vsub = 1, .is_yuv = true },
+	{ .format = DRM_FORMAT_NV12, .num_planes = 4,
+	  .char_per_block = { 1, 2, 1, 1 }, .block_w = { 1, 1, 4, 4 }, .block_h = { 1, 1, 1, 1 },
+	  .hsub = 2, .vsub = 2, .is_yuv = true },
+	{ .format = DRM_FORMAT_P010, .num_planes = 4,
+	  .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 },
+	  .hsub = 2, .vsub = 2, .is_yuv = true },
+	{ .format = DRM_FORMAT_P012, .num_planes = 4,
+	  .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 },
+	  .hsub = 2, .vsub = 2, .is_yuv = true },
+	{ .format = DRM_FORMAT_P016, .num_planes = 4,
+	  .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 },
+	  .hsub = 2, .vsub = 2, .is_yuv = true },
+};
+
 static const struct drm_format_info *
 lookup_format_info(const struct drm_format_info formats[],
 		   int num_formats, u32 format)
@@ -2504,8 +2671,13 @@ intel_get_format_info(const struct drm_mode_fb_cmd2 *cmd)
 	switch (cmd->modifier[0]) {
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
-		return lookup_format_info(ccs_formats,
-					  ARRAY_SIZE(ccs_formats),
+		return lookup_format_info(skl_ccs_formats,
+					  ARRAY_SIZE(skl_ccs_formats),
+					  cmd->pixel_format);
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		return lookup_format_info(gen12_ccs_formats,
+					  ARRAY_SIZE(gen12_ccs_formats),
 					  cmd->pixel_format);
 	default:
 		return NULL;
@@ -2514,10 +2686,18 @@ intel_get_format_info(const struct drm_mode_fb_cmd2 *cmd)
 
 bool is_ccs_modifier(u64 modifier)
 {
-	return modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+	return modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+	       modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
+	       modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 	       modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
 }
 
+static int gen12_ccs_aux_stride(struct drm_framebuffer *fb, int ccs_plane)
+{
+	return DIV_ROUND_UP(fb->pitches[ccs_to_main_plane(fb, ccs_plane)],
+			    512) * 64;
+}
+
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
 			      u32 pixel_format, u64 modifier)
 {
@@ -2562,8 +2742,9 @@ static u32
 intel_fb_stride_alignment(const struct drm_framebuffer *fb, int color_plane)
 {
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
+	u32 tile_width;
 
-	if (fb->modifier == DRM_FORMAT_MOD_LINEAR) {
+	if (is_surface_linear(fb, color_plane)) {
 		u32 max_stride = intel_plane_fb_max_stride(dev_priv,
 							   fb->format->format,
 							   fb->modifier);
@@ -2572,20 +2753,41 @@ intel_fb_stride_alignment(const struct drm_framebuffer *fb, int color_plane)
 		 * To make remapping with linear generally feasible
 		 * we need the stride to be page aligned.
 		 */
-		if (fb->pitches[color_plane] > max_stride)
+		if (fb->pitches[color_plane] > max_stride &&
+		    !is_ccs_modifier(fb->modifier))
 			return intel_tile_size(dev_priv);
 		else
 			return 64;
-	} else {
-		return intel_tile_width_bytes(fb, color_plane);
 	}
+
+	tile_width = intel_tile_width_bytes(fb, color_plane);
+	if (is_ccs_modifier(fb->modifier)) {
+		/*
+		 * Display WA #0531: skl,bxt,kbl,glk
+		 *
+		 * Render decompression and plane width > 3840
+		 * combined with horizontal panning requires the
+		 * plane stride to be a multiple of 4. We'll just
+		 * require the entire fb to accommodate that to avoid
+		 * potential runtime errors at plane configuration time.
+		 */
+		if (IS_GEN(dev_priv, 9) && color_plane == 0 && fb->width > 3840)
+			tile_width *= 4;
+		/*
+		 * The main surface pitch must be padded to a multiple of four
+		 * tile widths.
+		 */
+		else if (INTEL_GEN(dev_priv) >= 12)
+			tile_width *= 4;
+	}
+	return tile_width;
 }
 
 bool intel_plane_can_remap(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int i;
 
 	/* We don't want to deal with remapping with cursors */
@@ -2623,16 +2825,16 @@ bool intel_plane_can_remap(const struct intel_plane_state *plane_state)
 
 static bool intel_plane_needs_remap(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	u32 stride, max_stride;
 
 	/*
 	 * No remapping for invisible planes since we don't have
 	 * an actual source viewport to remap.
 	 */
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return false;
 
 	if (!intel_plane_can_remap(plane_state))
@@ -2649,12 +2851,171 @@ static bool intel_plane_needs_remap(const struct intel_plane_state *plane_state)
 	return stride > max_stride;
 }
 
+static void
+intel_fb_plane_get_subsampling(int *hsub, int *vsub,
+			       const struct drm_framebuffer *fb,
+			       int color_plane)
+{
+	int main_plane;
+
+	if (color_plane == 0) {
+		*hsub = 1;
+		*vsub = 1;
+
+		return;
+	}
+
+	/*
+	 * TODO: Deduct the subsampling from the char block for all CCS
+	 * formats and planes.
+	 */
+	if (!is_gen12_ccs_plane(fb, color_plane)) {
+		*hsub = fb->format->hsub;
+		*vsub = fb->format->vsub;
+
+		return;
+	}
+
+	main_plane = ccs_to_main_plane(fb, color_plane);
+	*hsub = drm_format_info_block_width(fb->format, color_plane) /
+		drm_format_info_block_width(fb->format, main_plane);
+
+	/*
+	 * The min stride check in the core framebuffer_check() function
+	 * assumes that format->hsub applies to every plane except for the
+	 * first plane. That's incorrect for the CCS AUX plane of the first
+	 * plane, but for the above check to pass we must define the block
+	 * width with that subsampling applied to it. Adjust the width here
+	 * accordingly, so we can calculate the actual subsampling factor.
+	 */
+	if (main_plane == 0)
+		*hsub *= fb->format->hsub;
+
+	*vsub = 32;
+}
+static int
+intel_fb_check_ccs_xy(struct drm_framebuffer *fb, int ccs_plane, int x, int y)
+{
+	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+	int main_plane;
+	int hsub, vsub;
+	int tile_width, tile_height;
+	int ccs_x, ccs_y;
+	int main_x, main_y;
+
+	if (!is_ccs_plane(fb, ccs_plane))
+		return 0;
+
+	intel_tile_dims(fb, ccs_plane, &tile_width, &tile_height);
+	intel_fb_plane_get_subsampling(&hsub, &vsub, fb, ccs_plane);
+
+	tile_width *= hsub;
+	tile_height *= vsub;
+
+	ccs_x = (x * hsub) % tile_width;
+	ccs_y = (y * vsub) % tile_height;
+
+	main_plane = ccs_to_main_plane(fb, ccs_plane);
+	main_x = intel_fb->normal[main_plane].x % tile_width;
+	main_y = intel_fb->normal[main_plane].y % tile_height;
+
+	/*
+	 * CCS doesn't have its own x/y offset register, so the intra CCS tile
+	 * x/y offsets must match between CCS and the main surface.
+	 */
+	if (main_x != ccs_x || main_y != ccs_y) {
+		DRM_DEBUG_KMS("Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n",
+			      main_x, main_y,
+			      ccs_x, ccs_y,
+			      intel_fb->normal[main_plane].x,
+			      intel_fb->normal[main_plane].y,
+			      x, y);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+intel_fb_plane_dims(int *w, int *h, struct drm_framebuffer *fb, int color_plane)
+{
+	int main_plane = is_ccs_plane(fb, color_plane) ?
+			 ccs_to_main_plane(fb, color_plane) : 0;
+	int main_hsub, main_vsub;
+	int hsub, vsub;
+
+	intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, fb, main_plane);
+	intel_fb_plane_get_subsampling(&hsub, &vsub, fb, color_plane);
+	*w = fb->width / main_hsub / hsub;
+	*h = fb->height / main_vsub / vsub;
+}
+
+/*
+ * Setup the rotated view for an FB plane and return the size the GTT mapping
+ * requires for this view.
+ */
+static u32
+setup_fb_rotation(int plane, const struct intel_remapped_plane_info *plane_info,
+		  u32 gtt_offset_rotated, int x, int y,
+		  unsigned int width, unsigned int height,
+		  unsigned int tile_size,
+		  unsigned int tile_width, unsigned int tile_height,
+		  struct drm_framebuffer *fb)
+{
+	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+	struct intel_rotation_info *rot_info = &intel_fb->rot_info;
+	unsigned int pitch_tiles;
+	struct drm_rect r;
+
+	/* Y or Yf modifiers required for 90/270 rotation */
+	if (fb->modifier != I915_FORMAT_MOD_Y_TILED &&
+	    fb->modifier != I915_FORMAT_MOD_Yf_TILED)
+		return 0;
+
+	if (WARN_ON(plane >= ARRAY_SIZE(rot_info->plane)))
+		return 0;
+
+	rot_info->plane[plane] = *plane_info;
+
+	intel_fb->rotated[plane].pitch = plane_info->height * tile_height;
+
+	/* rotate the x/y offsets to match the GTT view */
+	drm_rect_init(&r, x, y, width, height);
+	drm_rect_rotate(&r,
+			plane_info->width * tile_width,
+			plane_info->height * tile_height,
+			DRM_MODE_ROTATE_270);
+	x = r.x1;
+	y = r.y1;
+
+	/* rotate the tile dimensions to match the GTT view */
+	pitch_tiles = intel_fb->rotated[plane].pitch / tile_height;
+	swap(tile_width, tile_height);
+
+	/*
+	 * We only keep the x/y offsets, so push all of the
+	 * gtt offset into the x/y offsets.
+	 */
+	intel_adjust_tile_offset(&x, &y,
+				 tile_width, tile_height,
+				 tile_size, pitch_tiles,
+				 gtt_offset_rotated * tile_size, 0);
+
+	/*
+	 * First pixel of the framebuffer from
+	 * the start of the rotated gtt mapping.
+	 */
+	intel_fb->rotated[plane].x = x;
+	intel_fb->rotated[plane].y = y;
+
+	return plane_info->width * plane_info->height;
+}
+
 static int
 intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		   struct drm_framebuffer *fb)
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
-	struct intel_rotation_info *rot_info = &intel_fb->rot_info;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	u32 gtt_offset_rotated = 0;
 	unsigned int max_size = 0;
@@ -2669,8 +3030,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		int ret;
 
 		cpp = fb->format->cpp[i];
-		width = drm_framebuffer_plane_width(fb->width, fb, i);
-		height = drm_framebuffer_plane_height(fb->height, fb, i);
+		intel_fb_plane_dims(&width, &height, fb, i);
 
 		ret = intel_fb_offset_to_xy(&x, &y, fb, i);
 		if (ret) {
@@ -2679,36 +3039,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 			return ret;
 		}
 
-		if (is_ccs_modifier(fb->modifier) && i == 1) {
-			int hsub = fb->format->hsub;
-			int vsub = fb->format->vsub;
-			int tile_width, tile_height;
-			int main_x, main_y;
-			int ccs_x, ccs_y;
-
-			intel_tile_dims(fb, i, &tile_width, &tile_height);
-			tile_width *= hsub;
-			tile_height *= vsub;
-
-			ccs_x = (x * hsub) % tile_width;
-			ccs_y = (y * vsub) % tile_height;
-			main_x = intel_fb->normal[0].x % tile_width;
-			main_y = intel_fb->normal[0].y % tile_height;
-
-			/*
-			 * CCS doesn't have its own x/y offset register, so the intra CCS tile
-			 * x/y offsets must match between CCS and the main surface.
-			 */
-			if (main_x != ccs_x || main_y != ccs_y) {
-				DRM_DEBUG_KMS("Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n",
-					      main_x, main_y,
-					      ccs_x, ccs_y,
-					      intel_fb->normal[0].x,
-					      intel_fb->normal[0].y,
-					      x, y);
-				return -EINVAL;
-			}
-		}
+		ret = intel_fb_check_ccs_xy(fb, i, x, y);
+		if (ret)
+			return ret;
 
 		/*
 		 * The fence (if used) is aligned to the start of the object
@@ -2739,23 +3072,21 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 						      tile_size);
 		offset /= tile_size;
 
-		if (!is_surface_linear(fb->modifier, i)) {
+		if (!is_surface_linear(fb, i)) {
+			struct intel_remapped_plane_info plane_info;
 			unsigned int tile_width, tile_height;
-			unsigned int pitch_tiles;
-			struct drm_rect r;
 
 			intel_tile_dims(fb, i, &tile_width, &tile_height);
 
-			rot_info->plane[i].offset = offset;
-			rot_info->plane[i].stride = DIV_ROUND_UP(fb->pitches[i], tile_width * cpp);
-			rot_info->plane[i].width = DIV_ROUND_UP(x + width, tile_width);
-			rot_info->plane[i].height = DIV_ROUND_UP(y + height, tile_height);
-
-			intel_fb->rotated[i].pitch =
-				rot_info->plane[i].height * tile_height;
+			plane_info.offset = offset;
+			plane_info.stride = DIV_ROUND_UP(fb->pitches[i],
+							 tile_width * cpp);
+			plane_info.width = DIV_ROUND_UP(x + width, tile_width);
+			plane_info.height = DIV_ROUND_UP(y + height,
+							 tile_height);
 
 			/* how many tiles does this plane need */
-			size = rot_info->plane[i].stride * rot_info->plane[i].height;
+			size = plane_info.stride * plane_info.height;
 			/*
 			 * If the plane isn't horizontally tile aligned,
 			 * we need one more tile.
@@ -2763,36 +3094,13 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 			if (x != 0)
 				size++;
 
-			/* rotate the x/y offsets to match the GTT view */
-			drm_rect_init(&r, x, y, width, height);
-			drm_rect_rotate(&r,
-					rot_info->plane[i].width * tile_width,
-					rot_info->plane[i].height * tile_height,
-					DRM_MODE_ROTATE_270);
-			x = r.x1;
-			y = r.y1;
-
-			/* rotate the tile dimensions to match the GTT view */
-			pitch_tiles = intel_fb->rotated[i].pitch / tile_height;
-			swap(tile_width, tile_height);
-
-			/*
-			 * We only keep the x/y offsets, so push all of the
-			 * gtt offset into the x/y offsets.
-			 */
-			intel_adjust_tile_offset(&x, &y,
-						 tile_width, tile_height,
-						 tile_size, pitch_tiles,
-						 gtt_offset_rotated * tile_size, 0);
-
-			gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height;
-
-			/*
-			 * First pixel of the framebuffer from
-			 * the start of the rotated gtt mapping.
-			 */
-			intel_fb->rotated[i].x = x;
-			intel_fb->rotated[i].y = y;
+			gtt_offset_rotated +=
+				setup_fb_rotation(i, &plane_info,
+						  gtt_offset_rotated,
+						  x, y, width, height,
+						  tile_size,
+						  tile_width, tile_height,
+						  fb);
 		} else {
 			size = DIV_ROUND_UP((y + height) * fb->pitches[i] +
 					    x * cpp, tile_size);
@@ -2815,11 +3123,11 @@ static void
 intel_plane_remap_gtt(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	struct drm_framebuffer *fb = plane_state->base.fb;
+		to_i915(plane_state->uapi.plane->dev);
+	struct drm_framebuffer *fb = plane_state->hw.fb;
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 	struct intel_rotation_info *info = &plane_state->view.rotated;
-	unsigned int rotation = plane_state->base.rotation;
+	unsigned int rotation = plane_state->hw.rotation;
 	int i, num_planes = fb->format->num_planes;
 	unsigned int tile_size = intel_tile_size(dev_priv);
 	unsigned int src_x, src_y;
@@ -2830,20 +3138,20 @@ intel_plane_remap_gtt(struct intel_plane_state *plane_state)
 	plane_state->view.type = drm_rotation_90_or_270(rotation) ?
 		I915_GGTT_VIEW_ROTATED : I915_GGTT_VIEW_REMAPPED;
 
-	src_x = plane_state->base.src.x1 >> 16;
-	src_y = plane_state->base.src.y1 >> 16;
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	src_x = plane_state->uapi.src.x1 >> 16;
+	src_y = plane_state->uapi.src.y1 >> 16;
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 
 	WARN_ON(is_ccs_modifier(fb->modifier));
 
 	/* Make src coordinates relative to the viewport */
-	drm_rect_translate(&plane_state->base.src,
+	drm_rect_translate(&plane_state->uapi.src,
 			   -(src_x << 16), -(src_y << 16));
 
 	/* Rotate src coordinates to match rotated GTT view */
 	if (drm_rotation_90_or_270(rotation))
-		drm_rect_rotate(&plane_state->base.src,
+		drm_rect_rotate(&plane_state->uapi.src,
 				src_w << 16, src_h << 16,
 				DRM_MODE_ROTATE_270);
 
@@ -2876,6 +3184,7 @@ intel_plane_remap_gtt(struct intel_plane_state *plane_state)
 						      DRM_MODE_ROTATE_0, tile_size);
 		offset /= tile_size;
 
+		WARN_ON(i >= ARRAY_SIZE(info->plane));
 		info->plane[i].offset = offset;
 		info->plane[i].stride = DIV_ROUND_UP(fb->pitches[i],
 						     tile_width * cpp);
@@ -2925,8 +3234,8 @@ static int
 intel_plane_compute_gtt(struct intel_plane_state *plane_state)
 {
 	const struct intel_framebuffer *fb =
-		to_intel_framebuffer(plane_state->base.fb);
-	unsigned int rotation = plane_state->base.rotation;
+		to_intel_framebuffer(plane_state->hw.fb);
+	unsigned int rotation = plane_state->hw.rotation;
 	int i, num_planes;
 
 	if (!fb)
@@ -2963,7 +3272,7 @@ intel_plane_compute_gtt(struct intel_plane_state *plane_state)
 
 	/* Rotate src coordinates to match rotated GTT view */
 	if (drm_rotation_90_or_270(rotation))
-		drm_rect_rotate(&plane_state->base.src,
+		drm_rect_rotate(&plane_state->uapi.src,
 				fb->base.width << 16, fb->base.height << 16,
 				DRM_MODE_ROTATE_270);
 
@@ -2975,6 +3284,8 @@ static int i9xx_format_to_fourcc(int format)
 	switch (format) {
 	case DISPPLANE_8BPP:
 		return DRM_FORMAT_C8;
+	case DISPPLANE_BGRA555:
+		return DRM_FORMAT_ARGB1555;
 	case DISPPLANE_BGRX555:
 		return DRM_FORMAT_XRGB1555;
 	case DISPPLANE_BGRX565:
@@ -2984,10 +3295,18 @@ static int i9xx_format_to_fourcc(int format)
 		return DRM_FORMAT_XRGB8888;
 	case DISPPLANE_RGBX888:
 		return DRM_FORMAT_XBGR8888;
+	case DISPPLANE_BGRA888:
+		return DRM_FORMAT_ARGB8888;
+	case DISPPLANE_RGBA888:
+		return DRM_FORMAT_ABGR8888;
 	case DISPPLANE_BGRX101010:
 		return DRM_FORMAT_XRGB2101010;
 	case DISPPLANE_RGBX101010:
 		return DRM_FORMAT_XBGR2101010;
+	case DISPPLANE_BGRA101010:
+		return DRM_FORMAT_ARGB2101010;
+	case DISPPLANE_RGBA101010:
+		return DRM_FORMAT_ABGR2101010;
 	case DISPPLANE_RGBX161616:
 		return DRM_FORMAT_XBGR16161616F;
 	}
@@ -3032,10 +3351,17 @@ int skl_format_to_fourcc(int format, bool rgb_order, bool alpha)
 				return DRM_FORMAT_XRGB8888;
 		}
 	case PLANE_CTL_FORMAT_XRGB_2101010:
-		if (rgb_order)
-			return DRM_FORMAT_XBGR2101010;
-		else
-			return DRM_FORMAT_XRGB2101010;
+		if (rgb_order) {
+			if (alpha)
+				return DRM_FORMAT_ABGR2101010;
+			else
+				return DRM_FORMAT_XBGR2101010;
+		} else {
+			if (alpha)
+				return DRM_FORMAT_ARGB2101010;
+			else
+				return DRM_FORMAT_XRGB2101010;
+		}
 	case PLANE_CTL_FORMAT_XRGB_16161616F:
 		if (rgb_order) {
 			if (alpha)
@@ -3131,19 +3457,19 @@ intel_set_plane_visible(struct intel_crtc_state *crtc_state,
 			struct intel_plane_state *plane_state,
 			bool visible)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 
-	plane_state->base.visible = visible;
+	plane_state->uapi.visible = visible;
 
 	if (visible)
-		crtc_state->base.plane_mask |= drm_plane_mask(&plane->base);
+		crtc_state->uapi.plane_mask |= drm_plane_mask(&plane->base);
 	else
-		crtc_state->base.plane_mask &= ~drm_plane_mask(&plane->base);
+		crtc_state->uapi.plane_mask &= ~drm_plane_mask(&plane->base);
 }
 
 static void fixup_active_planes(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	struct drm_plane *plane;
 
 	/*
@@ -3154,13 +3480,14 @@ static void fixup_active_planes(struct intel_crtc_state *crtc_state)
 	crtc_state->active_planes = 0;
 
 	drm_for_each_plane_mask(plane, &dev_priv->drm,
-				crtc_state->base.plane_mask)
+				crtc_state->uapi.plane_mask)
 		crtc_state->active_planes |= BIT(to_intel_plane(plane)->id);
 }
 
 static void intel_plane_disable_noatomic(struct intel_crtc *crtc,
 					 struct intel_plane *plane)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_crtc_state *crtc_state =
 		to_intel_crtc_state(crtc->base.state);
 	struct intel_plane_state *plane_state =
@@ -3176,7 +3503,27 @@ static void intel_plane_disable_noatomic(struct intel_crtc *crtc,
 	crtc_state->min_cdclk[plane->id] = 0;
 
 	if (plane->id == PLANE_PRIMARY)
-		intel_pre_disable_primary_noatomic(&crtc->base);
+		hsw_disable_ips(crtc_state);
+
+	/*
+	 * Vblank time updates from the shadow to live plane control register
+	 * are blocked if the memory self-refresh mode is active at that
+	 * moment. So to make sure the plane gets truly disabled, disable
+	 * first the self-refresh mode. The self-refresh enable bit in turn
+	 * will be checked/applied by the HW only at the next frame start
+	 * event which is after the vblank start event, so we need to have a
+	 * wait-for-vblank between disabling the plane and the pipe.
+	 */
+	if (HAS_GMCH(dev_priv) &&
+	    intel_set_memory_cxsr(dev_priv, false))
+		intel_wait_for_vblank(dev_priv, crtc->pipe);
+
+	/*
+	 * Gen2 reports pipe underruns whenever all planes are disabled.
+	 * So disable underrun reporting before all the planes get disabled.
+	 */
+	if (IS_GEN(dev_priv, 2) && !crtc_state->active_planes)
+		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
 
 	intel_disable_plane(plane, crtc_state);
 }
@@ -3229,7 +3576,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 			continue;
 
 		if (intel_plane_ggtt_offset(state) == plane_config->base) {
-			fb = state->base.fb;
+			fb = state->hw.fb;
 			drm_framebuffer_get(fb);
 			goto valid_fb;
 		}
@@ -3247,11 +3594,11 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	return;
 
 valid_fb:
-	intel_state->base.rotation = plane_config->rotation;
+	intel_state->hw.rotation = plane_config->rotation;
 	intel_fill_fb_ggtt_view(&intel_state->view, fb,
-				intel_state->base.rotation);
+				intel_state->hw.rotation);
 	intel_state->color_plane[0].stride =
-		intel_fb_pitch(fb, 0, intel_state->base.rotation);
+		intel_fb_pitch(fb, 0, intel_state->hw.rotation);
 
 	intel_state->vma =
 		intel_pin_and_fence_fb_obj(fb,
@@ -3279,14 +3626,15 @@ valid_fb:
 	plane_state->crtc_w = fb->width;
 	plane_state->crtc_h = fb->height;
 
-	intel_state->base.src = drm_plane_state_src(plane_state);
-	intel_state->base.dst = drm_plane_state_dest(plane_state);
+	intel_state->uapi.src = drm_plane_state_src(plane_state);
+	intel_state->uapi.dst = drm_plane_state_dest(plane_state);
 
 	if (plane_config->tiling)
 		dev_priv->preserve_bios_swizzle = true;
 
 	plane_state->fb = fb;
 	plane_state->crtc = &intel_crtc->base;
+	intel_plane_copy_uapi_to_hw_state(intel_state, intel_state);
 
 	atomic_or(to_intel_plane(primary)->frontbuffer_bit,
 		  &to_intel_frontbuffer(fb)->bits);
@@ -3317,6 +3665,7 @@ static int skl_max_plane_width(const struct drm_framebuffer *fb,
 			return 5120;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
 		/* FIXME AUX plane? */
 	case I915_FORMAT_MOD_Y_TILED:
 	case I915_FORMAT_MOD_Yf_TILED:
@@ -3375,17 +3724,20 @@ static int icl_max_plane_height(void)
 	return 4320;
 }
 
-static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state,
-					   int main_x, int main_y, u32 main_offset)
-{
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	int hsub = fb->format->hsub;
-	int vsub = fb->format->vsub;
-	int aux_x = plane_state->color_plane[1].x;
-	int aux_y = plane_state->color_plane[1].y;
-	u32 aux_offset = plane_state->color_plane[1].offset;
-	u32 alignment = intel_surf_alignment(fb, 1);
-
+static bool
+skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state,
+			       int main_x, int main_y, u32 main_offset,
+			       int ccs_plane)
+{
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	int aux_x = plane_state->color_plane[ccs_plane].x;
+	int aux_y = plane_state->color_plane[ccs_plane].y;
+	u32 aux_offset = plane_state->color_plane[ccs_plane].offset;
+	u32 alignment = intel_surf_alignment(fb, ccs_plane);
+	int hsub;
+	int vsub;
+
+	intel_fb_plane_get_subsampling(&hsub, &vsub, fb, ccs_plane);
 	while (aux_offset >= main_offset && aux_y <= main_y) {
 		int x, y;
 
@@ -3397,8 +3749,12 @@ static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state
 
 		x = aux_x / hsub;
 		y = aux_y / vsub;
-		aux_offset = intel_plane_adjust_aligned_offset(&x, &y, plane_state, 1,
-							       aux_offset, aux_offset - alignment);
+		aux_offset = intel_plane_adjust_aligned_offset(&x, &y,
+							       plane_state,
+							       ccs_plane,
+							       aux_offset,
+							       aux_offset -
+								alignment);
 		aux_x = x * hsub + aux_x % hsub;
 		aux_y = y * vsub + aux_y % vsub;
 	}
@@ -3406,25 +3762,28 @@ static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state
 	if (aux_x != main_x || aux_y != main_y)
 		return false;
 
-	plane_state->color_plane[1].offset = aux_offset;
-	plane_state->color_plane[1].x = aux_x;
-	plane_state->color_plane[1].y = aux_y;
+	plane_state->color_plane[ccs_plane].offset = aux_offset;
+	plane_state->color_plane[ccs_plane].x = aux_x;
+	plane_state->color_plane[ccs_plane].y = aux_y;
 
 	return true;
 }
 
 static int skl_check_main_surface(struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
-	int x = plane_state->base.src.x1 >> 16;
-	int y = plane_state->base.src.y1 >> 16;
-	int w = drm_rect_width(&plane_state->base.src) >> 16;
-	int h = drm_rect_height(&plane_state->base.src) >> 16;
+	struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
+	int x = plane_state->uapi.src.x1 >> 16;
+	int y = plane_state->uapi.src.y1 >> 16;
+	int w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	int h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	int max_width;
 	int max_height;
-	u32 alignment, offset, aux_offset = plane_state->color_plane[1].offset;
+	u32 alignment;
+	u32 offset;
+	int aux_plane = intel_main_to_aux_plane(fb, 0);
+	u32 aux_offset = plane_state->color_plane[aux_plane].offset;
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		max_width = icl_max_plane_width(fb, 0, rotation);
@@ -3447,6 +3806,8 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	intel_add_fb_offsets(&x, &y, plane_state, 0);
 	offset = intel_plane_compute_aligned_offset(&x, &y, plane_state, 0);
 	alignment = intel_surf_alignment(fb, 0);
+	if (WARN_ON(alignment && !is_power_of_2(alignment)))
+		return -EINVAL;
 
 	/*
 	 * AUX surface offset is specified as the distance from the
@@ -3482,7 +3843,8 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	 * they match with the main surface x/y offsets.
 	 */
 	if (is_ccs_modifier(fb->modifier)) {
-		while (!skl_check_main_ccs_coordinates(plane_state, x, y, offset)) {
+		while (!skl_check_main_ccs_coordinates(plane_state, x, y,
+						       offset, aux_plane)) {
 			if (offset == 0)
 				break;
 
@@ -3490,7 +3852,8 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 								   offset, offset - alignment);
 		}
 
-		if (x != plane_state->color_plane[1].x || y != plane_state->color_plane[1].y) {
+		if (x != plane_state->color_plane[aux_plane].x ||
+		    y != plane_state->color_plane[aux_plane].y) {
 			DRM_DEBUG_KMS("Unable to find suitable display surface offset due to CCS\n");
 			return -EINVAL;
 		}
@@ -3504,7 +3867,7 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.
 	 */
-	drm_rect_translate_to(&plane_state->base.src,
+	drm_rect_translate_to(&plane_state->uapi.src,
 			      x << 16, y << 16);
 
 	return 0;
@@ -3512,18 +3875,20 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 
 static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
-	int max_width = skl_max_plane_width(fb, 1, rotation);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
+	int uv_plane = 1;
+	int max_width = skl_max_plane_width(fb, uv_plane, rotation);
 	int max_height = 4096;
-	int x = plane_state->base.src.x1 >> 17;
-	int y = plane_state->base.src.y1 >> 17;
-	int w = drm_rect_width(&plane_state->base.src) >> 17;
-	int h = drm_rect_height(&plane_state->base.src) >> 17;
+	int x = plane_state->uapi.src.x1 >> 17;
+	int y = plane_state->uapi.src.y1 >> 17;
+	int w = drm_rect_width(&plane_state->uapi.src) >> 17;
+	int h = drm_rect_height(&plane_state->uapi.src) >> 17;
 	u32 offset;
 
-	intel_add_fb_offsets(&x, &y, plane_state, 1);
-	offset = intel_plane_compute_aligned_offset(&x, &y, plane_state, 1);
+	intel_add_fb_offsets(&x, &y, plane_state, uv_plane);
+	offset = intel_plane_compute_aligned_offset(&x, &y,
+						    plane_state, uv_plane);
 
 	/* FIXME not quite sure how/if these apply to the chroma plane */
 	if (w > max_width || h > max_height) {
@@ -3532,62 +3897,126 @@ static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state)
 		return -EINVAL;
 	}
 
-	plane_state->color_plane[1].offset = offset;
-	plane_state->color_plane[1].x = x;
-	plane_state->color_plane[1].y = y;
+	if (is_ccs_modifier(fb->modifier)) {
+		int ccs_plane = main_to_ccs_plane(fb, uv_plane);
+		int aux_offset = plane_state->color_plane[ccs_plane].offset;
+		int alignment = intel_surf_alignment(fb, uv_plane);
+
+		if (offset > aux_offset)
+			offset = intel_plane_adjust_aligned_offset(&x, &y,
+								   plane_state,
+								   uv_plane,
+								   offset,
+								   aux_offset & ~(alignment - 1));
+
+		while (!skl_check_main_ccs_coordinates(plane_state, x, y,
+						       offset, ccs_plane)) {
+			if (offset == 0)
+				break;
+
+			offset = intel_plane_adjust_aligned_offset(&x, &y,
+								   plane_state,
+								   uv_plane,
+								   offset, offset - alignment);
+		}
+
+		if (x != plane_state->color_plane[ccs_plane].x ||
+		    y != plane_state->color_plane[ccs_plane].y) {
+			DRM_DEBUG_KMS("Unable to find suitable display surface offset due to CCS\n");
+			return -EINVAL;
+		}
+	}
+
+	plane_state->color_plane[uv_plane].offset = offset;
+	plane_state->color_plane[uv_plane].x = x;
+	plane_state->color_plane[uv_plane].y = y;
 
 	return 0;
 }
 
 static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	int src_x = plane_state->base.src.x1 >> 16;
-	int src_y = plane_state->base.src.y1 >> 16;
-	int hsub = fb->format->hsub;
-	int vsub = fb->format->vsub;
-	int x = src_x / hsub;
-	int y = src_y / vsub;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	int src_x = plane_state->uapi.src.x1 >> 16;
+	int src_y = plane_state->uapi.src.y1 >> 16;
 	u32 offset;
+	int ccs_plane;
+
+	for (ccs_plane = 0; ccs_plane < fb->format->num_planes; ccs_plane++) {
+		int main_hsub, main_vsub;
+		int hsub, vsub;
+		int x, y;
+
+		if (!is_ccs_plane(fb, ccs_plane))
+			continue;
+
+		intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, fb,
+					       ccs_to_main_plane(fb, ccs_plane));
+		intel_fb_plane_get_subsampling(&hsub, &vsub, fb, ccs_plane);
+
+		hsub *= main_hsub;
+		vsub *= main_vsub;
+		x = src_x / hsub;
+		y = src_y / vsub;
 
-	intel_add_fb_offsets(&x, &y, plane_state, 1);
-	offset = intel_plane_compute_aligned_offset(&x, &y, plane_state, 1);
+		intel_add_fb_offsets(&x, &y, plane_state, ccs_plane);
 
-	plane_state->color_plane[1].offset = offset;
-	plane_state->color_plane[1].x = x * hsub + src_x % hsub;
-	plane_state->color_plane[1].y = y * vsub + src_y % vsub;
+		offset = intel_plane_compute_aligned_offset(&x, &y,
+							    plane_state,
+							    ccs_plane);
+
+		plane_state->color_plane[ccs_plane].offset = offset;
+		plane_state->color_plane[ccs_plane].x = (x * hsub +
+							 src_x % hsub) /
+							main_hsub;
+		plane_state->color_plane[ccs_plane].y = (y * vsub +
+							 src_y % vsub) /
+							main_vsub;
+	}
 
 	return 0;
 }
 
 int skl_check_plane_surface(struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
+	bool needs_aux = false;
 
 	ret = intel_plane_compute_gtt(plane_state);
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	/*
-	 * Handle the AUX surface first since
-	 * the main surface setup depends on it.
+	 * Handle the AUX surface first since the main surface setup depends on
+	 * it.
 	 */
-	if (drm_format_info_is_yuv_semiplanar(fb->format)) {
-		ret = skl_check_nv12_aux_surface(plane_state);
+	if (is_ccs_modifier(fb->modifier)) {
+		needs_aux = true;
+		ret = skl_check_ccs_aux_surface(plane_state);
 		if (ret)
 			return ret;
-	} else if (is_ccs_modifier(fb->modifier)) {
-		ret = skl_check_ccs_aux_surface(plane_state);
+	}
+
+	if (intel_format_info_is_yuv_semiplanar(fb->format,
+						fb->modifier)) {
+		needs_aux = true;
+		ret = skl_check_nv12_aux_surface(plane_state);
 		if (ret)
 			return ret;
-	} else {
-		plane_state->color_plane[1].offset = ~0xfff;
-		plane_state->color_plane[1].x = 0;
-		plane_state->color_plane[1].y = 0;
+	}
+
+	if (!needs_aux) {
+		int i;
+
+		for (i = 1; i < fb->format->num_planes; i++) {
+			plane_state->color_plane[i].offset = ~0xfff;
+			plane_state->color_plane[i].x = 0;
+			plane_state->color_plane[i].y = 0;
+		}
 	}
 
 	ret = skl_check_main_surface(plane_state);
@@ -3601,7 +4030,7 @@ static void i9xx_plane_ratio(const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state,
 			     unsigned int *num, unsigned int *den)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	/*
@@ -3673,7 +4102,7 @@ i9xx_plane_max_stride(struct intel_plane *plane,
 
 static u32 i9xx_plane_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 dspcntr = 0;
 
@@ -3693,9 +4122,9 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	u32 dspcntr;
 
 	dspcntr = DISPLAY_PLANE_ENABLE;
@@ -3711,6 +4140,9 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XRGB1555:
 		dspcntr |= DISPPLANE_BGRX555;
 		break;
+	case DRM_FORMAT_ARGB1555:
+		dspcntr |= DISPPLANE_BGRA555;
+		break;
 	case DRM_FORMAT_RGB565:
 		dspcntr |= DISPPLANE_BGRX565;
 		break;
@@ -3720,12 +4152,24 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XBGR8888:
 		dspcntr |= DISPPLANE_RGBX888;
 		break;
+	case DRM_FORMAT_ARGB8888:
+		dspcntr |= DISPPLANE_BGRA888;
+		break;
+	case DRM_FORMAT_ABGR8888:
+		dspcntr |= DISPPLANE_RGBA888;
+		break;
 	case DRM_FORMAT_XRGB2101010:
 		dspcntr |= DISPPLANE_BGRX101010;
 		break;
 	case DRM_FORMAT_XBGR2101010:
 		dspcntr |= DISPPLANE_RGBX101010;
 		break;
+	case DRM_FORMAT_ARGB2101010:
+		dspcntr |= DISPPLANE_BGRA101010;
+		break;
+	case DRM_FORMAT_ABGR2101010:
+		dspcntr |= DISPPLANE_RGBA101010;
+		break;
 	case DRM_FORMAT_XBGR16161616F:
 		dspcntr |= DISPPLANE_RGBX161616;
 		break;
@@ -3750,8 +4194,8 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int src_x, src_y, src_w;
 	u32 offset;
 	int ret;
@@ -3760,12 +4204,12 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	src_x = plane_state->base.src.x1 >> 16;
-	src_y = plane_state->base.src.y1 >> 16;
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	src_x = plane_state->uapi.src.x1 >> 16;
+	src_y = plane_state->uapi.src.y1 >> 16;
 
 	/* Undocumented hardware limit on i965/g4x/vlv/chv */
 	if (HAS_GMCH(dev_priv) && fb->format->cpp[0] == 8 && src_w > 2048)
@@ -3783,14 +4227,14 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.
 	 */
-	drm_rect_translate_to(&plane_state->base.src,
+	drm_rect_translate_to(&plane_state->uapi.src,
 			      src_x << 16, src_y << 16);
 
 	/* HSW/BDW do this automagically in hardware */
 	if (!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv)) {
-		unsigned int rotation = plane_state->base.rotation;
-		int src_w = drm_rect_width(&plane_state->base.src) >> 16;
-		int src_h = drm_rect_height(&plane_state->base.src) >> 16;
+		unsigned int rotation = plane_state->hw.rotation;
+		int src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+		int src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 
 		if (rotation & DRM_MODE_ROTATE_180) {
 			src_x += src_w - 1;
@@ -3827,15 +4271,15 @@ static int
 i9xx_plane_check(struct intel_crtc_state *crtc_state,
 		 struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	int ret;
 
 	ret = chv_plane_check_rotation(plane_state);
 	if (ret)
 		return ret;
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  i9xx_plane_has_windowing(plane),
@@ -3847,7 +4291,7 @@ i9xx_plane_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = intel_plane_check_src_coordinates(plane_state);
@@ -3868,10 +4312,10 @@ static void i9xx_update_plane(struct intel_plane *plane,
 	u32 linear_offset;
 	int x = plane_state->color_plane[0].x;
 	int y = plane_state->color_plane[0].y;
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	int crtc_w = drm_rect_width(&plane_state->base.dst);
-	int crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	int crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	int crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	unsigned long irqflags;
 	u32 dspaddr_offset;
 	u32 dspcntr;
@@ -4011,7 +4455,7 @@ static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
  */
 static void skl_detach_scalers(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	const struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 	int i;
@@ -4030,7 +4474,7 @@ static unsigned int skl_plane_stride_mult(const struct drm_framebuffer *fb,
 	 * The stride is either expressed as a multiple of 64 bytes chunks for
 	 * linear buffers or in number of tiles for tiled buffers.
 	 */
-	if (fb->modifier == DRM_FORMAT_MOD_LINEAR)
+	if (is_surface_linear(fb, color_plane))
 		return 64;
 	else if (drm_rotation_90_or_270(rotation))
 		return intel_tile_height(fb, color_plane);
@@ -4041,8 +4485,8 @@ static unsigned int skl_plane_stride_mult(const struct drm_framebuffer *fb,
 u32 skl_plane_stride(const struct intel_plane_state *plane_state,
 		     int color_plane)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	u32 stride = plane_state->color_plane[color_plane].stride;
 
 	if (color_plane >= fb->format->num_planes)
@@ -4065,8 +4509,10 @@ static u32 skl_plane_ctl_format(u32 pixel_format)
 	case DRM_FORMAT_ARGB8888:
 		return PLANE_CTL_FORMAT_XRGB_8888;
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ABGR2101010:
 		return PLANE_CTL_FORMAT_XRGB_2101010 | PLANE_CTL_ORDER_RGBX;
 	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010:
 		return PLANE_CTL_FORMAT_XRGB_2101010;
 	case DRM_FORMAT_XBGR16161616F:
 	case DRM_FORMAT_ABGR16161616F:
@@ -4111,10 +4557,10 @@ static u32 skl_plane_ctl_format(u32 pixel_format)
 
 static u32 skl_plane_ctl_alpha(const struct intel_plane_state *plane_state)
 {
-	if (!plane_state->base.fb->format->has_alpha)
+	if (!plane_state->hw.fb->format->has_alpha)
 		return PLANE_CTL_ALPHA_DISABLE;
 
-	switch (plane_state->base.pixel_blend_mode) {
+	switch (plane_state->hw.pixel_blend_mode) {
 	case DRM_MODE_BLEND_PIXEL_NONE:
 		return PLANE_CTL_ALPHA_DISABLE;
 	case DRM_MODE_BLEND_PREMULTI:
@@ -4122,17 +4568,17 @@ static u32 skl_plane_ctl_alpha(const struct intel_plane_state *plane_state)
 	case DRM_MODE_BLEND_COVERAGE:
 		return PLANE_CTL_ALPHA_HW_PREMULTIPLY;
 	default:
-		MISSING_CASE(plane_state->base.pixel_blend_mode);
+		MISSING_CASE(plane_state->hw.pixel_blend_mode);
 		return PLANE_CTL_ALPHA_DISABLE;
 	}
 }
 
 static u32 glk_plane_color_ctl_alpha(const struct intel_plane_state *plane_state)
 {
-	if (!plane_state->base.fb->format->has_alpha)
+	if (!plane_state->hw.fb->format->has_alpha)
 		return PLANE_COLOR_ALPHA_DISABLE;
 
-	switch (plane_state->base.pixel_blend_mode) {
+	switch (plane_state->hw.pixel_blend_mode) {
 	case DRM_MODE_BLEND_PIXEL_NONE:
 		return PLANE_COLOR_ALPHA_DISABLE;
 	case DRM_MODE_BLEND_PREMULTI:
@@ -4140,7 +4586,7 @@ static u32 glk_plane_color_ctl_alpha(const struct intel_plane_state *plane_state
 	case DRM_MODE_BLEND_COVERAGE:
 		return PLANE_COLOR_ALPHA_HW_PREMULTIPLY;
 	default:
-		MISSING_CASE(plane_state->base.pixel_blend_mode);
+		MISSING_CASE(plane_state->hw.pixel_blend_mode);
 		return PLANE_COLOR_ALPHA_DISABLE;
 	}
 }
@@ -4156,6 +4602,12 @@ static u32 skl_plane_ctl_tiling(u64 fb_modifier)
 		return PLANE_CTL_TILED_Y;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 		return PLANE_CTL_TILED_Y | PLANE_CTL_RENDER_DECOMPRESSION_ENABLE;
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+		return PLANE_CTL_TILED_Y |
+		       PLANE_CTL_RENDER_DECOMPRESSION_ENABLE |
+		       PLANE_CTL_CLEAR_COLOR_DISABLE;
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		return PLANE_CTL_TILED_Y | PLANE_CTL_MEDIA_DECOMPRESSION_ENABLE;
 	case I915_FORMAT_MOD_Yf_TILED:
 		return PLANE_CTL_TILED_YF;
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
@@ -4206,7 +4658,7 @@ static u32 cnl_plane_ctl_flip(unsigned int reflect)
 
 u32 skl_plane_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 plane_ctl = 0;
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
@@ -4225,9 +4677,9 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 		  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 plane_ctl;
 
@@ -4237,10 +4689,10 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 		plane_ctl |= skl_plane_ctl_alpha(plane_state);
 		plane_ctl |= PLANE_CTL_PLANE_GAMMA_DISABLE;
 
-		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+		if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_ctl |= PLANE_CTL_YUV_TO_RGB_CSC_FORMAT_BT709;
 
-		if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+		if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 			plane_ctl |= PLANE_CTL_YUV_RANGE_CORRECTION_DISABLE;
 	}
 
@@ -4262,7 +4714,7 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 
 u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 plane_color_ctl = 0;
 
 	if (INTEL_GEN(dev_priv) >= 11)
@@ -4281,21 +4733,21 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	u32 plane_color_ctl = 0;
 
 	plane_color_ctl |= PLANE_COLOR_PLANE_GAMMA_DISABLE;
 	plane_color_ctl |= glk_plane_color_ctl_alpha(plane_state);
 
 	if (fb->format->is_yuv && !icl_is_hdr_plane(dev_priv, plane->id)) {
-		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+		if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
 		else
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV601_TO_RGB709;
 
-		if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+		if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 			plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE;
 	} else if (fb->format->is_yuv) {
 		plane_color_ctl |= PLANE_COLOR_INPUT_CSC_ENABLE;
@@ -4483,7 +4935,7 @@ static void icl_set_pipe_chicken(struct intel_crtc *crtc)
 
 static void icl_enable_trans_port_sync(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 trans_ddi_func_ctl2_val;
 	u8 master_select;
@@ -4511,20 +4963,6 @@ static void icl_enable_trans_port_sync(const struct intel_crtc_state *crtc_state
 		   trans_ddi_func_ctl2_val);
 }
 
-static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
-	if (old_crtc_state->master_transcoder == INVALID_TRANSCODER)
-		return;
-
-	DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n",
-		      transcoder_name(old_crtc_state->cpu_transcoder));
-
-	I915_WRITE(TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0);
-}
-
 static void intel_fdi_normal_train(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -4567,8 +5005,8 @@ static void intel_fdi_normal_train(struct intel_crtc *crtc)
 }
 
 /* The FDI link training functions for ILK/Ibexpeak. */
-static void ironlake_fdi_link_train(struct intel_crtc *crtc,
-				    const struct intel_crtc_state *crtc_state)
+static void ilk_fdi_link_train(struct intel_crtc *crtc,
+			       const struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -4577,7 +5015,7 @@ static void ironlake_fdi_link_train(struct intel_crtc *crtc,
 	u32 temp, tries;
 
 	/* FDI needs bits from pipe first */
-	assert_pipe_enabled(dev_priv, pipe);
+	assert_pipe_enabled(dev_priv, crtc_state->cpu_transcoder);
 
 	/* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit
 	   for train result */
@@ -4920,9 +5358,9 @@ train_done:
 	DRM_DEBUG_KMS("FDI train done.\n");
 }
 
-static void ironlake_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
+static void ilk_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	enum pipe pipe = intel_crtc->pipe;
 	i915_reg_t reg;
@@ -4957,7 +5395,7 @@ static void ironlake_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
 	}
 }
 
-static void ironlake_fdi_pll_disable(struct intel_crtc *intel_crtc)
+static void ilk_fdi_pll_disable(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -4987,12 +5425,10 @@ static void ironlake_fdi_pll_disable(struct intel_crtc *intel_crtc)
 	udelay(100);
 }
 
-static void ironlake_fdi_disable(struct drm_crtc *crtc)
+static void ilk_fdi_disable(struct intel_crtc *crtc)
 {
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
 
@@ -5083,9 +5519,9 @@ void lpt_disable_iclkip(struct drm_i915_private *dev_priv)
 /* Program iCLKIP clock to the desired frequency */
 static void lpt_program_iclkip(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int clock = crtc_state->base.adjusted_mode.crtc_clock;
+	int clock = crtc_state->hw.adjusted_mode.crtc_clock;
 	u32 divsel, phaseinc, auxdiv, phasedir = 0;
 	u32 temp;
 
@@ -5196,10 +5632,10 @@ int lpt_get_iclkip(struct drm_i915_private *dev_priv)
 				 desired_divisor << auxdiv);
 }
 
-static void ironlake_pch_transcoder_set_timings(const struct intel_crtc_state *crtc_state,
-						enum pipe pch_transcoder)
+static void ilk_pch_transcoder_set_timings(const struct intel_crtc_state *crtc_state,
+					   enum pipe pch_transcoder)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
@@ -5240,9 +5676,9 @@ static void cpt_set_fdi_bc_bifurcation(struct drm_i915_private *dev_priv, bool e
 	POSTING_READ(SOUTH_CHICKEN1);
 }
 
-static void ivybridge_update_fdi_bc_bifurcation(const struct intel_crtc_state *crtc_state)
+static void ivb_update_fdi_bc_bifurcation(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	switch (crtc->pipe) {
@@ -5272,7 +5708,7 @@ static struct intel_encoder *
 intel_get_crtc_new_encoder(const struct intel_atomic_state *state,
 			   const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	const struct drm_connector_state *connector_state;
 	const struct drm_connector *connector;
 	struct intel_encoder *encoder = NULL;
@@ -5301,10 +5737,10 @@ intel_get_crtc_new_encoder(const struct intel_atomic_state *state,
  *   - DP transcoding bits
  *   - transcoder
  */
-static void ironlake_pch_enable(const struct intel_atomic_state *state,
-				const struct intel_crtc_state *crtc_state)
+static void ilk_pch_enable(const struct intel_atomic_state *state,
+			   const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = crtc->pipe;
@@ -5313,7 +5749,7 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 	assert_pch_transcoder_disabled(dev_priv, pipe);
 
 	if (IS_IVYBRIDGE(dev_priv))
-		ivybridge_update_fdi_bc_bifurcation(crtc_state);
+		ivb_update_fdi_bc_bifurcation(crtc_state);
 
 	/* Write the TU size bits before fdi link training, so that error
 	 * detection works. */
@@ -5350,7 +5786,7 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 
 	/* set transcoder timing, panel must allow it */
 	assert_panel_unlocked(dev_priv, pipe);
-	ironlake_pch_transcoder_set_timings(crtc_state, pipe);
+	ilk_pch_transcoder_set_timings(crtc_state, pipe);
 
 	intel_fdi_normal_train(crtc);
 
@@ -5358,7 +5794,7 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 	if (HAS_PCH_CPT(dev_priv) &&
 	    intel_crtc_has_dp_encoder(crtc_state)) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc_state->base.adjusted_mode;
+			&crtc_state->hw.adjusted_mode;
 		u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPECONF_BPC_MASK) >> 5;
 		i915_reg_t reg = TRANS_DP_CTL(pipe);
 		enum port port;
@@ -5382,13 +5818,13 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 		I915_WRITE(reg, temp);
 	}
 
-	ironlake_enable_pch_transcoder(crtc_state);
+	ilk_enable_pch_transcoder(crtc_state);
 }
 
 static void lpt_pch_enable(const struct intel_atomic_state *state,
 			   const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
@@ -5397,14 +5833,14 @@ static void lpt_pch_enable(const struct intel_atomic_state *state,
 	lpt_program_iclkip(crtc_state);
 
 	/* Set transcoder timing. */
-	ironlake_pch_transcoder_set_timings(crtc_state, PIPE_A);
+	ilk_pch_transcoder_set_timings(crtc_state, PIPE_A);
 
 	lpt_enable_pch_transcoder(dev_priv, cpu_transcoder);
 }
 
-static void cpt_verify_modeset(struct drm_device *dev, enum pipe pipe)
+static void cpt_verify_modeset(struct drm_i915_private *dev_priv,
+			       enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t dslreg = PIPEDSL(pipe);
 	u32 temp;
 
@@ -5500,15 +5936,16 @@ static int
 skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		  unsigned int scaler_user, int *scaler_id,
 		  int src_w, int src_h, int dst_w, int dst_h,
-		  const struct drm_format_info *format, bool need_scaler)
+		  const struct drm_format_info *format,
+		  u64 modifier, bool need_scaler)
 {
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 	struct intel_crtc *intel_crtc =
-		to_intel_crtc(crtc_state->base.crtc);
+		to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	/*
 	 * Src coordinates are already rotated by 270 degrees for
@@ -5524,7 +5961,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 	 * Once NV12 is enabled, handle it here while allocating scaler
 	 * for NV12.
 	 */
-	if (INTEL_GEN(dev_priv) >= 9 && crtc_state->base.enable &&
+	if (INTEL_GEN(dev_priv) >= 9 && crtc_state->hw.enable &&
 	    need_scaler && adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) {
 		DRM_DEBUG_KMS("Pipe/Plane scaling not supported with IF-ID mode\n");
 		return -EINVAL;
@@ -5554,7 +5991,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		return 0;
 	}
 
-	if (format && drm_format_info_is_yuv_semiplanar(format) &&
+	if (format && intel_format_info_is_yuv_semiplanar(format, modifier) &&
 	    (src_h < SKL_MIN_YUV_420_SRC_H || src_w < SKL_MIN_YUV_420_SRC_W)) {
 		DRM_DEBUG_KMS("Planar YUV: src dimensions not met\n");
 		return -EINVAL;
@@ -5596,17 +6033,18 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
  */
 int skl_update_scaler_crtc(struct intel_crtc_state *state)
 {
-	const struct drm_display_mode *adjusted_mode = &state->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &state->hw.adjusted_mode;
 	bool need_scaler = false;
 
 	if (state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420)
 		need_scaler = true;
 
-	return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX,
+	return skl_update_scaler(state, !state->hw.active, SKL_CRTC_INDEX,
 				 &state->scaler_state.scaler_id,
 				 state->pipe_src_w, state->pipe_src_h,
 				 adjusted_mode->crtc_hdisplay,
-				 adjusted_mode->crtc_vdisplay, NULL, need_scaler);
+				 adjusted_mode->crtc_vdisplay, NULL, 0,
+				 need_scaler);
 }
 
 /**
@@ -5622,26 +6060,28 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 				   struct intel_plane_state *plane_state)
 {
 	struct intel_plane *intel_plane =
-		to_intel_plane(plane_state->base.plane);
+		to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev);
-	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
-	bool force_detach = !fb || !plane_state->base.visible;
+	bool force_detach = !fb || !plane_state->uapi.visible;
 	bool need_scaler = false;
 
 	/* Pre-gen11 and SDR planes always need a scaler for planar formats. */
 	if (!icl_is_hdr_plane(dev_priv, intel_plane->id) &&
-	    fb && drm_format_info_is_yuv_semiplanar(fb->format))
+	    fb && intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		need_scaler = true;
 
 	ret = skl_update_scaler(crtc_state, force_detach,
 				drm_plane_index(&intel_plane->base),
 				&plane_state->scaler_id,
-				drm_rect_width(&plane_state->base.src) >> 16,
-				drm_rect_height(&plane_state->base.src) >> 16,
-				drm_rect_width(&plane_state->base.dst),
-				drm_rect_height(&plane_state->base.dst),
-				fb ? fb->format : NULL, need_scaler);
+				drm_rect_width(&plane_state->uapi.src) >> 16,
+				drm_rect_height(&plane_state->uapi.src) >> 16,
+				drm_rect_width(&plane_state->uapi.dst),
+				drm_rect_height(&plane_state->uapi.dst),
+				fb ? fb->format : NULL,
+				fb ? fb->modifier : 0,
+				need_scaler);
 
 	if (ret || plane_state->scaler_id < 0)
 		return ret;
@@ -5663,6 +6103,8 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -5695,17 +6137,18 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
-static void skylake_scaler_disable(struct intel_crtc *crtc)
+void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	int i;
 
 	for (i = 0; i < crtc->num_scalers; i++)
 		skl_detach_scaler(crtc, i);
 }
 
-static void skylake_pfit_enable(const struct intel_crtc_state *crtc_state)
+static void skl_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	const struct intel_crtc_scaler_state *scaler_state =
@@ -5740,9 +6183,9 @@ static void skylake_pfit_enable(const struct intel_crtc_state *crtc_state)
 	}
 }
 
-static void ironlake_pfit_enable(const struct intel_crtc_state *crtc_state)
+static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -5763,7 +6206,7 @@ static void ironlake_pfit_enable(const struct intel_crtc_state *crtc_state)
 
 void hsw_enable_ips(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
@@ -5799,7 +6242,7 @@ void hsw_enable_ips(const struct intel_crtc_state *crtc_state)
 
 void hsw_disable_ips(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
@@ -5834,77 +6277,10 @@ static void intel_crtc_dpms_overlay_disable(struct intel_crtc *intel_crtc)
 	 */
 }
 
-/**
- * intel_post_enable_primary - Perform operations after enabling primary plane
- * @crtc: the CRTC whose primary plane was just enabled
- * @new_crtc_state: the enabling state
- *
- * Performs potentially sleeping operations that must be done after the primary
- * plane is enabled, such as updating FBC and IPS.  Note that this may be
- * called due to an explicit primary plane update, or due to an implicit
- * re-enable that is caused when a sprite plane is updated to no longer
- * completely hide the primary plane.
- */
-static void
-intel_post_enable_primary(struct drm_crtc *crtc,
-			  const struct intel_crtc_state *new_crtc_state)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
-
-	/*
-	 * Gen2 reports pipe underruns whenever all planes are disabled.
-	 * So don't enable underrun reporting before at least some planes
-	 * are enabled.
-	 * FIXME: Need to fix the logic to work when we turn off all planes
-	 * but leave the pipe running.
-	 */
-	if (IS_GEN(dev_priv, 2))
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
-
-	/* Underruns don't always raise interrupts, so check manually. */
-	intel_check_cpu_fifo_underruns(dev_priv);
-	intel_check_pch_fifo_underruns(dev_priv);
-}
-
-/* FIXME get rid of this and use pre_plane_update */
-static void
-intel_pre_disable_primary_noatomic(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
-
-	/*
-	 * Gen2 reports pipe underruns whenever all planes are disabled.
-	 * So disable underrun reporting before all the planes get disabled.
-	 */
-	if (IS_GEN(dev_priv, 2))
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
-
-	hsw_disable_ips(to_intel_crtc_state(crtc->state));
-
-	/*
-	 * Vblank time updates from the shadow to live plane control register
-	 * are blocked if the memory self-refresh mode is active at that
-	 * moment. So to make sure the plane gets truly disabled, disable
-	 * first the self-refresh mode. The self-refresh enable bit in turn
-	 * will be checked/applied by the HW only at the next frame start
-	 * event which is after the vblank start event, so we need to have a
-	 * wait-for-vblank between disabling the plane and the pipe.
-	 */
-	if (HAS_GMCH(dev_priv) &&
-	    intel_set_memory_cxsr(dev_priv, false))
-		intel_wait_for_vblank(dev_priv, pipe);
-}
-
 static bool hsw_pre_update_disable_ips(const struct intel_crtc_state *old_crtc_state,
 				       const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!old_crtc_state->ips_enabled)
@@ -5920,7 +6296,7 @@ static bool hsw_pre_update_disable_ips(const struct intel_crtc_state *old_crtc_s
 	 * Disable IPS before we program the LUT.
 	 */
 	if (IS_HASWELL(dev_priv) &&
-	    (new_crtc_state->base.color_mgmt_changed ||
+	    (new_crtc_state->uapi.color_mgmt_changed ||
 	     new_crtc_state->update_pipe) &&
 	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
 		return true;
@@ -5931,7 +6307,7 @@ static bool hsw_pre_update_disable_ips(const struct intel_crtc_state *old_crtc_s
 static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_state,
 				       const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!new_crtc_state->ips_enabled)
@@ -5947,7 +6323,7 @@ static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_s
 	 * Re-enable IPS after the LUT has been programmed.
 	 */
 	if (IS_HASWELL(dev_priv) &&
-	    (new_crtc_state->base.color_mgmt_changed ||
+	    (new_crtc_state->uapi.color_mgmt_changed ||
 	     new_crtc_state->update_pipe) &&
 	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
 		return true;
@@ -5957,15 +6333,16 @@ static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_s
 	 * forcibly enable IPS on the first fastset.
 	 */
 	if (new_crtc_state->update_pipe &&
-	    old_crtc_state->base.adjusted_mode.private_flags & I915_MODE_FLAG_INHERITED)
+	    old_crtc_state->hw.adjusted_mode.private_flags & I915_MODE_FLAG_INHERITED)
 		return true;
 
 	return !old_crtc_state->ips_enabled;
 }
 
-static bool needs_nv12_wa(struct drm_i915_private *dev_priv,
-			  const struct intel_crtc_state *crtc_state)
+static bool needs_nv12_wa(const struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+
 	if (!crtc_state->nv12_planes)
 		return false;
 
@@ -5976,9 +6353,10 @@ static bool needs_nv12_wa(struct drm_i915_private *dev_priv,
 	return false;
 }
 
-static bool needs_scalerclk_wa(struct drm_i915_private *dev_priv,
-			       const struct intel_crtc_state *crtc_state)
+static bool needs_scalerclk_wa(const struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+
 	/* Wa_2006604312:icl */
 	if (crtc_state->scaler_state.scaler_users > 0 && IS_ICELAKE(dev_priv))
 		return true;
@@ -5986,89 +6364,82 @@ static bool needs_scalerclk_wa(struct drm_i915_private *dev_priv,
 	return false;
 }
 
-static void intel_post_plane_update(struct intel_crtc_state *old_crtc_state)
+static bool planes_enabling(const struct intel_crtc_state *old_crtc_state,
+			    const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_atomic_state *state = old_crtc_state->base.state;
-	struct intel_crtc_state *pipe_config =
-		intel_atomic_get_new_crtc_state(to_intel_atomic_state(state),
-						crtc);
-	struct drm_plane *primary = crtc->base.primary;
-	struct drm_plane_state *old_primary_state =
-		drm_atomic_get_old_plane_state(state, primary);
+	return (!old_crtc_state->active_planes || needs_modeset(new_crtc_state)) &&
+		new_crtc_state->active_planes;
+}
 
-	intel_frontbuffer_flip(to_i915(crtc->base.dev), pipe_config->fb_bits);
+static bool planes_disabling(const struct intel_crtc_state *old_crtc_state,
+			     const struct intel_crtc_state *new_crtc_state)
+{
+	return old_crtc_state->active_planes &&
+		(!new_crtc_state->active_planes || needs_modeset(new_crtc_state));
+}
 
-	if (pipe_config->update_wm_post && pipe_config->base.active)
-		intel_update_watermarks(crtc);
+static void intel_post_plane_update(struct intel_atomic_state *state,
+				    struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_plane *primary = to_intel_plane(crtc->base.primary);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct intel_plane_state *new_primary_state =
+		intel_atomic_get_new_plane_state(state, primary);
+	enum pipe pipe = crtc->pipe;
 
-	if (hsw_post_update_enable_ips(old_crtc_state, pipe_config))
-		hsw_enable_ips(pipe_config);
+	intel_frontbuffer_flip(dev_priv, new_crtc_state->fb_bits);
 
-	if (old_primary_state) {
-		struct drm_plane_state *new_primary_state =
-			drm_atomic_get_new_plane_state(state, primary);
+	if (new_crtc_state->update_wm_post && new_crtc_state->hw.active)
+		intel_update_watermarks(crtc);
 
-		intel_fbc_post_update(crtc);
+	if (hsw_post_update_enable_ips(old_crtc_state, new_crtc_state))
+		hsw_enable_ips(new_crtc_state);
 
-		if (new_primary_state->visible &&
-		    (needs_modeset(pipe_config) ||
-		     !old_primary_state->visible))
-			intel_post_enable_primary(&crtc->base, pipe_config);
-	}
+	if (new_primary_state)
+		intel_fbc_post_update(crtc);
 
-	if (needs_nv12_wa(dev_priv, old_crtc_state) &&
-	    !needs_nv12_wa(dev_priv, pipe_config))
-		skl_wa_827(dev_priv, crtc->pipe, false);
+	if (needs_nv12_wa(old_crtc_state) &&
+	    !needs_nv12_wa(new_crtc_state))
+		skl_wa_827(dev_priv, pipe, false);
 
-	if (needs_scalerclk_wa(dev_priv, old_crtc_state) &&
-	    !needs_scalerclk_wa(dev_priv, pipe_config))
-		icl_wa_scalerclkgating(dev_priv, crtc->pipe, false);
+	if (needs_scalerclk_wa(old_crtc_state) &&
+	    !needs_scalerclk_wa(new_crtc_state))
+		icl_wa_scalerclkgating(dev_priv, pipe, false);
 }
 
-static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
-				   struct intel_crtc_state *pipe_config)
+static void intel_pre_plane_update(struct intel_atomic_state *state,
+				   struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_atomic_state *state = old_crtc_state->base.state;
-	struct drm_plane *primary = crtc->base.primary;
-	struct drm_plane_state *old_primary_state =
-		drm_atomic_get_old_plane_state(state, primary);
-	bool modeset = needs_modeset(pipe_config);
-	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(state);
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_plane *primary = to_intel_plane(crtc->base.primary);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct intel_plane_state *new_primary_state =
+		intel_atomic_get_new_plane_state(state, primary);
+	enum pipe pipe = crtc->pipe;
 
-	if (hsw_pre_update_disable_ips(old_crtc_state, pipe_config))
+	if (hsw_pre_update_disable_ips(old_crtc_state, new_crtc_state))
 		hsw_disable_ips(old_crtc_state);
 
-	if (old_primary_state) {
-		struct intel_plane_state *new_primary_state =
-			intel_atomic_get_new_plane_state(intel_state,
-							 to_intel_plane(primary));
-
-		intel_fbc_pre_update(crtc, pipe_config, new_primary_state);
-		/*
-		 * Gen2 reports pipe underruns whenever all planes are disabled.
-		 * So disable underrun reporting before all the planes get disabled.
-		 */
-		if (IS_GEN(dev_priv, 2) && old_primary_state->visible &&
-		    (modeset || !new_primary_state->base.visible))
-			intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
-	}
+	if (new_primary_state &&
+	    intel_fbc_pre_update(crtc, new_crtc_state, new_primary_state))
+		intel_wait_for_vblank(dev_priv, pipe);
 
 	/* Display WA 827 */
-	if (!needs_nv12_wa(dev_priv, old_crtc_state) &&
-	    needs_nv12_wa(dev_priv, pipe_config))
-		skl_wa_827(dev_priv, crtc->pipe, true);
+	if (!needs_nv12_wa(old_crtc_state) &&
+	    needs_nv12_wa(new_crtc_state))
+		skl_wa_827(dev_priv, pipe, true);
 
 	/* Wa_2006604312:icl */
-	if (!needs_scalerclk_wa(dev_priv, old_crtc_state) &&
-	    needs_scalerclk_wa(dev_priv, pipe_config))
-		icl_wa_scalerclkgating(dev_priv, crtc->pipe, true);
+	if (!needs_scalerclk_wa(old_crtc_state) &&
+	    needs_scalerclk_wa(new_crtc_state))
+		icl_wa_scalerclkgating(dev_priv, pipe, true);
 
 	/*
 	 * Vblank time updates from the shadow to live plane control register
@@ -6079,9 +6450,9 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
 	 * event which is after the vblank start event, so we need to have a
 	 * wait-for-vblank between disabling the plane and the pipe.
 	 */
-	if (HAS_GMCH(dev_priv) && old_crtc_state->base.active &&
-	    pipe_config->disable_cxsr && intel_set_memory_cxsr(dev_priv, false))
-		intel_wait_for_vblank(dev_priv, crtc->pipe);
+	if (HAS_GMCH(dev_priv) && old_crtc_state->hw.active &&
+	    new_crtc_state->disable_cxsr && intel_set_memory_cxsr(dev_priv, false))
+		intel_wait_for_vblank(dev_priv, pipe);
 
 	/*
 	 * IVB workaround: must disable low power watermarks for at least
@@ -6090,36 +6461,45 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
 	 *
 	 * WaCxSRDisabledForSpriteScaling:ivb
 	 */
-	if (pipe_config->disable_lp_wm && ilk_disable_lp_wm(dev) &&
-	    old_crtc_state->base.active)
-		intel_wait_for_vblank(dev_priv, crtc->pipe);
+	if (old_crtc_state->hw.active &&
+	    new_crtc_state->disable_lp_wm && ilk_disable_lp_wm(dev_priv))
+		intel_wait_for_vblank(dev_priv, pipe);
 
 	/*
-	 * If we're doing a modeset, we're done.  No need to do any pre-vblank
-	 * watermark programming here.
+	 * If we're doing a modeset we don't need to do any
+	 * pre-vblank watermark programming here.
 	 */
-	if (needs_modeset(pipe_config))
-		return;
+	if (!needs_modeset(new_crtc_state)) {
+		/*
+		 * For platforms that support atomic watermarks, program the
+		 * 'intermediate' watermarks immediately.  On pre-gen9 platforms, these
+		 * will be the intermediate values that are safe for both pre- and
+		 * post- vblank; when vblank happens, the 'active' values will be set
+		 * to the final 'target' values and we'll do this again to get the
+		 * optimal watermarks.  For gen9+ platforms, the values we program here
+		 * will be the final target values which will get automatically latched
+		 * at vblank time; no further programming will be necessary.
+		 *
+		 * If a platform hasn't been transitioned to atomic watermarks yet,
+		 * we'll continue to update watermarks the old way, if flags tell
+		 * us to.
+		 */
+		if (dev_priv->display.initial_watermarks)
+			dev_priv->display.initial_watermarks(state, crtc);
+		else if (new_crtc_state->update_wm_pre)
+			intel_update_watermarks(crtc);
+	}
 
 	/*
-	 * For platforms that support atomic watermarks, program the
-	 * 'intermediate' watermarks immediately.  On pre-gen9 platforms, these
-	 * will be the intermediate values that are safe for both pre- and
-	 * post- vblank; when vblank happens, the 'active' values will be set
-	 * to the final 'target' values and we'll do this again to get the
-	 * optimal watermarks.  For gen9+ platforms, the values we program here
-	 * will be the final target values which will get automatically latched
-	 * at vblank time; no further programming will be necessary.
+	 * Gen2 reports pipe underruns whenever all planes are disabled.
+	 * So disable underrun reporting before all the planes get disabled.
 	 *
-	 * If a platform hasn't been transitioned to atomic watermarks yet,
-	 * we'll continue to update watermarks the old way, if flags tell
-	 * us to.
+	 * We do this after .initial_watermarks() so that we have a
+	 * chance of catching underruns with the intermediate watermarks
+	 * vs. the old plane configuration.
 	 */
-	if (dev_priv->display.initial_watermarks != NULL)
-		dev_priv->display.initial_watermarks(intel_state,
-						     pipe_config);
-	else if (pipe_config->update_wm_pre)
-		intel_update_watermarks(crtc);
+	if (IS_GEN(dev_priv, 2) && planes_disabling(old_crtc_state, new_crtc_state))
+		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 }
 
 static void intel_crtc_disable_planes(struct intel_atomic_state *state,
@@ -6143,7 +6523,7 @@ static void intel_crtc_disable_planes(struct intel_atomic_state *state,
 
 		intel_disable_plane(plane, new_crtc_state);
 
-		if (old_plane_state->base.visible)
+		if (old_plane_state->uapi.visible)
 			fb_bits |= plane->frontbuffer_bit;
 	}
 
@@ -6167,45 +6547,29 @@ intel_connector_primary_encoder(struct intel_connector *connector)
 	if (connector->mst_port)
 		return &dp_to_dig_port(connector->mst_port)->base;
 
-	encoder = intel_attached_encoder(&connector->base);
+	encoder = intel_attached_encoder(connector);
 	WARN_ON(!encoder);
 
 	return encoder;
 }
 
-static bool
-intel_connector_needs_modeset(struct intel_atomic_state *state,
-			      const struct drm_connector_state *old_conn_state,
-			      const struct drm_connector_state *new_conn_state)
-{
-	struct intel_crtc *old_crtc = old_conn_state->crtc ?
-				      to_intel_crtc(old_conn_state->crtc) : NULL;
-	struct intel_crtc *new_crtc = new_conn_state->crtc ?
-				      to_intel_crtc(new_conn_state->crtc) : NULL;
-
-	return new_crtc != old_crtc ||
-	       (new_crtc &&
-		needs_modeset(intel_atomic_get_new_crtc_state(state, new_crtc)));
-}
-
 static void intel_encoders_update_prepare(struct intel_atomic_state *state)
 {
-	struct drm_connector_state *old_conn_state;
 	struct drm_connector_state *new_conn_state;
-	struct drm_connector *conn;
+	struct drm_connector *connector;
 	int i;
 
-	for_each_oldnew_connector_in_state(&state->base, conn,
-					   old_conn_state, new_conn_state, i) {
+	for_each_new_connector_in_state(&state->base, connector, new_conn_state,
+					i) {
+		struct intel_connector *intel_connector;
 		struct intel_encoder *encoder;
 		struct intel_crtc *crtc;
 
-		if (!intel_connector_needs_modeset(state,
-						   old_conn_state,
-						   new_conn_state))
+		if (!intel_connector_needs_modeset(state, connector))
 			continue;
 
-		encoder = intel_connector_primary_encoder(to_intel_connector(conn));
+		intel_connector = to_intel_connector(connector);
+		encoder = intel_connector_primary_encoder(intel_connector);
 		if (!encoder->update_prepare)
 			continue;
 
@@ -6217,22 +6581,21 @@ static void intel_encoders_update_prepare(struct intel_atomic_state *state)
 
 static void intel_encoders_update_complete(struct intel_atomic_state *state)
 {
-	struct drm_connector_state *old_conn_state;
 	struct drm_connector_state *new_conn_state;
-	struct drm_connector *conn;
+	struct drm_connector *connector;
 	int i;
 
-	for_each_oldnew_connector_in_state(&state->base, conn,
-					   old_conn_state, new_conn_state, i) {
+	for_each_new_connector_in_state(&state->base, connector, new_conn_state,
+					i) {
+		struct intel_connector *intel_connector;
 		struct intel_encoder *encoder;
 		struct intel_crtc *crtc;
 
-		if (!intel_connector_needs_modeset(state,
-						   old_conn_state,
-						   new_conn_state))
+		if (!intel_connector_needs_modeset(state, connector))
 			continue;
 
-		encoder = intel_connector_primary_encoder(to_intel_connector(conn));
+		intel_connector = to_intel_connector(connector);
+		encoder = intel_connector_primary_encoder(intel_connector);
 		if (!encoder->update_complete)
 			continue;
 
@@ -6242,11 +6605,12 @@ static void intel_encoders_update_complete(struct intel_atomic_state *state)
 	}
 }
 
-static void intel_encoders_pre_pll_enable(struct intel_crtc *crtc,
-					  struct intel_crtc_state *crtc_state,
-					  struct intel_atomic_state *state)
+static void intel_encoders_pre_pll_enable(struct intel_atomic_state *state,
+					  struct intel_crtc *crtc)
 {
-	struct drm_connector_state *conn_state;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct drm_connector_state *conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6262,11 +6626,12 @@ static void intel_encoders_pre_pll_enable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_pre_enable(struct intel_crtc *crtc,
-				      struct intel_crtc_state *crtc_state,
-				      struct intel_atomic_state *state)
+static void intel_encoders_pre_enable(struct intel_atomic_state *state,
+				      struct intel_crtc *crtc)
 {
-	struct drm_connector_state *conn_state;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct drm_connector_state *conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6282,11 +6647,12 @@ static void intel_encoders_pre_enable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_enable(struct intel_crtc *crtc,
-				  struct intel_crtc_state *crtc_state,
-				  struct intel_atomic_state *state)
+static void intel_encoders_enable(struct intel_atomic_state *state,
+				  struct intel_crtc *crtc)
 {
-	struct drm_connector_state *conn_state;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct drm_connector_state *conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6303,11 +6669,12 @@ static void intel_encoders_enable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_disable(struct intel_crtc *crtc,
-				   struct intel_crtc_state *old_crtc_state,
-				   struct intel_atomic_state *state)
+static void intel_encoders_disable(struct intel_atomic_state *state,
+				   struct intel_crtc *crtc)
 {
-	struct drm_connector_state *old_conn_state;
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct drm_connector_state *old_conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6324,11 +6691,12 @@ static void intel_encoders_disable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_post_disable(struct intel_crtc *crtc,
-					struct intel_crtc_state *old_crtc_state,
-					struct intel_atomic_state *state)
+static void intel_encoders_post_disable(struct intel_atomic_state *state,
+					struct intel_crtc *crtc)
 {
-	struct drm_connector_state *old_conn_state;
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct drm_connector_state *old_conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6344,11 +6712,12 @@ static void intel_encoders_post_disable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_post_pll_disable(struct intel_crtc *crtc,
-					    struct intel_crtc_state *old_crtc_state,
-					    struct intel_atomic_state *state)
+static void intel_encoders_post_pll_disable(struct intel_atomic_state *state,
+					    struct intel_crtc *crtc)
 {
-	struct drm_connector_state *old_conn_state;
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct drm_connector_state *old_conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6364,11 +6733,12 @@ static void intel_encoders_post_pll_disable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_update_pipe(struct intel_crtc *crtc,
-				       struct intel_crtc_state *crtc_state,
-				       struct intel_atomic_state *state)
+static void intel_encoders_update_pipe(struct intel_atomic_state *state,
+				       struct intel_crtc *crtc)
 {
-	struct drm_connector_state *conn_state;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct drm_connector_state *conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6386,22 +6756,21 @@ static void intel_encoders_update_pipe(struct intel_crtc *crtc,
 
 static void intel_disable_primary_plane(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
 
 	plane->disable_plane(plane, crtc_state);
 }
 
-static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
-				 struct intel_atomic_state *state)
+static void ilk_crtc_enable(struct intel_atomic_state *state,
+			    struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
-	if (WARN_ON(intel_crtc->active))
+	if (WARN_ON(crtc->active))
 		return;
 
 	/*
@@ -6417,61 +6786,59 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
 
-	if (pipe_config->has_pch_encoder)
-		intel_prepare_shared_dpll(pipe_config);
+	if (new_crtc_state->has_pch_encoder)
+		intel_prepare_shared_dpll(new_crtc_state);
 
-	if (intel_crtc_has_dp_encoder(pipe_config))
-		intel_dp_set_m_n(pipe_config, M1_N1);
+	if (intel_crtc_has_dp_encoder(new_crtc_state))
+		intel_dp_set_m_n(new_crtc_state, M1_N1);
 
-	intel_set_pipe_timings(pipe_config);
-	intel_set_pipe_src_size(pipe_config);
+	intel_set_pipe_timings(new_crtc_state);
+	intel_set_pipe_src_size(new_crtc_state);
 
-	if (pipe_config->has_pch_encoder) {
-		intel_cpu_transcoder_set_m_n(pipe_config,
-					     &pipe_config->fdi_m_n, NULL);
-	}
+	if (new_crtc_state->has_pch_encoder)
+		intel_cpu_transcoder_set_m_n(new_crtc_state,
+					     &new_crtc_state->fdi_m_n, NULL);
 
-	ironlake_set_pipeconf(pipe_config);
+	ilk_set_pipeconf(new_crtc_state);
 
-	intel_crtc->active = true;
+	crtc->active = true;
 
-	intel_encoders_pre_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_enable(state, crtc);
 
-	if (pipe_config->has_pch_encoder) {
+	if (new_crtc_state->has_pch_encoder) {
 		/* Note: FDI PLL enabling _must_ be done before we enable the
 		 * cpu pipes, hence this is separate from all the other fdi/pch
 		 * enabling. */
-		ironlake_fdi_pll_enable(pipe_config);
+		ilk_fdi_pll_enable(new_crtc_state);
 	} else {
 		assert_fdi_tx_disabled(dev_priv, pipe);
 		assert_fdi_rx_disabled(dev_priv, pipe);
 	}
 
-	ironlake_pfit_enable(pipe_config);
+	ilk_pfit_enable(new_crtc_state);
 
 	/*
 	 * On ILK+ LUT must be loaded before the pipe is running but with
 	 * clocks enabled
 	 */
-	intel_color_load_luts(pipe_config);
-	intel_color_commit(pipe_config);
+	intel_color_load_luts(new_crtc_state);
+	intel_color_commit(new_crtc_state);
 	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(pipe_config);
+	intel_disable_primary_plane(new_crtc_state);
 
-	if (dev_priv->display.initial_watermarks != NULL)
-		dev_priv->display.initial_watermarks(state, pipe_config);
-	intel_enable_pipe(pipe_config);
+	if (dev_priv->display.initial_watermarks)
+		dev_priv->display.initial_watermarks(state, crtc);
+	intel_enable_pipe(new_crtc_state);
 
-	if (pipe_config->has_pch_encoder)
-		ironlake_pch_enable(state, pipe_config);
+	if (new_crtc_state->has_pch_encoder)
+		ilk_pch_enable(state, new_crtc_state);
 
-	assert_vblank_disabled(crtc);
-	intel_crtc_vblank_on(pipe_config);
+	intel_crtc_vblank_on(new_crtc_state);
 
-	intel_encoders_enable(intel_crtc, pipe_config, state);
+	intel_encoders_enable(state, crtc);
 
 	if (HAS_PCH_CPT(dev_priv))
-		cpt_verify_modeset(dev, intel_crtc->pipe);
+		cpt_verify_modeset(dev_priv, pipe);
 
 	/*
 	 * Must wait for vblank to avoid spurious PCH FIFO underruns.
@@ -6479,7 +6846,7 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	 * some interlaced HDMI modes. Let's do the double wait always
 	 * in case there are more corner cases we don't know about.
 	 */
-	if (pipe_config->has_pch_encoder) {
+	if (new_crtc_state->has_pch_encoder) {
 		intel_wait_for_vblank(dev_priv, pipe);
 		intel_wait_for_vblank(dev_priv, pipe);
 	}
@@ -6526,103 +6893,112 @@ static void icl_pipe_mbus_enable(struct intel_crtc *crtc)
 	I915_WRITE(PIPE_MBUS_DBOX_CTL(pipe), val);
 }
 
-static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
-				struct intel_atomic_state *state)
+static void hsw_set_frame_start_delay(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe, hsw_workaround_pipe;
-	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	i915_reg_t reg = CHICKEN_TRANS(crtc_state->cpu_transcoder);
+	u32 val;
+
+	val = I915_READ(reg);
+	val &= ~HSW_FRAME_START_DELAY_MASK;
+	val |= HSW_FRAME_START_DELAY(0);
+	I915_WRITE(reg, val);
+}
+
+static void hsw_crtc_enable(struct intel_atomic_state *state,
+			    struct intel_crtc *crtc)
+{
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe, hsw_workaround_pipe;
+	enum transcoder cpu_transcoder = new_crtc_state->cpu_transcoder;
 	bool psl_clkgate_wa;
 
-	if (WARN_ON(intel_crtc->active))
+	if (WARN_ON(crtc->active))
 		return;
 
-	intel_encoders_pre_pll_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_pll_enable(state, crtc);
 
-	if (pipe_config->shared_dpll)
-		intel_enable_shared_dpll(pipe_config);
+	if (new_crtc_state->shared_dpll)
+		intel_enable_shared_dpll(new_crtc_state);
 
-	intel_encoders_pre_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_enable(state, crtc);
 
-	if (intel_crtc_has_dp_encoder(pipe_config))
-		intel_dp_set_m_n(pipe_config, M1_N1);
+	if (intel_crtc_has_dp_encoder(new_crtc_state))
+		intel_dp_set_m_n(new_crtc_state, M1_N1);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_set_pipe_timings(pipe_config);
+		intel_set_pipe_timings(new_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		icl_enable_trans_port_sync(pipe_config);
+		icl_enable_trans_port_sync(new_crtc_state);
 
-	intel_set_pipe_src_size(pipe_config);
+	intel_set_pipe_src_size(new_crtc_state);
 
 	if (cpu_transcoder != TRANSCODER_EDP &&
-	    !transcoder_is_dsi(cpu_transcoder)) {
+	    !transcoder_is_dsi(cpu_transcoder))
 		I915_WRITE(PIPE_MULT(cpu_transcoder),
-			   pipe_config->pixel_multiplier - 1);
-	}
+			   new_crtc_state->pixel_multiplier - 1);
 
-	if (pipe_config->has_pch_encoder) {
-		intel_cpu_transcoder_set_m_n(pipe_config,
-					     &pipe_config->fdi_m_n, NULL);
-	}
+	if (new_crtc_state->has_pch_encoder)
+		intel_cpu_transcoder_set_m_n(new_crtc_state,
+					     &new_crtc_state->fdi_m_n, NULL);
 
-	if (!transcoder_is_dsi(cpu_transcoder))
-		haswell_set_pipeconf(pipe_config);
+	if (!transcoder_is_dsi(cpu_transcoder)) {
+		hsw_set_frame_start_delay(new_crtc_state);
+		hsw_set_pipeconf(new_crtc_state);
+	}
 
 	if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
-		bdw_set_pipemisc(pipe_config);
+		bdw_set_pipemisc(new_crtc_state);
 
-	intel_crtc->active = true;
+	crtc->active = true;
 
 	/* Display WA #1180: WaDisableScalarClockGating: glk, cnl */
 	psl_clkgate_wa = (IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) &&
-			 pipe_config->pch_pfit.enabled;
+		new_crtc_state->pch_pfit.enabled;
 	if (psl_clkgate_wa)
 		glk_pipe_scaler_clock_gating_wa(dev_priv, pipe, true);
 
 	if (INTEL_GEN(dev_priv) >= 9)
-		skylake_pfit_enable(pipe_config);
+		skl_pfit_enable(new_crtc_state);
 	else
-		ironlake_pfit_enable(pipe_config);
+		ilk_pfit_enable(new_crtc_state);
 
 	/*
 	 * On ILK+ LUT must be loaded before the pipe is running but with
 	 * clocks enabled
 	 */
-	intel_color_load_luts(pipe_config);
-	intel_color_commit(pipe_config);
+	intel_color_load_luts(new_crtc_state);
+	intel_color_commit(new_crtc_state);
 	/* update DSPCNTR to configure gamma/csc for pipe bottom color */
 	if (INTEL_GEN(dev_priv) < 9)
-		intel_disable_primary_plane(pipe_config);
+		intel_disable_primary_plane(new_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		icl_set_pipe_chicken(intel_crtc);
+		icl_set_pipe_chicken(crtc);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_enable_transcoder_func(pipe_config);
+		intel_ddi_enable_transcoder_func(new_crtc_state);
 
-	if (dev_priv->display.initial_watermarks != NULL)
-		dev_priv->display.initial_watermarks(state, pipe_config);
+	if (dev_priv->display.initial_watermarks)
+		dev_priv->display.initial_watermarks(state, crtc);
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		icl_pipe_mbus_enable(intel_crtc);
+		icl_pipe_mbus_enable(crtc);
 
 	/* XXX: Do the pipe assertions at the right place for BXT DSI. */
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_enable_pipe(pipe_config);
+		intel_enable_pipe(new_crtc_state);
 
-	if (pipe_config->has_pch_encoder)
-		lpt_pch_enable(state, pipe_config);
-
-	if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST))
-		intel_ddi_set_vc_payload_alloc(pipe_config, true);
+	if (new_crtc_state->has_pch_encoder)
+		lpt_pch_enable(state, new_crtc_state);
 
-	assert_vblank_disabled(crtc);
-	intel_crtc_vblank_on(pipe_config);
+	intel_crtc_vblank_on(new_crtc_state);
 
-	intel_encoders_enable(intel_crtc, pipe_config, state);
+	intel_encoders_enable(state, crtc);
 
 	if (psl_clkgate_wa) {
 		intel_wait_for_vblank(dev_priv, pipe);
@@ -6631,16 +7007,16 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 
 	/* If we change the relative order between pipe/planes enabling, we need
 	 * to change the workaround. */
-	hsw_workaround_pipe = pipe_config->hsw_workaround_pipe;
+	hsw_workaround_pipe = new_crtc_state->hsw_workaround_pipe;
 	if (IS_HASWELL(dev_priv) && hsw_workaround_pipe != INVALID_PIPE) {
 		intel_wait_for_vblank(dev_priv, hsw_workaround_pipe);
 		intel_wait_for_vblank(dev_priv, hsw_workaround_pipe);
 	}
 }
 
-static void ironlake_pfit_disable(const struct intel_crtc_state *old_crtc_state)
+void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -6653,14 +7029,13 @@ static void ironlake_pfit_disable(const struct intel_crtc_state *old_crtc_state)
 	}
 }
 
-static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
-				  struct intel_atomic_state *state)
+static void ilk_crtc_disable(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = old_crtc_state->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	/*
 	 * Sometimes spurious CPU pipe underruns happen when the
@@ -6670,22 +7045,21 @@ static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
 
-	intel_encoders_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_disable(state, crtc);
 
-	drm_crtc_vblank_off(crtc);
-	assert_vblank_disabled(crtc);
+	intel_crtc_vblank_off(old_crtc_state);
 
 	intel_disable_pipe(old_crtc_state);
 
-	ironlake_pfit_disable(old_crtc_state);
+	ilk_pfit_disable(old_crtc_state);
 
 	if (old_crtc_state->has_pch_encoder)
-		ironlake_fdi_disable(crtc);
+		ilk_fdi_disable(crtc);
 
-	intel_encoders_post_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_post_disable(state, crtc);
 
 	if (old_crtc_state->has_pch_encoder) {
-		ironlake_disable_pch_transcoder(dev_priv, pipe);
+		ilk_disable_pch_transcoder(dev_priv, pipe);
 
 		if (HAS_PCH_CPT(dev_priv)) {
 			i915_reg_t reg;
@@ -6705,54 +7079,27 @@ static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
 			I915_WRITE(PCH_DPLL_SEL, temp);
 		}
 
-		ironlake_fdi_pll_disable(intel_crtc);
+		ilk_fdi_pll_disable(crtc);
 	}
 
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true);
 }
 
-static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
-				 struct intel_atomic_state *state)
+static void hsw_crtc_disable(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = old_crtc_state->base.crtc;
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
-
-	intel_encoders_disable(intel_crtc, old_crtc_state, state);
-
-	drm_crtc_vblank_off(crtc);
-	assert_vblank_disabled(crtc);
-
-	/* XXX: Do the pipe assertions at the right place for BXT DSI. */
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_disable_pipe(old_crtc_state);
-
-	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST))
-		intel_ddi_set_vc_payload_alloc(old_crtc_state, false);
-
-	if (INTEL_GEN(dev_priv) >= 11)
-		icl_disable_transcoder_port_sync(old_crtc_state);
-
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_transcoder_func(old_crtc_state);
-
-	intel_dsc_disable(old_crtc_state);
-
-	if (INTEL_GEN(dev_priv) >= 9)
-		skylake_scaler_disable(intel_crtc);
-	else
-		ironlake_pfit_disable(old_crtc_state);
-
-	intel_encoders_post_disable(intel_crtc, old_crtc_state, state);
-
-	intel_encoders_post_pll_disable(intel_crtc, old_crtc_state, state);
+	/*
+	 * FIXME collapse everything to one hook.
+	 * Need care with mst->ddi interactions.
+	 */
+	intel_encoders_disable(state, crtc);
+	intel_encoders_post_disable(state, crtc);
 }
 
 static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!crtc_state->gmch_pfit.control)
@@ -6763,7 +7110,7 @@ static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state)
 	 * according to register description and PRM.
 	 */
 	WARN_ON(I915_READ(PFIT_CONTROL) & PFIT_ENABLE);
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder);
 
 	I915_WRITE(PFIT_PGM_RATIOS, crtc_state->gmch_pfit.pgm_ratios);
 	I915_WRITE(PFIT_CONTROL, crtc_state->gmch_pfit.control);
@@ -6888,14 +7235,14 @@ intel_aux_power_domain(struct intel_digital_port *dig_port)
 
 static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct drm_encoder *encoder;
 	enum pipe pipe = crtc->pipe;
 	u64 mask;
 	enum transcoder transcoder = crtc_state->cpu_transcoder;
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return 0;
 
 	mask = BIT_ULL(POWER_DOMAIN_PIPE(pipe));
@@ -6905,7 +7252,7 @@ static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 		mask |= BIT_ULL(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
 
 	drm_for_each_encoder_mask(encoder, &dev_priv->drm,
-				  crtc_state->base.encoder_mask) {
+				  crtc_state->uapi.encoder_mask) {
 		struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
 
 		mask |= BIT_ULL(intel_encoder->power_domain);
@@ -6923,7 +7270,7 @@ static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 static u64
 modeset_get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum intel_display_power_domain domain;
 	u64 domains, new_domains, old_domains;
@@ -6949,146 +7296,140 @@ static void modeset_put_power_domains(struct drm_i915_private *dev_priv,
 		intel_display_power_put_unchecked(dev_priv, domain);
 }
 
-static void valleyview_crtc_enable(struct intel_crtc_state *pipe_config,
-				   struct intel_atomic_state *state)
+static void valleyview_crtc_enable(struct intel_atomic_state *state,
+				   struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
-	if (WARN_ON(intel_crtc->active))
+	if (WARN_ON(crtc->active))
 		return;
 
-	if (intel_crtc_has_dp_encoder(pipe_config))
-		intel_dp_set_m_n(pipe_config, M1_N1);
+	if (intel_crtc_has_dp_encoder(new_crtc_state))
+		intel_dp_set_m_n(new_crtc_state, M1_N1);
 
-	intel_set_pipe_timings(pipe_config);
-	intel_set_pipe_src_size(pipe_config);
+	intel_set_pipe_timings(new_crtc_state);
+	intel_set_pipe_src_size(new_crtc_state);
 
 	if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) {
 		I915_WRITE(CHV_BLEND(pipe), CHV_BLEND_LEGACY);
 		I915_WRITE(CHV_CANVAS(pipe), 0);
 	}
 
-	i9xx_set_pipeconf(pipe_config);
+	i9xx_set_pipeconf(new_crtc_state);
 
-	intel_crtc->active = true;
+	crtc->active = true;
 
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 
-	intel_encoders_pre_pll_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_pll_enable(state, crtc);
 
 	if (IS_CHERRYVIEW(dev_priv)) {
-		chv_prepare_pll(intel_crtc, pipe_config);
-		chv_enable_pll(intel_crtc, pipe_config);
+		chv_prepare_pll(crtc, new_crtc_state);
+		chv_enable_pll(crtc, new_crtc_state);
 	} else {
-		vlv_prepare_pll(intel_crtc, pipe_config);
-		vlv_enable_pll(intel_crtc, pipe_config);
+		vlv_prepare_pll(crtc, new_crtc_state);
+		vlv_enable_pll(crtc, new_crtc_state);
 	}
 
-	intel_encoders_pre_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_enable(state, crtc);
 
-	i9xx_pfit_enable(pipe_config);
+	i9xx_pfit_enable(new_crtc_state);
 
-	intel_color_load_luts(pipe_config);
-	intel_color_commit(pipe_config);
+	intel_color_load_luts(new_crtc_state);
+	intel_color_commit(new_crtc_state);
 	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(pipe_config);
+	intel_disable_primary_plane(new_crtc_state);
 
-	dev_priv->display.initial_watermarks(state, pipe_config);
-	intel_enable_pipe(pipe_config);
+	dev_priv->display.initial_watermarks(state, crtc);
+	intel_enable_pipe(new_crtc_state);
 
-	assert_vblank_disabled(crtc);
-	intel_crtc_vblank_on(pipe_config);
+	intel_crtc_vblank_on(new_crtc_state);
 
-	intel_encoders_enable(intel_crtc, pipe_config, state);
+	intel_encoders_enable(state, crtc);
 }
 
 static void i9xx_set_pll_dividers(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	I915_WRITE(FP0(crtc->pipe), crtc_state->dpll_hw_state.fp0);
 	I915_WRITE(FP1(crtc->pipe), crtc_state->dpll_hw_state.fp1);
 }
 
-static void i9xx_crtc_enable(struct intel_crtc_state *pipe_config,
-			     struct intel_atomic_state *state)
+static void i9xx_crtc_enable(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
-	if (WARN_ON(intel_crtc->active))
+	if (WARN_ON(crtc->active))
 		return;
 
-	i9xx_set_pll_dividers(pipe_config);
+	i9xx_set_pll_dividers(new_crtc_state);
 
-	if (intel_crtc_has_dp_encoder(pipe_config))
-		intel_dp_set_m_n(pipe_config, M1_N1);
+	if (intel_crtc_has_dp_encoder(new_crtc_state))
+		intel_dp_set_m_n(new_crtc_state, M1_N1);
 
-	intel_set_pipe_timings(pipe_config);
-	intel_set_pipe_src_size(pipe_config);
+	intel_set_pipe_timings(new_crtc_state);
+	intel_set_pipe_src_size(new_crtc_state);
 
-	i9xx_set_pipeconf(pipe_config);
+	i9xx_set_pipeconf(new_crtc_state);
 
-	intel_crtc->active = true;
+	crtc->active = true;
 
 	if (!IS_GEN(dev_priv, 2))
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 
-	intel_encoders_pre_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_enable(state, crtc);
 
-	i9xx_enable_pll(intel_crtc, pipe_config);
+	i9xx_enable_pll(crtc, new_crtc_state);
 
-	i9xx_pfit_enable(pipe_config);
+	i9xx_pfit_enable(new_crtc_state);
 
-	intel_color_load_luts(pipe_config);
-	intel_color_commit(pipe_config);
+	intel_color_load_luts(new_crtc_state);
+	intel_color_commit(new_crtc_state);
 	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(pipe_config);
+	intel_disable_primary_plane(new_crtc_state);
 
-	if (dev_priv->display.initial_watermarks != NULL)
-		dev_priv->display.initial_watermarks(state,
-						     pipe_config);
+	if (dev_priv->display.initial_watermarks)
+		dev_priv->display.initial_watermarks(state, crtc);
 	else
-		intel_update_watermarks(intel_crtc);
-	intel_enable_pipe(pipe_config);
+		intel_update_watermarks(crtc);
+	intel_enable_pipe(new_crtc_state);
 
-	assert_vblank_disabled(crtc);
-	intel_crtc_vblank_on(pipe_config);
+	intel_crtc_vblank_on(new_crtc_state);
 
-	intel_encoders_enable(intel_crtc, pipe_config, state);
+	intel_encoders_enable(state, crtc);
 }
 
 static void i9xx_pfit_disable(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!old_crtc_state->gmch_pfit.control)
 		return;
 
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, old_crtc_state->cpu_transcoder);
 
 	DRM_DEBUG_KMS("disabling pfit, current: 0x%08x\n",
 		      I915_READ(PFIT_CONTROL));
 	I915_WRITE(PFIT_CONTROL, 0);
 }
 
-static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state,
-			      struct intel_atomic_state *state)
+static void i9xx_crtc_disable(struct intel_atomic_state *state,
+			      struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = old_crtc_state->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	/*
 	 * On gen2 planes are double buffered but the pipe isn't, so we must
@@ -7097,16 +7438,15 @@ static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	if (IS_GEN(dev_priv, 2))
 		intel_wait_for_vblank(dev_priv, pipe);
 
-	intel_encoders_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_disable(state, crtc);
 
-	drm_crtc_vblank_off(crtc);
-	assert_vblank_disabled(crtc);
+	intel_crtc_vblank_off(old_crtc_state);
 
 	intel_disable_pipe(old_crtc_state);
 
 	i9xx_pfit_disable(old_crtc_state);
 
-	intel_encoders_post_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_post_disable(state, crtc);
 
 	if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DSI)) {
 		if (IS_CHERRYVIEW(dev_priv))
@@ -7117,92 +7457,97 @@ static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state,
 			i9xx_disable_pll(old_crtc_state);
 	}
 
-	intel_encoders_post_pll_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_post_pll_disable(state, crtc);
 
 	if (!IS_GEN(dev_priv, 2))
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 
 	if (!dev_priv->display.initial_watermarks)
-		intel_update_watermarks(intel_crtc);
+		intel_update_watermarks(crtc);
 
 	/* clock the pipe down to 640x480@60 to potentially save power */
 	if (IS_I830(dev_priv))
 		i830_enable_pipe(dev_priv, pipe);
 }
 
-static void intel_crtc_disable_noatomic(struct drm_crtc *crtc,
+static void intel_crtc_disable_noatomic(struct intel_crtc *crtc,
 					struct drm_modeset_acquire_ctx *ctx)
 {
 	struct intel_encoder *encoder;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_bw_state *bw_state =
 		to_intel_bw_state(dev_priv->bw_obj.state);
+	struct intel_crtc_state *crtc_state =
+		to_intel_crtc_state(crtc->base.state);
 	enum intel_display_power_domain domain;
 	struct intel_plane *plane;
-	u64 domains;
 	struct drm_atomic_state *state;
-	struct intel_crtc_state *crtc_state;
+	struct intel_crtc_state *temp_crtc_state;
+	enum pipe pipe = crtc->pipe;
+	u64 domains;
 	int ret;
 
-	if (!intel_crtc->active)
+	if (!crtc_state->hw.active)
 		return;
 
-	for_each_intel_plane_on_crtc(&dev_priv->drm, intel_crtc, plane) {
+	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
 		const struct intel_plane_state *plane_state =
 			to_intel_plane_state(plane->base.state);
 
-		if (plane_state->base.visible)
-			intel_plane_disable_noatomic(intel_crtc, plane);
+		if (plane_state->uapi.visible)
+			intel_plane_disable_noatomic(crtc, plane);
 	}
 
-	state = drm_atomic_state_alloc(crtc->dev);
+	state = drm_atomic_state_alloc(&dev_priv->drm);
 	if (!state) {
 		DRM_DEBUG_KMS("failed to disable [CRTC:%d:%s], out of memory",
-			      crtc->base.id, crtc->name);
+			      crtc->base.base.id, crtc->base.name);
 		return;
 	}
 
 	state->acquire_ctx = ctx;
 
 	/* Everything's already locked, -EDEADLK can't happen. */
-	crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
-	ret = drm_atomic_add_affected_connectors(state, crtc);
+	temp_crtc_state = intel_atomic_get_crtc_state(state, crtc);
+	ret = drm_atomic_add_affected_connectors(state, &crtc->base);
 
-	WARN_ON(IS_ERR(crtc_state) || ret);
+	WARN_ON(IS_ERR(temp_crtc_state) || ret);
 
-	dev_priv->display.crtc_disable(crtc_state, to_intel_atomic_state(state));
+	dev_priv->display.crtc_disable(to_intel_atomic_state(state), crtc);
 
 	drm_atomic_state_put(state);
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s] hw state adjusted, was enabled, now disabled\n",
-		      crtc->base.id, crtc->name);
+		      crtc->base.base.id, crtc->base.name);
 
-	WARN_ON(drm_atomic_set_mode_for_crtc(crtc->state, NULL) < 0);
-	crtc->state->active = false;
-	intel_crtc->active = false;
-	crtc->enabled = false;
-	crtc->state->connector_mask = 0;
-	crtc->state->encoder_mask = 0;
+	crtc->active = false;
+	crtc->base.enabled = false;
+
+	WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->uapi, NULL) < 0);
+	crtc_state->uapi.active = false;
+	crtc_state->uapi.connector_mask = 0;
+	crtc_state->uapi.encoder_mask = 0;
+	intel_crtc_free_hw_state(crtc_state);
+	memset(&crtc_state->hw, 0, sizeof(crtc_state->hw));
 
-	for_each_encoder_on_crtc(crtc->dev, crtc, encoder)
+	for_each_encoder_on_crtc(&dev_priv->drm, &crtc->base, encoder)
 		encoder->base.crtc = NULL;
 
-	intel_fbc_disable(intel_crtc);
-	intel_update_watermarks(intel_crtc);
-	intel_disable_shared_dpll(to_intel_crtc_state(crtc->state));
+	intel_fbc_disable(crtc);
+	intel_update_watermarks(crtc);
+	intel_disable_shared_dpll(crtc_state);
 
-	domains = intel_crtc->enabled_power_domains;
+	domains = crtc->enabled_power_domains;
 	for_each_power_domain(domain, domains)
 		intel_display_power_put_unchecked(dev_priv, domain);
-	intel_crtc->enabled_power_domains = 0;
+	crtc->enabled_power_domains = 0;
 
-	dev_priv->active_pipes &= ~BIT(intel_crtc->pipe);
-	dev_priv->min_cdclk[intel_crtc->pipe] = 0;
-	dev_priv->min_voltage_level[intel_crtc->pipe] = 0;
+	dev_priv->active_pipes &= ~BIT(pipe);
+	dev_priv->min_cdclk[pipe] = 0;
+	dev_priv->min_voltage_level[pipe] = 0;
 
-	bw_state->data_rate[intel_crtc->pipe] = 0;
-	bw_state->num_active_planes[intel_crtc->pipe] = 0;
+	bw_state->data_rate[pipe] = 0;
+	bw_state->num_active_planes[pipe] = 0;
 }
 
 /*
@@ -7252,8 +7597,8 @@ static void intel_connector_verify_state(struct intel_crtc_state *crtc_state,
 		if (!crtc_state)
 			return;
 
-		I915_STATE_WARN(!crtc_state->base.active,
-		      "connector is active, but attached crtc isn't\n");
+		I915_STATE_WARN(!crtc_state->hw.active,
+				"connector is active, but attached crtc isn't\n");
 
 		if (!encoder || encoder->type == INTEL_OUTPUT_DP_MST)
 			return;
@@ -7264,8 +7609,8 @@ static void intel_connector_verify_state(struct intel_crtc_state *crtc_state,
 		I915_STATE_WARN(conn_state->crtc != encoder->base.crtc,
 			"attached encoder crtc differs from connector crtc\n");
 	} else {
-		I915_STATE_WARN(crtc_state && crtc_state->base.active,
-			"attached crtc is active, but connector isn't\n");
+		I915_STATE_WARN(crtc_state && crtc_state->hw.active,
+				"attached crtc is active, but connector isn't\n");
 		I915_STATE_WARN(!crtc_state && conn_state->best_encoder,
 			"best encoder set without crtc!\n");
 	}
@@ -7273,17 +7618,17 @@ static void intel_connector_verify_state(struct intel_crtc_state *crtc_state,
 
 static int pipe_required_fdi_lanes(struct intel_crtc_state *crtc_state)
 {
-	if (crtc_state->base.enable && crtc_state->has_pch_encoder)
+	if (crtc_state->hw.enable && crtc_state->has_pch_encoder)
 		return crtc_state->fdi_lanes;
 
 	return 0;
 }
 
-static int ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
-				     struct intel_crtc_state *pipe_config)
+static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
+			       struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_atomic_state *state = pipe_config->base.state;
+	struct drm_atomic_state *state = pipe_config->uapi.state;
 	struct intel_crtc *other_crtc;
 	struct intel_crtc_state *other_crtc_state;
 
@@ -7352,11 +7697,11 @@ static int ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
 }
 
 #define RETRY 1
-static int ironlake_fdi_compute_config(struct intel_crtc *intel_crtc,
-				       struct intel_crtc_state *pipe_config)
+static int ilk_fdi_compute_config(struct intel_crtc *intel_crtc,
+				  struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int lane, link_bw, fdi_dotclock, ret;
 	bool needs_recompute = false;
 
@@ -7372,15 +7717,15 @@ retry:
 
 	fdi_dotclock = adjusted_mode->crtc_clock;
 
-	lane = ironlake_get_lanes_required(fdi_dotclock, link_bw,
-					   pipe_config->pipe_bpp);
+	lane = ilk_get_lanes_required(fdi_dotclock, link_bw,
+				      pipe_config->pipe_bpp);
 
 	pipe_config->fdi_lanes = lane;
 
 	intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
 			       link_bw, &pipe_config->fdi_m_n, false, false);
 
-	ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
+	ret = ilk_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
 	if (ret == -EDEADLK)
 		return ret;
 
@@ -7402,7 +7747,7 @@ retry:
 
 bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	/* IPS only exists on ULT machines and is tied to pipe A. */
@@ -7432,9 +7777,9 @@ bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state)
 static bool hsw_compute_ips_config(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->base.crtc->dev);
+		to_i915(crtc_state->uapi.crtc->dev);
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 
 	if (!hsw_crtc_state_ips_capable(crtc_state))
 		return false;
@@ -7473,7 +7818,7 @@ static u32 ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config)
 {
 	u32 pixel_rate;
 
-	pixel_rate = pipe_config->base.adjusted_mode.crtc_clock;
+	pixel_rate = pipe_config->hw.adjusted_mode.crtc_clock;
 
 	/*
 	 * We only use IF-ID interlacing. If we ever use
@@ -7506,12 +7851,12 @@ static u32 ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config)
 
 static void intel_crtc_compute_pixel_rate(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (HAS_GMCH(dev_priv))
 		/* FIXME calculate proper pipe pixel rate for GMCH pfit */
 		crtc_state->pixel_rate =
-			crtc_state->base.adjusted_mode.crtc_clock;
+			crtc_state->hw.adjusted_mode.crtc_clock;
 	else
 		crtc_state->pixel_rate =
 			ilk_pipe_pixel_rate(crtc_state);
@@ -7521,7 +7866,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 				     struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int clock_limit = dev_priv->max_dotclk_freq;
 
 	if (INTEL_GEN(dev_priv) < 4) {
@@ -7547,7 +7892,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 
 	if ((pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 ||
 	     pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR444) &&
-	     pipe_config->base.ctm) {
+	     pipe_config->hw.ctm) {
 		/*
 		 * There is only one pipe CSC unit per pipe, and we need that
 		 * for output conversion from RGB->YCBCR. So if CTM is already
@@ -7586,7 +7931,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 	intel_crtc_compute_pixel_rate(pipe_config);
 
 	if (pipe_config->has_pch_encoder)
-		return ironlake_fdi_compute_config(crtc, pipe_config);
+		return ilk_fdi_compute_config(crtc, pipe_config);
 
 	return 0;
 }
@@ -7741,7 +8086,7 @@ static void vlv_pllb_recal_opamp(struct drm_i915_private *dev_priv, enum pipe
 static void intel_pch_transcoder_set_m_n(const struct intel_crtc_state *crtc_state,
 					 const struct intel_link_m_n *m_n)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -7768,7 +8113,7 @@ static void intel_cpu_transcoder_set_m_n(const struct intel_crtc_state *crtc_sta
 					 const struct intel_link_m_n *m_n,
 					 const struct intel_link_m_n *m2_n2)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	enum transcoder transcoder = crtc_state->cpu_transcoder;
@@ -8077,11 +8422,11 @@ int vlv_force_pll_on(struct drm_i915_private *dev_priv, enum pipe pipe,
 	struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 	struct intel_crtc_state *pipe_config;
 
-	pipe_config = kzalloc(sizeof(*pipe_config), GFP_KERNEL);
+	pipe_config = intel_crtc_state_alloc(crtc);
 	if (!pipe_config)
 		return -ENOMEM;
 
-	pipe_config->base.crtc = &crtc->base;
+	pipe_config->cpu_transcoder = (enum transcoder)pipe;
 	pipe_config->pixel_multiplier = 1;
 	pipe_config->dpll = *dpll;
 
@@ -8241,11 +8586,11 @@ static void i8xx_compute_dpll(struct intel_crtc *crtc,
 
 static void intel_set_pipe_timings(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	u32 crtc_vtotal, crtc_vblank_end;
 	int vsyncshift = 0;
 
@@ -8303,7 +8648,7 @@ static void intel_set_pipe_timings(const struct intel_crtc_state *crtc_state)
 
 static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -8317,7 +8662,7 @@ static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state)
 
 static bool intel_pipe_is_interlaced(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
 	if (IS_GEN(dev_priv, 2))
@@ -8339,39 +8684,39 @@ static void intel_get_pipe_timings(struct intel_crtc *crtc,
 	u32 tmp;
 
 	tmp = I915_READ(HTOTAL(cpu_transcoder));
-	pipe_config->base.adjusted_mode.crtc_hdisplay = (tmp & 0xffff) + 1;
-	pipe_config->base.adjusted_mode.crtc_htotal = ((tmp >> 16) & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_hdisplay = (tmp & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_htotal = ((tmp >> 16) & 0xffff) + 1;
 
 	if (!transcoder_is_dsi(cpu_transcoder)) {
 		tmp = I915_READ(HBLANK(cpu_transcoder));
-		pipe_config->base.adjusted_mode.crtc_hblank_start =
+		pipe_config->hw.adjusted_mode.crtc_hblank_start =
 							(tmp & 0xffff) + 1;
-		pipe_config->base.adjusted_mode.crtc_hblank_end =
+		pipe_config->hw.adjusted_mode.crtc_hblank_end =
 						((tmp >> 16) & 0xffff) + 1;
 	}
 	tmp = I915_READ(HSYNC(cpu_transcoder));
-	pipe_config->base.adjusted_mode.crtc_hsync_start = (tmp & 0xffff) + 1;
-	pipe_config->base.adjusted_mode.crtc_hsync_end = ((tmp >> 16) & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_hsync_start = (tmp & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_hsync_end = ((tmp >> 16) & 0xffff) + 1;
 
 	tmp = I915_READ(VTOTAL(cpu_transcoder));
-	pipe_config->base.adjusted_mode.crtc_vdisplay = (tmp & 0xffff) + 1;
-	pipe_config->base.adjusted_mode.crtc_vtotal = ((tmp >> 16) & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_vdisplay = (tmp & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_vtotal = ((tmp >> 16) & 0xffff) + 1;
 
 	if (!transcoder_is_dsi(cpu_transcoder)) {
 		tmp = I915_READ(VBLANK(cpu_transcoder));
-		pipe_config->base.adjusted_mode.crtc_vblank_start =
+		pipe_config->hw.adjusted_mode.crtc_vblank_start =
 							(tmp & 0xffff) + 1;
-		pipe_config->base.adjusted_mode.crtc_vblank_end =
+		pipe_config->hw.adjusted_mode.crtc_vblank_end =
 						((tmp >> 16) & 0xffff) + 1;
 	}
 	tmp = I915_READ(VSYNC(cpu_transcoder));
-	pipe_config->base.adjusted_mode.crtc_vsync_start = (tmp & 0xffff) + 1;
-	pipe_config->base.adjusted_mode.crtc_vsync_end = ((tmp >> 16) & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_vsync_start = (tmp & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_vsync_end = ((tmp >> 16) & 0xffff) + 1;
 
 	if (intel_pipe_is_interlaced(pipe_config)) {
-		pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_INTERLACE;
-		pipe_config->base.adjusted_mode.crtc_vtotal += 1;
-		pipe_config->base.adjusted_mode.crtc_vblank_end += 1;
+		pipe_config->hw.adjusted_mode.flags |= DRM_MODE_FLAG_INTERLACE;
+		pipe_config->hw.adjusted_mode.crtc_vtotal += 1;
+		pipe_config->hw.adjusted_mode.crtc_vblank_end += 1;
 	}
 }
 
@@ -8386,27 +8731,27 @@ static void intel_get_pipe_src_size(struct intel_crtc *crtc,
 	pipe_config->pipe_src_h = (tmp & 0xffff) + 1;
 	pipe_config->pipe_src_w = ((tmp >> 16) & 0xffff) + 1;
 
-	pipe_config->base.mode.vdisplay = pipe_config->pipe_src_h;
-	pipe_config->base.mode.hdisplay = pipe_config->pipe_src_w;
+	pipe_config->hw.mode.vdisplay = pipe_config->pipe_src_h;
+	pipe_config->hw.mode.hdisplay = pipe_config->pipe_src_w;
 }
 
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_state *pipe_config)
 {
-	mode->hdisplay = pipe_config->base.adjusted_mode.crtc_hdisplay;
-	mode->htotal = pipe_config->base.adjusted_mode.crtc_htotal;
-	mode->hsync_start = pipe_config->base.adjusted_mode.crtc_hsync_start;
-	mode->hsync_end = pipe_config->base.adjusted_mode.crtc_hsync_end;
+	mode->hdisplay = pipe_config->hw.adjusted_mode.crtc_hdisplay;
+	mode->htotal = pipe_config->hw.adjusted_mode.crtc_htotal;
+	mode->hsync_start = pipe_config->hw.adjusted_mode.crtc_hsync_start;
+	mode->hsync_end = pipe_config->hw.adjusted_mode.crtc_hsync_end;
 
-	mode->vdisplay = pipe_config->base.adjusted_mode.crtc_vdisplay;
-	mode->vtotal = pipe_config->base.adjusted_mode.crtc_vtotal;
-	mode->vsync_start = pipe_config->base.adjusted_mode.crtc_vsync_start;
-	mode->vsync_end = pipe_config->base.adjusted_mode.crtc_vsync_end;
+	mode->vdisplay = pipe_config->hw.adjusted_mode.crtc_vdisplay;
+	mode->vtotal = pipe_config->hw.adjusted_mode.crtc_vtotal;
+	mode->vsync_start = pipe_config->hw.adjusted_mode.crtc_vsync_start;
+	mode->vsync_end = pipe_config->hw.adjusted_mode.crtc_vsync_end;
 
-	mode->flags = pipe_config->base.adjusted_mode.flags;
+	mode->flags = pipe_config->hw.adjusted_mode.flags;
 	mode->type = DRM_MODE_TYPE_DRIVER;
 
-	mode->clock = pipe_config->base.adjusted_mode.crtc_clock;
+	mode->clock = pipe_config->hw.adjusted_mode.crtc_clock;
 
 	mode->hsync = drm_mode_hsync(mode);
 	mode->vrefresh = drm_mode_vrefresh(mode);
@@ -8415,7 +8760,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 
 static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 pipeconf;
 
@@ -8452,7 +8797,7 @@ static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state)
 		}
 	}
 
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) {
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) {
 		if (INTEL_GEN(dev_priv) < 4 ||
 		    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_SDVO))
 			pipeconf |= PIPECONF_INTERLACE_W_FIELD_INDICATION;
@@ -8468,6 +8813,8 @@ static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state)
 
 	pipeconf |= PIPECONF_GAMMA_MODE(crtc_state->gamma_mode);
 
+	pipeconf |= PIPECONF_FRAME_START_DELAY(0);
+
 	I915_WRITE(PIPECONF(crtc->pipe), pipeconf);
 	POSTING_READ(PIPECONF(crtc->pipe));
 }
@@ -8567,9 +8914,9 @@ static int pnv_crtc_compute_clock(struct intel_crtc *crtc,
 			DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n", refclk);
 		}
 
-		limit = &intel_limits_pineview_lvds;
+		limit = &pnv_limits_lvds;
 	} else {
-		limit = &intel_limits_pineview_sdvo;
+		limit = &pnv_limits_sdvo;
 	}
 
 	if (!crtc_state->clock_set &&
@@ -8861,7 +9208,7 @@ bdw_get_pipemisc_output_format(struct intel_crtc *crtc)
 
 static void i9xx_get_pipe_color_config(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
@@ -8985,7 +9332,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	 * but in case the pipe is enabled w/o any ports we need a sane
 	 * default.
 	 */
-	pipe_config->base.adjusted_mode.crtc_clock =
+	pipe_config->hw.adjusted_mode.crtc_clock =
 		pipe_config->port_clock / pipe_config->pixel_multiplier;
 
 	ret = true;
@@ -8996,7 +9343,7 @@ out:
 	return ret;
 }
 
-static void ironlake_init_pch_refclk(struct drm_i915_private *dev_priv)
+static void ilk_init_pch_refclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_encoder *encoder;
 	int i;
@@ -9494,14 +9841,14 @@ static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
 void intel_init_pch_refclk(struct drm_i915_private *dev_priv)
 {
 	if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv))
-		ironlake_init_pch_refclk(dev_priv);
+		ilk_init_pch_refclk(dev_priv);
 	else if (HAS_PCH_LPT(dev_priv))
 		lpt_init_pch_refclk(dev_priv);
 }
 
-static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state)
+static void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
@@ -9529,7 +9876,7 @@ static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state)
 	if (crtc_state->dither)
 		val |= (PIPECONF_DITHER_EN | PIPECONF_DITHER_TYPE_SP);
 
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
 		val |= PIPECONF_INTERLACED_ILK;
 	else
 		val |= PIPECONF_PROGRESSIVE;
@@ -9549,13 +9896,15 @@ static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state)
 
 	val |= PIPECONF_GAMMA_MODE(crtc_state->gamma_mode);
 
+	val |= PIPECONF_FRAME_START_DELAY(0);
+
 	I915_WRITE(PIPECONF(pipe), val);
 	POSTING_READ(PIPECONF(pipe));
 }
 
-static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state)
+static void hsw_set_pipeconf(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 val = 0;
@@ -9563,7 +9912,7 @@ static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state)
 	if (IS_HASWELL(dev_priv) && crtc_state->dither)
 		val |= (PIPECONF_DITHER_EN | PIPECONF_DITHER_TYPE_SP);
 
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
 		val |= PIPECONF_INTERLACED_ILK;
 	else
 		val |= PIPECONF_PROGRESSIVE;
@@ -9578,7 +9927,7 @@ static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state)
 
 static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 val = 0;
 
@@ -9641,7 +9990,7 @@ int bdw_get_pipemisc_bpp(struct intel_crtc *crtc)
 	}
 }
 
-int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp)
+int ilk_get_lanes_required(int target_clock, int link_bw, int bpp)
 {
 	/*
 	 * Account for spread spectrum to avoid
@@ -9652,14 +10001,14 @@ int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp)
 	return DIV_ROUND_UP(bps, link_bw * 8);
 }
 
-static bool ironlake_needs_fb_cb_tune(struct dpll *dpll, int factor)
+static bool ilk_needs_fb_cb_tune(struct dpll *dpll, int factor)
 {
 	return i9xx_dpll_compute_m(dpll) < factor * dpll->n;
 }
 
-static void ironlake_compute_dpll(struct intel_crtc *crtc,
-				  struct intel_crtc_state *crtc_state,
-				  struct dpll *reduced_clock)
+static void ilk_compute_dpll(struct intel_crtc *crtc,
+			     struct intel_crtc_state *crtc_state,
+			     struct dpll *reduced_clock)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 dpll, fp, fp2;
@@ -9679,7 +10028,7 @@ static void ironlake_compute_dpll(struct intel_crtc *crtc,
 
 	fp = i9xx_dpll_compute_fp(&crtc_state->dpll);
 
-	if (ironlake_needs_fb_cb_tune(&crtc_state->dpll, factor))
+	if (ilk_needs_fb_cb_tune(&crtc_state->dpll, factor))
 		fp |= FP_CB_TUNE;
 
 	if (reduced_clock) {
@@ -9759,12 +10108,12 @@ static void ironlake_compute_dpll(struct intel_crtc *crtc,
 	crtc_state->dpll_hw_state.fp1 = fp2;
 }
 
-static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
-				       struct intel_crtc_state *crtc_state)
+static int ilk_crtc_compute_clock(struct intel_crtc *crtc,
+				  struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 	const struct intel_limit *limit;
 	int refclk = 120000;
 
@@ -9784,17 +10133,17 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
 
 		if (intel_is_dual_link_lvds(dev_priv)) {
 			if (refclk == 100000)
-				limit = &intel_limits_ironlake_dual_lvds_100m;
+				limit = &ilk_limits_dual_lvds_100m;
 			else
-				limit = &intel_limits_ironlake_dual_lvds;
+				limit = &ilk_limits_dual_lvds;
 		} else {
 			if (refclk == 100000)
-				limit = &intel_limits_ironlake_single_lvds_100m;
+				limit = &ilk_limits_single_lvds_100m;
 			else
-				limit = &intel_limits_ironlake_single_lvds;
+				limit = &ilk_limits_single_lvds;
 		}
 	} else {
-		limit = &intel_limits_ironlake_dac;
+		limit = &ilk_limits_dac;
 	}
 
 	if (!crtc_state->clock_set &&
@@ -9804,7 +10153,7 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
 		return -EINVAL;
 	}
 
-	ironlake_compute_dpll(crtc, crtc_state, NULL);
+	ilk_compute_dpll(crtc, crtc_state, NULL);
 
 	if (!intel_reserve_shared_dplls(state, crtc, NULL)) {
 		DRM_DEBUG_KMS("failed to find PLL for pipe %c\n",
@@ -9879,15 +10228,15 @@ void intel_dp_get_m_n(struct intel_crtc *crtc,
 					     &pipe_config->dp_m2_n2);
 }
 
-static void ironlake_get_fdi_m_n_config(struct intel_crtc *crtc,
-					struct intel_crtc_state *pipe_config)
+static void ilk_get_fdi_m_n_config(struct intel_crtc *crtc,
+				   struct intel_crtc_state *pipe_config)
 {
 	intel_cpu_transcoder_get_m_n(crtc, pipe_config->cpu_transcoder,
 				     &pipe_config->fdi_m_n, NULL);
 }
 
-static void skylake_get_pfit_config(struct intel_crtc *crtc,
-				    struct intel_crtc_state *pipe_config)
+static void skl_get_pfit_config(struct intel_crtc *crtc,
+				struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -9918,8 +10267,8 @@ static void skylake_get_pfit_config(struct intel_crtc *crtc,
 }
 
 static void
-skylake_get_initial_plane_config(struct intel_crtc *crtc,
-				 struct intel_initial_plane_config *plane_config)
+skl_get_initial_plane_config(struct intel_crtc *crtc,
+			     struct intel_initial_plane_config *plane_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -9977,7 +10326,11 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	case PLANE_CTL_TILED_Y:
 		plane_config->tiling = I915_TILING_Y;
 		if (val & PLANE_CTL_RENDER_DECOMPRESSION_ENABLE)
-			fb->modifier = I915_FORMAT_MOD_Y_TILED_CCS;
+			fb->modifier = INTEL_GEN(dev_priv) >= 12 ?
+				I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS :
+				I915_FORMAT_MOD_Y_TILED_CCS;
+		else if (val & PLANE_CTL_MEDIA_DECOMPRESSION_ENABLE)
+			fb->modifier = I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
 		else
 			fb->modifier = I915_FORMAT_MOD_Y_TILED;
 		break;
@@ -10044,8 +10397,8 @@ error:
 	kfree(intel_fb);
 }
 
-static void ironlake_get_pfit_config(struct intel_crtc *crtc,
-				     struct intel_crtc_state *pipe_config)
+static void ilk_get_pfit_config(struct intel_crtc *crtc,
+				struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -10068,8 +10421,8 @@ static void ironlake_get_pfit_config(struct intel_crtc *crtc,
 	}
 }
 
-static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
-				     struct intel_crtc_state *pipe_config)
+static bool ilk_get_pipe_config(struct intel_crtc *crtc,
+				struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -10140,7 +10493,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->fdi_lanes = ((FDI_DP_PORT_WIDTH_MASK & tmp) >>
 					  FDI_DP_PORT_WIDTH_SHIFT) + 1;
 
-		ironlake_get_fdi_m_n_config(crtc, pipe_config);
+		ilk_get_fdi_m_n_config(crtc, pipe_config);
 
 		if (HAS_PCH_IBX(dev_priv)) {
 			/*
@@ -10168,7 +10521,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 			((tmp & PLL_REF_SDVO_HDMI_MULTIPLIER_MASK)
 			 >> PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT) + 1;
 
-		ironlake_pch_clock_get(crtc, pipe_config);
+		ilk_pch_clock_get(crtc, pipe_config);
 	} else {
 		pipe_config->pixel_multiplier = 1;
 	}
@@ -10176,7 +10529,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	intel_get_pipe_timings(crtc, pipe_config);
 	intel_get_pipe_src_size(crtc, pipe_config);
 
-	ironlake_get_pfit_config(crtc, pipe_config);
+	ilk_get_pfit_config(crtc, pipe_config);
 
 	ret = true;
 
@@ -10185,12 +10538,13 @@ out:
 
 	return ret;
 }
-static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
-				      struct intel_crtc_state *crtc_state)
+
+static int hsw_crtc_compute_clock(struct intel_crtc *crtc,
+				  struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 
 	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) ||
 	    INTEL_GEN(dev_priv) >= 11) {
@@ -10207,9 +10561,8 @@ static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
 	return 0;
 }
 
-static void cannonlake_get_ddi_pll(struct drm_i915_private *dev_priv,
-				   enum port port,
-				   struct intel_crtc_state *pipe_config)
+static void cnl_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
+			    struct intel_crtc_state *pipe_config)
 {
 	enum intel_dpll_id id;
 	u32 temp;
@@ -10223,9 +10576,8 @@ static void cannonlake_get_ddi_pll(struct drm_i915_private *dev_priv,
 	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
 }
 
-static void icelake_get_ddi_pll(struct drm_i915_private *dev_priv,
-				enum port port,
-				struct intel_crtc_state *pipe_config)
+static void icl_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
+			    struct intel_crtc_state *pipe_config)
 {
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 	enum icl_port_dpll_id port_dpll_id;
@@ -10284,9 +10636,8 @@ static void bxt_get_ddi_pll(struct drm_i915_private *dev_priv,
 	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
 }
 
-static void skylake_get_ddi_pll(struct drm_i915_private *dev_priv,
-				enum port port,
-				struct intel_crtc_state *pipe_config)
+static void skl_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
+			    struct intel_crtc_state *pipe_config)
 {
 	enum intel_dpll_id id;
 	u32 temp;
@@ -10300,9 +10651,8 @@ static void skylake_get_ddi_pll(struct drm_i915_private *dev_priv,
 	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
 }
 
-static void haswell_get_ddi_pll(struct drm_i915_private *dev_priv,
-				enum port port,
-				struct intel_crtc_state *pipe_config)
+static void hsw_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
+			    struct intel_crtc_state *pipe_config)
 {
 	enum intel_dpll_id id;
 	u32 ddi_pll_sel = I915_READ(PORT_CLK_SEL(port));
@@ -10403,6 +10753,9 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 		case TRANS_DDI_EDP_INPUT_C_ONOFF:
 			trans_pipe = PIPE_C;
 			break;
+		case TRANS_DDI_EDP_INPUT_D_ONOFF:
+			trans_pipe = PIPE_D;
+			break;
 		}
 
 		if (trans_pipe == crtc->pipe) {
@@ -10487,31 +10840,36 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 	return transcoder_is_dsi(pipe_config->cpu_transcoder);
 }
 
-static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
-				       struct intel_crtc_state *pipe_config)
+static void hsw_get_ddi_port_state(struct intel_crtc *crtc,
+				   struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	struct intel_shared_dpll *pll;
 	enum port port;
 	u32 tmp;
 
-	tmp = I915_READ(TRANS_DDI_FUNC_CTL(pipe_config->cpu_transcoder));
-
-	if (INTEL_GEN(dev_priv) >= 12)
-		port = TGL_TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp);
-	else
-		port = TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp);
+	if (transcoder_is_dsi(cpu_transcoder)) {
+		port = (cpu_transcoder == TRANSCODER_DSI_A) ?
+						PORT_A : PORT_B;
+	} else {
+		tmp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
+		if (INTEL_GEN(dev_priv) >= 12)
+			port = TGL_TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp);
+		else
+			port = TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp);
+	}
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		icelake_get_ddi_pll(dev_priv, port, pipe_config);
+		icl_get_ddi_pll(dev_priv, port, pipe_config);
 	else if (IS_CANNONLAKE(dev_priv))
-		cannonlake_get_ddi_pll(dev_priv, port, pipe_config);
+		cnl_get_ddi_pll(dev_priv, port, pipe_config);
 	else if (IS_GEN9_BC(dev_priv))
-		skylake_get_ddi_pll(dev_priv, port, pipe_config);
+		skl_get_ddi_pll(dev_priv, port, pipe_config);
 	else if (IS_GEN9_LP(dev_priv))
 		bxt_get_ddi_pll(dev_priv, port, pipe_config);
 	else
-		haswell_get_ddi_pll(dev_priv, port, pipe_config);
+		hsw_get_ddi_pll(dev_priv, port, pipe_config);
 
 	pll = pipe_config->shared_dpll;
 	if (pll) {
@@ -10532,7 +10890,7 @@ static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 		pipe_config->fdi_lanes = ((FDI_DP_PORT_WIDTH_MASK & tmp) >>
 					  FDI_DP_PORT_WIDTH_SHIFT) + 1;
 
-		ironlake_get_fdi_m_n_config(crtc, pipe_config);
+		ilk_get_fdi_m_n_config(crtc, pipe_config);
 	}
 }
 
@@ -10554,9 +10912,9 @@ static enum transcoder transcoder_master_readout(struct drm_i915_private *dev_pr
 		return master_select - 1;
 }
 
-static void icelake_get_trans_port_sync_config(struct intel_crtc_state *crtc_state)
+static void icl_get_trans_port_sync_config(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 transcoders;
 	enum transcoder cpu_transcoder;
 
@@ -10589,8 +10947,8 @@ static void icelake_get_trans_port_sync_config(struct intel_crtc_state *crtc_sta
 		crtc_state->sync_mode_slaves_mask);
 }
 
-static bool haswell_get_pipe_config(struct intel_crtc *crtc,
-				    struct intel_crtc_state *pipe_config)
+static bool hsw_get_pipe_config(struct intel_crtc *crtc,
+				struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	intel_wakeref_t wakerefs[POWER_DOMAIN_NUM], wf;
@@ -10598,8 +10956,6 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	u64 power_domain_mask;
 	bool active;
 
-	intel_crtc_init_scalers(crtc, pipe_config);
-
 	pipe_config->master_transcoder = INVALID_TRANSCODER;
 
 	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
@@ -10627,7 +10983,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 	if (!transcoder_is_dsi(pipe_config->cpu_transcoder) ||
 	    INTEL_GEN(dev_priv) >= 11) {
-		haswell_get_ddi_port_state(crtc, pipe_config);
+		hsw_get_ddi_port_state(crtc, pipe_config);
 		intel_get_pipe_timings(crtc, pipe_config);
 	}
 
@@ -10684,9 +11040,9 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		power_domain_mask |= BIT_ULL(power_domain);
 
 		if (INTEL_GEN(dev_priv) >= 9)
-			skylake_get_pfit_config(crtc, pipe_config);
+			skl_get_pfit_config(crtc, pipe_config);
 		else
-			ironlake_get_pfit_config(crtc, pipe_config);
+			ilk_get_pfit_config(crtc, pipe_config);
 	}
 
 	if (hsw_crtc_supports_ips(crtc)) {
@@ -10712,7 +11068,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 	if (INTEL_GEN(dev_priv) >= 11 &&
 	    !transcoder_is_dsi(pipe_config->cpu_transcoder))
-		icelake_get_trans_port_sync_config(pipe_config);
+		icl_get_trans_port_sync_config(pipe_config);
 
 out:
 	for_each_power_domain(power_domain, power_domain_mask)
@@ -10725,8 +11081,8 @@ out:
 static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	const struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	u32 base;
 
@@ -10740,8 +11096,8 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 
 static u32 intel_cursor_position(const struct intel_plane_state *plane_state)
 {
-	int x = plane_state->base.dst.x1;
-	int y = plane_state->base.dst.y1;
+	int x = plane_state->uapi.dst.x1;
+	int y = plane_state->uapi.dst.y1;
 	u32 pos = 0;
 
 	if (x < 0) {
@@ -10762,9 +11118,9 @@ static u32 intel_cursor_position(const struct intel_plane_state *plane_state)
 static bool intel_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
 	const struct drm_mode_config *config =
-		&plane_state->base.plane->dev->mode_config;
-	int width = drm_rect_width(&plane_state->base.dst);
-	int height = drm_rect_height(&plane_state->base.dst);
+		&plane_state->uapi.plane->dev->mode_config;
+	int width = drm_rect_width(&plane_state->uapi.dst);
+	int height = drm_rect_height(&plane_state->uapi.dst);
 
 	return width > 0 && width <= config->cursor_width &&
 		height > 0 && height <= config->cursor_height;
@@ -10773,8 +11129,8 @@ static bool intel_cursor_size_ok(const struct intel_plane_state *plane_state)
 static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	unsigned int rotation = plane_state->hw.rotation;
 	int src_x, src_y;
 	u32 offset;
 	int ret;
@@ -10783,11 +11139,11 @@ static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
-	src_x = plane_state->base.src.x1 >> 16;
-	src_y = plane_state->base.src.y1 >> 16;
+	src_x = plane_state->uapi.src.x1 >> 16;
+	src_y = plane_state->uapi.src.y1 >> 16;
 
 	intel_add_fb_offsets(&src_x, &src_y, plane_state, 0);
 	offset = intel_plane_compute_aligned_offset(&src_x, &src_y,
@@ -10802,14 +11158,14 @@ static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.
 	 */
-	drm_rect_translate_to(&plane_state->base.src,
+	drm_rect_translate_to(&plane_state->uapi.src,
 			      src_x << 16, src_y << 16);
 
 	/* ILK+ do this automagically in hardware */
 	if (HAS_GMCH(dev_priv) && rotation & DRM_MODE_ROTATE_180) {
-		const struct drm_framebuffer *fb = plane_state->base.fb;
-		int src_w = drm_rect_width(&plane_state->base.src) >> 16;
-		int src_h = drm_rect_height(&plane_state->base.src) >> 16;
+		const struct drm_framebuffer *fb = plane_state->hw.fb;
+		int src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+		int src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 
 		offset += (src_h * src_w - 1) * fb->format->cpp[0];
 	}
@@ -10824,7 +11180,7 @@ static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 static int intel_check_cursor(struct intel_crtc_state *crtc_state,
 			      struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
 
 	if (fb && fb->modifier != DRM_FORMAT_MOD_LINEAR) {
@@ -10832,8 +11188,8 @@ static int intel_check_cursor(struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  true, true);
@@ -10841,14 +11197,14 @@ static int intel_check_cursor(struct intel_crtc_state *crtc_state,
 		return ret;
 
 	/* Use the unclipped src/dst rectangles, which we program to hw */
-	plane_state->base.src = drm_plane_state_src(&plane_state->base);
-	plane_state->base.dst = drm_plane_state_dest(&plane_state->base);
+	plane_state->uapi.src = drm_plane_state_src(&plane_state->uapi);
+	plane_state->uapi.dst = drm_plane_state_dest(&plane_state->uapi);
 
 	ret = intel_cursor_check_surface(plane_state);
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = intel_plane_check_src_coordinates(plane_state);
@@ -10886,7 +11242,7 @@ static u32 i845_cursor_ctl(const struct intel_crtc_state *crtc_state,
 
 static bool i845_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
-	int width = drm_rect_width(&plane_state->base.dst);
+	int width = drm_rect_width(&plane_state->uapi.dst);
 
 	/*
 	 * 845g/865g are only limited by the width of their cursors,
@@ -10898,7 +11254,7 @@ static bool i845_cursor_size_ok(const struct intel_plane_state *plane_state)
 static int i845_check_cursor(struct intel_crtc_state *crtc_state,
 			     struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
 
 	ret = intel_check_cursor(crtc_state, plane_state);
@@ -10912,12 +11268,12 @@ static int i845_check_cursor(struct intel_crtc_state *crtc_state,
 	/* Check for which cursor types we support */
 	if (!i845_cursor_size_ok(plane_state)) {
 		DRM_DEBUG("Cursor dimension %dx%d not supported\n",
-			  drm_rect_width(&plane_state->base.dst),
-			  drm_rect_height(&plane_state->base.dst));
+			  drm_rect_width(&plane_state->uapi.dst),
+			  drm_rect_height(&plane_state->uapi.dst));
 		return -EINVAL;
 	}
 
-	WARN_ON(plane_state->base.visible &&
+	WARN_ON(plane_state->uapi.visible &&
 		plane_state->color_plane[0].stride != fb->pitches[0]);
 
 	switch (fb->pitches[0]) {
@@ -10945,9 +11301,9 @@ static void i845_update_cursor(struct intel_plane *plane,
 	u32 cntl = 0, base = 0, pos = 0, size = 0;
 	unsigned long irqflags;
 
-	if (plane_state && plane_state->base.visible) {
-		unsigned int width = drm_rect_width(&plane_state->base.dst);
-		unsigned int height = drm_rect_height(&plane_state->base.dst);
+	if (plane_state && plane_state->uapi.visible) {
+		unsigned int width = drm_rect_width(&plane_state->uapi.dst);
+		unsigned int height = drm_rect_height(&plane_state->uapi.dst);
 
 		cntl = plane_state->ctl |
 			i845_cursor_ctl_crtc(crtc_state);
@@ -11020,7 +11376,7 @@ i9xx_cursor_max_stride(struct intel_plane *plane,
 
 static u32 i9xx_cursor_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 cntl = 0;
 
@@ -11043,13 +11399,13 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 			   const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
+		to_i915(plane_state->uapi.plane->dev);
 	u32 cntl = 0;
 
 	if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv))
 		cntl |= MCURSOR_TRICKLE_FEED_DISABLE;
 
-	switch (drm_rect_width(&plane_state->base.dst)) {
+	switch (drm_rect_width(&plane_state->uapi.dst)) {
 	case 64:
 		cntl |= MCURSOR_MODE_64_ARGB_AX;
 		break;
@@ -11060,11 +11416,11 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 		cntl |= MCURSOR_MODE_256_ARGB_AX;
 		break;
 	default:
-		MISSING_CASE(drm_rect_width(&plane_state->base.dst));
+		MISSING_CASE(drm_rect_width(&plane_state->uapi.dst));
 		return 0;
 	}
 
-	if (plane_state->base.rotation & DRM_MODE_ROTATE_180)
+	if (plane_state->hw.rotation & DRM_MODE_ROTATE_180)
 		cntl |= MCURSOR_ROTATE_180;
 
 	return cntl;
@@ -11073,9 +11429,9 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 static bool i9xx_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	int width = drm_rect_width(&plane_state->base.dst);
-	int height = drm_rect_height(&plane_state->base.dst);
+		to_i915(plane_state->uapi.plane->dev);
+	int width = drm_rect_width(&plane_state->uapi.dst);
+	int height = drm_rect_height(&plane_state->uapi.dst);
 
 	if (!intel_cursor_size_ok(plane_state))
 		return false;
@@ -11097,7 +11453,7 @@ static bool i9xx_cursor_size_ok(const struct intel_plane_state *plane_state)
 	 * cursors.
 	 */
 	if (HAS_CUR_FBC(dev_priv) &&
-	    plane_state->base.rotation & DRM_MODE_ROTATE_0) {
+	    plane_state->hw.rotation & DRM_MODE_ROTATE_0) {
 		if (height < 8 || height > width)
 			return false;
 	} else {
@@ -11111,9 +11467,9 @@ static bool i9xx_cursor_size_ok(const struct intel_plane_state *plane_state)
 static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 			     struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	int ret;
 
@@ -11128,19 +11484,19 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 	/* Check for which cursor types we support */
 	if (!i9xx_cursor_size_ok(plane_state)) {
 		DRM_DEBUG("Cursor dimension %dx%d not supported\n",
-			  drm_rect_width(&plane_state->base.dst),
-			  drm_rect_height(&plane_state->base.dst));
+			  drm_rect_width(&plane_state->uapi.dst),
+			  drm_rect_height(&plane_state->uapi.dst));
 		return -EINVAL;
 	}
 
-	WARN_ON(plane_state->base.visible &&
+	WARN_ON(plane_state->uapi.visible &&
 		plane_state->color_plane[0].stride != fb->pitches[0]);
 
 	if (fb->pitches[0] !=
-	    drm_rect_width(&plane_state->base.dst) * fb->format->cpp[0]) {
+	    drm_rect_width(&plane_state->uapi.dst) * fb->format->cpp[0]) {
 		DRM_DEBUG_KMS("Invalid cursor stride (%u) (cursor width %d)\n",
 			      fb->pitches[0],
-			      drm_rect_width(&plane_state->base.dst));
+			      drm_rect_width(&plane_state->uapi.dst));
 		return -EINVAL;
 	}
 
@@ -11155,7 +11511,7 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 	 * Refuse the put the cursor into that compromised position.
 	 */
 	if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_C &&
-	    plane_state->base.visible && plane_state->base.dst.x1 < 0) {
+	    plane_state->uapi.visible && plane_state->uapi.dst.x1 < 0) {
 		DRM_DEBUG_KMS("CHV cursor C not allowed to straddle the left screen edge\n");
 		return -EINVAL;
 	}
@@ -11174,9 +11530,9 @@ static void i9xx_update_cursor(struct intel_plane *plane,
 	u32 cntl = 0, base = 0, pos = 0, fbc_ctl = 0;
 	unsigned long irqflags;
 
-	if (plane_state && plane_state->base.visible) {
-		unsigned width = drm_rect_width(&plane_state->base.dst);
-		unsigned height = drm_rect_height(&plane_state->base.dst);
+	if (plane_state && plane_state->uapi.visible) {
+		unsigned width = drm_rect_width(&plane_state->uapi.dst);
+		unsigned height = drm_rect_height(&plane_state->uapi.dst);
 
 		cntl = plane_state->ctl |
 			i9xx_cursor_ctl_crtc(crtc_state);
@@ -11332,7 +11688,7 @@ int intel_get_load_detect_pipe(struct drm_connector *connector,
 {
 	struct intel_crtc *intel_crtc;
 	struct intel_encoder *intel_encoder =
-		intel_attached_encoder(connector);
+		intel_attached_encoder(to_intel_connector(connector));
 	struct drm_crtc *possible_crtc;
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_crtc *crtc = NULL;
@@ -11431,9 +11787,9 @@ found:
 		goto fail;
 	}
 
-	crtc_state->base.active = crtc_state->base.enable = true;
+	crtc_state->uapi.active = true;
 
-	ret = drm_atomic_set_mode_for_crtc(&crtc_state->base,
+	ret = drm_atomic_set_mode_for_crtc(&crtc_state->uapi,
 					   &load_detect_mode);
 	if (ret)
 		goto fail;
@@ -11486,7 +11842,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 				    struct drm_modeset_acquire_ctx *ctx)
 {
 	struct intel_encoder *intel_encoder =
-		intel_attached_encoder(connector);
+		intel_attached_encoder(to_intel_connector(connector));
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_atomic_state *state = old->restore_state;
 	int ret;
@@ -11629,8 +11985,8 @@ int intel_dotclock_calculate(int link_freq,
 	return div_u64(mul_u32_u32(m_n->link_m, link_freq), m_n->link_n);
 }
 
-static void ironlake_pch_clock_get(struct intel_crtc *crtc,
-				   struct intel_crtc_state *pipe_config)
+static void ilk_pch_clock_get(struct intel_crtc *crtc,
+			      struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
@@ -11642,11 +11998,38 @@ static void ironlake_pch_clock_get(struct intel_crtc *crtc,
 	 * we may need some idea for the dotclock anyway.
 	 * Calculate one based on the FDI configuration.
 	 */
-	pipe_config->base.adjusted_mode.crtc_clock =
+	pipe_config->hw.adjusted_mode.crtc_clock =
 		intel_dotclock_calculate(intel_fdi_link_freq(dev_priv, pipe_config),
 					 &pipe_config->fdi_m_n);
 }
 
+static void intel_crtc_state_reset(struct intel_crtc_state *crtc_state,
+				   struct intel_crtc *crtc)
+{
+	memset(crtc_state, 0, sizeof(*crtc_state));
+
+	__drm_atomic_helper_crtc_state_reset(&crtc_state->uapi, &crtc->base);
+
+	crtc_state->cpu_transcoder = INVALID_TRANSCODER;
+	crtc_state->master_transcoder = INVALID_TRANSCODER;
+	crtc_state->hsw_workaround_pipe = INVALID_PIPE;
+	crtc_state->output_format = INTEL_OUTPUT_FORMAT_INVALID;
+	crtc_state->scaler_state.scaler_id = -1;
+	crtc_state->mst_master_transcoder = INVALID_TRANSCODER;
+}
+
+static struct intel_crtc_state *intel_crtc_state_alloc(struct intel_crtc *crtc)
+{
+	struct intel_crtc_state *crtc_state;
+
+	crtc_state = kmalloc(sizeof(*crtc_state), GFP_KERNEL);
+
+	if (crtc_state)
+		intel_crtc_state_reset(crtc_state, crtc);
+
+	return crtc_state;
+}
+
 /* Returns the currently programmed mode of the given encoder. */
 struct drm_display_mode *
 intel_encoder_current_mode(struct intel_encoder *encoder)
@@ -11666,14 +12049,12 @@ intel_encoder_current_mode(struct intel_encoder *encoder)
 	if (!mode)
 		return NULL;
 
-	crtc_state = kzalloc(sizeof(*crtc_state), GFP_KERNEL);
+	crtc_state = intel_crtc_state_alloc(crtc);
 	if (!crtc_state) {
 		kfree(mode);
 		return NULL;
 	}
 
-	crtc_state->base.crtc = &crtc->base;
-
 	if (!dev_priv->display.get_pipe_config(crtc, crtc_state)) {
 		kfree(crtc_state);
 		kfree(mode);
@@ -11711,18 +12092,18 @@ static bool intel_wm_need_update(const struct intel_plane_state *cur,
 				 struct intel_plane_state *new)
 {
 	/* Update watermarks on tiling or size changes. */
-	if (new->base.visible != cur->base.visible)
+	if (new->uapi.visible != cur->uapi.visible)
 		return true;
 
-	if (!cur->base.fb || !new->base.fb)
+	if (!cur->hw.fb || !new->hw.fb)
 		return false;
 
-	if (cur->base.fb->modifier != new->base.fb->modifier ||
-	    cur->base.rotation != new->base.rotation ||
-	    drm_rect_width(&new->base.src) != drm_rect_width(&cur->base.src) ||
-	    drm_rect_height(&new->base.src) != drm_rect_height(&cur->base.src) ||
-	    drm_rect_width(&new->base.dst) != drm_rect_width(&cur->base.dst) ||
-	    drm_rect_height(&new->base.dst) != drm_rect_height(&cur->base.dst))
+	if (cur->hw.fb->modifier != new->hw.fb->modifier ||
+	    cur->hw.rotation != new->hw.rotation ||
+	    drm_rect_width(&new->uapi.src) != drm_rect_width(&cur->uapi.src) ||
+	    drm_rect_height(&new->uapi.src) != drm_rect_height(&cur->uapi.src) ||
+	    drm_rect_width(&new->uapi.dst) != drm_rect_width(&cur->uapi.dst) ||
+	    drm_rect_height(&new->uapi.dst) != drm_rect_height(&cur->uapi.dst))
 		return true;
 
 	return false;
@@ -11730,10 +12111,10 @@ static bool intel_wm_need_update(const struct intel_plane_state *cur,
 
 static bool needs_scaling(const struct intel_plane_state *state)
 {
-	int src_w = drm_rect_width(&state->base.src) >> 16;
-	int src_h = drm_rect_height(&state->base.src) >> 16;
-	int dst_w = drm_rect_width(&state->base.dst);
-	int dst_h = drm_rect_height(&state->base.dst);
+	int src_w = drm_rect_width(&state->uapi.src) >> 16;
+	int src_h = drm_rect_height(&state->uapi.src) >> 16;
+	int dst_w = drm_rect_width(&state->uapi.dst);
+	int dst_h = drm_rect_height(&state->uapi.dst);
 
 	return (src_w != dst_w || src_h != dst_h);
 }
@@ -11743,12 +12124,12 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 				    const struct intel_plane_state *old_plane_state,
 				    struct intel_plane_state *plane_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	bool mode_changed = needs_modeset(crtc_state);
-	bool was_crtc_enabled = old_crtc_state->base.active;
-	bool is_crtc_enabled = crtc_state->base.active;
+	bool was_crtc_enabled = old_crtc_state->hw.active;
+	bool is_crtc_enabled = crtc_state->hw.active;
 	bool turn_off, turn_on, visible, was_visible;
 	int ret;
 
@@ -11758,8 +12139,8 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 			return ret;
 	}
 
-	was_visible = old_plane_state->base.visible;
-	visible = plane_state->base.visible;
+	was_visible = old_plane_state->uapi.visible;
+	visible = plane_state->uapi.visible;
 
 	if (!was_crtc_enabled && WARN_ON(was_visible))
 		was_visible = false;
@@ -11775,7 +12156,7 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 	 * only combine the results from all planes in the current place?
 	 */
 	if (!is_crtc_enabled) {
-		plane_state->base.visible = visible = false;
+		plane_state->uapi.visible = visible = false;
 		crtc_state->active_planes &= ~BIT(plane->id);
 		crtc_state->data_rate[plane->id] = 0;
 		crtc_state->min_cdclk[plane->id] = 0;
@@ -11916,9 +12297,9 @@ static int icl_add_linked_planes(struct intel_atomic_state *state)
 
 static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->base.state);
+	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->uapi.state);
 	struct intel_plane *plane, *linked;
 	struct intel_plane_state *plane_state;
 	int i;
@@ -11935,7 +12316,7 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 			continue;
 
 		plane_state->planar_linked_plane = NULL;
-		if (plane_state->planar_slave && !plane_state->base.visible) {
+		if (plane_state->planar_slave && !plane_state->uapi.visible) {
 			crtc_state->active_planes &= ~BIT(plane->id);
 			crtc_state->update_planes |= BIT(plane->id);
 		}
@@ -11981,6 +12362,25 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 		crtc_state->active_planes |= BIT(linked->id);
 		crtc_state->update_planes |= BIT(linked->id);
 		DRM_DEBUG_KMS("Using %s as Y plane for %s\n", linked->base.name, plane->base.name);
+
+		/* Copy parameters to slave plane */
+		linked_state->ctl = plane_state->ctl | PLANE_CTL_YUV420_Y_PLANE;
+		linked_state->color_ctl = plane_state->color_ctl;
+		memcpy(linked_state->color_plane, plane_state->color_plane,
+		       sizeof(linked_state->color_plane));
+
+		intel_plane_copy_uapi_to_hw_state(linked_state, plane_state);
+		linked_state->uapi.src = plane_state->uapi.src;
+		linked_state->uapi.dst = plane_state->uapi.dst;
+
+		if (icl_is_hdr_plane(dev_priv, plane->id)) {
+			if (linked->id == PLANE_SPRITE5)
+				plane_state->cus_ctl |= PLANE_CUS_PLANE_7;
+			else if (linked->id == PLANE_SPRITE4)
+				plane_state->cus_ctl |= PLANE_CUS_PLANE_6;
+			else
+				MISSING_CASE(linked->id);
+		}
 	}
 
 	return 0;
@@ -11988,97 +12388,130 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 
 static bool c8_planes_changed(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
 	return !old_crtc_state->c8_planes != !new_crtc_state->c8_planes;
 }
 
-static int icl_add_sync_mode_crtcs(struct intel_crtc_state *crtc_state)
+static bool
+intel_atomic_is_master_connector(struct intel_crtc_state *crtc_state)
 {
-	struct drm_crtc *crtc = crtc_state->base.crtc;
-	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->base.state);
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct drm_connector *master_connector, *connector;
+	struct drm_crtc *crtc = crtc_state->uapi.crtc;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
+	struct drm_connector *connector;
 	struct drm_connector_state *connector_state;
+	int i;
+
+	for_each_new_connector_in_state(state, connector, connector_state, i) {
+		if (connector_state->crtc != crtc)
+			continue;
+		if (connector->has_tile &&
+		    connector->tile_h_loc == connector->num_h_tile - 1 &&
+		    connector->tile_v_loc == connector->num_v_tile - 1)
+			return true;
+	}
+
+	return false;
+}
+
+static void reset_port_sync_mode_state(struct intel_crtc_state *crtc_state)
+{
+	crtc_state->master_transcoder = INVALID_TRANSCODER;
+	crtc_state->sync_mode_slaves_mask = 0;
+}
+
+static int icl_compute_port_sync_crtc_state(struct drm_connector *connector,
+					    struct intel_crtc_state *crtc_state,
+					    int num_tiled_conns)
+{
+	struct drm_crtc *crtc = crtc_state->uapi.crtc;
+	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->uapi.state);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	struct drm_connector *master_connector;
 	struct drm_connector_list_iter conn_iter;
 	struct drm_crtc *master_crtc = NULL;
 	struct drm_crtc_state *master_crtc_state;
 	struct intel_crtc_state *master_pipe_config;
-	int i, tile_group_id;
 
 	if (INTEL_GEN(dev_priv) < 11)
 		return 0;
 
+	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP))
+		return 0;
+
 	/*
 	 * In case of tiled displays there could be one or more slaves but there is
 	 * only one master. Lets make the CRTC used by the connector corresponding
 	 * to the last horizonal and last vertical tile a master/genlock CRTC.
 	 * All the other CRTCs corresponding to other tiles of the same Tile group
 	 * are the slave CRTCs and hold a pointer to their genlock CRTC.
+	 * If all tiles not present do not make master slave assignments.
 	 */
-	for_each_new_connector_in_state(&state->base, connector, connector_state, i) {
-		if (connector_state->crtc != crtc)
-			continue;
-		if (!connector->has_tile)
+	if (!connector->has_tile ||
+	    crtc_state->hw.mode.hdisplay != connector->tile_h_size ||
+	    crtc_state->hw.mode.vdisplay != connector->tile_v_size ||
+	    num_tiled_conns < connector->num_h_tile * connector->num_v_tile) {
+		reset_port_sync_mode_state(crtc_state);
+		return 0;
+	}
+	/* Last Horizontal and last vertical tile connector is a master
+	 * Master's crtc state is already populated in slave for port sync
+	 */
+	if (connector->tile_h_loc == connector->num_h_tile - 1 &&
+	    connector->tile_v_loc == connector->num_v_tile - 1)
+		return 0;
+
+	/* Loop through all connectors and configure the Slave crtc_state
+	 * to point to the correct master.
+	 */
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
+	drm_for_each_connector_iter(master_connector, &conn_iter) {
+		struct drm_connector_state *master_conn_state = NULL;
+
+		if (!(master_connector->has_tile &&
+		      master_connector->tile_group->id == connector->tile_group->id))
 			continue;
-		if (crtc_state->base.mode.hdisplay != connector->tile_h_size ||
-		    crtc_state->base.mode.vdisplay != connector->tile_v_size)
-			return 0;
-		if (connector->tile_h_loc == connector->num_h_tile - 1 &&
-		    connector->tile_v_loc == connector->num_v_tile - 1)
+		if (master_connector->tile_h_loc != master_connector->num_h_tile - 1 ||
+		    master_connector->tile_v_loc != master_connector->num_v_tile - 1)
 			continue;
-		crtc_state->sync_mode_slaves_mask = 0;
-		tile_group_id = connector->tile_group->id;
-		drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
-		drm_for_each_connector_iter(master_connector, &conn_iter) {
-			struct drm_connector_state *master_conn_state = NULL;
-
-			if (!master_connector->has_tile)
-				continue;
-			if (master_connector->tile_h_loc != master_connector->num_h_tile - 1 ||
-			    master_connector->tile_v_loc != master_connector->num_v_tile - 1)
-				continue;
-			if (master_connector->tile_group->id != tile_group_id)
-				continue;
 
-			master_conn_state = drm_atomic_get_connector_state(&state->base,
-									   master_connector);
-			if (IS_ERR(master_conn_state)) {
-				drm_connector_list_iter_end(&conn_iter);
-				return PTR_ERR(master_conn_state);
-			}
-			if (master_conn_state->crtc) {
-				master_crtc = master_conn_state->crtc;
-				break;
-			}
+		master_conn_state = drm_atomic_get_connector_state(&state->base,
+								   master_connector);
+		if (IS_ERR(master_conn_state)) {
+			drm_connector_list_iter_end(&conn_iter);
+			return PTR_ERR(master_conn_state);
 		}
-		drm_connector_list_iter_end(&conn_iter);
-
-		if (!master_crtc) {
-			DRM_DEBUG_KMS("Could not find Master CRTC for Slave CRTC %d\n",
-				      connector_state->crtc->base.id);
-			return -EINVAL;
+		if (master_conn_state->crtc) {
+			master_crtc = master_conn_state->crtc;
+			break;
 		}
+	}
+	drm_connector_list_iter_end(&conn_iter);
 
-		master_crtc_state = drm_atomic_get_crtc_state(&state->base,
-							      master_crtc);
-		if (IS_ERR(master_crtc_state))
-			return PTR_ERR(master_crtc_state);
-
-		master_pipe_config = to_intel_crtc_state(master_crtc_state);
-		crtc_state->master_transcoder = master_pipe_config->cpu_transcoder;
-		master_pipe_config->sync_mode_slaves_mask |=
-			BIT(crtc_state->cpu_transcoder);
-		DRM_DEBUG_KMS("Master Transcoder = %s added for Slave CRTC = %d, slave transcoder bitmask = %d\n",
-			      transcoder_name(crtc_state->master_transcoder),
-			      crtc_state->base.crtc->base.id,
-			      master_pipe_config->sync_mode_slaves_mask);
+	if (!master_crtc) {
+		DRM_DEBUG_KMS("Could not find Master CRTC for Slave CRTC %d\n",
+			      crtc->base.id);
+		return -EINVAL;
 	}
 
+	master_crtc_state = drm_atomic_get_crtc_state(&state->base,
+						      master_crtc);
+	if (IS_ERR(master_crtc_state))
+		return PTR_ERR(master_crtc_state);
+
+	master_pipe_config = to_intel_crtc_state(master_crtc_state);
+	crtc_state->master_transcoder = master_pipe_config->cpu_transcoder;
+	master_pipe_config->sync_mode_slaves_mask |=
+		BIT(crtc_state->cpu_transcoder);
+	DRM_DEBUG_KMS("Master Transcoder = %s added for Slave CRTC = %d, slave transcoder bitmask = %d\n",
+		      transcoder_name(crtc_state->master_transcoder),
+		      crtc->base.id,
+		      master_pipe_config->sync_mode_slaves_mask);
+
 	return 0;
 }
 
@@ -12092,10 +12525,10 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	int ret;
 
 	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv) &&
-	    mode_changed && !crtc_state->base.active)
+	    mode_changed && !crtc_state->hw.active)
 		crtc_state->update_wm_post = true;
 
-	if (mode_changed && crtc_state->base.enable &&
+	if (mode_changed && crtc_state->hw.enable &&
 	    dev_priv->display.crtc_compute_clock &&
 	    !WARN_ON(crtc_state->shared_dpll)) {
 		ret = dev_priv->display.crtc_compute_clock(crtc, crtc_state);
@@ -12108,10 +12541,10 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	 * when C8 planes are getting enabled/disabled.
 	 */
 	if (c8_planes_changed(crtc_state))
-		crtc_state->base.color_mgmt_changed = true;
+		crtc_state->uapi.color_mgmt_changed = true;
 
 	if (mode_changed || crtc_state->update_pipe ||
-	    crtc_state->base.color_mgmt_changed) {
+	    crtc_state->uapi.color_mgmt_changed) {
 		ret = intel_color_check(crtc_state);
 		if (ret)
 			return ret;
@@ -12224,7 +12657,7 @@ compute_baseline_pipe_bpp(struct intel_crtc *crtc,
 			  struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct drm_atomic_state *state = pipe_config->base.state;
+	struct drm_atomic_state *state = pipe_config->uapi.state;
 	struct drm_connector *connector;
 	struct drm_connector_state *connector_state;
 	int bpp, i;
@@ -12281,7 +12714,7 @@ static void
 intel_dump_infoframe(struct drm_i915_private *dev_priv,
 		     const union hdmi_infoframe *frame)
 {
-	if ((drm_debug & DRM_UT_KMS) == 0)
+	if (!drm_debug_enabled(DRM_UT_KMS))
 		return;
 
 	hdmi_infoframe_log(KERN_DEBUG, dev_priv->drm.dev, frame);
@@ -12349,14 +12782,14 @@ static const char *output_formats(enum intel_output_format format)
 
 static void intel_dump_plane_state(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	struct drm_format_name_buf format_name;
 
 	if (!fb) {
 		DRM_DEBUG_KMS("[PLANE:%d:%s] fb: [NOFB], visible: %s\n",
 			      plane->base.base.id, plane->base.name,
-			      yesno(plane_state->base.visible));
+			      yesno(plane_state->uapi.visible));
 		return;
 	}
 
@@ -12364,20 +12797,20 @@ static void intel_dump_plane_state(const struct intel_plane_state *plane_state)
 		      plane->base.base.id, plane->base.name,
 		      fb->base.id, fb->width, fb->height,
 		      drm_get_format_name(fb->format->format, &format_name),
-		      yesno(plane_state->base.visible));
+		      yesno(plane_state->uapi.visible));
 	DRM_DEBUG_KMS("\trotation: 0x%x, scaler: %d\n",
-		      plane_state->base.rotation, plane_state->scaler_id);
-	if (plane_state->base.visible)
+		      plane_state->hw.rotation, plane_state->scaler_id);
+	if (plane_state->uapi.visible)
 		DRM_DEBUG_KMS("\tsrc: " DRM_RECT_FP_FMT " dst: " DRM_RECT_FMT "\n",
-			      DRM_RECT_FP_ARG(&plane_state->base.src),
-			      DRM_RECT_ARG(&plane_state->base.dst));
+			      DRM_RECT_FP_ARG(&plane_state->uapi.src),
+			      DRM_RECT_ARG(&plane_state->uapi.dst));
 }
 
 static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 				   struct intel_atomic_state *state,
 				   const char *context)
 {
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct intel_plane_state *plane_state;
 	struct intel_plane *plane;
@@ -12386,14 +12819,14 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s] enable: %s %s\n",
 		      crtc->base.base.id, crtc->base.name,
-		      yesno(pipe_config->base.enable), context);
+		      yesno(pipe_config->hw.enable), context);
 
-	if (!pipe_config->base.enable)
+	if (!pipe_config->hw.enable)
 		goto dump_planes;
 
 	snprintf_output_types(buf, sizeof(buf), pipe_config->output_types);
 	DRM_DEBUG_KMS("active: %s, output_types: %s (0x%x), output format: %s\n",
-		      yesno(pipe_config->base.active),
+		      yesno(pipe_config->hw.active),
 		      buf, pipe_config->output_types,
 		      output_formats(pipe_config->output_format));
 
@@ -12433,10 +12866,10 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 		intel_dump_infoframe(dev_priv, &pipe_config->infoframes.hdmi);
 
 	DRM_DEBUG_KMS("requested mode:\n");
-	drm_mode_debug_printmodeline(&pipe_config->base.mode);
+	drm_mode_debug_printmodeline(&pipe_config->hw.mode);
 	DRM_DEBUG_KMS("adjusted mode:\n");
-	drm_mode_debug_printmodeline(&pipe_config->base.adjusted_mode);
-	intel_dump_crtc_timings(&pipe_config->base.adjusted_mode);
+	drm_mode_debug_printmodeline(&pipe_config->hw.adjusted_mode);
+	intel_dump_crtc_timings(&pipe_config->hw.adjusted_mode);
 	DRM_DEBUG_KMS("port clock: %d, pipe src size: %dx%d, pixel rate %d\n",
 		      pipe_config->port_clock,
 		      pipe_config->pipe_src_w, pipe_config->pipe_src_h,
@@ -12474,6 +12907,9 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 			      pipe_config->csc_mode, pipe_config->gamma_mode,
 			      pipe_config->gamma_enable, pipe_config->csc_enable);
 
+	DRM_DEBUG_KMS("MST master transcoder: %s\n",
+		      transcoder_name(pipe_config->mst_master_transcoder));
+
 dump_planes:
 	if (!state)
 		return;
@@ -12556,22 +12992,59 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state)
 	return ret;
 }
 
+static void
+intel_crtc_copy_uapi_to_hw_state_nomodeset(struct intel_crtc_state *crtc_state)
+{
+	intel_crtc_copy_color_blobs(crtc_state);
+}
+
+static void
+intel_crtc_copy_uapi_to_hw_state(struct intel_crtc_state *crtc_state)
+{
+	crtc_state->hw.enable = crtc_state->uapi.enable;
+	crtc_state->hw.active = crtc_state->uapi.active;
+	crtc_state->hw.mode = crtc_state->uapi.mode;
+	crtc_state->hw.adjusted_mode = crtc_state->uapi.adjusted_mode;
+	intel_crtc_copy_uapi_to_hw_state_nomodeset(crtc_state);
+}
+
+static void intel_crtc_copy_hw_to_uapi_state(struct intel_crtc_state *crtc_state)
+{
+	crtc_state->uapi.enable = crtc_state->hw.enable;
+	crtc_state->uapi.active = crtc_state->hw.active;
+	WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->uapi, &crtc_state->hw.mode) < 0);
+
+	crtc_state->uapi.adjusted_mode = crtc_state->hw.adjusted_mode;
+
+	/* copy color blobs to uapi */
+	drm_property_replace_blob(&crtc_state->uapi.degamma_lut,
+				  crtc_state->hw.degamma_lut);
+	drm_property_replace_blob(&crtc_state->uapi.gamma_lut,
+				  crtc_state->hw.gamma_lut);
+	drm_property_replace_blob(&crtc_state->uapi.ctm,
+				  crtc_state->hw.ctm);
+}
+
 static int
-clear_intel_crtc_state(struct intel_crtc_state *crtc_state)
+intel_crtc_prepare_cleared_state(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->base.crtc->dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_crtc_state *saved_state;
 
-	saved_state = kzalloc(sizeof(*saved_state), GFP_KERNEL);
+	saved_state = intel_crtc_state_alloc(crtc);
 	if (!saved_state)
 		return -ENOMEM;
 
+	/* free the old crtc_state->hw members */
+	intel_crtc_free_hw_state(crtc_state);
+
 	/* FIXME: before the switch to atomic started, a new pipe_config was
 	 * kzalloc'd. Code that depends on any field being zero should be
 	 * fixed, so that the crtc_state can be safely duplicated. For now,
 	 * only fields that are know to not cause problems are preserved. */
 
+	saved_state->uapi = crtc_state->uapi;
 	saved_state->scaler_state = crtc_state->scaler_state;
 	saved_state->shared_dpll = crtc_state->shared_dpll;
 	saved_state->dpll_hw_state = crtc_state->dpll_hw_state;
@@ -12583,37 +13056,34 @@ clear_intel_crtc_state(struct intel_crtc_state *crtc_state)
 		saved_state->wm = crtc_state->wm;
 	/*
 	 * Save the slave bitmask which gets filled for master crtc state during
-	 * slave atomic check call.
+	 * slave atomic check call. For all other CRTCs reset the port sync variables
+	 * crtc_state->master_transcoder needs to be set to INVALID
 	 */
-	if (is_trans_port_sync_master(crtc_state))
+	reset_port_sync_mode_state(saved_state);
+	if (intel_atomic_is_master_connector(crtc_state))
 		saved_state->sync_mode_slaves_mask =
 			crtc_state->sync_mode_slaves_mask;
 
-	/* Keep base drm_crtc_state intact, only clear our extended struct */
-	BUILD_BUG_ON(offsetof(struct intel_crtc_state, base));
-	memcpy(&crtc_state->base + 1, &saved_state->base + 1,
-	       sizeof(*crtc_state) - sizeof(crtc_state->base));
-
+	memcpy(crtc_state, saved_state, sizeof(*crtc_state));
 	kfree(saved_state);
+
+	intel_crtc_copy_uapi_to_hw_state(crtc_state);
+
 	return 0;
 }
 
 static int
 intel_modeset_pipe_config(struct intel_crtc_state *pipe_config)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_atomic_state *state = pipe_config->base.state;
+	struct drm_crtc *crtc = pipe_config->uapi.crtc;
+	struct drm_atomic_state *state = pipe_config->uapi.state;
 	struct intel_encoder *encoder;
 	struct drm_connector *connector;
 	struct drm_connector_state *connector_state;
 	int base_bpp, ret;
-	int i;
+	int i, tile_group_id = -1, num_tiled_conns = 0;
 	bool retry = true;
 
-	ret = clear_intel_crtc_state(pipe_config);
-	if (ret)
-		return ret;
-
 	pipe_config->cpu_transcoder =
 		(enum transcoder) to_intel_crtc(crtc)->pipe;
 
@@ -12622,13 +13092,13 @@ intel_modeset_pipe_config(struct intel_crtc_state *pipe_config)
 	 * positive or negative polarity is requested, treat this as meaning
 	 * negative polarity.
 	 */
-	if (!(pipe_config->base.adjusted_mode.flags &
+	if (!(pipe_config->hw.adjusted_mode.flags &
 	      (DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NHSYNC)))
-		pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_NHSYNC;
+		pipe_config->hw.adjusted_mode.flags |= DRM_MODE_FLAG_NHSYNC;
 
-	if (!(pipe_config->base.adjusted_mode.flags &
+	if (!(pipe_config->hw.adjusted_mode.flags &
 	      (DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC)))
-		pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_NVSYNC;
+		pipe_config->hw.adjusted_mode.flags |= DRM_MODE_FLAG_NVSYNC;
 
 	ret = compute_baseline_pipe_bpp(to_intel_crtc(crtc),
 					pipe_config);
@@ -12645,7 +13115,7 @@ intel_modeset_pipe_config(struct intel_crtc_state *pipe_config)
 	 * computation to clearly distinguish it from the adjusted mode, which
 	 * can be changed by the connectors in the below retry loop.
 	 */
-	drm_mode_get_hv_timing(&pipe_config->base.mode,
+	drm_mode_get_hv_timing(&pipe_config->hw.mode,
 			       &pipe_config->pipe_src_w,
 			       &pipe_config->pipe_src_h);
 
@@ -12678,16 +13148,25 @@ encoder_retry:
 	pipe_config->pixel_multiplier = 1;
 
 	/* Fill in default crtc timings, allow encoders to overwrite them. */
-	drm_mode_set_crtcinfo(&pipe_config->base.adjusted_mode,
+	drm_mode_set_crtcinfo(&pipe_config->hw.adjusted_mode,
 			      CRTC_STEREO_DOUBLE);
 
-	/* Set the crtc_state defaults for trans_port_sync */
-	pipe_config->master_transcoder = INVALID_TRANSCODER;
-	ret = icl_add_sync_mode_crtcs(pipe_config);
-	if (ret) {
-		DRM_DEBUG_KMS("Cannot assign Sync Mode CRTCs: %d\n",
-			      ret);
-		return ret;
+	/* Get tile_group_id of tiled connector */
+	for_each_new_connector_in_state(state, connector, connector_state, i) {
+		if (connector_state->crtc == crtc &&
+		    connector->has_tile) {
+			tile_group_id = connector->tile_group->id;
+			break;
+		}
+	}
+
+	/* Get total number of tiled connectors in state that belong to
+	 * this tile group.
+	 */
+	for_each_new_connector_in_state(state, connector, connector_state, i) {
+		if (connector->has_tile &&
+		    connector->tile_group->id == tile_group_id)
+			num_tiled_conns++;
 	}
 
 	/* Pass our mode to the connectors and the CRTC to give them a chance to
@@ -12698,6 +13177,14 @@ encoder_retry:
 		if (connector_state->crtc != crtc)
 			continue;
 
+		ret = icl_compute_port_sync_crtc_state(connector, pipe_config,
+						       num_tiled_conns);
+		if (ret) {
+			DRM_DEBUG_KMS("Cannot assign Sync Mode CRTCs: %d\n",
+				      ret);
+			return ret;
+		}
+
 		encoder = to_intel_encoder(connector_state->best_encoder);
 		ret = encoder->compute_config(encoder, pipe_config,
 					      connector_state);
@@ -12712,7 +13199,7 @@ encoder_retry:
 	/* Set default port clock if not overwritten by the encoder. Needs to be
 	 * done afterwards in case the encoder adjusts the mode. */
 	if (!pipe_config->port_clock)
-		pipe_config->port_clock = pipe_config->base.adjusted_mode.crtc_clock
+		pipe_config->port_clock = pipe_config->hw.adjusted_mode.crtc_clock
 			* pipe_config->pixel_multiplier;
 
 	ret = intel_crtc_compute_config(to_intel_crtc(crtc), pipe_config);
@@ -12741,6 +13228,12 @@ encoder_retry:
 	DRM_DEBUG_KMS("hw max bpp: %i, pipe bpp: %i, dithering: %i\n",
 		      base_bpp, pipe_config->pipe_bpp, pipe_config->dither);
 
+	/*
+	 * Make drm_calc_timestamping_constants in
+	 * drm_atomic_helper_update_legacy_modeset_state() happy
+	 */
+	pipe_config->uapi.adjusted_mode = pipe_config->hw.adjusted_mode;
+
 	return 0;
 }
 
@@ -12819,7 +13312,7 @@ pipe_config_infoframe_mismatch(struct drm_i915_private *dev_priv,
 			       const union hdmi_infoframe *b)
 {
 	if (fastset) {
-		if ((drm_debug & DRM_UT_KMS) == 0)
+		if (!drm_debug_enabled(DRM_UT_KMS))
 			return;
 
 		DRM_DEBUG_KMS("fastset mismatch in %s infoframe\n", name);
@@ -12879,13 +13372,13 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 			  const struct intel_crtc_state *pipe_config,
 			  bool fastset)
 {
-	struct drm_i915_private *dev_priv = to_i915(current_config->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(current_config->uapi.crtc->dev);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	bool ret = true;
 	u32 bp_gamma = 0;
 	bool fixup_inherited = fastset &&
-		(current_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED) &&
-		!(pipe_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED);
+		(current_config->hw.mode.private_flags & I915_MODE_FLAG_INHERITED) &&
+		!(pipe_config->hw.mode.private_flags & I915_MODE_FLAG_INHERITED);
 
 	if (fixup_inherited && !fastboot_enabled(dev_priv)) {
 		DRM_DEBUG_KMS("initial modeset and fastboot not set\n");
@@ -13074,19 +13567,19 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 	PIPE_CONF_CHECK_X(output_types);
 
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hdisplay);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_htotal);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hblank_start);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hblank_end);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hsync_start);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hsync_end);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hdisplay);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_htotal);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hblank_start);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hblank_end);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hsync_start);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hsync_end);
 
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vdisplay);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vtotal);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vblank_start);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vblank_end);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vsync_start);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vsync_end);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vdisplay);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vtotal);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vblank_start);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vblank_end);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vsync_start);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vsync_end);
 
 	PIPE_CONF_CHECK_I(pixel_multiplier);
 	PIPE_CONF_CHECK_I(output_format);
@@ -13103,17 +13596,17 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 	PIPE_CONF_CHECK_BOOL_INCOMPLETE(has_audio);
 
-	PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+	PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 			      DRM_MODE_FLAG_INTERLACE);
 
 	if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS)) {
-		PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+		PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 				      DRM_MODE_FLAG_PHSYNC);
-		PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+		PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 				      DRM_MODE_FLAG_NHSYNC);
-		PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+		PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 				      DRM_MODE_FLAG_PVSYNC);
-		PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+		PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 				      DRM_MODE_FLAG_NVSYNC);
 	}
 
@@ -13152,7 +13645,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 		bp_gamma = intel_color_get_gamma_bit_precision(pipe_config);
 		if (bp_gamma)
-			PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, base.gamma_lut, bp_gamma);
+			PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, hw.gamma_lut, bp_gamma);
 
 	}
 
@@ -13197,7 +13690,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	if (IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5)
 		PIPE_CONF_CHECK_I(pipe_bpp);
 
-	PIPE_CONF_CHECK_CLOCK_FUZZY(base.adjusted_mode.crtc_clock);
+	PIPE_CONF_CHECK_CLOCK_FUZZY(hw.adjusted_mode.crtc_clock);
 	PIPE_CONF_CHECK_CLOCK_FUZZY(port_clock);
 
 	PIPE_CONF_CHECK_I(min_voltage_level);
@@ -13212,6 +13705,12 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	PIPE_CONF_CHECK_I(sync_mode_slaves_mask);
 	PIPE_CONF_CHECK_I(master_transcoder);
 
+	PIPE_CONF_CHECK_I(dsc.compression_enable);
+	PIPE_CONF_CHECK_I(dsc.dsc_split);
+	PIPE_CONF_CHECK_I(dsc.compressed_bpp);
+
+	PIPE_CONF_CHECK_I(mst_master_transcoder);
+
 #undef PIPE_CONF_CHECK_X
 #undef PIPE_CONF_CHECK_I
 #undef PIPE_CONF_CHECK_BOOL
@@ -13231,7 +13730,7 @@ static void intel_pipe_config_sanity_check(struct drm_i915_private *dev_priv,
 	if (pipe_config->has_pch_encoder) {
 		int fdi_dotclock = intel_dotclock_calculate(intel_fdi_link_freq(dev_priv, pipe_config),
 							    &pipe_config->fdi_m_n);
-		int dotclock = pipe_config->base.adjusted_mode.crtc_clock;
+		int dotclock = pipe_config->hw.adjusted_mode.crtc_clock;
 
 		/*
 		 * FDI already provided one idea for the dotclock.
@@ -13259,7 +13758,7 @@ static void verify_wm_state(struct intel_crtc *crtc,
 	const enum pipe pipe = crtc->pipe;
 	int plane, level, max_level = ilk_wm_max_level(dev_priv);
 
-	if (INTEL_GEN(dev_priv) < 9 || !new_crtc_state->base.active)
+	if (INTEL_GEN(dev_priv) < 9 || !new_crtc_state->hw.active)
 		return;
 
 	hw = kzalloc(sizeof(*hw), GFP_KERNEL);
@@ -13464,16 +13963,14 @@ verify_crtc_state(struct intel_crtc *crtc,
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
-	struct intel_crtc_state *pipe_config;
-	struct drm_atomic_state *state;
+	struct intel_crtc_state *pipe_config = old_crtc_state;
+	struct drm_atomic_state *state = old_crtc_state->uapi.state;
 	bool active;
 
-	state = old_crtc_state->base.state;
-	__drm_atomic_helper_crtc_destroy_state(&old_crtc_state->base);
-	pipe_config = old_crtc_state;
-	memset(pipe_config, 0, sizeof(*pipe_config));
-	pipe_config->base.crtc = &crtc->base;
-	pipe_config->base.state = state;
+	__drm_atomic_helper_crtc_destroy_state(&old_crtc_state->uapi);
+	intel_crtc_free_hw_state(old_crtc_state);
+	intel_crtc_state_reset(old_crtc_state, crtc);
+	old_crtc_state->uapi.state = state;
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.base.id, crtc->base.name);
 
@@ -13481,23 +13978,26 @@ verify_crtc_state(struct intel_crtc *crtc,
 
 	/* we keep both pipes enabled on 830 */
 	if (IS_I830(dev_priv))
-		active = new_crtc_state->base.active;
+		active = new_crtc_state->hw.active;
 
-	I915_STATE_WARN(new_crtc_state->base.active != active,
-	     "crtc active state doesn't match with hw state "
-	     "(expected %i, found %i)\n", new_crtc_state->base.active, active);
+	I915_STATE_WARN(new_crtc_state->hw.active != active,
+			"crtc active state doesn't match with hw state "
+			"(expected %i, found %i)\n",
+			new_crtc_state->hw.active, active);
 
-	I915_STATE_WARN(crtc->active != new_crtc_state->base.active,
-	     "transitional active state does not match atomic hw state "
-	     "(expected %i, found %i)\n", new_crtc_state->base.active, crtc->active);
+	I915_STATE_WARN(crtc->active != new_crtc_state->hw.active,
+			"transitional active state does not match atomic hw state "
+			"(expected %i, found %i)\n",
+			new_crtc_state->hw.active, crtc->active);
 
 	for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
 		enum pipe pipe;
 
 		active = encoder->get_hw_state(encoder, &pipe);
-		I915_STATE_WARN(active != new_crtc_state->base.active,
-			"[ENCODER:%i] active %i with crtc active %i\n",
-			encoder->base.base.id, active, new_crtc_state->base.active);
+		I915_STATE_WARN(active != new_crtc_state->hw.active,
+				"[ENCODER:%i] active %i with crtc active %i\n",
+				encoder->base.base.id, active,
+				new_crtc_state->hw.active);
 
 		I915_STATE_WARN(active && crtc->pipe != pipe,
 				"Encoder connected to wrong pipe %c\n",
@@ -13509,7 +14009,7 @@ verify_crtc_state(struct intel_crtc *crtc,
 
 	intel_crtc_compute_pixel_rate(pipe_config);
 
-	if (!new_crtc_state->base.active)
+	if (!new_crtc_state->hw.active)
 		return;
 
 	intel_pipe_config_sanity_check(dev_priv, pipe_config);
@@ -13532,7 +14032,7 @@ intel_verify_planes(struct intel_atomic_state *state)
 	for_each_new_intel_plane_in_state(state, plane,
 					  plane_state, i)
 		assert_plane(plane, plane_state->planar_slave ||
-			     plane_state->base.visible);
+			     plane_state->uapi.visible);
 }
 
 static void
@@ -13571,7 +14071,7 @@ verify_single_dpll_state(struct drm_i915_private *dev_priv,
 
 	crtc_mask = drm_crtc_mask(&crtc->base);
 
-	if (new_crtc_state->base.active)
+	if (new_crtc_state->hw.active)
 		I915_STATE_WARN(!(pll->active_mask & crtc_mask),
 				"pll active mismatch (expected pipe %c in active mask 0x%02x)\n",
 				pipe_name(drm_crtc_index(&crtc->base)), pll->active_mask);
@@ -13650,10 +14150,10 @@ intel_modeset_verify_disabled(struct drm_i915_private *dev_priv,
 static void
 intel_crtc_update_active_timings(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	drm_calc_timestamping_constants(&crtc->base, adjusted_mode);
 
@@ -13724,7 +14224,7 @@ static void intel_modeset_clear_plls(struct intel_atomic_state *state)
  * multiple pipes, and planes are enabled after the pipe, we need to wait at
  * least 2 vblanks on the first pipe before enabling planes on the second pipe.
  */
-static int haswell_mode_set_planes_workaround(struct intel_atomic_state *state)
+static int hsw_mode_set_planes_workaround(struct intel_atomic_state *state)
 {
 	struct intel_crtc_state *crtc_state;
 	struct intel_crtc *crtc;
@@ -13735,7 +14235,7 @@ static int haswell_mode_set_planes_workaround(struct intel_atomic_state *state)
 
 	/* look at all crtc's that are going to be enabled in during modeset */
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
-		if (!crtc_state->base.active ||
+		if (!crtc_state->hw.active ||
 		    !needs_modeset(crtc_state))
 			continue;
 
@@ -13760,7 +14260,7 @@ static int haswell_mode_set_planes_workaround(struct intel_atomic_state *state)
 
 		crtc_state->hsw_workaround_pipe = INVALID_PIPE;
 
-		if (!crtc_state->base.active ||
+		if (!crtc_state->hw.active ||
 		    needs_modeset(crtc_state))
 			continue;
 
@@ -13797,12 +14297,12 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
-		if (new_crtc_state->base.active)
+		if (new_crtc_state->hw.active)
 			state->active_pipes |= BIT(crtc->pipe);
 		else
 			state->active_pipes &= ~BIT(crtc->pipe);
 
-		if (old_crtc_state->base.active != new_crtc_state->base.active)
+		if (old_crtc_state->hw.active != new_crtc_state->hw.active)
 			state->active_pipe_changes |= BIT(crtc->pipe);
 	}
 
@@ -13819,7 +14319,7 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 	intel_modeset_clear_plls(state);
 
 	if (IS_HASWELL(dev_priv))
-		return haswell_mode_set_planes_workaround(state);
+		return hsw_mode_set_planes_workaround(state);
 
 	return 0;
 }
@@ -13847,9 +14347,13 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta
 	if (!intel_pipe_config_compare(old_crtc_state, new_crtc_state, true))
 		return;
 
-	new_crtc_state->base.mode_changed = false;
+	new_crtc_state->uapi.mode_changed = false;
 	new_crtc_state->update_pipe = true;
+}
 
+static void intel_crtc_copy_fastset(const struct intel_crtc_state *old_crtc_state,
+				    struct intel_crtc_state *new_crtc_state)
+{
 	/*
 	 * If we're not doing the full modeset we want to
 	 * keep the current M/N values as they may be
@@ -13972,6 +14476,107 @@ static int intel_atomic_check_crtcs(struct intel_atomic_state *state)
 	return 0;
 }
 
+static bool intel_cpu_transcoder_needs_modeset(struct intel_atomic_state *state,
+					       enum transcoder transcoder)
+{
+	struct intel_crtc_state *new_crtc_state;
+	struct intel_crtc *crtc;
+	int i;
+
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i)
+		if (new_crtc_state->cpu_transcoder == transcoder)
+			return needs_modeset(new_crtc_state);
+
+	return false;
+}
+
+static void
+intel_modeset_synced_crtcs(struct intel_atomic_state *state,
+			   u8 transcoders)
+{
+	struct intel_crtc_state *new_crtc_state;
+	struct intel_crtc *crtc;
+	int i;
+
+	for_each_new_intel_crtc_in_state(state, crtc,
+					 new_crtc_state, i) {
+		if (transcoders & BIT(new_crtc_state->cpu_transcoder)) {
+			new_crtc_state->uapi.mode_changed = true;
+			new_crtc_state->update_pipe = false;
+		}
+	}
+}
+
+static int
+intel_modeset_all_tiles(struct intel_atomic_state *state, int tile_grp_id)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
+	int ret = 0;
+
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
+		struct drm_connector_state *conn_state;
+		struct drm_crtc_state *crtc_state;
+
+		if (!connector->has_tile ||
+		    connector->tile_group->id != tile_grp_id)
+			continue;
+		conn_state = drm_atomic_get_connector_state(&state->base,
+							    connector);
+		if (IS_ERR(conn_state)) {
+			ret =  PTR_ERR(conn_state);
+			break;
+		}
+
+		if (!conn_state->crtc)
+			continue;
+
+		crtc_state = drm_atomic_get_crtc_state(&state->base,
+						       conn_state->crtc);
+		if (IS_ERR(crtc_state)) {
+			ret = PTR_ERR(crtc_state);
+			break;
+		}
+		crtc_state->mode_changed = true;
+		ret = drm_atomic_add_affected_connectors(&state->base,
+							 conn_state->crtc);
+		if (ret)
+			break;
+	}
+	drm_connector_list_iter_end(&conn_iter);
+
+	return ret;
+}
+
+static int
+intel_atomic_check_tiled_conns(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct drm_connector *connector;
+	struct drm_connector_state *old_conn_state, *new_conn_state;
+	int i, ret;
+
+	if (INTEL_GEN(dev_priv) < 11)
+		return 0;
+
+	/* Is tiled, mark all other tiled CRTCs as needing a modeset */
+	for_each_oldnew_connector_in_state(&state->base, connector,
+					   old_conn_state, new_conn_state, i) {
+		if (!connector->has_tile)
+			continue;
+		if (!intel_connector_needs_modeset(state, connector))
+			continue;
+
+		ret = intel_modeset_all_tiles(state, connector->tile_group->id);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /**
  * intel_atomic_check - validate state object
  * @dev: drm device
@@ -13990,33 +14595,96 @@ static int intel_atomic_check(struct drm_device *dev,
 	/* Catch I915_MODE_FLAG_INHERITED */
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
-		if (new_crtc_state->base.mode.private_flags !=
-		    old_crtc_state->base.mode.private_flags)
-			new_crtc_state->base.mode_changed = true;
+		if (new_crtc_state->hw.mode.private_flags !=
+		    old_crtc_state->hw.mode.private_flags)
+			new_crtc_state->uapi.mode_changed = true;
 	}
 
 	ret = drm_atomic_helper_check_modeset(dev, &state->base);
 	if (ret)
 		goto fail;
 
+	/**
+	 * This check adds all the connectors in current state that belong to
+	 * the same tile group to a full modeset.
+	 * This function directly sets the mode_changed to true and we also call
+	 * drm_atomic_add_affected_connectors(). Hence we are not explicitly
+	 * calling drm_atomic_helper_check_modeset() after this.
+	 *
+	 * Fixme: Handle some corner cases where one of the
+	 * tiled connectors gets disconnected and tile info is lost but since it
+	 * was previously synced to other conn, we need to add that to the modeset.
+	 */
+	ret = intel_atomic_check_tiled_conns(state);
+	if (ret)
+		goto fail;
+
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
-		if (!needs_modeset(new_crtc_state))
+		if (!needs_modeset(new_crtc_state)) {
+			/* Light copy */
+			intel_crtc_copy_uapi_to_hw_state_nomodeset(new_crtc_state);
+
 			continue;
+		}
 
-		if (!new_crtc_state->base.enable) {
-			any_ms = true;
+		if (!new_crtc_state->uapi.enable) {
+			intel_crtc_copy_uapi_to_hw_state(new_crtc_state);
 			continue;
 		}
 
+		ret = intel_crtc_prepare_cleared_state(new_crtc_state);
+		if (ret)
+			goto fail;
+
 		ret = intel_modeset_pipe_config(new_crtc_state);
 		if (ret)
 			goto fail;
 
 		intel_crtc_check_fastset(old_crtc_state, new_crtc_state);
+	}
+
+	/**
+	 * Check if fastset is allowed by external dependencies like other
+	 * pipes and transcoders.
+	 *
+	 * Right now it only forces a fullmodeset when the MST master
+	 * transcoder did not changed but the pipe of the master transcoder
+	 * needs a fullmodeset so all slaves also needs to do a fullmodeset or
+	 * in case of port synced crtcs, if one of the synced crtcs
+	 * needs a full modeset, all other synced crtcs should be
+	 * forced a full modeset.
+	 */
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (!new_crtc_state->hw.enable || needs_modeset(new_crtc_state))
+			continue;
+
+		if (intel_dp_mst_is_slave_trans(new_crtc_state)) {
+			enum transcoder master = new_crtc_state->mst_master_transcoder;
+
+			if (intel_cpu_transcoder_needs_modeset(state, master)) {
+				new_crtc_state->uapi.mode_changed = true;
+				new_crtc_state->update_pipe = false;
+			}
+		} else if (is_trans_port_sync_mode(new_crtc_state)) {
+			u8 trans = new_crtc_state->sync_mode_slaves_mask |
+				   BIT(new_crtc_state->master_transcoder);
 
-		if (needs_modeset(new_crtc_state))
+			intel_modeset_synced_crtcs(state, trans);
+		}
+	}
+
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		if (needs_modeset(new_crtc_state)) {
 			any_ms = true;
+			continue;
+		}
+
+		if (!new_crtc_state->update_pipe)
+			continue;
+
+		intel_crtc_copy_fastset(old_crtc_state, new_crtc_state);
 	}
 
 	if (any_ms && !check_digital_port_conflicts(state)) {
@@ -14106,7 +14774,7 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	if (!IS_GEN(dev_priv, 2))
+	if (!IS_GEN(dev_priv, 2) || crtc_state->active_planes)
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
 
 	if (crtc_state->has_pch_encoder) {
@@ -14120,7 +14788,7 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state,
 			       const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	/*
@@ -14138,12 +14806,12 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state,
 		skl_detach_scalers(new_crtc_state);
 
 		if (new_crtc_state->pch_pfit.enabled)
-			skylake_pfit_enable(new_crtc_state);
+			skl_pfit_enable(new_crtc_state);
 	} else if (HAS_PCH_SPLIT(dev_priv)) {
 		if (new_crtc_state->pch_pfit.enabled)
-			ironlake_pfit_enable(new_crtc_state);
+			ilk_pfit_enable(new_crtc_state);
 		else if (old_crtc_state->pch_pfit.enabled)
-			ironlake_pfit_disable(old_crtc_state);
+			ilk_pfit_disable(old_crtc_state);
 	}
 
 	if (INTEL_GEN(dev_priv) >= 11)
@@ -14154,6 +14822,7 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 			       struct intel_crtc_state *old_crtc_state,
 			       struct intel_crtc_state *new_crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	bool modeset = needs_modeset(new_crtc_state);
 
@@ -14162,7 +14831,7 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 	 * CRTC was enabled.
 	 */
 	if (!modeset) {
-		if (new_crtc_state->base.color_mgmt_changed ||
+		if (new_crtc_state->uapi.color_mgmt_changed ||
 		    new_crtc_state->update_pipe)
 			intel_color_commit(new_crtc_state);
 
@@ -14177,8 +14846,7 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 	}
 
 	if (dev_priv->display.atomic_update_watermarks)
-		dev_priv->display.atomic_update_watermarks(state,
-							   new_crtc_state);
+		dev_priv->display.atomic_update_watermarks(state, crtc);
 }
 
 static void intel_update_crtc(struct intel_crtc *crtc,
@@ -14195,20 +14863,20 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 	if (modeset) {
 		intel_crtc_update_active_timings(new_crtc_state);
 
-		dev_priv->display.crtc_enable(new_crtc_state, state);
+		dev_priv->display.crtc_enable(state, crtc);
 
 		/* vblanks work again, re-enable pipe CRC. */
 		intel_crtc_enable_pipe_crc(crtc);
 	} else {
 		if (new_crtc_state->preload_luts &&
-		    (new_crtc_state->base.color_mgmt_changed ||
+		    (new_crtc_state->uapi.color_mgmt_changed ||
 		     new_crtc_state->update_pipe))
 			intel_color_load_luts(new_crtc_state);
 
-		intel_pre_plane_update(old_crtc_state, new_crtc_state);
+		intel_pre_plane_update(state, crtc);
 
 		if (new_crtc_state->update_pipe)
-			intel_encoders_update_pipe(crtc, new_crtc_state, state);
+			intel_encoders_update_pipe(state, crtc);
 	}
 
 	if (new_crtc_state->update_pipe && !new_crtc_state->enable_fbc)
@@ -14235,13 +14903,13 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 	 * of enabling them on the CRTC's first fastset.
 	 */
 	if (new_crtc_state->update_pipe && !modeset &&
-	    old_crtc_state->base.mode.private_flags & I915_MODE_FLAG_INHERITED)
+	    old_crtc_state->hw.mode.private_flags & I915_MODE_FLAG_INHERITED)
 		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
 }
 
 static struct intel_crtc *intel_get_slave_crtc(const struct intel_crtc_state *new_crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(new_crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(new_crtc_state->uapi.crtc->dev);
 	enum transcoder slave_transcoder;
 
 	WARN_ON(!is_power_of_2(new_crtc_state->sync_mode_slaves_mask));
@@ -14266,97 +14934,60 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state,
 	 */
 	intel_crtc_disable_pipe_crc(crtc);
 
-	dev_priv->display.crtc_disable(old_crtc_state, state);
+	dev_priv->display.crtc_disable(state, crtc);
 	crtc->active = false;
 	intel_fbc_disable(crtc);
 	intel_disable_shared_dpll(old_crtc_state);
 
-	/*
-	 * Underruns don't always raise interrupts,
-	 * so check manually.
-	 */
-	intel_check_cpu_fifo_underruns(dev_priv);
-	intel_check_pch_fifo_underruns(dev_priv);
-
 	/* FIXME unify this for all platforms */
-	if (!new_crtc_state->base.active &&
+	if (!new_crtc_state->hw.active &&
 	    !HAS_GMCH(dev_priv) &&
 	    dev_priv->display.initial_watermarks)
-		dev_priv->display.initial_watermarks(state,
-						     new_crtc_state);
-}
-
-static void intel_trans_port_sync_modeset_disables(struct intel_atomic_state *state,
-						   struct intel_crtc *crtc,
-						   struct intel_crtc_state *old_crtc_state,
-						   struct intel_crtc_state *new_crtc_state)
-{
-	struct intel_crtc *slave_crtc = intel_get_slave_crtc(new_crtc_state);
-	struct intel_crtc_state *new_slave_crtc_state =
-		intel_atomic_get_new_crtc_state(state, slave_crtc);
-	struct intel_crtc_state *old_slave_crtc_state =
-		intel_atomic_get_old_crtc_state(state, slave_crtc);
-
-	WARN_ON(!slave_crtc || !new_slave_crtc_state ||
-		!old_slave_crtc_state);
-
-	/* Disable Slave first */
-	intel_pre_plane_update(old_slave_crtc_state, new_slave_crtc_state);
-	if (old_slave_crtc_state->base.active)
-		intel_old_crtc_state_disables(state,
-					      old_slave_crtc_state,
-					      new_slave_crtc_state,
-					      slave_crtc);
-
-	/* Disable Master */
-	intel_pre_plane_update(old_crtc_state, new_crtc_state);
-	if (old_crtc_state->base.active)
-		intel_old_crtc_state_disables(state,
-					      old_crtc_state,
-					      new_crtc_state,
-					      crtc);
+		dev_priv->display.initial_watermarks(state, crtc);
 }
 
 static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 {
 	struct intel_crtc_state *new_crtc_state, *old_crtc_state;
 	struct intel_crtc *crtc;
+	u32 handled = 0;
 	int i;
 
-	/*
-	 * Disable CRTC/pipes in reverse order because some features(MST in
-	 * TGL+) requires master and slave relationship between pipes, so it
-	 * should always pick the lowest pipe as master as it will be enabled
-	 * first and disable in the reverse order so the master will be the
-	 * last one to be disabled.
-	 */
-	for_each_oldnew_intel_crtc_in_state_reverse(state, crtc, old_crtc_state,
-						    new_crtc_state, i) {
+	/* Only disable port sync and MST slaves */
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
 		if (!needs_modeset(new_crtc_state))
 			continue;
 
+		if (!old_crtc_state->hw.active)
+			continue;
+
 		/* In case of Transcoder port Sync master slave CRTCs can be
 		 * assigned in any order and we need to make sure that
 		 * slave CRTCs are disabled first and then master CRTC since
 		 * Slave vblanks are masked till Master Vblanks.
 		 */
-		if (is_trans_port_sync_mode(new_crtc_state)) {
-			if (is_trans_port_sync_master(new_crtc_state))
-				intel_trans_port_sync_modeset_disables(state,
-								       crtc,
-								       old_crtc_state,
-								       new_crtc_state);
-			else
-				continue;
-		} else {
-			intel_pre_plane_update(old_crtc_state, new_crtc_state);
+		if (!is_trans_port_sync_slave(old_crtc_state) &&
+		    !intel_dp_mst_is_slave_trans(old_crtc_state))
+			continue;
 
-			if (old_crtc_state->base.active)
-				intel_old_crtc_state_disables(state,
-							      old_crtc_state,
-							      new_crtc_state,
-							      crtc);
-		}
+		intel_pre_plane_update(state, crtc);
+		intel_old_crtc_state_disables(state, old_crtc_state,
+					      new_crtc_state, crtc);
+		handled |= BIT(crtc->pipe);
+	}
+
+	/* Disable everything else left on */
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		if (!needs_modeset(new_crtc_state) ||
+		    (handled & BIT(crtc->pipe)))
+			continue;
+
+		intel_pre_plane_update(state, crtc);
+		if (old_crtc_state->hw.active)
+			intel_old_crtc_state_disables(state, old_crtc_state,
+						      new_crtc_state, crtc);
 	}
 }
 
@@ -14367,7 +14998,7 @@ static void intel_commit_modeset_enables(struct intel_atomic_state *state)
 	int i;
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-		if (!new_crtc_state->base.active)
+		if (!new_crtc_state->hw.active)
 			continue;
 
 		intel_update_crtc(crtc, state, old_crtc_state,
@@ -14382,7 +15013,7 @@ static void intel_crtc_enable_trans_port_sync(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 
 	intel_crtc_update_active_timings(new_crtc_state);
-	dev_priv->display.crtc_enable(new_crtc_state, state);
+	dev_priv->display.crtc_enable(state, crtc);
 	intel_crtc_enable_pipe_crc(crtc);
 }
 
@@ -14398,10 +15029,14 @@ static void intel_set_dp_tp_ctl_normal(struct intel_crtc *crtc,
 		if (conn_state->crtc == &crtc->base)
 			break;
 	}
-	intel_dp = enc_to_intel_dp(&intel_attached_encoder(conn)->base);
+	intel_dp = enc_to_intel_dp(intel_attached_encoder(to_intel_connector(conn)));
 	intel_dp_stop_link_train(intel_dp);
 }
 
+/*
+ * TODO: This is only called from port sync and it is identical to what will be
+ * executed again in intel_update_crtc() over port sync pipes
+ */
 static void intel_post_crtc_enable_updates(struct intel_crtc *crtc,
 					   struct intel_atomic_state *state)
 {
@@ -14432,7 +15067,7 @@ static void intel_post_crtc_enable_updates(struct intel_crtc *crtc,
 	 * of enabling them on the CRTC's first fastset.
 	 */
 	if (new_crtc_state->update_pipe && !modeset &&
-	    old_crtc_state->base.mode.private_flags & I915_MODE_FLAG_INHERITED)
+	    old_crtc_state->hw.mode.private_flags & I915_MODE_FLAG_INHERITED)
 		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
 }
 
@@ -14487,17 +15122,25 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc *crtc;
 	struct intel_crtc_state *old_crtc_state, *new_crtc_state;
-	unsigned int updated = 0;
-	bool progress;
-	int i;
 	u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices;
 	u8 required_slices = state->wm_results.ddb.enabled_slices;
 	struct skl_ddb_entry entries[I915_MAX_PIPES] = {};
+	const u8 num_pipes = INTEL_NUM_PIPES(dev_priv);
+	u8 update_pipes = 0, modeset_pipes = 0;
+	int i;
+
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		if (!new_crtc_state->hw.active)
+			continue;
 
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i)
 		/* ignore allocations for crtc's that have been turned off. */
-		if (new_crtc_state->base.active)
+		if (!needs_modeset(new_crtc_state)) {
 			entries[i] = old_crtc_state->wm.skl.ddb;
+			update_pipes |= BIT(crtc->pipe);
+		} else {
+			modeset_pipes |= BIT(crtc->pipe);
+		}
+	}
 
 	/* If 2nd DBuf slice required, enable it here */
 	if (INTEL_GEN(dev_priv) >= 11 && required_slices > hw_enabled_slices)
@@ -14506,27 +15149,29 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 	/*
 	 * Whenever the number of active pipes changes, we need to make sure we
 	 * update the pipes in the right order so that their ddb allocations
-	 * never overlap with eachother inbetween CRTC updates. Otherwise we'll
+	 * never overlap with each other between CRTC updates. Otherwise we'll
 	 * cause pipe underruns and other bad stuff.
+	 *
+	 * So first lets enable all pipes that do not need a fullmodeset as
+	 * those don't have any external dependency.
 	 */
-	do {
-		progress = false;
-
-		for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+	while (update_pipes) {
+		for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+						    new_crtc_state, i) {
 			enum pipe pipe = crtc->pipe;
-			bool vbl_wait = false;
-			bool modeset = needs_modeset(new_crtc_state);
 
-			if (updated & BIT(crtc->pipe) || !new_crtc_state->base.active)
+			if ((update_pipes & BIT(pipe)) == 0)
 				continue;
 
 			if (skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
-							entries,
-							INTEL_NUM_PIPES(dev_priv), i))
+							entries, num_pipes, i))
 				continue;
 
-			updated |= BIT(pipe);
 			entries[i] = new_crtc_state->wm.skl.ddb;
+			update_pipes &= ~BIT(pipe);
+
+			intel_update_crtc(crtc, state, old_crtc_state,
+					  new_crtc_state);
 
 			/*
 			 * If this is an already active pipe, it's DDB changed,
@@ -14536,29 +15181,71 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 			 */
 			if (!skl_ddb_entry_equal(&new_crtc_state->wm.skl.ddb,
 						 &old_crtc_state->wm.skl.ddb) &&
-			    !modeset &&
-			    state->wm_results.dirty_pipes != updated)
-				vbl_wait = true;
-
-			if (modeset && is_trans_port_sync_mode(new_crtc_state)) {
-				if (is_trans_port_sync_master(new_crtc_state))
-					intel_update_trans_port_sync_crtcs(crtc,
-									   state,
-									   old_crtc_state,
-									   new_crtc_state);
-				else
-					continue;
-			} else {
-				intel_update_crtc(crtc, state, old_crtc_state,
-						  new_crtc_state);
-			}
-
-			if (vbl_wait)
+			    (update_pipes | modeset_pipes))
 				intel_wait_for_vblank(dev_priv, pipe);
+		}
+	}
+
+	/*
+	 * Enable all pipes that needs a modeset and do not depends on other
+	 * pipes
+	 */
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		enum pipe pipe = crtc->pipe;
 
-			progress = true;
+		if ((modeset_pipes & BIT(pipe)) == 0)
+			continue;
+
+		if (intel_dp_mst_is_slave_trans(new_crtc_state) ||
+		    is_trans_port_sync_slave(new_crtc_state))
+			continue;
+
+		WARN_ON(skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
+						    entries, num_pipes, i));
+
+		entries[i] = new_crtc_state->wm.skl.ddb;
+		modeset_pipes &= ~BIT(pipe);
+
+		if (is_trans_port_sync_mode(new_crtc_state)) {
+			struct intel_crtc *slave_crtc;
+
+			intel_update_trans_port_sync_crtcs(crtc, state,
+							   old_crtc_state,
+							   new_crtc_state);
+
+			slave_crtc = intel_get_slave_crtc(new_crtc_state);
+			/* TODO: update entries[] of slave */
+			modeset_pipes &= ~BIT(slave_crtc->pipe);
+
+		} else {
+			intel_update_crtc(crtc, state, old_crtc_state,
+					  new_crtc_state);
 		}
-	} while (progress);
+	}
+
+	/*
+	 * Finally enable all pipes that needs a modeset and depends on
+	 * other pipes, right now it is only MST slaves as both port sync slave
+	 * and master are enabled together
+	 */
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		enum pipe pipe = crtc->pipe;
+
+		if ((modeset_pipes & BIT(pipe)) == 0)
+			continue;
+
+		WARN_ON(skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
+						    entries, num_pipes, i));
+
+		entries[i] = new_crtc_state->wm.skl.ddb;
+		modeset_pipes &= ~BIT(pipe);
+
+		intel_update_crtc(crtc, state, old_crtc_state, new_crtc_state);
+	}
+
+	WARN_ON(modeset_pipes);
 
 	/* If 2nd DBuf slice is no more required disable it */
 	if (INTEL_GEN(dev_priv) >= 11 && required_slices < hw_enabled_slices)
@@ -14679,12 +15366,13 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		bool modeset = needs_modeset(new_crtc_state);
 
 		/* Complete events for now disable pipes here. */
-		if (modeset && !new_crtc_state->base.active && new_crtc_state->base.event) {
+		if (modeset && !new_crtc_state->hw.active && new_crtc_state->uapi.event) {
 			spin_lock_irq(&dev->event_lock);
-			drm_crtc_send_vblank_event(&crtc->base, new_crtc_state->base.event);
+			drm_crtc_send_vblank_event(&crtc->base,
+						   new_crtc_state->uapi.event);
 			spin_unlock_irq(&dev->event_lock);
 
-			new_crtc_state->base.event = NULL;
+			new_crtc_state->uapi.event = NULL;
 		}
 	}
 
@@ -14715,10 +15403,10 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	drm_atomic_helper_wait_for_flip_done(dev, &state->base);
 
 	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
-		if (new_crtc_state->base.active &&
+		if (new_crtc_state->hw.active &&
 		    !needs_modeset(new_crtc_state) &&
 		    !new_crtc_state->preload_luts &&
-		    (new_crtc_state->base.color_mgmt_changed ||
+		    (new_crtc_state->uapi.color_mgmt_changed ||
 		     new_crtc_state->update_pipe))
 			intel_color_load_luts(new_crtc_state);
 	}
@@ -14730,14 +15418,25 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	 *
 	 * TODO: Move this (and other cleanup) to an async worker eventually.
 	 */
-	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		/*
+		 * Gen2 reports pipe underruns whenever all planes are disabled.
+		 * So re-enable underrun reporting after some planes get enabled.
+		 *
+		 * We do this before .optimize_watermarks() so that we have a
+		 * chance of catching underruns with the intermediate watermarks
+		 * vs. the new plane configuration.
+		 */
+		if (IS_GEN(dev_priv, 2) && planes_enabling(old_crtc_state, new_crtc_state))
+			intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
+
 		if (dev_priv->display.optimize_watermarks)
-			dev_priv->display.optimize_watermarks(state,
-							      new_crtc_state);
+			dev_priv->display.optimize_watermarks(state, crtc);
 	}
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-		intel_post_plane_update(old_crtc_state);
+		intel_post_plane_update(state, crtc);
 
 		if (put_domains[i])
 			modeset_put_power_domains(dev_priv, put_domains[i]);
@@ -14745,6 +15444,10 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		intel_modeset_verify_crtc(crtc, state, old_crtc_state, new_crtc_state);
 	}
 
+	/* Underruns don't always raise interrupts, so check manually */
+	intel_check_cpu_fifo_underruns(dev_priv);
+	intel_check_pch_fifo_underruns(dev_priv);
+
 	if (state->modeset)
 		intel_verify_planes(state);
 
@@ -14818,8 +15521,8 @@ static void intel_atomic_track_fbs(struct intel_atomic_state *state)
 
 	for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state,
 					     new_plane_state, i)
-		intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->base.fb),
-					to_intel_frontbuffer(new_plane_state->base.fb),
+		intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->hw.fb),
+					to_intel_frontbuffer(new_plane_state->hw.fb),
 					plane->frontbuffer_bit);
 }
 
@@ -14986,9 +15689,9 @@ static void add_rps_boost_after_vblank(struct drm_crtc *crtc,
 
 static int intel_plane_pin_fb(struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_framebuffer *fb = plane_state->hw.fb;
 	struct i915_vma *vma;
 
 	if (plane->id == PLANE_CURSOR &&
@@ -15051,9 +15754,9 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	struct intel_plane_state *new_plane_state =
 		to_intel_plane_state(_new_plane_state);
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_plane_state->base.state);
+		to_intel_atomic_state(new_plane_state->uapi.state);
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
-	struct drm_framebuffer *fb = new_plane_state->base.fb;
+	struct drm_framebuffer *fb = new_plane_state->hw.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct drm_i915_gem_object *old_obj = intel_fb_obj(plane->state->fb);
 	int ret;
@@ -15084,9 +15787,9 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		}
 	}
 
-	if (new_plane_state->base.fence) { /* explicit fencing */
+	if (new_plane_state->uapi.fence) { /* explicit fencing */
 		ret = i915_sw_fence_await_dma_fence(&intel_state->commit_ready,
-						    new_plane_state->base.fence,
+						    new_plane_state->uapi.fence,
 						    I915_FENCE_TIMEOUT,
 						    GFP_KERNEL);
 		if (ret < 0)
@@ -15109,7 +15812,7 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	fb_obj_bump_render_priority(obj);
 	i915_gem_object_flush_frontbuffer(obj, ORIGIN_DIRTYFB);
 
-	if (!new_plane_state->base.fence) { /* implicit fencing */
+	if (!new_plane_state->uapi.fence) { /* implicit fencing */
 		struct dma_fence *fence;
 
 		ret = i915_sw_fence_await_reservation(&intel_state->commit_ready,
@@ -15121,13 +15824,13 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 
 		fence = dma_resv_get_excl_rcu(obj->base.resv);
 		if (fence) {
-			add_rps_boost_after_vblank(new_plane_state->base.crtc,
+			add_rps_boost_after_vblank(new_plane_state->hw.crtc,
 						   fence);
 			dma_fence_put(fence);
 		}
 	} else {
-		add_rps_boost_after_vblank(new_plane_state->base.crtc,
-					   new_plane_state->base.fence);
+		add_rps_boost_after_vblank(new_plane_state->hw.crtc,
+					   new_plane_state->uapi.fence);
 	}
 
 	/*
@@ -15160,7 +15863,7 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 	struct intel_plane_state *old_plane_state =
 		to_intel_plane_state(_old_plane_state);
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(old_plane_state->base.state);
+		to_intel_atomic_state(old_plane_state->uapi.state);
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
 
 	if (intel_state->rps_interactive) {
@@ -15224,8 +15927,12 @@ static bool i965_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_XBGR16161616F:
 		return modifier == DRM_FORMAT_MOD_LINEAR ||
 			modifier == I915_FORMAT_MOD_X_TILED;
@@ -15283,7 +15990,7 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 * When crtc is inactive or there is a modeset pending,
 	 * wait for it to complete in the slowpath
 	 */
-	if (!crtc_state->base.active || needs_modeset(crtc_state) ||
+	if (!crtc_state->hw.active || needs_modeset(crtc_state) ||
 	    crtc_state->update_pipe)
 		goto slow;
 
@@ -15292,8 +15999,8 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 * the plane.  This prevents our async update's changes from getting
 	 * overridden by a previous synchronous update's state.
 	 */
-	if (old_plane_state->base.commit &&
-	    !try_wait_for_completion(&old_plane_state->base.commit->hw_done))
+	if (old_plane_state->uapi.commit &&
+	    !try_wait_for_completion(&old_plane_state->uapi.commit->hw_done))
 		goto slow;
 
 	/*
@@ -15301,12 +16008,12 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 * take the slowpath. Only changing fb or position should be
 	 * in the fastpath.
 	 */
-	if (old_plane_state->base.crtc != &crtc->base ||
-	    old_plane_state->base.src_w != src_w ||
-	    old_plane_state->base.src_h != src_h ||
-	    old_plane_state->base.crtc_w != crtc_w ||
-	    old_plane_state->base.crtc_h != crtc_h ||
-	    !old_plane_state->base.fb != !fb)
+	if (old_plane_state->uapi.crtc != &crtc->base ||
+	    old_plane_state->uapi.src_w != src_w ||
+	    old_plane_state->uapi.src_h != src_h ||
+	    old_plane_state->uapi.crtc_w != crtc_w ||
+	    old_plane_state->uapi.crtc_h != crtc_h ||
+	    !old_plane_state->uapi.fb != !fb)
 		goto slow;
 
 	new_plane_state = to_intel_plane_state(intel_plane_duplicate_state(&plane->base));
@@ -15319,16 +16026,16 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 		goto out_free;
 	}
 
-	drm_atomic_set_fb_for_plane(&new_plane_state->base, fb);
+	drm_atomic_set_fb_for_plane(&new_plane_state->uapi, fb);
 
-	new_plane_state->base.src_x = src_x;
-	new_plane_state->base.src_y = src_y;
-	new_plane_state->base.src_w = src_w;
-	new_plane_state->base.src_h = src_h;
-	new_plane_state->base.crtc_x = crtc_x;
-	new_plane_state->base.crtc_y = crtc_y;
-	new_plane_state->base.crtc_w = crtc_w;
-	new_plane_state->base.crtc_h = crtc_h;
+	new_plane_state->uapi.src_x = src_x;
+	new_plane_state->uapi.src_y = src_y;
+	new_plane_state->uapi.src_w = src_w;
+	new_plane_state->uapi.src_h = src_h;
+	new_plane_state->uapi.crtc_x = crtc_x;
+	new_plane_state->uapi.crtc_y = crtc_y;
+	new_plane_state->uapi.crtc_w = crtc_w;
+	new_plane_state->uapi.crtc_h = crtc_h;
 
 	ret = intel_plane_atomic_check_with_state(crtc_state, new_crtc_state,
 						  old_plane_state, new_plane_state);
@@ -15339,13 +16046,14 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	if (ret)
 		goto out_free;
 
-	intel_frontbuffer_flush(to_intel_frontbuffer(new_plane_state->base.fb), ORIGIN_FLIP);
-	intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->base.fb),
-				to_intel_frontbuffer(new_plane_state->base.fb),
+	intel_frontbuffer_flush(to_intel_frontbuffer(new_plane_state->hw.fb),
+				ORIGIN_FLIP);
+	intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->hw.fb),
+				to_intel_frontbuffer(new_plane_state->hw.fb),
 				plane->frontbuffer_bit);
 
 	/* Swap plane state */
-	plane->base.state = &new_plane_state->base;
+	plane->base.state = &new_plane_state->uapi;
 
 	/*
 	 * We cannot swap crtc_state as it may be in use by an atomic commit or
@@ -15359,7 +16067,7 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 */
 	crtc_state->active_planes = new_crtc_state->active_planes;
 
-	if (new_plane_state->base.visible)
+	if (new_plane_state->uapi.visible)
 		intel_update_plane(plane, crtc_state, new_plane_state);
 	else
 		intel_disable_plane(plane, crtc_state);
@@ -15368,11 +16076,11 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 
 out_free:
 	if (new_crtc_state)
-		intel_crtc_destroy_state(&crtc->base, &new_crtc_state->base);
+		intel_crtc_destroy_state(&crtc->base, &new_crtc_state->uapi);
 	if (ret)
-		intel_plane_destroy_state(&plane->base, &new_plane_state->base);
+		intel_plane_destroy_state(&plane->base, &new_plane_state->uapi);
 	else
-		intel_plane_destroy_state(&plane->base, &old_plane_state->base);
+		intel_plane_destroy_state(&plane->base, &old_plane_state->uapi);
 	return ret;
 
 slow:
@@ -15414,7 +16122,6 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	const struct drm_plane_funcs *plane_funcs;
 	unsigned int supported_rotations;
 	unsigned int possible_crtcs;
-	const u64 *modifiers;
 	const u32 *formats;
 	int num_formats;
 	int ret, zpos;
@@ -15446,7 +16153,10 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		fbc->possible_framebuffer_bits |= plane->frontbuffer_bit;
 	}
 
-	if (INTEL_GEN(dev_priv) >= 4) {
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		formats = vlv_primary_formats;
+		num_formats = ARRAY_SIZE(vlv_primary_formats);
+	} else if (INTEL_GEN(dev_priv) >= 4) {
 		/*
 		 * WaFP16GammaEnabling:ivb
 		 * "Workaround : When using the 64-bit format, the plane
@@ -15467,51 +16177,45 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 			formats = i965_primary_formats;
 			num_formats = ARRAY_SIZE(i965_primary_formats);
 		}
-		modifiers = i9xx_format_modifiers;
-
-		plane->max_stride = i9xx_plane_max_stride;
-		plane->update_plane = i9xx_update_plane;
-		plane->disable_plane = i9xx_disable_plane;
-		plane->get_hw_state = i9xx_plane_get_hw_state;
-		plane->check_plane = i9xx_plane_check;
-
-		if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
-			plane->min_cdclk = hsw_plane_min_cdclk;
-		else if (IS_IVYBRIDGE(dev_priv))
-			plane->min_cdclk = ivb_plane_min_cdclk;
-		else if (IS_CHERRYVIEW(dev_priv) || IS_VALLEYVIEW(dev_priv))
-			plane->min_cdclk = vlv_plane_min_cdclk;
-		else
-			plane->min_cdclk = i9xx_plane_min_cdclk;
-
-		plane_funcs = &i965_plane_funcs;
 	} else {
 		formats = i8xx_primary_formats;
 		num_formats = ARRAY_SIZE(i8xx_primary_formats);
-		modifiers = i9xx_format_modifiers;
+	}
 
-		plane->max_stride = i9xx_plane_max_stride;
-		plane->update_plane = i9xx_update_plane;
-		plane->disable_plane = i9xx_disable_plane;
-		plane->get_hw_state = i9xx_plane_get_hw_state;
-		plane->check_plane = i9xx_plane_check;
+	if (INTEL_GEN(dev_priv) >= 4)
+		plane_funcs = &i965_plane_funcs;
+	else
+		plane_funcs = &i8xx_plane_funcs;
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		plane->min_cdclk = vlv_plane_min_cdclk;
+	else if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
+		plane->min_cdclk = hsw_plane_min_cdclk;
+	else if (IS_IVYBRIDGE(dev_priv))
+		plane->min_cdclk = ivb_plane_min_cdclk;
+	else
 		plane->min_cdclk = i9xx_plane_min_cdclk;
 
-		plane_funcs = &i8xx_plane_funcs;
-	}
+	plane->max_stride = i9xx_plane_max_stride;
+	plane->update_plane = i9xx_update_plane;
+	plane->disable_plane = i9xx_disable_plane;
+	plane->get_hw_state = i9xx_plane_get_hw_state;
+	plane->check_plane = i9xx_plane_check;
 
 	possible_crtcs = BIT(pipe);
 
 	if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
 		ret = drm_universal_plane_init(&dev_priv->drm, &plane->base,
 					       possible_crtcs, plane_funcs,
-					       formats, num_formats, modifiers,
+					       formats, num_formats,
+					       i9xx_format_modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
 					       "primary %c", pipe_name(pipe));
 	else
 		ret = drm_universal_plane_init(&dev_priv->drm, &plane->base,
 					       possible_crtcs, plane_funcs,
-					       formats, num_formats, modifiers,
+					       formats, num_formats,
+					       i9xx_format_modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
 					       "plane %c",
 					       plane_name(plane->i9xx_plane));
@@ -15615,28 +16319,6 @@ fail:
 	return ERR_PTR(ret);
 }
 
-static void intel_crtc_init_scalers(struct intel_crtc *crtc,
-				    struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc_scaler_state *scaler_state =
-		&crtc_state->scaler_state;
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int i;
-
-	crtc->num_scalers = RUNTIME_INFO(dev_priv)->num_scalers[crtc->pipe];
-	if (!crtc->num_scalers)
-		return;
-
-	for (i = 0; i < crtc->num_scalers; i++) {
-		struct intel_scaler *scaler = &scaler_state->scalers[i];
-
-		scaler->in_use = 0;
-		scaler->mode = 0;
-	}
-
-	scaler_state->scaler_id = -1;
-}
-
 #define INTEL_CRTC_FUNCS \
 	.gamma_set = drm_atomic_helper_legacy_gamma_set, \
 	.set_config = drm_atomic_helper_set_config, \
@@ -15704,33 +16386,53 @@ static const struct drm_crtc_funcs i8xx_crtc_funcs = {
 	.disable_vblank = i8xx_disable_vblank,
 };
 
+static struct intel_crtc *intel_crtc_alloc(void)
+{
+	struct intel_crtc_state *crtc_state;
+	struct intel_crtc *crtc;
+
+	crtc = kzalloc(sizeof(*crtc), GFP_KERNEL);
+	if (!crtc)
+		return ERR_PTR(-ENOMEM);
+
+	crtc_state = intel_crtc_state_alloc(crtc);
+	if (!crtc_state) {
+		kfree(crtc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	crtc->base.state = &crtc_state->uapi;
+	crtc->config = crtc_state;
+
+	return crtc;
+}
+
+static void intel_crtc_free(struct intel_crtc *crtc)
+{
+	intel_crtc_destroy_state(&crtc->base, crtc->base.state);
+	kfree(crtc);
+}
+
 static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
+	struct intel_plane *primary, *cursor;
 	const struct drm_crtc_funcs *funcs;
-	struct intel_crtc *intel_crtc;
-	struct intel_crtc_state *crtc_state = NULL;
-	struct intel_plane *primary = NULL;
-	struct intel_plane *cursor = NULL;
+	struct intel_crtc *crtc;
 	int sprite, ret;
 
-	intel_crtc = kzalloc(sizeof(*intel_crtc), GFP_KERNEL);
-	if (!intel_crtc)
-		return -ENOMEM;
+	crtc = intel_crtc_alloc();
+	if (IS_ERR(crtc))
+		return PTR_ERR(crtc);
 
-	crtc_state = kzalloc(sizeof(*crtc_state), GFP_KERNEL);
-	if (!crtc_state) {
-		ret = -ENOMEM;
-		goto fail;
-	}
-	__drm_atomic_helper_crtc_reset(&intel_crtc->base, &crtc_state->base);
-	intel_crtc->config = crtc_state;
+	crtc->pipe = pipe;
+	crtc->num_scalers = RUNTIME_INFO(dev_priv)->num_scalers[pipe];
 
 	primary = intel_primary_plane_create(dev_priv, pipe);
 	if (IS_ERR(primary)) {
 		ret = PTR_ERR(primary);
 		goto fail;
 	}
-	intel_crtc->plane_ids_mask |= BIT(primary->id);
+	crtc->plane_ids_mask |= BIT(primary->id);
 
 	for_each_sprite(dev_priv, pipe, sprite) {
 		struct intel_plane *plane;
@@ -15740,7 +16442,7 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 			ret = PTR_ERR(plane);
 			goto fail;
 		}
-		intel_crtc->plane_ids_mask |= BIT(plane->id);
+		crtc->plane_ids_mask |= BIT(plane->id);
 	}
 
 	cursor = intel_cursor_plane_create(dev_priv, pipe);
@@ -15748,7 +16450,7 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 		ret = PTR_ERR(cursor);
 		goto fail;
 	}
-	intel_crtc->plane_ids_mask |= BIT(cursor->id);
+	crtc->plane_ids_mask |= BIT(cursor->id);
 
 	if (HAS_GMCH(dev_priv)) {
 		if (IS_CHERRYVIEW(dev_priv) ||
@@ -15769,42 +16471,32 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 			funcs = &ilk_crtc_funcs;
 	}
 
-	ret = drm_crtc_init_with_planes(&dev_priv->drm, &intel_crtc->base,
+	ret = drm_crtc_init_with_planes(&dev_priv->drm, &crtc->base,
 					&primary->base, &cursor->base,
 					funcs, "pipe %c", pipe_name(pipe));
 	if (ret)
 		goto fail;
 
-	intel_crtc->pipe = pipe;
-
-	/* initialize shared scalers */
-	intel_crtc_init_scalers(intel_crtc, crtc_state);
-
 	BUG_ON(pipe >= ARRAY_SIZE(dev_priv->pipe_to_crtc_mapping) ||
 	       dev_priv->pipe_to_crtc_mapping[pipe] != NULL);
-	dev_priv->pipe_to_crtc_mapping[pipe] = intel_crtc;
+	dev_priv->pipe_to_crtc_mapping[pipe] = crtc;
 
 	if (INTEL_GEN(dev_priv) < 9) {
 		enum i9xx_plane_id i9xx_plane = primary->i9xx_plane;
 
 		BUG_ON(i9xx_plane >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
 		       dev_priv->plane_to_crtc_mapping[i9xx_plane] != NULL);
-		dev_priv->plane_to_crtc_mapping[i9xx_plane] = intel_crtc;
+		dev_priv->plane_to_crtc_mapping[i9xx_plane] = crtc;
 	}
 
-	intel_color_init(intel_crtc);
+	intel_color_init(crtc);
 
-	WARN_ON(drm_crtc_index(&intel_crtc->base) != intel_crtc->pipe);
+	WARN_ON(drm_crtc_index(&crtc->base) != crtc->pipe);
 
 	return 0;
 
 fail:
-	/*
-	 * drm_mode_config_cleanup() will free up any
-	 * crtcs/planes already initialized.
-	 */
-	kfree(crtc_state);
-	kfree(intel_crtc);
+	intel_crtc_free(crtc);
 
 	return ret;
 }
@@ -16291,8 +16983,11 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 	}
 
 	/* FIXME need to adjust LINOFF/TILEOFF accordingly. */
-	if (mode_cmd->offsets[0] != 0)
+	if (mode_cmd->offsets[0] != 0) {
+		DRM_DEBUG_KMS("plane 0 offset (0x%08x) must be 0\n",
+			      mode_cmd->offsets[0]);
 		goto err;
+	}
 
 	drm_helper_mode_fill_fb_struct(&dev_priv->drm, fb, mode_cmd);
 
@@ -16305,26 +17000,23 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 		}
 
 		stride_alignment = intel_fb_stride_alignment(fb, i);
-
-		/*
-		 * Display WA #0531: skl,bxt,kbl,glk
-		 *
-		 * Render decompression and plane width > 3840
-		 * combined with horizontal panning requires the
-		 * plane stride to be a multiple of 4. We'll just
-		 * require the entire fb to accommodate that to avoid
-		 * potential runtime errors at plane configuration time.
-		 */
-		if (IS_GEN(dev_priv, 9) && i == 0 && fb->width > 3840 &&
-		    is_ccs_modifier(fb->modifier))
-			stride_alignment *= 4;
-
 		if (fb->pitches[i] & (stride_alignment - 1)) {
 			DRM_DEBUG_KMS("plane %d pitch (%d) must be at least %u byte aligned\n",
 				      i, fb->pitches[i], stride_alignment);
 			goto err;
 		}
 
+		if (is_gen12_ccs_plane(fb, i)) {
+			int ccs_aux_stride = gen12_ccs_aux_stride(fb, i);
+
+			if (fb->pitches[i] != ccs_aux_stride) {
+				DRM_DEBUG_KMS("ccs aux plane %d pitch (%d) must be %d\n",
+					      i,
+					      fb->pitches[i], ccs_aux_stride);
+				goto err;
+			}
+		}
+
 		fb->obj[i] = &obj->base;
 	}
 
@@ -16522,29 +17214,28 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 	intel_init_cdclk_hooks(dev_priv);
 
 	if (INTEL_GEN(dev_priv) >= 9) {
-		dev_priv->display.get_pipe_config = haswell_get_pipe_config;
+		dev_priv->display.get_pipe_config = hsw_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
-			skylake_get_initial_plane_config;
-		dev_priv->display.crtc_compute_clock =
-			haswell_crtc_compute_clock;
-		dev_priv->display.crtc_enable = haswell_crtc_enable;
-		dev_priv->display.crtc_disable = haswell_crtc_disable;
+			skl_get_initial_plane_config;
+		dev_priv->display.crtc_compute_clock = hsw_crtc_compute_clock;
+		dev_priv->display.crtc_enable = hsw_crtc_enable;
+		dev_priv->display.crtc_disable = hsw_crtc_disable;
 	} else if (HAS_DDI(dev_priv)) {
-		dev_priv->display.get_pipe_config = haswell_get_pipe_config;
+		dev_priv->display.get_pipe_config = hsw_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
 			i9xx_get_initial_plane_config;
 		dev_priv->display.crtc_compute_clock =
-			haswell_crtc_compute_clock;
-		dev_priv->display.crtc_enable = haswell_crtc_enable;
-		dev_priv->display.crtc_disable = haswell_crtc_disable;
+			hsw_crtc_compute_clock;
+		dev_priv->display.crtc_enable = hsw_crtc_enable;
+		dev_priv->display.crtc_disable = hsw_crtc_disable;
 	} else if (HAS_PCH_SPLIT(dev_priv)) {
-		dev_priv->display.get_pipe_config = ironlake_get_pipe_config;
+		dev_priv->display.get_pipe_config = ilk_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
 			i9xx_get_initial_plane_config;
 		dev_priv->display.crtc_compute_clock =
-			ironlake_crtc_compute_clock;
-		dev_priv->display.crtc_enable = ironlake_crtc_enable;
-		dev_priv->display.crtc_disable = ironlake_crtc_disable;
+			ilk_crtc_compute_clock;
+		dev_priv->display.crtc_enable = ilk_crtc_enable;
+		dev_priv->display.crtc_disable = ilk_crtc_disable;
 	} else if (IS_CHERRYVIEW(dev_priv)) {
 		dev_priv->display.get_pipe_config = i9xx_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
@@ -16590,14 +17281,12 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 	}
 
 	if (IS_GEN(dev_priv, 5)) {
-		dev_priv->display.fdi_link_train = ironlake_fdi_link_train;
+		dev_priv->display.fdi_link_train = ilk_fdi_link_train;
 	} else if (IS_GEN(dev_priv, 6)) {
 		dev_priv->display.fdi_link_train = gen6_fdi_link_train;
 	} else if (IS_IVYBRIDGE(dev_priv)) {
 		/* FIXME: detect B0+ stepping and use auto training */
 		dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train;
-	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
-		dev_priv->display.fdi_link_train = hsw_fdi_link_train;
 	}
 
 	if (INTEL_GEN(dev_priv) >= 9)
@@ -16687,7 +17376,7 @@ retry:
 	/* Write calculated watermark values back */
 	for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
 		crtc_state->wm.need_postvbl_update = true;
-		dev_priv->display.optimize_watermarks(intel_state, crtc_state);
+		dev_priv->display.optimize_watermarks(intel_state, crtc);
 
 		to_intel_crtc_state(crtc->base.state)->wm = crtc_state->wm;
 	}
@@ -16719,8 +17408,7 @@ static int intel_initial_commit(struct drm_device *dev)
 {
 	struct drm_atomic_state *state = NULL;
 	struct drm_modeset_acquire_ctx ctx;
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *crtc_state;
+	struct intel_crtc *crtc;
 	int ret = 0;
 
 	state = drm_atomic_state_alloc(dev);
@@ -16732,15 +17420,17 @@ static int intel_initial_commit(struct drm_device *dev)
 retry:
 	state->acquire_ctx = &ctx;
 
-	drm_for_each_crtc(crtc, dev) {
-		crtc_state = drm_atomic_get_crtc_state(state, crtc);
+	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			intel_atomic_get_crtc_state(state, crtc);
+
 		if (IS_ERR(crtc_state)) {
 			ret = PTR_ERR(crtc_state);
 			goto out;
 		}
 
-		if (crtc_state->active) {
-			ret = drm_atomic_add_affected_planes(state, crtc);
+		if (crtc_state->hw.active) {
+			ret = drm_atomic_add_affected_planes(state, &crtc->base);
 			if (ret)
 				goto out;
 
@@ -16750,7 +17440,7 @@ retry:
 			 * having a proper LUT loaded. Remove once we
 			 * have readout for pipe gamma enable.
 			 */
-			crtc_state->color_mgmt_changed = true;
+			crtc_state->uapi.color_mgmt_changed = true;
 		}
 	}
 
@@ -17073,31 +17763,76 @@ static bool has_pch_trancoder(struct drm_i915_private *dev_priv,
 		(HAS_PCH_LPT_H(dev_priv) && pch_transcoder == PIPE_A);
 }
 
-static void intel_sanitize_crtc(struct intel_crtc *crtc,
-				struct drm_modeset_acquire_ctx *ctx)
+static void intel_sanitize_frame_start_delay(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
-	/* Clear any frame start delays used for debugging left by the BIOS */
-	if (crtc->active && !transcoder_is_dsi(cpu_transcoder)) {
+	if (INTEL_GEN(dev_priv) >= 9 ||
+	    IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) {
+		i915_reg_t reg = CHICKEN_TRANS(cpu_transcoder);
+		u32 val;
+
+		if (transcoder_is_dsi(cpu_transcoder))
+			return;
+
+		val = I915_READ(reg);
+		val &= ~HSW_FRAME_START_DELAY_MASK;
+		val |= HSW_FRAME_START_DELAY(0);
+		I915_WRITE(reg, val);
+	} else {
 		i915_reg_t reg = PIPECONF(cpu_transcoder);
+		u32 val;
 
-		I915_WRITE(reg,
-			   I915_READ(reg) & ~PIPECONF_FRAME_START_DELAY_MASK);
+		val = I915_READ(reg);
+		val &= ~PIPECONF_FRAME_START_DELAY_MASK;
+		val |= PIPECONF_FRAME_START_DELAY(0);
+		I915_WRITE(reg, val);
 	}
 
-	if (crtc_state->base.active) {
+	if (!crtc_state->has_pch_encoder)
+		return;
+
+	if (HAS_PCH_IBX(dev_priv)) {
+		i915_reg_t reg = PCH_TRANSCONF(crtc->pipe);
+		u32 val;
+
+		val = I915_READ(reg);
+		val &= ~TRANS_FRAME_START_DELAY_MASK;
+		val |= TRANS_FRAME_START_DELAY(0);
+		I915_WRITE(reg, val);
+	} else {
+		enum pipe pch_transcoder = intel_crtc_pch_transcoder(crtc);
+		i915_reg_t reg = TRANS_CHICKEN2(pch_transcoder);
+		u32 val;
+
+		val = I915_READ(reg);
+		val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
+		val |= TRANS_CHICKEN2_FRAME_START_DELAY(0);
+		I915_WRITE(reg, val);
+	}
+}
+
+static void intel_sanitize_crtc(struct intel_crtc *crtc,
+				struct drm_modeset_acquire_ctx *ctx)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state);
+
+	if (crtc_state->hw.active) {
 		struct intel_plane *plane;
 
+		/* Clear any frame start delays used for debugging left by the BIOS */
+		intel_sanitize_frame_start_delay(crtc_state);
+
 		/* Disable everything but the primary plane */
 		for_each_intel_plane_on_crtc(dev, crtc, plane) {
 			const struct intel_plane_state *plane_state =
 				to_intel_plane_state(plane->base.state);
 
-			if (plane_state->base.visible &&
+			if (plane_state->uapi.visible &&
 			    plane->base.type != DRM_PLANE_TYPE_PRIMARY)
 				intel_plane_disable_noatomic(crtc, plane);
 		}
@@ -17114,10 +17849,10 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc,
 
 	/* Adjust the state of the output pipe according to whether we
 	 * have active connectors/encoders. */
-	if (crtc_state->base.active && !intel_crtc_has_encoders(crtc))
-		intel_crtc_disable_noatomic(&crtc->base, ctx);
+	if (crtc_state->hw.active && !intel_crtc_has_encoders(crtc))
+		intel_crtc_disable_noatomic(crtc, ctx);
 
-	if (crtc_state->base.active || HAS_GMCH(dev_priv)) {
+	if (crtc_state->hw.active || HAS_GMCH(dev_priv)) {
 		/*
 		 * We start out with underrun reporting disabled to avoid races.
 		 * For correct bookkeeping mark this on active crtcs.
@@ -17148,7 +17883,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc,
 
 static bool has_bogus_dpll_config(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	/*
 	 * Some SNB BIOSen (eg. ASUS K53SV) are known to misprogram
@@ -17161,7 +17896,7 @@ static bool has_bogus_dpll_config(const struct intel_crtc_state *crtc_state)
 	 * road.
 	 */
 	return IS_GEN(dev_priv, 6) &&
-		crtc_state->base.active &&
+		crtc_state->hw.active &&
 		crtc_state->shared_dpll &&
 		crtc_state->port_clock == 0;
 }
@@ -17178,7 +17913,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 	 * encoder is active and trying to read from a pipe) and the
 	 * pipe itself being active. */
 	bool has_active_crtc = crtc_state &&
-		crtc_state->base.active;
+		crtc_state->hw.active;
 
 	if (crtc_state && has_bogus_dpll_config(crtc_state)) {
 		DRM_DEBUG_KMS("BIOS has misprogrammed the hardware. Disabling pipe %c\n",
@@ -17282,22 +18017,22 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
 
-		__drm_atomic_helper_crtc_destroy_state(&crtc_state->base);
-		memset(crtc_state, 0, sizeof(*crtc_state));
-		__drm_atomic_helper_crtc_reset(&crtc->base, &crtc_state->base);
+		__drm_atomic_helper_crtc_destroy_state(&crtc_state->uapi);
+		intel_crtc_free_hw_state(crtc_state);
+		intel_crtc_state_reset(crtc_state, crtc);
 
-		crtc_state->base.active = crtc_state->base.enable =
+		crtc_state->hw.active = crtc_state->hw.enable =
 			dev_priv->display.get_pipe_config(crtc, crtc_state);
 
-		crtc->base.enabled = crtc_state->base.enable;
-		crtc->active = crtc_state->base.active;
+		crtc->base.enabled = crtc_state->hw.enable;
+		crtc->active = crtc_state->hw.active;
 
-		if (crtc_state->base.active)
+		if (crtc_state->hw.active)
 			dev_priv->active_pipes |= BIT(crtc->pipe);
 
 		DRM_DEBUG_KMS("[CRTC:%d:%s] hw state readout: %s\n",
 			      crtc->base.base.id, crtc->base.name,
-			      enableddisabled(crtc_state->base.active));
+			      enableddisabled(crtc_state->hw.active));
 	}
 
 	readout_plane_state(dev_priv);
@@ -17319,7 +18054,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			struct intel_crtc_state *crtc_state =
 				to_intel_crtc_state(crtc->base.state);
 
-			if (crtc_state->base.active &&
+			if (crtc_state->hw.active &&
 			    crtc_state->shared_dpll == pll)
 				pll->state.crtc_mask |= 1 << crtc->pipe;
 		}
@@ -17364,15 +18099,15 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			crtc = to_intel_crtc(encoder->base.crtc);
 			crtc_state = crtc ? to_intel_crtc_state(crtc->base.state) : NULL;
 
-			if (crtc_state && crtc_state->base.active) {
+			if (crtc_state && crtc_state->hw.active) {
 				/*
 				 * This has to be done during hardware readout
 				 * because anything calling .crtc_disable may
 				 * rely on the connector_mask being accurate.
 				 */
-				crtc_state->base.connector_mask |=
+				crtc_state->uapi.connector_mask |=
 					drm_connector_mask(&connector->base);
-				crtc_state->base.encoder_mask |=
+				crtc_state->uapi.encoder_mask |=
 					drm_encoder_mask(&encoder->base);
 			}
 		} else {
@@ -17393,16 +18128,15 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		struct intel_plane *plane;
 		int min_cdclk = 0;
 
-		if (crtc_state->base.active) {
-			struct drm_display_mode mode;
+		if (crtc_state->hw.active) {
+			struct drm_display_mode *mode = &crtc_state->hw.mode;
 
-			intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode,
+			intel_mode_from_pipe_config(&crtc_state->hw.adjusted_mode,
 						    crtc_state);
 
-			mode = crtc_state->base.adjusted_mode;
-			mode.hdisplay = crtc_state->pipe_src_w;
-			mode.vdisplay = crtc_state->pipe_src_h;
-			WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->base, &mode));
+			*mode = crtc_state->hw.adjusted_mode;
+			mode->hdisplay = crtc_state->pipe_src_w;
+			mode->vdisplay = crtc_state->pipe_src_h;
 
 			/*
 			 * The initial mode needs to be set in order to keep
@@ -17413,11 +18147,13 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			 * set a flag to indicate that a full recalculation is
 			 * needed on the next commit.
 			 */
-			crtc_state->base.mode.private_flags = I915_MODE_FLAG_INHERITED;
+			mode->private_flags = I915_MODE_FLAG_INHERITED;
 
 			intel_crtc_compute_pixel_rate(crtc_state);
 
 			intel_crtc_update_active_timings(crtc_state);
+
+			intel_crtc_copy_hw_to_uapi_state(crtc_state);
 		}
 
 		for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
@@ -17428,14 +18164,14 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			 * FIXME don't have the fb yet, so can't
 			 * use intel_plane_data_rate() :(
 			 */
-			if (plane_state->base.visible)
+			if (plane_state->uapi.visible)
 				crtc_state->data_rate[plane->id] =
 					4 * crtc_state->pixel_rate;
 			/*
 			 * FIXME don't have the fb yet, so can't
 			 * use plane->min_cdclk() :(
 			 */
-			if (plane_state->base.visible && plane->min_cdclk) {
+			if (plane_state->uapi.visible && plane->min_cdclk) {
 				if (crtc_state->double_wide ||
 				    INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 					crtc_state->min_cdclk[plane->id] =
@@ -17449,7 +18185,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 				      crtc_state->min_cdclk[plane->id]);
 		}
 
-		if (crtc_state->base.active) {
+		if (crtc_state->hw.active) {
 			min_cdclk = intel_crtc_compute_min_cdclk(crtc_state);
 			if (WARN_ON(min_cdclk < 0))
 				min_cdclk = 0;
@@ -17490,8 +18226,11 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 
 static void intel_early_display_was(struct drm_i915_private *dev_priv)
 {
-	/* Display WA #1185 WaDisableDARBFClkGating:cnl,glk */
-	if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+	/*
+	 * Display WA #1185 WaDisableDARBFClkGating:cnl,glk,icl,ehl,tgl
+	 * Also known as Wa_14010480278.
+	 */
+	if (IS_GEN_RANGE(dev_priv, 10, 12) || IS_GEMINILAKE(dev_priv))
 		I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
 			   DARBF_GATING_DIS);
 
@@ -17572,7 +18311,6 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 			     struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc_state *crtc_state;
 	struct intel_encoder *encoder;
 	struct intel_crtc *crtc;
 	intel_wakeref_t wakeref;
@@ -17592,7 +18330,7 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 		/* We need to sanitize only the MST primary port. */
 		if (encoder->type != INTEL_OUTPUT_DP_MST &&
 		    intel_phy_is_tc(dev_priv, phy))
-			intel_tc_port_sanitize(enc_to_dig_port(&encoder->base));
+			intel_tc_port_sanitize(enc_to_dig_port(encoder));
 	}
 
 	get_encoder_power_domains(dev_priv);
@@ -17605,11 +18343,12 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 	 * waits, so we need vblank interrupts restored beforehand.
 	 */
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
-		crtc_state = to_intel_crtc_state(crtc->base.state);
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
 
 		drm_crtc_vblank_reset(&crtc->base);
 
-		if (crtc_state->base.active)
+		if (crtc_state->hw.active)
 			intel_crtc_vblank_on(crtc_state);
 	}
 
@@ -17619,7 +18358,9 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 		intel_sanitize_encoder(encoder);
 
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
-		crtc_state = to_intel_crtc_state(crtc->base.state);
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
+
 		intel_sanitize_crtc(crtc, ctx);
 		intel_dump_pipe_config(crtc_state, NULL, "[setup_hw_state]");
 	}
@@ -17652,17 +18393,16 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 	}
 
 	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
 		u64 put_domains;
 
-		crtc_state = to_intel_crtc_state(crtc->base.state);
 		put_domains = modeset_get_crtc_power_domains(crtc_state);
 		if (WARN_ON(put_domains))
 			modeset_put_power_domains(dev_priv, put_domains);
 	}
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, wakeref);
-
-	intel_fbc_init_pipe_state(dev_priv);
 }
 
 void intel_display_resume(struct drm_device *dev)
@@ -17738,6 +18478,13 @@ void intel_modeset_driver_remove(struct drm_i915_private *i915)
 	 */
 	intel_hpd_poll_fini(i915);
 
+	/*
+	 * MST topology needs to be suspended so we don't have any calls to
+	 * fbdev after it's finalized. MST will be destroyed later as part of
+	 * drm_mode_config_cleanup()
+	 */
+	intel_dp_mst_suspend(i915);
+
 	/* poll work can call into fbdev, hence clean that up afterwards */
 	intel_fbdev_fini(i915);
 
@@ -17756,6 +18503,8 @@ void intel_modeset_driver_remove(struct drm_i915_private *i915)
 
 	intel_gmbus_teardown(i915);
 
+	intel_bw_cleanup(i915);
+
 	destroy_workqueue(i915->flip_wq);
 	destroy_workqueue(i915->modeset_wq);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index f417e0948001..028aab728514 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -332,8 +332,11 @@ enum phy_fia {
 	     (__s) < RUNTIME_INFO(__dev_priv)->num_sprites[(__p)];	\
 	     (__s)++)
 
-#define for_each_port_masked(__port, __ports_mask) \
-	for ((__port) = PORT_A; (__port) < I915_MAX_PORTS; (__port)++)	\
+#define for_each_port(__port) \
+	for ((__port) = PORT_A; (__port) < I915_MAX_PORTS; (__port)++)
+
+#define for_each_port_masked(__port, __ports_mask)			\
+	for_each_port(__port)						\
 		for_each_if((__ports_mask) & BIT(__port))
 
 #define for_each_phy_masked(__phy, __phys_mask) \
@@ -377,6 +380,13 @@ enum phy_fia {
 			    &(dev)->mode_config.encoder_list,	\
 			    base.head)
 
+#define for_each_intel_encoder_mask(dev, intel_encoder, encoder_mask)	\
+	list_for_each_entry(intel_encoder,				\
+			    &(dev)->mode_config.encoder_list,		\
+			    base.head)					\
+		for_each_if((encoder_mask) &				\
+			    drm_encoder_mask(&intel_encoder->base))
+
 #define for_each_intel_dp(dev, intel_encoder)			\
 	for_each_intel_encoder(dev, intel_encoder)		\
 		for_each_if(intel_encoder_is_dp(intel_encoder))
@@ -446,16 +456,25 @@ enum phy_fia {
 #define intel_atomic_crtc_state_for_each_plane_state( \
 		  plane, plane_state, \
 		  crtc_state) \
-	for_each_intel_plane_mask(((crtc_state)->base.state->dev), (plane), \
-				((crtc_state)->base.plane_mask)) \
+	for_each_intel_plane_mask(((crtc_state)->uapi.state->dev), (plane), \
+				((crtc_state)->uapi.plane_mask)) \
 		for_each_if ((plane_state = \
-			      to_intel_plane_state(__drm_atomic_get_current_plane_state((crtc_state)->base.state, &plane->base))))
+			      to_intel_plane_state(__drm_atomic_get_current_plane_state((crtc_state)->uapi.state, &plane->base))))
+
+#define for_each_new_intel_connector_in_state(__state, connector, new_connector_state, __i) \
+	for ((__i) = 0; \
+	     (__i) < (__state)->base.num_connector; \
+	     (__i)++) \
+		for_each_if ((__state)->base.connectors[__i].ptr && \
+			     ((connector) = to_intel_connector((__state)->base.connectors[__i].ptr), \
+			     (new_connector_state) = to_intel_digital_connector_state((__state)->base.connectors[__i].new_state), 1))
 
 void intel_link_compute_m_n(u16 bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,
 			    bool constant_n, bool fec_enable);
 bool is_ccs_modifier(u64 modifier);
+int intel_main_to_aux_plane(const struct drm_framebuffer *fb, int main_plane);
 void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv);
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
 			      u32 pixel_format, u64 modifier);
@@ -467,6 +486,7 @@ enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port);
 bool is_trans_port_sync_mode(const struct intel_crtc_state *state);
 
 void intel_plane_destroy(struct drm_plane *plane);
+void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state);
 void i830_enable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe);
 void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe);
 enum pipe intel_crtc_pch_transcoder(struct intel_crtc *crtc);
@@ -499,11 +519,10 @@ enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv,
 			      enum port port);
 int intel_get_pipe_from_crtc_id_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
-enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
-					     enum pipe pipe);
 u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc);
+void intel_crtc_vblank_off(const struct intel_crtc_state *crtc_state);
 
-int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp);
+int ilk_get_lanes_required(int target_clock, int link_bw, int bpp);
 void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 			 struct intel_digital_port *dport,
 			 unsigned int expected_mask);
@@ -547,7 +566,6 @@ bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state,
 			struct dpll *best_clock);
 int chv_calc_dpll_params(int refclk, struct dpll *pll_clock);
 
-bool intel_crtc_active(struct intel_crtc *crtc);
 bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state);
 void hsw_enable_ips(const struct intel_crtc_state *crtc_state);
 void hsw_disable_ips(const struct intel_crtc_state *crtc_state);
@@ -561,6 +579,8 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 
 u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_center);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
+void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state);
+void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state);
 u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state);
 u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state);
@@ -582,6 +602,10 @@ intel_display_capture_error_state(struct drm_i915_private *dev_priv);
 void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 				     struct intel_display_error_state *error);
 
+bool
+intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info,
+				    uint64_t modifier);
+
 /* modesetting */
 void intel_modeset_init_hw(struct drm_i915_private *i915);
 int intel_modeset_init(struct drm_i915_private *i915);
@@ -603,9 +627,10 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
 		       enum pipe pipe, bool state);
 #define assert_fdi_rx_pll_enabled(d, p) assert_fdi_rx_pll(d, p, true)
 #define assert_fdi_rx_pll_disabled(d, p) assert_fdi_rx_pll(d, p, false)
-void assert_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, bool state);
-#define assert_pipe_enabled(d, p) assert_pipe(d, p, true)
-#define assert_pipe_disabled(d, p) assert_pipe(d, p, false)
+void assert_pipe(struct drm_i915_private *dev_priv,
+		 enum transcoder cpu_transcoder, bool state);
+#define assert_pipe_enabled(d, t) assert_pipe(d, t, true)
+#define assert_pipe_disabled(d, t) assert_pipe(d, t, false)
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 12ba74788cce..21561acfa3ac 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -418,7 +418,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 	int pw_idx = power_well->desc->hsw.idx;
 	enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx);
 	u32 val;
-	int wa_idx_max;
+
+	WARN_ON(!IS_ICELAKE(dev_priv));
 
 	val = I915_READ(regs->driver);
 	I915_WRITE(regs->driver, val | HSW_PWR_WELL_CTL_REQ(pw_idx));
@@ -430,14 +431,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 
 	hsw_wait_for_power_well_enable(dev_priv, power_well);
 
-	/* Display WA #1178: icl, tgl */
-	if (IS_TIGERLAKE(dev_priv))
-		wa_idx_max = ICL_PW_CTL_IDX_AUX_C;
-	else
-		wa_idx_max = ICL_PW_CTL_IDX_AUX_B;
-
-	if (!IS_ELKHARTLAKE(dev_priv) &&
-	    pw_idx >= ICL_PW_CTL_IDX_AUX_A && pw_idx <= wa_idx_max &&
+	/* Display WA #1178: icl */
+	if (pw_idx >= ICL_PW_CTL_IDX_AUX_A && pw_idx <= ICL_PW_CTL_IDX_AUX_B &&
 	    !intel_bios_is_port_edp(dev_priv, (enum port)phy)) {
 		val = I915_READ(ICL_AUX_ANAOVRD1(pw_idx));
 		val |= ICL_AUX_ANAOVRD1_ENABLE | ICL_AUX_ANAOVRD1_LDO_BYPASS;
@@ -454,10 +449,10 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
 	enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx);
 	u32 val;
 
-	if (INTEL_GEN(dev_priv) < 12) {
-		val = I915_READ(ICL_PORT_CL_DW12(phy));
-		I915_WRITE(ICL_PORT_CL_DW12(phy), val & ~ICL_LANE_ENABLE_AUX);
-	}
+	WARN_ON(!IS_ICELAKE(dev_priv));
+
+	val = I915_READ(ICL_PORT_CL_DW12(phy));
+	I915_WRITE(ICL_PORT_CL_DW12(phy), val & ~ICL_LANE_ENABLE_AUX);
 
 	val = I915_READ(regs->driver);
 	I915_WRITE(regs->driver, val & ~HSW_PWR_WELL_CTL_REQ(pw_idx));
@@ -519,7 +514,7 @@ static void icl_tc_port_assert_ref_held(struct drm_i915_private *dev_priv,
 		if (encoder->type == INTEL_OUTPUT_DP_MST)
 			continue;
 
-		dig_port = enc_to_dig_port(&encoder->base);
+		dig_port = enc_to_dig_port(encoder);
 		if (WARN_ON(!dig_port))
 			continue;
 
@@ -1669,8 +1664,8 @@ void chv_phy_powergate_lanes(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
-	enum dpio_phy phy = vlv_dport_to_phy(enc_to_dig_port(&encoder->base));
-	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
+	enum dpio_phy phy = vlv_dport_to_phy(enc_to_dig_port(encoder));
+	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(encoder));
 
 	mutex_lock(&power_domains->lock);
 
@@ -4928,6 +4923,56 @@ static void cnl_display_core_uninit(struct drm_i915_private *dev_priv)
 	intel_combo_phy_uninit(dev_priv);
 }
 
+struct buddy_page_mask {
+	u32 page_mask;
+	u8 type;
+	u8 num_channels;
+};
+
+static const struct buddy_page_mask tgl_buddy_page_masks[] = {
+	{ .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0xE },
+	{ .num_channels = 1, .type = INTEL_DRAM_DDR4,   .page_mask = 0xF },
+	{ .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1C },
+	{ .num_channels = 2, .type = INTEL_DRAM_DDR4,   .page_mask = 0x1F },
+	{}
+};
+
+static const struct buddy_page_mask wa_1409767108_buddy_page_masks[] = {
+	{ .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1 },
+	{ .num_channels = 1, .type = INTEL_DRAM_DDR4,   .page_mask = 0x1 },
+	{ .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x3 },
+	{ .num_channels = 2, .type = INTEL_DRAM_DDR4,   .page_mask = 0x3 },
+	{}
+};
+
+static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv)
+{
+	enum intel_dram_type type = dev_priv->dram_info.type;
+	u8 num_channels = dev_priv->dram_info.num_channels;
+	const struct buddy_page_mask *table;
+	int i;
+
+	if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0))
+		/* Wa_1409767108: tgl */
+		table = wa_1409767108_buddy_page_masks;
+	else
+		table = tgl_buddy_page_masks;
+
+	for (i = 0; table[i].page_mask != 0; i++)
+		if (table[i].num_channels == num_channels &&
+		    table[i].type == type)
+			break;
+
+	if (table[i].page_mask == 0) {
+		DRM_DEBUG_DRIVER("Unknown memory configuration; disabling address buddy logic.\n");
+		I915_WRITE(BW_BUDDY1_CTL, BW_BUDDY_DISABLE);
+		I915_WRITE(BW_BUDDY2_CTL, BW_BUDDY_DISABLE);
+	} else {
+		I915_WRITE(BW_BUDDY1_PAGE_MASK, table[i].page_mask);
+		I915_WRITE(BW_BUDDY2_PAGE_MASK, table[i].page_mask);
+	}
+}
+
 static void icl_display_core_init(struct drm_i915_private *dev_priv,
 				  bool resume)
 {
@@ -4960,6 +5005,10 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 	/* 6. Setup MBUS. */
 	icl_mbus_init(dev_priv);
 
+	/* 7. Program arbiter BW_BUDDY registers */
+	if (INTEL_GEN(dev_priv) >= 12)
+		tgl_bw_buddy_init(dev_priv);
+
 	if (resume && dev_priv->csr.dmc_payload)
 		intel_csr_load_program(dev_priv);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h
index 1da04f3e0fb3..2608a65af7fa 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.h
+++ b/drivers/gpu/drm/i915/display/intel_display_power.h
@@ -28,7 +28,7 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_TRANSCODER_C,
 	POWER_DOMAIN_TRANSCODER_D,
 	POWER_DOMAIN_TRANSCODER_EDP,
-	/* VDSC/joining for TRANSCODER_EDP (ICL) or TRANSCODER_A (TGL) */
+	/* VDSC/joining for eDP/DSI transcoder (ICL) or pipe A (TGL) */
 	POWER_DOMAIN_TRANSCODER_VDSC_PW2,
 	POWER_DOMAIN_TRANSCODER_DSI_A,
 	POWER_DOMAIN_TRANSCODER_DSI_C,
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 1a7334dbe802..888ea8a170d1 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -90,8 +90,8 @@ struct intel_framebuffer {
 	/* for each plane in the normal GTT view */
 	struct {
 		unsigned int x, y;
-	} normal[2];
-	/* for each plane in the rotated GTT view */
+	} normal[4];
+	/* for each plane in the rotated GTT view for no-CCS formats */
 	struct {
 		unsigned int x, y;
 		unsigned int pitch; /* pixels */
@@ -523,7 +523,24 @@ struct intel_atomic_state {
 };
 
 struct intel_plane_state {
-	struct drm_plane_state base;
+	struct drm_plane_state uapi;
+
+	/*
+	 * actual hardware state, the state we program to the hardware.
+	 * The following members are used to verify the hardware state:
+	 * During initial hw readout, they need to be copied from uapi.
+	 */
+	struct {
+		struct drm_crtc *crtc;
+		struct drm_framebuffer *fb;
+
+		u16 alpha;
+		uint16_t pixel_blend_mode;
+		unsigned int rotation;
+		enum drm_color_encoding color_encoding;
+		enum drm_color_range color_range;
+	} hw;
+
 	struct i915_ggtt_view view;
 	struct i915_vma *vma;
 	unsigned long flags;
@@ -538,7 +555,7 @@ struct intel_plane_state {
 		 */
 		u32 stride;
 		int x, y;
-	} color_plane[2];
+	} color_plane[4];
 
 	/* plane control register */
 	u32 ctl;
@@ -546,6 +563,9 @@ struct intel_plane_state {
 	/* plane color control register */
 	u32 color_ctl;
 
+	/* chroma upsampler control register */
+	u32 cus_ctl;
+
 	/*
 	 * scaler_id
 	 *    = -1 : not using a scaler
@@ -757,7 +777,33 @@ enum intel_output_format {
 };
 
 struct intel_crtc_state {
-	struct drm_crtc_state base;
+	/*
+	 * uapi (drm) state. This is the software state shown to userspace.
+	 * In particular, the following members are used for bookkeeping:
+	 * - crtc
+	 * - state
+	 * - *_changed
+	 * - event
+	 * - commit
+	 * - mode_blob
+	 */
+	struct drm_crtc_state uapi;
+
+	/*
+	 * actual hardware state, the state we program to the hardware.
+	 * The following members are used to verify the hardware state:
+	 * - enable
+	 * - active
+	 * - mode / adjusted_mode
+	 * - color property blobs.
+	 *
+	 * During initial hw readout, they need to be copied to uapi.
+	 */
+	struct {
+		bool active, enable;
+		struct drm_property_blob *degamma_lut, *gamma_lut, *ctm;
+		struct drm_display_mode mode, adjusted_mode;
+	} hw;
 
 	/**
 	 * quirks - bitfield with hw state readout quirks
@@ -1008,6 +1054,9 @@ struct intel_crtc_state {
 
 	/* Bitmask to indicate slaves attached */
 	u8 sync_mode_slaves_mask;
+
+	/* Only valid on TGL+ */
+	enum transcoder mst_master_transcoder;
 };
 
 struct intel_crtc {
@@ -1080,9 +1129,6 @@ struct intel_plane {
 	void (*update_plane)(struct intel_plane *plane,
 			     const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state);
-	void (*update_slave)(struct intel_plane *plane,
-			     const struct intel_crtc_state *crtc_state,
-			     const struct intel_plane_state *plane_state);
 	void (*disable_plane)(struct intel_plane *plane,
 			      const struct intel_crtc_state *crtc_state);
 	bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe);
@@ -1113,12 +1159,12 @@ struct cxsr_latency {
 
 #define to_intel_atomic_state(x) container_of(x, struct intel_atomic_state, base)
 #define to_intel_crtc(x) container_of(x, struct intel_crtc, base)
-#define to_intel_crtc_state(x) container_of(x, struct intel_crtc_state, base)
+#define to_intel_crtc_state(x) container_of(x, struct intel_crtc_state, uapi)
 #define to_intel_connector(x) container_of(x, struct intel_connector, base)
 #define to_intel_encoder(x) container_of(x, struct intel_encoder, base)
 #define to_intel_framebuffer(x) container_of(x, struct intel_framebuffer, base)
 #define to_intel_plane(x) container_of(x, struct intel_plane, base)
-#define to_intel_plane_state(x) container_of(x, struct intel_plane_state, base)
+#define to_intel_plane_state(x) container_of(x, struct intel_plane_state, uapi)
 #define intel_fb_obj(x) ((x) ? to_intel_bo((x)->obj[0]) : NULL)
 
 struct intel_hdmi {
@@ -1392,9 +1438,9 @@ struct intel_load_detect_pipe {
 };
 
 static inline struct intel_encoder *
-intel_attached_encoder(struct drm_connector *connector)
+intel_attached_encoder(struct intel_connector *connector)
 {
-	return to_intel_connector(connector)->encoder;
+	return connector->encoder;
 }
 
 static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder)
@@ -1411,12 +1457,12 @@ static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder)
 }
 
 static inline struct intel_digital_port *
-enc_to_dig_port(struct drm_encoder *encoder)
+enc_to_dig_port(struct intel_encoder *encoder)
 {
-	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
+	struct intel_encoder *intel_encoder = encoder;
 
 	if (intel_encoder_is_dig_port(intel_encoder))
-		return container_of(encoder, struct intel_digital_port,
+		return container_of(&encoder->base, struct intel_digital_port,
 				    base.base);
 	else
 		return NULL;
@@ -1425,16 +1471,17 @@ enc_to_dig_port(struct drm_encoder *encoder)
 static inline struct intel_digital_port *
 conn_to_dig_port(struct intel_connector *connector)
 {
-	return enc_to_dig_port(&intel_attached_encoder(&connector->base)->base);
+	return enc_to_dig_port(intel_attached_encoder(connector));
 }
 
 static inline struct intel_dp_mst_encoder *
-enc_to_mst(struct drm_encoder *encoder)
+enc_to_mst(struct intel_encoder *encoder)
 {
-	return container_of(encoder, struct intel_dp_mst_encoder, base.base);
+	return container_of(&encoder->base, struct intel_dp_mst_encoder,
+			    base.base);
 }
 
-static inline struct intel_dp *enc_to_intel_dp(struct drm_encoder *encoder)
+static inline struct intel_dp *enc_to_intel_dp(struct intel_encoder *encoder)
 {
 	return &enc_to_dig_port(encoder)->dp;
 }
@@ -1447,14 +1494,14 @@ static inline bool intel_encoder_is_dp(struct intel_encoder *encoder)
 		return true;
 	case INTEL_OUTPUT_DDI:
 		/* Skip pure HDMI/DVI DDI encoders */
-		return i915_mmio_reg_valid(enc_to_intel_dp(&encoder->base)->output_reg);
+		return i915_mmio_reg_valid(enc_to_intel_dp(encoder)->output_reg);
 	default:
 		return false;
 	}
 }
 
 static inline struct intel_lspcon *
-enc_to_intel_lspcon(struct drm_encoder *encoder)
+enc_to_intel_lspcon(struct intel_encoder *encoder)
 {
 	return &enc_to_dig_port(encoder)->lspcon;
 }
@@ -1528,6 +1575,24 @@ intel_atomic_get_new_crtc_state(struct intel_atomic_state *state,
 								 &crtc->base));
 }
 
+static inline struct intel_digital_connector_state *
+intel_atomic_get_new_connector_state(struct intel_atomic_state *state,
+				     struct intel_connector *connector)
+{
+	return to_intel_digital_connector_state(
+			drm_atomic_get_new_connector_state(&state->base,
+			&connector->base));
+}
+
+static inline struct intel_digital_connector_state *
+intel_atomic_get_old_connector_state(struct intel_atomic_state *state,
+				     struct intel_connector *connector)
+{
+	return to_intel_digital_connector_state(
+			drm_atomic_get_old_connector_state(&state->base,
+			&connector->base));
+}
+
 /* intel_display.c */
 static inline bool
 intel_crtc_has_type(const struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index b05b2191b919..c7424e2a04a3 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -146,9 +146,9 @@ bool intel_dp_is_edp(struct intel_dp *intel_dp)
 	return intel_dig_port->base.type == INTEL_OUTPUT_EDP;
 }
 
-static struct intel_dp *intel_attached_dp(struct drm_connector *connector)
+static struct intel_dp *intel_attached_dp(struct intel_connector *connector)
 {
-	return enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+	return enc_to_intel_dp(intel_attached_encoder(connector));
 }
 
 static void intel_dp_link_down(struct intel_encoder *encoder,
@@ -614,7 +614,7 @@ static enum drm_mode_status
 intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
@@ -834,7 +834,7 @@ static enum pipe vlv_find_free_pps(struct drm_i915_private *dev_priv)
 	 * Pick one that's not used by other ports.
 	 */
 	for_each_intel_dp(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		if (encoder->type == INTEL_OUTPUT_EDP) {
 			WARN_ON(intel_dp->active_pipe != INVALID_PIPE &&
@@ -1031,7 +1031,7 @@ void intel_power_sequencer_reset(struct drm_i915_private *dev_priv)
 	 */
 
 	for_each_intel_dp(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		WARN_ON(intel_dp->active_pipe != INVALID_PIPE);
 
@@ -1814,7 +1814,7 @@ static void intel_dp_print_rates(struct intel_dp *intel_dp)
 {
 	char str[128]; /* FIXME: too big for stack? */
 
-	if ((drm_debug & DRM_UT_KMS) == 0)
+	if (!drm_debug_enabled(DRM_UT_KMS))
 		return;
 
 	snprintf_int_array(str, sizeof(str),
@@ -1889,32 +1889,15 @@ static bool intel_dp_supports_fec(struct intel_dp *intel_dp,
 		drm_dp_sink_supports_fec(intel_dp->fec_capable);
 }
 
-static bool intel_dp_source_supports_dsc(struct intel_dp *intel_dp,
-					 const struct intel_crtc_state *pipe_config)
-{
-	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-
-	if (!INTEL_INFO(dev_priv)->display.has_dsc)
-		return false;
-
-	/* On TGL, DSC is supported on all Pipes */
-	if (INTEL_GEN(dev_priv) >= 12)
-		return true;
-
-	if (INTEL_GEN(dev_priv) >= 10 &&
-	    pipe_config->cpu_transcoder != TRANSCODER_A)
-		return true;
-
-	return false;
-}
-
 static bool intel_dp_supports_dsc(struct intel_dp *intel_dp,
-				  const struct intel_crtc_state *pipe_config)
+				  const struct intel_crtc_state *crtc_state)
 {
-	if (!intel_dp_is_edp(intel_dp) && !pipe_config->fec_enable)
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+
+	if (!intel_dp_is_edp(intel_dp) && !crtc_state->fec_enable)
 		return false;
 
-	return intel_dp_source_supports_dsc(intel_dp, pipe_config) &&
+	return intel_dsc_source_support(encoder, crtc_state) &&
 		drm_dp_sink_supports_dsc(intel_dp->dsc_dpcd);
 }
 
@@ -1999,7 +1982,7 @@ intel_dp_compute_link_config_wide(struct intel_dp *intel_dp,
 				  struct intel_crtc_state *pipe_config,
 				  const struct link_config_limits *limits)
 {
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int bpp, clock, lane_count;
 	int mode_rate, link_clock, link_avail;
 
@@ -2046,6 +2029,63 @@ static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc)
 	return 0;
 }
 
+#define DSC_SUPPORTED_VERSION_MIN		1
+
+static int intel_dp_dsc_compute_params(struct intel_encoder *encoder,
+				       struct intel_crtc_state *crtc_state)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	u8 line_buf_depth;
+	int ret;
+
+	ret = intel_dsc_compute_params(encoder, crtc_state);
+	if (ret)
+		return ret;
+
+	/*
+	 * Slice Height of 8 works for all currently available panels. So start
+	 * with that if pic_height is an integral multiple of 8. Eventually add
+	 * logic to try multiple slice heights.
+	 */
+	if (vdsc_cfg->pic_height % 8 == 0)
+		vdsc_cfg->slice_height = 8;
+	else if (vdsc_cfg->pic_height % 4 == 0)
+		vdsc_cfg->slice_height = 4;
+	else
+		vdsc_cfg->slice_height = 2;
+
+	vdsc_cfg->dsc_version_major =
+		(intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] &
+		 DP_DSC_MAJOR_MASK) >> DP_DSC_MAJOR_SHIFT;
+	vdsc_cfg->dsc_version_minor =
+		min(DSC_SUPPORTED_VERSION_MIN,
+		    (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] &
+		     DP_DSC_MINOR_MASK) >> DP_DSC_MINOR_SHIFT);
+
+	vdsc_cfg->convert_rgb = intel_dp->dsc_dpcd[DP_DSC_DEC_COLOR_FORMAT_CAP - DP_DSC_SUPPORT] &
+		DP_DSC_RGB;
+
+	line_buf_depth = drm_dp_dsc_sink_line_buf_depth(intel_dp->dsc_dpcd);
+	if (!line_buf_depth) {
+		DRM_DEBUG_KMS("DSC Sink Line Buffer Depth invalid\n");
+		return -EINVAL;
+	}
+
+	if (vdsc_cfg->dsc_version_minor == 2)
+		vdsc_cfg->line_buf_depth = (line_buf_depth == DSC_1_2_MAX_LINEBUF_DEPTH_BITS) ?
+			DSC_1_2_MAX_LINEBUF_DEPTH_VAL : line_buf_depth;
+	else
+		vdsc_cfg->line_buf_depth = (line_buf_depth > DSC_1_1_MAX_LINEBUF_DEPTH_BITS) ?
+			DSC_1_1_MAX_LINEBUF_DEPTH_BITS : line_buf_depth;
+
+	vdsc_cfg->block_pred_enable =
+		intel_dp->dsc_dpcd[DP_DSC_BLK_PREDICTION_SUPPORT - DP_DSC_SUPPORT] &
+		DP_DSC_BLK_PREDICTION_IS_SUPPORTED;
+
+	return drm_dsc_compute_rc_parameters(vdsc_cfg);
+}
+
 static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 				       struct intel_crtc_state *pipe_config,
 				       struct drm_connector_state *conn_state,
@@ -2053,7 +2093,7 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	u8 dsc_max_bpc;
 	int pipe_bpp;
 	int ret;
@@ -2132,7 +2172,7 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 		}
 	}
 
-	ret = intel_dp_compute_dsc_params(intel_dp, pipe_config);
+	ret = intel_dp_dsc_compute_params(&dig_port->base, pipe_config);
 	if (ret < 0) {
 		DRM_DEBUG_KMS("Cannot compute valid DSC parameters for Input Bpp = %d "
 			      "Compressed BPP = %d\n",
@@ -2164,8 +2204,8 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 			     struct intel_crtc_state *pipe_config,
 			     struct drm_connector_state *conn_state)
 {
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct link_config_limits limits;
 	int common_len;
 	int ret;
@@ -2252,8 +2292,8 @@ intel_dp_ycbcr420_config(struct intel_dp *intel_dp,
 {
 	const struct drm_display_info *info = &connector->display_info;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+		&crtc_state->hw.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	int ret;
 
 	if (!drm_mode_is_420_only(info, adjusted_mode) ||
@@ -2281,7 +2321,7 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
 	const struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	/*
 	 * Our YCbCr output is always limited range.
@@ -2308,17 +2348,28 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
 	}
 }
 
+static bool intel_dp_port_has_audio(struct drm_i915_private *dev_priv,
+				    enum port port)
+{
+	if (IS_G4X(dev_priv))
+		return false;
+	if (INTEL_GEN(dev_priv) < 12 && port == PORT_A)
+		return false;
+
+	return true;
+}
+
 int
 intel_dp_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_state *pipe_config,
 			struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_lspcon *lspcon = enc_to_intel_lspcon(&encoder->base);
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_lspcon *lspcon = enc_to_intel_lspcon(encoder);
 	enum port port = encoder->port;
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
@@ -2341,7 +2392,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		return ret;
 
 	pipe_config->has_drrs = false;
-	if (IS_G4X(dev_priv) || port == PORT_A)
+	if (!intel_dp_port_has_audio(dev_priv, port))
 		pipe_config->has_audio = false;
 	else if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO)
 		pipe_config->has_audio = intel_dp->has_audio;
@@ -2431,10 +2482,10 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 
 	intel_dp_set_link_params(intel_dp, pipe_config->port_clock,
 				 pipe_config->lane_count,
@@ -2458,7 +2509,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 	 *
 	 * CPT PCH is quite different, having many bits moved
 	 * to the TRANS_DP_CTL register instead. That
-	 * configuration happens (oddly) in ironlake_pch_enable
+	 * configuration happens (oddly) in ilk_pch_enable
 	 */
 
 	/* Preserve the BIOS-computed detected bit. This is
@@ -2602,7 +2653,7 @@ static void edp_wait_backlight_off(struct intel_dp *intel_dp)
  * is locked
  */
 
-static  u32 ironlake_get_pp_control(struct intel_dp *intel_dp)
+static  u32 ilk_get_pp_control(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	u32 control;
@@ -2652,7 +2703,7 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
 	if (!edp_have_panel_power(intel_dp))
 		wait_panel_power_cycle(intel_dp);
 
-	pp = ironlake_get_pp_control(intel_dp);
+	pp = ilk_get_pp_control(intel_dp);
 	pp |= EDP_FORCE_VDD;
 
 	pp_stat_reg = _pp_stat_reg(intel_dp);
@@ -2717,7 +2768,7 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 		      intel_dig_port->base.base.base.id,
 		      intel_dig_port->base.base.name);
 
-	pp = ironlake_get_pp_control(intel_dp);
+	pp = ilk_get_pp_control(intel_dp);
 	pp &= ~EDP_FORCE_VDD;
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
@@ -2813,7 +2864,7 @@ static void edp_panel_on(struct intel_dp *intel_dp)
 	wait_panel_power_cycle(intel_dp);
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
-	pp = ironlake_get_pp_control(intel_dp);
+	pp = ilk_get_pp_control(intel_dp);
 	if (IS_GEN(dev_priv, 5)) {
 		/* ILK workaround: disable reset around power sequence */
 		pp &= ~PANEL_POWER_RESET;
@@ -2868,7 +2919,7 @@ static void edp_panel_off(struct intel_dp *intel_dp)
 	WARN(!intel_dp->want_panel_vdd, "Need [ENCODER:%d:%s] VDD to turn off panel\n",
 	     dig_port->base.base.base.id, dig_port->base.base.name);
 
-	pp = ironlake_get_pp_control(intel_dp);
+	pp = ilk_get_pp_control(intel_dp);
 	/* We need to switch off panel power _and_ force vdd, for otherwise some
 	 * panels get very unhappy and cease to work. */
 	pp &= ~(PANEL_POWER_ON | PANEL_POWER_RESET | EDP_FORCE_VDD |
@@ -2917,7 +2968,7 @@ static void _intel_edp_backlight_on(struct intel_dp *intel_dp)
 		i915_reg_t pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 		u32 pp;
 
-		pp = ironlake_get_pp_control(intel_dp);
+		pp = ilk_get_pp_control(intel_dp);
 		pp |= EDP_BLC_ENABLE;
 
 		I915_WRITE(pp_ctrl_reg, pp);
@@ -2929,7 +2980,7 @@ static void _intel_edp_backlight_on(struct intel_dp *intel_dp)
 void intel_edp_backlight_on(const struct intel_crtc_state *crtc_state,
 			    const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(conn_state->best_encoder);
+	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(conn_state->best_encoder));
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
@@ -2953,7 +3004,7 @@ static void _intel_edp_backlight_off(struct intel_dp *intel_dp)
 		i915_reg_t pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 		u32 pp;
 
-		pp = ironlake_get_pp_control(intel_dp);
+		pp = ilk_get_pp_control(intel_dp);
 		pp &= ~EDP_BLC_ENABLE;
 
 		I915_WRITE(pp_ctrl_reg, pp);
@@ -2967,7 +3018,7 @@ static void _intel_edp_backlight_off(struct intel_dp *intel_dp)
 /* Disable backlight PP control and backlight PWM. */
 void intel_edp_backlight_off(const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(old_conn_state->best_encoder);
+	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(old_conn_state->best_encoder));
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
@@ -2985,13 +3036,13 @@ void intel_edp_backlight_off(const struct drm_connector_state *old_conn_state)
 static void intel_edp_backlight_power(struct intel_connector *connector,
 				      bool enable)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(&connector->base);
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	intel_wakeref_t wakeref;
 	bool is_enabled;
 
 	is_enabled = false;
 	with_pps_lock(intel_dp, wakeref)
-		is_enabled = ironlake_get_pp_control(intel_dp) & EDP_BLC_ENABLE;
+		is_enabled = ilk_get_pp_control(intel_dp) & EDP_BLC_ENABLE;
 	if (is_enabled == enable)
 		return;
 
@@ -3028,13 +3079,13 @@ static void assert_edp_pll(struct drm_i915_private *dev_priv, bool state)
 #define assert_edp_pll_enabled(d) assert_edp_pll((d), true)
 #define assert_edp_pll_disabled(d) assert_edp_pll((d), false)
 
-static void ironlake_edp_pll_on(struct intel_dp *intel_dp,
-				const struct intel_crtc_state *pipe_config)
+static void ilk_edp_pll_on(struct intel_dp *intel_dp,
+			   const struct intel_crtc_state *pipe_config)
 {
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder);
 	assert_dp_port_disabled(intel_dp);
 	assert_edp_pll_disabled(dev_priv);
 
@@ -3068,13 +3119,13 @@ static void ironlake_edp_pll_on(struct intel_dp *intel_dp,
 	udelay(200);
 }
 
-static void ironlake_edp_pll_off(struct intel_dp *intel_dp,
-				 const struct intel_crtc_state *old_crtc_state)
+static void ilk_edp_pll_off(struct intel_dp *intel_dp,
+			    const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, old_crtc_state->cpu_transcoder);
 	assert_dp_port_disabled(intel_dp);
 	assert_edp_pll_enabled(dev_priv);
 
@@ -3207,7 +3258,7 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 				  enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	intel_wakeref_t wakeref;
 	bool ret;
 
@@ -3228,10 +3279,10 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 				struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	u32 tmp, flags = 0;
 	enum port port = encoder->port;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 
 	if (encoder->type == INTEL_OUTPUT_EDP)
 		pipe_config->output_types |= BIT(INTEL_OUTPUT_EDP);
@@ -3266,7 +3317,7 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 			flags |= DRM_MODE_FLAG_NVSYNC;
 	}
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	if (IS_G4X(dev_priv) && tmp & DP_COLOR_RANGE_16_235)
 		pipe_config->limited_color_range = true;
@@ -3283,7 +3334,7 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 			pipe_config->port_clock = 270000;
 	}
 
-	pipe_config->base.adjusted_mode.crtc_clock =
+	pipe_config->hw.adjusted_mode.crtc_clock =
 		intel_dotclock_calculate(pipe_config->port_clock,
 					 &pipe_config->dp_m_n);
 
@@ -3312,7 +3363,7 @@ static void intel_disable_dp(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *old_crtc_state,
 			     const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	intel_dp->link_trained = false;
 
@@ -3346,7 +3397,7 @@ static void g4x_post_disable_dp(struct intel_encoder *encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
 
 	/*
@@ -3359,7 +3410,7 @@ static void g4x_post_disable_dp(struct intel_encoder *encoder,
 
 	/* Only ilk+ has port A */
 	if (port == PORT_A)
-		ironlake_edp_pll_off(intel_dp, old_crtc_state);
+		ilk_edp_pll_off(intel_dp, old_crtc_state);
 }
 
 static void vlv_post_disable_dp(struct intel_encoder *encoder,
@@ -3497,8 +3548,8 @@ static void intel_enable_dp(struct intel_encoder *encoder,
 			    const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	u32 dp_reg = I915_READ(intel_dp->output_reg);
 	enum pipe pipe = crtc->pipe;
 	intel_wakeref_t wakeref;
@@ -3557,14 +3608,14 @@ static void g4x_pre_enable_dp(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config,
 			      const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
 
 	intel_dp_prepare(encoder, pipe_config);
 
 	/* Only ilk+ has port A */
 	if (port == PORT_A)
-		ironlake_edp_pll_on(intel_dp, pipe_config);
+		ilk_edp_pll_on(intel_dp, pipe_config);
 }
 
 static void vlv_detach_power_sequencer(struct intel_dp *intel_dp)
@@ -3607,7 +3658,7 @@ static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv,
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
 	for_each_intel_dp(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		WARN(intel_dp->active_pipe == pipe,
 		     "stealing pipe %c power sequencer from active [ENCODER:%d:%s]\n",
@@ -3630,8 +3681,8 @@ static void vlv_init_panel_power_sequencer(struct intel_encoder *encoder,
 					   const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
@@ -4152,8 +4203,8 @@ intel_dp_link_down(struct intel_encoder *encoder,
 		   const struct intel_crtc_state *old_crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum port port = encoder->port;
 	u32 DP = intel_dp->DP;
 
@@ -4852,7 +4903,7 @@ static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp)
 	intel_dp->compliance.test_data.hdisplay = be16_to_cpu(h_width);
 	intel_dp->compliance.test_data.vdisplay = be16_to_cpu(v_height);
 	/* Set test active flag here so userspace doesn't interrupt things */
-	intel_dp->compliance.test_active = 1;
+	intel_dp->compliance.test_active = true;
 
 	return DP_TEST_ACK;
 }
@@ -4896,7 +4947,7 @@ static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp)
 	}
 
 	/* Set test active flag here so userspace doesn't interrupt things */
-	intel_dp->compliance.test_active = 1;
+	intel_dp->compliance.test_active = true;
 
 	return test_result;
 }
@@ -5045,7 +5096,7 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 			  struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_connector *connector = intel_dp->attached_connector;
 	struct drm_connector_state *conn_state;
 	struct intel_crtc_state *crtc_state;
@@ -5076,7 +5127,7 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 
 	WARN_ON(!intel_crtc_has_dp_encoder(crtc_state));
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return 0;
 
 	if (conn_state->commit &&
@@ -5482,10 +5533,10 @@ static bool intel_combo_phy_connected(struct drm_i915_private *dev_priv,
 	return I915_READ(SDEISR) & SDE_DDI_HOTPLUG_ICP(phy);
 }
 
-static bool icl_digital_port_connected(struct intel_encoder *encoder)
+static bool icp_digital_port_connected(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 
 	if (intel_phy_is_combo(dev_priv, phy))
@@ -5520,9 +5571,9 @@ static bool __intel_digital_port_connected(struct intel_encoder *encoder)
 			return g4x_digital_port_connected(encoder);
 	}
 
-	if (INTEL_GEN(dev_priv) >= 11)
-		return icl_digital_port_connected(encoder);
-	else if (IS_GEN(dev_priv, 10) || IS_GEN9_BC(dev_priv))
+	if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
+		return icp_digital_port_connected(encoder);
+	else if (INTEL_PCH_TYPE(dev_priv) >= PCH_SPT)
 		return spt_digital_port_connected(encoder);
 	else if (IS_GEN9_LP(dev_priv))
 		return bxt_digital_port_connected(encoder);
@@ -5600,7 +5651,7 @@ intel_dp_detect(struct drm_connector *connector,
 		bool force)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *encoder = &dig_port->base;
 	enum drm_connector_status status;
@@ -5704,7 +5755,7 @@ out:
 static void
 intel_dp_force(struct drm_connector *connector)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *intel_encoder = &dig_port->base;
 	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
@@ -5739,7 +5790,7 @@ static int intel_dp_get_modes(struct drm_connector *connector)
 	}
 
 	/* if eDP has no EDID, fall back to fixed mode */
-	if (intel_dp_is_edp(intel_attached_dp(connector)) &&
+	if (intel_dp_is_edp(intel_attached_dp(to_intel_connector(connector))) &&
 	    intel_connector->panel.fixed_mode) {
 		struct drm_display_mode *mode;
 
@@ -5757,7 +5808,7 @@ static int intel_dp_get_modes(struct drm_connector *connector)
 static int
 intel_dp_connector_register(struct drm_connector *connector)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	int ret;
 
 	ret = intel_connector_register(connector);
@@ -5779,7 +5830,7 @@ intel_dp_connector_register(struct drm_connector *connector)
 static void
 intel_dp_connector_unregister(struct drm_connector *connector)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 
 	drm_dp_cec_unregister_connector(&intel_dp->aux);
 	drm_dp_aux_unregister(&intel_dp->aux);
@@ -5788,7 +5839,7 @@ intel_dp_connector_unregister(struct drm_connector *connector)
 
 void intel_dp_encoder_flush_work(struct drm_encoder *encoder)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(to_intel_encoder(encoder));
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 
 	intel_dp_mst_encoder_cleanup(intel_dig_port);
@@ -5817,12 +5868,12 @@ static void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 	intel_dp_encoder_flush_work(encoder);
 
 	drm_encoder_cleanup(encoder);
-	kfree(enc_to_dig_port(encoder));
+	kfree(enc_to_dig_port(to_intel_encoder(encoder)));
 }
 
 void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(intel_encoder);
 	intel_wakeref_t wakeref;
 
 	if (!intel_dp_is_edp(intel_dp))
@@ -5853,7 +5904,7 @@ static
 int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
 				u8 *an)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_dig_port->base.base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(&intel_dig_port->base.base));
 	static const struct drm_dp_aux_msg msg = {
 		.request = DP_AUX_NATIVE_WRITE,
 		.address = DP_AUX_HDCP_AKSV,
@@ -6463,7 +6514,7 @@ static enum pipe vlv_active_pipe(struct intel_dp *intel_dp)
 void intel_dp_encoder_reset(struct drm_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(encoder));
 	struct intel_lspcon *lspcon = dp_to_lspcon(intel_dp);
 	intel_wakeref_t wakeref;
 
@@ -6642,7 +6693,7 @@ intel_pps_readout_hw_state(struct intel_dp *intel_dp, struct edp_power_seq *seq)
 
 	intel_pps_get_registers(intel_dp, &regs);
 
-	pp_ctl = ironlake_get_pp_control(intel_dp);
+	pp_ctl = ilk_get_pp_control(intel_dp);
 
 	/* Ensure PPS is unlocked */
 	if (!HAS_DDI(dev_priv))
@@ -6812,7 +6863,7 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 	 * soon as the new power sequencer gets initialized.
 	 */
 	if (force_disable_vdd) {
-		u32 pp = ironlake_get_pp_control(intel_dp);
+		u32 pp = ilk_get_pp_control(intel_dp);
 
 		WARN(pp & PANEL_POWER_ON, "Panel power already on\n");
 
@@ -6909,7 +6960,7 @@ static void intel_dp_set_drrs_state(struct drm_i915_private *dev_priv,
 				    int refresh_rate)
 {
 	struct intel_dp *intel_dp = dev_priv->drrs.dp;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum drrs_refresh_rate_type index = DRRS_HIGH_RR;
 
 	if (refresh_rate <= 0) {
@@ -6942,7 +6993,7 @@ static void intel_dp_set_drrs_state(struct drm_i915_private *dev_priv,
 		return;
 	}
 
-	if (!crtc_state->base.active) {
+	if (!crtc_state->hw.active) {
 		DRM_DEBUG_KMS("eDP encoder disabled. CRTC not Active\n");
 		return;
 	}
@@ -7609,7 +7660,7 @@ void intel_dp_mst_suspend(struct drm_i915_private *dev_priv)
 		if (encoder->type != INTEL_OUTPUT_DDI)
 			continue;
 
-		intel_dp = enc_to_intel_dp(&encoder->base);
+		intel_dp = enc_to_intel_dp(encoder);
 
 		if (!intel_dp->can_mst)
 			continue;
@@ -7630,7 +7681,7 @@ void intel_dp_mst_resume(struct drm_i915_private *dev_priv)
 		if (encoder->type != INTEL_OUTPUT_DDI)
 			continue;
 
-		intel_dp = enc_to_intel_dp(&encoder->base);
+		intel_dp = enc_to_intel_dp(encoder);
 
 		if (!intel_dp->can_mst)
 			continue;
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index 020422da2ae2..7c653f8c307f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -57,7 +57,7 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
  */
 static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	u8 read_val[2] = { 0x0 };
 	u16 level = 0;
 
@@ -82,7 +82,7 @@ static void
 intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 level)
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	u8 vals[2] = { 0x0 };
 
 	vals[0] = level;
@@ -110,7 +110,7 @@ intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 lev
 static bool intel_dp_aux_set_pwm_freq(struct intel_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	int freq, fxp, fxp_min, fxp_max, fxp_actual, f = 1;
 	u8 pn, pn_min, pn_max;
 
@@ -178,7 +178,7 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 					  const struct drm_connector_state *conn_state)
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	u8 dpcd_buf, new_dpcd_buf, edp_backlight_mode;
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
@@ -222,13 +222,14 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 
 static void intel_dp_aux_disable_backlight(const struct drm_connector_state *old_conn_state)
 {
-	set_aux_backlight_enable(enc_to_intel_dp(old_conn_state->best_encoder), false);
+	set_aux_backlight_enable(enc_to_intel_dp(to_intel_encoder(old_conn_state->best_encoder)),
+				 false);
 }
 
 static int intel_dp_aux_setup_backlight(struct intel_connector *connector,
 					enum pipe pipe)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	struct intel_panel *panel = &connector->panel;
 
 	if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT)
@@ -247,7 +248,7 @@ static int intel_dp_aux_setup_backlight(struct intel_connector *connector,
 static bool
 intel_dp_aux_display_control_capable(struct intel_connector *connector)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 
 	/* Check the eDP Display control capabilities registers to determine if
 	 * the panel can support backlight control over the aux channel
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 03d1cba0b696..cba68c5a80fa 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -42,13 +42,13 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 					    struct drm_connector_state *conn_state,
 					    struct link_config_limits *limits)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct drm_atomic_state *state = crtc_state->uapi.state;
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_dp *intel_dp = &intel_mst->primary->dp;
 	struct intel_connector *connector =
 		to_intel_connector(conn_state->connector);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	void *port = connector->port;
 	bool constant_n = drm_dp_has_quirk(&intel_dp->desc,
 					   DP_DPCD_QUIRK_CONSTANT_N);
@@ -61,10 +61,11 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 		crtc_state->pipe_bpp = bpp;
 
 		crtc_state->pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock,
-						       crtc_state->pipe_bpp);
+						       crtc_state->pipe_bpp,
+						       false);
 
 		slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr,
-						      port, crtc_state->pbn);
+						      port, crtc_state->pbn, 0);
 		if (slots == -EDEADLK)
 			return slots;
 		if (slots >= 0)
@@ -87,19 +88,65 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 	return 0;
 }
 
+/*
+ * Iterate over all connectors and return the smallest transcoder in the MST
+ * stream
+ */
+static enum transcoder
+intel_dp_mst_master_trans_compute(struct intel_atomic_state *state,
+				  struct intel_dp *mst_port)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_digital_connector_state *conn_state;
+	struct intel_connector *connector;
+	enum pipe ret = I915_MAX_PIPES;
+	int i;
+
+	if (INTEL_GEN(dev_priv) < 12)
+		return INVALID_TRANSCODER;
+
+	for_each_new_intel_connector_in_state(state, connector, conn_state, i) {
+		struct intel_crtc_state *crtc_state;
+		struct intel_crtc *crtc;
+
+		if (connector->mst_port != mst_port || !conn_state->base.crtc)
+			continue;
+
+		crtc = to_intel_crtc(conn_state->base.crtc);
+		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+		if (!crtc_state->uapi.active)
+			continue;
+
+		/*
+		 * Using crtc->pipe because crtc_state->cpu_transcoder is
+		 * computed, so others CRTCs could have non-computed
+		 * cpu_transcoder
+		 */
+		if (crtc->pipe < ret)
+			ret = crtc->pipe;
+	}
+
+	if (ret == I915_MAX_PIPES)
+		return INVALID_TRANSCODER;
+
+	/* Simple cast works because TGL don't have a eDP transcoder */
+	return (enum transcoder)ret;
+}
+
 static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 				       struct intel_crtc_state *pipe_config,
 				       struct drm_connector_state *conn_state)
 {
+	struct intel_atomic_state *state = to_intel_atomic_state(conn_state->state);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_dp *intel_dp = &intel_mst->primary->dp;
 	struct intel_connector *connector =
 		to_intel_connector(conn_state->connector);
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
 	const struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 	void *port = connector->port;
 	struct link_config_limits limits;
 	int ret;
@@ -154,25 +201,91 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 
 	intel_ddi_compute_min_voltage_level(dev_priv, pipe_config);
 
+	pipe_config->mst_master_transcoder = intel_dp_mst_master_trans_compute(state, intel_dp);
+
+	return 0;
+}
+
+/*
+ * If one of the connectors in a MST stream needs a modeset, mark all CRTCs
+ * that shares the same MST stream as mode changed,
+ * intel_modeset_pipe_config()+intel_crtc_check_fastset() will take care to do
+ * a fastset when possible.
+ */
+static int
+intel_dp_mst_atomic_master_trans_check(struct intel_connector *connector,
+				       struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct drm_connector_list_iter connector_list_iter;
+	struct intel_connector *connector_iter;
+
+	if (INTEL_GEN(dev_priv) < 12)
+		return  0;
+
+	if (!intel_connector_needs_modeset(state, &connector->base))
+		return 0;
+
+	drm_connector_list_iter_begin(&dev_priv->drm, &connector_list_iter);
+	for_each_intel_connector_iter(connector_iter, &connector_list_iter) {
+		struct intel_digital_connector_state *conn_iter_state;
+		struct intel_crtc_state *crtc_state;
+		struct intel_crtc *crtc;
+		int ret;
+
+		if (connector_iter->mst_port != connector->mst_port ||
+		    connector_iter == connector)
+			continue;
+
+		conn_iter_state = intel_atomic_get_digital_connector_state(state,
+									   connector_iter);
+		if (IS_ERR(conn_iter_state)) {
+			drm_connector_list_iter_end(&connector_list_iter);
+			return PTR_ERR(conn_iter_state);
+		}
+
+		if (!conn_iter_state->base.crtc)
+			continue;
+
+		crtc = to_intel_crtc(conn_iter_state->base.crtc);
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state)) {
+			drm_connector_list_iter_end(&connector_list_iter);
+			return PTR_ERR(crtc_state);
+		}
+
+		ret = drm_atomic_add_affected_planes(&state->base, &crtc->base);
+		if (ret) {
+			drm_connector_list_iter_end(&connector_list_iter);
+			return ret;
+		}
+		crtc_state->uapi.mode_changed = true;
+	}
+	drm_connector_list_iter_end(&connector_list_iter);
+
 	return 0;
 }
 
 static int
 intel_dp_mst_atomic_check(struct drm_connector *connector,
-			  struct drm_atomic_state *state)
+			  struct drm_atomic_state *_state)
 {
+	struct intel_atomic_state *state = to_intel_atomic_state(_state);
 	struct drm_connector_state *new_conn_state =
-		drm_atomic_get_new_connector_state(state, connector);
+		drm_atomic_get_new_connector_state(&state->base, connector);
 	struct drm_connector_state *old_conn_state =
-		drm_atomic_get_old_connector_state(state, connector);
+		drm_atomic_get_old_connector_state(&state->base, connector);
 	struct intel_connector *intel_connector =
 		to_intel_connector(connector);
 	struct drm_crtc *new_crtc = new_conn_state->crtc;
-	struct drm_crtc_state *crtc_state;
 	struct drm_dp_mst_topology_mgr *mgr;
 	int ret;
 
-	ret = intel_digital_connector_atomic_check(connector, state);
+	ret = intel_digital_connector_atomic_check(connector, &state->base);
+	if (ret)
+		return ret;
+
+	ret = intel_dp_mst_atomic_master_trans_check(intel_connector, state);
 	if (ret)
 		return ret;
 
@@ -183,16 +296,18 @@ intel_dp_mst_atomic_check(struct drm_connector *connector,
 	 * connector
 	 */
 	if (new_crtc) {
-		crtc_state = drm_atomic_get_new_crtc_state(state, new_crtc);
+		struct intel_crtc *intel_crtc = to_intel_crtc(new_crtc);
+		struct intel_crtc_state *crtc_state =
+			intel_atomic_get_new_crtc_state(state, intel_crtc);
 
 		if (!crtc_state ||
-		    !drm_atomic_crtc_needs_modeset(crtc_state) ||
-		    crtc_state->enable)
+		    !drm_atomic_crtc_needs_modeset(&crtc_state->uapi) ||
+		    crtc_state->uapi.enable)
 			return 0;
 	}
 
-	mgr = &enc_to_mst(old_conn_state->best_encoder)->primary->dp.mst_mgr;
-	ret = drm_dp_atomic_release_vcpi_slots(state, mgr,
+	mgr = &enc_to_mst(to_intel_encoder(old_conn_state->best_encoder))->primary->dp.mst_mgr;
+	ret = drm_dp_atomic_release_vcpi_slots(&state->base, mgr,
 					       intel_connector->port);
 
 	return ret;
@@ -202,7 +317,7 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
 				 const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct intel_connector *connector =
@@ -226,36 +341,65 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder,
 				      const struct intel_crtc_state *old_crtc_state,
 				      const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct intel_connector *connector =
 		to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	bool last_mst_stream;
+	u32 val;
+
+	intel_dp->active_mst_links--;
+	last_mst_stream = intel_dp->active_mst_links == 0;
+	WARN_ON(INTEL_GEN(dev_priv) >= 12 && last_mst_stream &&
+		!intel_dp_mst_is_master_trans(old_crtc_state));
 
-	intel_ddi_disable_pipe_clock(old_crtc_state);
+	intel_crtc_vblank_off(old_crtc_state);
+
+	intel_disable_pipe(old_crtc_state);
 
-	/* this can fail */
-	drm_dp_check_act_status(&intel_dp->mst_mgr);
-	/* and this can also fail */
 	drm_dp_update_payload_part2(&intel_dp->mst_mgr);
 
+	val = I915_READ(TRANS_DDI_FUNC_CTL(old_crtc_state->cpu_transcoder));
+	val &= ~TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
+	I915_WRITE(TRANS_DDI_FUNC_CTL(old_crtc_state->cpu_transcoder), val);
+
+	if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status,
+				  DP_TP_STATUS_ACT_SENT, 1))
+		DRM_ERROR("Timed out waiting for ACT sent when disabling\n");
+	drm_dp_check_act_status(&intel_dp->mst_mgr);
+
 	drm_dp_mst_deallocate_vcpi(&intel_dp->mst_mgr, connector->port);
 
+	intel_ddi_disable_transcoder_func(old_crtc_state);
+
+	if (INTEL_GEN(dev_priv) >= 9)
+		skl_scaler_disable(old_crtc_state);
+	else
+		ilk_pfit_disable(old_crtc_state);
+
 	/*
 	 * Power down mst path before disabling the port, otherwise we end
 	 * up getting interrupts from the sink upon detecting link loss.
 	 */
 	drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port,
 				     false);
+	/*
+	 * From TGL spec: "If multi-stream slave transcoder: Configure
+	 * Transcoder Clock Select to direct no clock to the transcoder"
+	 *
+	 * From older GENs spec: "Configure Transcoder Clock Select to direct
+	 * no clock to the transcoder"
+	 */
+	if (INTEL_GEN(dev_priv) < 12 || !last_mst_stream)
+		intel_ddi_disable_pipe_clock(old_crtc_state);
 
-	intel_dp->active_mst_links--;
 
 	intel_mst->connector = NULL;
-	if (intel_dp->active_mst_links == 0) {
-		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+	if (last_mst_stream)
 		intel_dig_port->base.post_disable(&intel_dig_port->base,
 						  old_crtc_state, NULL);
-	}
 
 	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
 }
@@ -264,7 +408,7 @@ static void intel_mst_pre_pll_enable_dp(struct intel_encoder *encoder,
 					const struct intel_crtc_state *pipe_config,
 					const struct drm_connector_state *conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 
@@ -273,25 +417,11 @@ static void intel_mst_pre_pll_enable_dp(struct intel_encoder *encoder,
 						    pipe_config, NULL);
 }
 
-static void intel_mst_post_pll_disable_dp(struct intel_encoder *encoder,
-					  const struct intel_crtc_state *old_crtc_state,
-					  const struct drm_connector_state *old_conn_state)
-{
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
-	struct intel_digital_port *intel_dig_port = intel_mst->primary;
-	struct intel_dp *intel_dp = &intel_dig_port->dp;
-
-	if (intel_dp->active_mst_links == 0)
-		intel_dig_port->base.post_pll_disable(&intel_dig_port->base,
-						      old_crtc_state,
-						      old_conn_state);
-}
-
 static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 				    const struct intel_crtc_state *pipe_config,
 				    const struct drm_connector_state *conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -299,21 +429,25 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 		to_intel_connector(conn_state->connector);
 	int ret;
 	u32 temp;
+	bool first_mst_stream;
 
 	/* MST encoders are bound to a crtc, not to a connector,
 	 * force the mapping here for get_hw_state.
 	 */
 	connector->encoder = encoder;
 	intel_mst->connector = connector;
+	first_mst_stream = intel_dp->active_mst_links == 0;
+	WARN_ON(INTEL_GEN(dev_priv) >= 12 && first_mst_stream &&
+		!intel_dp_mst_is_master_trans(pipe_config));
 
 	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
 
-	if (intel_dp->active_mst_links == 0)
+	if (first_mst_stream)
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 
 	drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port, true);
 
-	if (intel_dp->active_mst_links == 0)
+	if (first_mst_stream)
 		intel_dig_port->base.pre_enable(&intel_dig_port->base,
 						pipe_config, NULL);
 
@@ -330,7 +464,15 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 
 	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr);
 
-	intel_ddi_enable_pipe_clock(pipe_config);
+	/*
+	 * Before Gen 12 this is not done as part of
+	 * intel_dig_port->base.pre_enable() and should be done here. For
+	 * Gen 12+ the step in which this should be done is different for the
+	 * first MST stream, so it's done on the DDI for the first stream and
+	 * here for the following ones.
+	 */
+	if (INTEL_GEN(dev_priv) < 12 || !first_mst_stream)
+		intel_ddi_enable_pipe_clock(pipe_config);
 
 	intel_ddi_set_dp_msa(pipe_config, conn_state);
 }
@@ -339,7 +481,7 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -360,7 +502,7 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder,
 static bool intel_dp_mst_enc_get_hw_state(struct intel_encoder *encoder,
 				      enum pipe *pipe)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	*pipe = intel_mst->pipe;
 	if (intel_mst->connector)
 		return true;
@@ -370,7 +512,7 @@ static bool intel_dp_mst_enc_get_hw_state(struct intel_encoder *encoder,
 static void intel_dp_mst_enc_get_config(struct intel_encoder *encoder,
 					struct intel_crtc_state *pipe_config)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 
 	intel_ddi_get_config(&intel_dig_port->base, pipe_config);
@@ -478,7 +620,7 @@ static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_fun
 
 static void intel_dp_mst_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(to_intel_encoder(encoder));
 
 	drm_encoder_cleanup(encoder);
 	kfree(intel_mst);
@@ -633,7 +775,6 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->disable = intel_mst_disable_dp;
 	intel_encoder->post_disable = intel_mst_post_disable_dp;
 	intel_encoder->pre_pll_enable = intel_mst_pre_pll_enable_dp;
-	intel_encoder->post_pll_disable = intel_mst_post_pll_disable_dp;
 	intel_encoder->pre_enable = intel_mst_pre_enable_dp;
 	intel_encoder->enable = intel_mst_enable_dp;
 	intel_encoder->get_hw_state = intel_dp_mst_enc_get_hw_state;
@@ -703,3 +844,14 @@ intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port)
 	drm_dp_mst_topology_mgr_destroy(&intel_dp->mst_mgr);
 	/* encoders will get killed by normal cleanup */
 }
+
+bool intel_dp_mst_is_master_trans(const struct intel_crtc_state *crtc_state)
+{
+	return crtc_state->mst_master_transcoder == crtc_state->cpu_transcoder;
+}
+
+bool intel_dp_mst_is_slave_trans(const struct intel_crtc_state *crtc_state)
+{
+	return crtc_state->mst_master_transcoder != INVALID_TRANSCODER &&
+	       crtc_state->mst_master_transcoder != crtc_state->cpu_transcoder;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.h b/drivers/gpu/drm/i915/display/intel_dp_mst.h
index f660ad80db04..854724f68f09 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.h
@@ -6,10 +6,15 @@
 #ifndef __INTEL_DP_MST_H__
 #define __INTEL_DP_MST_H__
 
+#include <linux/types.h>
+
 struct intel_digital_port;
+struct intel_crtc_state;
 
 int intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_id);
 void intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port);
 int intel_dp_mst_encoder_active_links(struct intel_digital_port *intel_dig_port);
+bool intel_dp_mst_is_master_trans(const struct intel_crtc_state *crtc_state);
+bool intel_dp_mst_is_slave_trans(const struct intel_crtc_state *crtc_state);
 
 #endif /* __INTEL_DP_MST_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dpio_phy.c b/drivers/gpu/drm/i915/display/intel_dpio_phy.c
index 556d1b30f06a..6fb1f7a7364e 100644
--- a/drivers/gpu/drm/i915/display/intel_dpio_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_dpio_phy.c
@@ -642,7 +642,7 @@ void chv_set_phy_signal_level(struct intel_encoder *encoder,
 			      bool uniq_trans_scale)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	enum dpio_channel ch = vlv_dport_to_channel(dport);
 	enum pipe pipe = intel_crtc->pipe;
@@ -738,8 +738,8 @@ void chv_data_lane_soft_reset(struct intel_encoder *encoder,
 			      bool reset)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(encoder));
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
 
@@ -781,9 +781,9 @@ void chv_data_lane_soft_reset(struct intel_encoder *encoder,
 void chv_phy_pre_pll_enable(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum dpio_channel ch = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 	unsigned int lane_mask =
@@ -861,10 +861,10 @@ void chv_phy_pre_pll_enable(struct intel_encoder *encoder,
 void chv_phy_pre_encoder_enable(struct intel_encoder *encoder,
 				const struct intel_crtc_state *crtc_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum dpio_channel ch = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 	int data, i, stagger;
@@ -940,7 +940,7 @@ void chv_phy_pre_encoder_enable(struct intel_encoder *encoder,
 
 void chv_phy_release_cl2_override(struct intel_encoder *encoder)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
 	if (dport->release_cl2_override) {
@@ -953,7 +953,7 @@ void chv_phy_post_pll_disable(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(old_crtc_state->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(old_crtc_state->uapi.crtc)->pipe;
 	u32 val;
 
 	vlv_dpio_get(dev_priv);
@@ -989,7 +989,7 @@ void vlv_set_phy_signal_level(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	enum pipe pipe = intel_crtc->pipe;
 
@@ -1014,9 +1014,9 @@ void vlv_set_phy_signal_level(struct intel_encoder *encoder,
 void vlv_phy_pre_pll_enable(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 
@@ -1043,10 +1043,10 @@ void vlv_phy_pre_pll_enable(struct intel_encoder *encoder,
 void vlv_phy_pre_encoder_enable(struct intel_encoder *encoder,
 				const struct intel_crtc_state *crtc_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
@@ -1073,9 +1073,9 @@ void vlv_phy_pre_encoder_enable(struct intel_encoder *encoder,
 void vlv_phy_reset_lanes(struct intel_encoder *encoder,
 			 const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 3ce0a023eee0..c75e34d87111 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -136,7 +136,7 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv,
  */
 void intel_prepare_shared_dpll(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 
@@ -163,7 +163,7 @@ void intel_prepare_shared_dpll(const struct intel_crtc_state *crtc_state)
  */
 void intel_enable_shared_dpll(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 	unsigned int crtc_mask = drm_crtc_mask(&crtc->base);
@@ -208,7 +208,7 @@ out:
  */
 void intel_disable_shared_dpll(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 	unsigned int crtc_mask = drm_crtc_mask(&crtc->base);
@@ -842,7 +842,7 @@ hsw_ddi_hdmi_get_dpll(struct intel_atomic_state *state,
 static struct intel_shared_dpll *
 hsw_ddi_dp_get_dpll(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	struct intel_shared_dpll *pll;
 	enum intel_dpll_id pll_id;
 	int clock = crtc_state->port_clock;
@@ -1751,7 +1751,7 @@ static bool
 bxt_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state,
 			  struct bxt_clk_div *clk_div)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct dpll best_clock;
 
 	/* Calculate HDMI div */
@@ -2274,7 +2274,7 @@ static bool
 cnl_ddi_calculate_wrpll(struct intel_crtc_state *crtc_state,
 			struct skl_wrpll_params *wrpll_params)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 afe_clock = crtc_state->port_clock * 5;
 	u32 ref_clock;
 	u32 dco_min = 7998000;
@@ -2553,7 +2553,7 @@ static const struct skl_wrpll_params tgl_tbt_pll_24MHz_values = {
 static bool icl_calc_dp_combo_pll(struct intel_crtc_state *crtc_state,
 				  struct skl_wrpll_params *pll_params)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	const struct icl_combo_pll_params *params =
 		dev_priv->cdclk.hw.ref == 24000 ?
 		icl_dp_combo_pll_24MHz_values :
@@ -2575,7 +2575,7 @@ static bool icl_calc_dp_combo_pll(struct intel_crtc_state *crtc_state,
 static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state,
 			     struct skl_wrpll_params *pll_params)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (INTEL_GEN(dev_priv) >= 12) {
 		switch (dev_priv->cdclk.hw.ref) {
@@ -2612,7 +2612,7 @@ static bool icl_calc_dpll_state(struct intel_crtc_state *crtc_state,
 				struct intel_encoder *encoder,
 				struct intel_dpll_hw_state *pll_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 cfgcr0, cfgcr1;
 	struct skl_wrpll_params pll_params = { 0 };
 	bool ret;
@@ -2744,7 +2744,7 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 				  struct intel_dpll_hw_state *pll_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int refclk_khz = dev_priv->cdclk.hw.ref;
 	int clock = crtc_state->port_clock;
 	u32 dco_khz, m1div, m2div_int, m2div_rem, m2div_frac;
@@ -2972,8 +2972,8 @@ static void icl_update_active_dpll(struct intel_atomic_state *state,
 	enum icl_port_dpll_id port_dpll_id = ICL_PORT_DPLL_DEFAULT;
 
 	primary_port = encoder->type == INTEL_OUTPUT_DP_MST ?
-		enc_to_mst(&encoder->base)->primary :
-		enc_to_dig_port(&encoder->base);
+		enc_to_mst(encoder)->primary :
+		enc_to_dig_port(encoder);
 
 	if (primary_port &&
 	    (primary_port->tc_mode == TC_PORT_DP_ALT ||
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index bb5a0e91b370..ada006a690df 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -102,43 +102,50 @@ intel_dsb_get(struct intel_crtc *crtc)
 	struct intel_dsb *dsb = &crtc->dsb;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
+	u32 *buf;
 	intel_wakeref_t wakeref;
 
 	if (!HAS_DSB(i915))
 		return dsb;
 
-	if (atomic_add_return(1, &dsb->refcount) != 1)
+	if (dsb->refcount++ != 0)
 		return dsb;
 
-	dsb->id = DSB1;
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
 	obj = i915_gem_object_create_internal(i915, DSB_BUF_SIZE);
 	if (IS_ERR(obj)) {
 		DRM_ERROR("Gem object creation failed\n");
-		goto err;
+		goto out;
 	}
 
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
 	if (IS_ERR(vma)) {
 		DRM_ERROR("Vma creation failed\n");
 		i915_gem_object_put(obj);
-		atomic_dec(&dsb->refcount);
-		goto err;
+		goto out;
 	}
 
-	dsb->cmd_buf = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
-	if (IS_ERR(dsb->cmd_buf)) {
+	buf = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
+	if (IS_ERR(buf)) {
 		DRM_ERROR("Command buffer creation failed\n");
-		i915_vma_unpin_and_release(&vma, 0);
-		dsb->cmd_buf = NULL;
-		atomic_dec(&dsb->refcount);
-		goto err;
+		goto out;
 	}
+
+	dsb->id = DSB1;
 	dsb->vma = vma;
+	dsb->cmd_buf = buf;
+
+out:
+	/*
+	 * On error dsb->cmd_buf will continue to be NULL, making the writes
+	 * pass-through. Leave the dangling ref to be removed later by the
+	 * corresponding intel_dsb_put(): the important error message will
+	 * already be logged above.
+	 */
 
-err:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+
 	return dsb;
 }
 
@@ -158,10 +165,10 @@ void intel_dsb_put(struct intel_dsb *dsb)
 	if (!HAS_DSB(i915))
 		return;
 
-	if (WARN_ON(atomic_read(&dsb->refcount) == 0))
+	if (WARN_ON(dsb->refcount == 0))
 		return;
 
-	if (atomic_dec_and_test(&dsb->refcount)) {
+	if (--dsb->refcount == 0) {
 		i915_vma_unpin_and_release(&dsb->vma, I915_VMA_RELEASE_MAP);
 		dsb->cmd_buf = NULL;
 		dsb->free_pos = 0;
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h
index 6f95c8e909e6..395ef9ce558e 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.h
+++ b/drivers/gpu/drm/i915/display/intel_dsb.h
@@ -22,7 +22,7 @@ enum dsb_id {
 };
 
 struct intel_dsb {
-	atomic_t refcount;
+	long refcount;
 	enum dsb_id id;
 	u32 *cmd_buf;
 	struct i915_vma *vma;
diff --git a/drivers/gpu/drm/i915/display/intel_dsi.h b/drivers/gpu/drm/i915/display/intel_dsi.h
index b15be5814599..19f78a4022d3 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi.h
+++ b/drivers/gpu/drm/i915/display/intel_dsi.h
@@ -45,8 +45,9 @@ struct intel_dsi {
 	struct intel_dsi_host *dsi_hosts[I915_MAX_PORTS];
 	intel_wakeref_t io_wakeref[I915_MAX_PORTS];
 
-	/* GPIO Desc for CRC based Panel control */
+	/* GPIO Desc for panel and backlight control */
 	struct gpio_desc *gpio_panel;
+	struct gpio_desc *gpio_backlight;
 
 	struct intel_connector *attached_connector;
 
@@ -68,6 +69,9 @@ struct intel_dsi {
 	/* number of DSI lanes */
 	unsigned int lane_count;
 
+	/* i2c bus associated with the slave device */
+	int i2c_bus_num;
+
 	/*
 	 * video mode pixel format
 	 *
@@ -141,9 +145,9 @@ static inline struct intel_dsi_host *to_intel_dsi_host(struct mipi_dsi_host *h)
 #define for_each_dsi_phy(__phy, __phys_mask) \
 	for_each_phy_masked(__phy, __phys_mask)
 
-static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
+static inline struct intel_dsi *enc_to_intel_dsi(struct intel_encoder *encoder)
 {
-	return container_of(encoder, struct intel_dsi, base.base);
+	return container_of(&encoder->base, struct intel_dsi, base.base);
 }
 
 static inline bool is_vid_mode(struct intel_dsi *intel_dsi)
@@ -158,7 +162,7 @@ static inline bool is_cmd_mode(struct intel_dsi *intel_dsi)
 
 static inline u16 intel_dsi_encoder_ports(struct intel_encoder *encoder)
 {
-	return enc_to_intel_dsi(&encoder->base)->ports;
+	return enc_to_intel_dsi(encoder)->ports;
 }
 
 /* icl_dsi.c */
@@ -203,6 +207,8 @@ void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port);
 
 /* intel_dsi_vbt.c */
 bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id);
+void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on);
+void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi);
 void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
 				 enum mipi_seq seq_id);
 void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec);
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c b/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c
index bb3fd8b786a2..c87838843d0b 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c
@@ -46,7 +46,7 @@
 static u32 dcs_get_backlight(struct intel_connector *connector)
 {
 	struct intel_encoder *encoder = connector->encoder;
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct mipi_dsi_device *dsi_device;
 	u8 data = 0;
 	enum port port;
@@ -64,7 +64,7 @@ static u32 dcs_get_backlight(struct intel_connector *connector)
 
 static void dcs_set_backlight(const struct drm_connector_state *conn_state, u32 level)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(conn_state->best_encoder);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(conn_state->best_encoder));
 	struct mipi_dsi_device *dsi_device;
 	u8 data = level;
 	enum port port;
@@ -79,7 +79,7 @@ static void dcs_set_backlight(const struct drm_connector_state *conn_state, u32
 
 static void dcs_disable_backlight(const struct drm_connector_state *conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(conn_state->best_encoder);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(conn_state->best_encoder));
 	struct mipi_dsi_device *dsi_device;
 	enum port port;
 
@@ -113,7 +113,7 @@ static void dcs_disable_backlight(const struct drm_connector_state *conn_state)
 static void dcs_enable_backlight(const struct intel_crtc_state *crtc_state,
 				 const struct drm_connector_state *conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(conn_state->best_encoder);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(conn_state->best_encoder));
 	struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel;
 	struct mipi_dsi_device *dsi_device;
 	enum port port;
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
index f90946c912ee..89fb0d90b694 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
@@ -25,7 +25,10 @@
  */
 
 #include <linux/gpio/consumer.h>
+#include <linux/gpio/machine.h>
 #include <linux/mfd/intel_soc_pmic.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/pinctrl/machine.h>
 #include <linux/slab.h>
 
 #include <asm/intel-mid.h>
@@ -83,6 +86,12 @@ static struct gpio_map vlv_gpio_table[] = {
 	{ VLV_GPIO_NC_11_PANEL1_BKLTCTL },
 };
 
+struct i2c_adapter_lookup {
+	u16 slave_addr;
+	struct intel_dsi *intel_dsi;
+	acpi_handle dev_handle;
+};
+
 #define CHV_GPIO_IDX_START_N		0
 #define CHV_GPIO_IDX_START_E		73
 #define CHV_GPIO_IDX_START_SW		100
@@ -375,11 +384,98 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 	return data;
 }
 
+static int i2c_adapter_lookup(struct acpi_resource *ares, void *data)
+{
+	struct i2c_adapter_lookup *lookup = data;
+	struct intel_dsi *intel_dsi = lookup->intel_dsi;
+	struct acpi_resource_i2c_serialbus *sb;
+	struct i2c_adapter *adapter;
+	acpi_handle adapter_handle;
+	acpi_status status;
+
+	if (intel_dsi->i2c_bus_num >= 0 ||
+	    !i2c_acpi_get_i2c_resource(ares, &sb))
+		return 1;
+
+	if (lookup->slave_addr != sb->slave_address)
+		return 1;
+
+	status = acpi_get_handle(lookup->dev_handle,
+				 sb->resource_source.string_ptr,
+				 &adapter_handle);
+	if (ACPI_FAILURE(status))
+		return 1;
+
+	adapter = i2c_acpi_find_adapter_by_handle(adapter_handle);
+	if (adapter)
+		intel_dsi->i2c_bus_num = adapter->nr;
+
+	return 1;
+}
+
 static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data)
 {
-	DRM_DEBUG_KMS("Skipping I2C element execution\n");
+	struct drm_device *drm_dev = intel_dsi->base.base.dev;
+	struct device *dev = &drm_dev->pdev->dev;
+	struct i2c_adapter *adapter;
+	struct acpi_device *acpi_dev;
+	struct list_head resource_list;
+	struct i2c_adapter_lookup lookup;
+	struct i2c_msg msg;
+	int ret;
+	u8 vbt_i2c_bus_num = *(data + 2);
+	u16 slave_addr = *(u16 *)(data + 3);
+	u8 reg_offset = *(data + 5);
+	u8 payload_size = *(data + 6);
+	u8 *payload_data;
+
+	if (intel_dsi->i2c_bus_num < 0) {
+		intel_dsi->i2c_bus_num = vbt_i2c_bus_num;
+
+		acpi_dev = ACPI_COMPANION(dev);
+		if (acpi_dev) {
+			memset(&lookup, 0, sizeof(lookup));
+			lookup.slave_addr = slave_addr;
+			lookup.intel_dsi = intel_dsi;
+			lookup.dev_handle = acpi_device_handle(acpi_dev);
+
+			INIT_LIST_HEAD(&resource_list);
+			acpi_dev_get_resources(acpi_dev, &resource_list,
+					       i2c_adapter_lookup,
+					       &lookup);
+			acpi_dev_free_resource_list(&resource_list);
+		}
+	}
 
-	return data + *(data + 6) + 7;
+	adapter = i2c_get_adapter(intel_dsi->i2c_bus_num);
+	if (!adapter) {
+		DRM_DEV_ERROR(dev, "Cannot find a valid i2c bus for xfer\n");
+		goto err_bus;
+	}
+
+	payload_data = kzalloc(payload_size + 1, GFP_KERNEL);
+	if (!payload_data)
+		goto err_alloc;
+
+	payload_data[0] = reg_offset;
+	memcpy(&payload_data[1], (data + 7), payload_size);
+
+	msg.addr = slave_addr;
+	msg.flags = 0;
+	msg.len = payload_size + 1;
+	msg.buf = payload_data;
+
+	ret = i2c_transfer(adapter, &msg, 1);
+	if (ret < 0)
+		DRM_DEV_ERROR(dev,
+			      "Failed to xfer payload of size (%u) to reg (%u)\n",
+			      payload_size, reg_offset);
+
+	kfree(payload_data);
+err_alloc:
+	i2c_put_adapter(adapter);
+err_bus:
+	return data + payload_size + 7;
 }
 
 static const u8 *mipi_exec_spi(struct intel_dsi *intel_dsi, const u8 *data)
@@ -453,8 +549,8 @@ static const char *sequence_name(enum mipi_seq seq_id)
 		return "(unknown)";
 }
 
-void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
-				 enum mipi_seq seq_id)
+static void intel_dsi_vbt_exec(struct intel_dsi *intel_dsi,
+			       enum mipi_seq seq_id)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev);
 	const u8 *data;
@@ -519,6 +615,22 @@ void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
 	}
 }
 
+void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
+				 enum mipi_seq seq_id)
+{
+	if (seq_id == MIPI_SEQ_POWER_ON && intel_dsi->gpio_panel)
+		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 1);
+	if (seq_id == MIPI_SEQ_BACKLIGHT_ON && intel_dsi->gpio_backlight)
+		gpiod_set_value_cansleep(intel_dsi->gpio_backlight, 1);
+
+	intel_dsi_vbt_exec(intel_dsi, seq_id);
+
+	if (seq_id == MIPI_SEQ_POWER_OFF && intel_dsi->gpio_panel)
+		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 0);
+	if (seq_id == MIPI_SEQ_BACKLIGHT_OFF && intel_dsi->gpio_backlight)
+		gpiod_set_value_cansleep(intel_dsi->gpio_backlight, 0);
+}
+
 void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev);
@@ -664,6 +776,8 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id)
 	intel_dsi->panel_off_delay = pps->panel_off_delay / 10;
 	intel_dsi->panel_pwr_cycle_delay = pps->panel_power_cycle_delay / 10;
 
+	intel_dsi->i2c_bus_num = -1;
+
 	/* a regular driver would get the device in probe */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		mipi_dsi_attach(intel_dsi->dsi_hosts[port]->device);
@@ -671,3 +785,110 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id)
 
 	return true;
 }
+
+/*
+ * On some BYT/CHT devs some sequences are incomplete and we need to manually
+ * control some GPIOs. We need to add a GPIO lookup table before we get these.
+ * If the GOP did not initialize the panel (HDMI inserted) we may need to also
+ * change the pinmux for the SoC's PWM0 pin from GPIO to PWM.
+ */
+static struct gpiod_lookup_table pmic_panel_gpio_table = {
+	/* Intel GFX is consumer */
+	.dev_id = "0000:00:02.0",
+	.table = {
+		/* Panel EN/DISABLE */
+		GPIO_LOOKUP("gpio_crystalcove", 94, "panel", GPIO_ACTIVE_HIGH),
+		{ }
+	},
+};
+
+static struct gpiod_lookup_table soc_panel_gpio_table = {
+	.dev_id = "0000:00:02.0",
+	.table = {
+		GPIO_LOOKUP("INT33FC:01", 10, "backlight", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("INT33FC:01", 11, "panel", GPIO_ACTIVE_HIGH),
+		{ }
+	},
+};
+
+static const struct pinctrl_map soc_pwm_pinctrl_map[] = {
+	PIN_MAP_MUX_GROUP("0000:00:02.0", "soc_pwm0", "INT33FC:00",
+			  "pwm0_grp", "pwm"),
+};
+
+void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on)
+{
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct mipi_config *mipi_config = dev_priv->vbt.dsi.config;
+	enum gpiod_flags flags = panel_is_on ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW;
+	bool want_backlight_gpio = false;
+	bool want_panel_gpio = false;
+	struct pinctrl *pinctrl;
+	int ret;
+
+	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	    mipi_config->pwm_blc == PPS_BLC_PMIC) {
+		gpiod_add_lookup_table(&pmic_panel_gpio_table);
+		want_panel_gpio = true;
+	}
+
+	if (IS_VALLEYVIEW(dev_priv) && mipi_config->pwm_blc == PPS_BLC_SOC) {
+		gpiod_add_lookup_table(&soc_panel_gpio_table);
+		want_panel_gpio = true;
+		want_backlight_gpio = true;
+
+		/* Ensure PWM0 pin is muxed as PWM instead of GPIO */
+		ret = pinctrl_register_mappings(soc_pwm_pinctrl_map,
+					     ARRAY_SIZE(soc_pwm_pinctrl_map));
+		if (ret)
+			DRM_ERROR("Failed to register pwm0 pinmux mapping\n");
+
+		pinctrl = devm_pinctrl_get_select(dev->dev, "soc_pwm0");
+		if (IS_ERR(pinctrl))
+			DRM_ERROR("Failed to set pinmux to PWM\n");
+	}
+
+	if (want_panel_gpio) {
+		intel_dsi->gpio_panel = gpiod_get(dev->dev, "panel", flags);
+		if (IS_ERR(intel_dsi->gpio_panel)) {
+			DRM_ERROR("Failed to own gpio for panel control\n");
+			intel_dsi->gpio_panel = NULL;
+		}
+	}
+
+	if (want_backlight_gpio) {
+		intel_dsi->gpio_backlight =
+			gpiod_get(dev->dev, "backlight", flags);
+		if (IS_ERR(intel_dsi->gpio_backlight)) {
+			DRM_ERROR("Failed to own gpio for backlight control\n");
+			intel_dsi->gpio_backlight = NULL;
+		}
+	}
+}
+
+void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi)
+{
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct mipi_config *mipi_config = dev_priv->vbt.dsi.config;
+
+	if (intel_dsi->gpio_panel) {
+		gpiod_put(intel_dsi->gpio_panel);
+		intel_dsi->gpio_panel = NULL;
+	}
+
+	if (intel_dsi->gpio_backlight) {
+		gpiod_put(intel_dsi->gpio_backlight);
+		intel_dsi->gpio_backlight = NULL;
+	}
+
+	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	    mipi_config->pwm_blc == PPS_BLC_PMIC)
+		gpiod_remove_lookup_table(&pmic_panel_gpio_table);
+
+	if (IS_VALLEYVIEW(dev_priv) && mipi_config->pwm_blc == PPS_BLC_SOC) {
+		pinctrl_unregister_mappings(soc_pwm_pinctrl_map);
+		gpiod_remove_lookup_table(&soc_panel_gpio_table);
+	}
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index bcfbcb743e7d..86a337c9d85d 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -125,7 +125,7 @@ static struct intel_dvo *enc_to_dvo(struct intel_encoder *encoder)
 	return container_of(encoder, struct intel_dvo, base);
 }
 
-static struct intel_dvo *intel_attached_dvo(struct drm_connector *connector)
+static struct intel_dvo *intel_attached_dvo(struct intel_connector *connector)
 {
 	return enc_to_dvo(intel_attached_encoder(connector));
 }
@@ -134,7 +134,7 @@ static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector)
 {
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_dvo *intel_dvo = intel_attached_dvo(&connector->base);
+	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
 	u32 tmp;
 
 	tmp = I915_READ(intel_dvo->dev.dvo_reg);
@@ -178,9 +178,9 @@ static void intel_dvo_get_config(struct intel_encoder *encoder,
 	else
 		flags |= DRM_MODE_FLAG_NVSYNC;
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
-	pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock;
+	pipe_config->hw.adjusted_mode.crtc_clock = pipe_config->port_clock;
 }
 
 static void intel_disable_dvo(struct intel_encoder *encoder,
@@ -207,8 +207,8 @@ static void intel_enable_dvo(struct intel_encoder *encoder,
 	u32 temp = I915_READ(dvo_reg);
 
 	intel_dvo->dev.dev_ops->mode_set(&intel_dvo->dev,
-					 &pipe_config->base.mode,
-					 &pipe_config->base.adjusted_mode);
+					 &pipe_config->hw.mode,
+					 &pipe_config->hw.adjusted_mode);
 
 	I915_WRITE(dvo_reg, temp | DVO_ENABLE);
 	I915_READ(dvo_reg);
@@ -220,7 +220,7 @@ static enum drm_mode_status
 intel_dvo_mode_valid(struct drm_connector *connector,
 		     struct drm_display_mode *mode)
 {
-	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
+	struct intel_dvo *intel_dvo = intel_attached_dvo(to_intel_connector(connector));
 	const struct drm_display_mode *fixed_mode =
 		to_intel_connector(connector)->panel.fixed_mode;
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
@@ -253,7 +253,7 @@ static int intel_dvo_compute_config(struct intel_encoder *encoder,
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	const struct drm_display_mode *fixed_mode =
 		intel_dvo->attached_connector->panel.fixed_mode;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 
 	/*
 	 * If we have timings from the BIOS for the panel, put them in
@@ -277,8 +277,8 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder,
 				 const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	enum pipe pipe = crtc->pipe;
 	u32 dvo_val;
@@ -311,7 +311,7 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder,
 static enum drm_connector_status
 intel_dvo_detect(struct drm_connector *connector, bool force)
 {
-	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
+	struct intel_dvo *intel_dvo = intel_attached_dvo(to_intel_connector(connector));
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
 	return intel_dvo->dev.dev_ops->detect(&intel_dvo->dev);
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 20616639b8ab..a1048ece541e 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -50,11 +50,6 @@ static inline bool fbc_supported(struct drm_i915_private *dev_priv)
 	return HAS_FBC(dev_priv);
 }
 
-static inline bool no_fbc_on_multiple_pipes(struct drm_i915_private *dev_priv)
-{
-	return INTEL_GEN(dev_priv) <= 3;
-}
-
 /*
  * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the
  * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's
@@ -73,7 +68,7 @@ static unsigned int get_crtc_fence_y_offset(struct intel_fbc *fbc)
  * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value
  * we wrote to PIPESRC.
  */
-static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
+static void intel_fbc_get_plane_source_size(const struct intel_fbc_state_cache *cache,
 					    int *width, int *height)
 {
 	if (width)
@@ -83,7 +78,7 @@ static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
 }
 
 static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
-					struct intel_fbc_state_cache *cache)
+					const struct intel_fbc_state_cache *cache)
 {
 	int lines;
 
@@ -143,8 +138,10 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv)
 		u32 fbc_ctl2;
 
 		/* Set it up... */
-		fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | FBC_CTL_CPU_FENCE;
+		fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM;
 		fbc_ctl2 |= FBC_CTL_PLANE(params->crtc.i9xx_plane);
+		if (params->fence_id >= 0)
+			fbc_ctl2 |= FBC_CTL_CPU_FENCE;
 		I915_WRITE(FBC_CONTROL2, fbc_ctl2);
 		I915_WRITE(FBC_FENCE_OFF, params->crtc.fence_y_offset);
 	}
@@ -156,7 +153,8 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv)
 	if (IS_I945GM(dev_priv))
 		fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */
 	fbc_ctl |= (cfb_pitch & 0xff) << FBC_CTL_STRIDE_SHIFT;
-	fbc_ctl |= params->vma->fence->id;
+	if (params->fence_id >= 0)
+		fbc_ctl |= params->fence_id;
 	I915_WRITE(FBC_CONTROL, fbc_ctl);
 }
 
@@ -176,8 +174,8 @@ static void g4x_fbc_activate(struct drm_i915_private *dev_priv)
 	else
 		dpfc_ctl |= DPFC_CTL_LIMIT_1X;
 
-	if (params->flags & PLANE_HAS_FENCE) {
-		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->vma->fence->id;
+	if (params->fence_id >= 0) {
+		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fence_id;
 		I915_WRITE(DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
 	} else {
 		I915_WRITE(DPFC_FENCE_YOFF, 0);
@@ -234,14 +232,14 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	if (params->flags & PLANE_HAS_FENCE) {
+	if (params->fence_id >= 0) {
 		dpfc_ctl |= DPFC_CTL_FENCE_EN;
 		if (IS_GEN(dev_priv, 5))
-			dpfc_ctl |= params->vma->fence->id;
+			dpfc_ctl |= params->fence_id;
 		if (IS_GEN(dev_priv, 6)) {
 			I915_WRITE(SNB_DPFC_CTL_SA,
 				   SNB_CPU_FENCE_ENABLE |
-				   params->vma->fence->id);
+				   params->fence_id);
 			I915_WRITE(DPFC_CPU_FENCE_OFFSET,
 				   params->crtc.fence_y_offset);
 		}
@@ -253,8 +251,6 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 	}
 
 	I915_WRITE(ILK_DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
-	I915_WRITE(ILK_FBC_RT_BASE,
-		   i915_ggtt_offset(params->vma) | ILK_FBC_RT_VALID);
 	/* enable it... */
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -285,13 +281,12 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 	int threshold = dev_priv->fbc.threshold;
 
 	/* Display WA #0529: skl, kbl, bxt. */
-	if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) {
 		u32 val = I915_READ(CHICKEN_MISC_4);
 
 		val &= ~(FBC_STRIDE_OVERRIDE | FBC_STRIDE_MASK);
 
-		if (i915_gem_object_get_tiling(params->vma->obj) !=
-		    I915_TILING_X)
+		if (params->gen9_wa_cfb_stride)
 			val |= FBC_STRIDE_OVERRIDE | params->gen9_wa_cfb_stride;
 
 		I915_WRITE(CHICKEN_MISC_4, val);
@@ -317,11 +312,11 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	if (params->flags & PLANE_HAS_FENCE) {
+	if (params->fence_id >= 0) {
 		dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN;
 		I915_WRITE(SNB_DPFC_CTL_SA,
 			   SNB_CPU_FENCE_ENABLE |
-			   params->vma->fence->id);
+			   params->fence_id);
 		I915_WRITE(DPFC_CPU_FENCE_OFFSET, params->crtc.fence_y_offset);
 	} else {
 		I915_WRITE(SNB_DPFC_CTL_SA,0);
@@ -367,6 +362,7 @@ static void intel_fbc_hw_activate(struct drm_i915_private *dev_priv)
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	fbc->active = true;
+	fbc->activated = true;
 
 	if (INTEL_GEN(dev_priv) >= 7)
 		gen7_fbc_activate(dev_priv);
@@ -419,29 +415,10 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 	fbc->no_fbc_reason = reason;
 }
 
-static bool multiple_pipes_ok(struct intel_crtc *crtc,
-			      struct intel_plane_state *plane_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_fbc *fbc = &dev_priv->fbc;
-	enum pipe pipe = crtc->pipe;
-
-	/* Don't even bother tracking anything we don't need. */
-	if (!no_fbc_on_multiple_pipes(dev_priv))
-		return true;
-
-	if (plane_state->base.visible)
-		fbc->visible_pipes_mask |= (1 << pipe);
-	else
-		fbc->visible_pipes_mask &= ~(1 << pipe);
-
-	return (fbc->visible_pipes_mask & ~(1 << pipe)) != 0;
-}
-
 static int find_compression_threshold(struct drm_i915_private *dev_priv,
 				      struct drm_mm_node *node,
-				      int size,
-				      int fb_cpp)
+				      unsigned int size,
+				      unsigned int fb_cpp)
 {
 	int compression_threshold = 1;
 	int ret;
@@ -487,18 +464,15 @@ again:
 	}
 }
 
-static int intel_fbc_alloc_cfb(struct intel_crtc *crtc)
+static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
+			       unsigned int size, unsigned int fb_cpp)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct drm_mm_node *uninitialized_var(compressed_llb);
-	int size, fb_cpp, ret;
+	int ret;
 
 	WARN_ON(drm_mm_node_allocated(&fbc->compressed_fb));
 
-	size = intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache);
-	fb_cpp = fbc->state_cache.fb.format->cpp[0];
-
 	ret = find_compression_threshold(dev_priv, &fbc->compressed_fb,
 					 size, fb_cpp);
 	if (!ret)
@@ -656,46 +630,55 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 }
 
 static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
-					 struct intel_crtc_state *crtc_state,
-					 struct intel_plane_state *plane_state)
+					 const struct intel_crtc_state *crtc_state,
+					 const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_state_cache *cache = &fbc->state_cache;
-	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_framebuffer *fb = plane_state->hw.fb;
 
-	cache->vma = NULL;
-	cache->flags = 0;
+	cache->plane.visible = plane_state->uapi.visible;
+	if (!cache->plane.visible)
+		return;
 
-	cache->crtc.mode_flags = crtc_state->base.adjusted_mode.flags;
+	cache->crtc.mode_flags = crtc_state->hw.adjusted_mode.flags;
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		cache->crtc.hsw_bdw_pixel_rate = crtc_state->pixel_rate;
 
-	cache->plane.rotation = plane_state->base.rotation;
+	cache->plane.rotation = plane_state->hw.rotation;
 	/*
 	 * Src coordinates are already rotated by 270 degrees for
 	 * the 90/270 degree plane rotation cases (to match the
 	 * GTT mapping), hence no need to account for rotation here.
 	 */
-	cache->plane.src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	cache->plane.src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	cache->plane.visible = plane_state->base.visible;
+	cache->plane.src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	cache->plane.src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	cache->plane.adjusted_x = plane_state->color_plane[0].x;
 	cache->plane.adjusted_y = plane_state->color_plane[0].y;
-	cache->plane.y = plane_state->base.src.y1 >> 16;
+	cache->plane.y = plane_state->uapi.src.y1 >> 16;
 
-	cache->plane.pixel_blend_mode = plane_state->base.pixel_blend_mode;
-
-	if (!cache->plane.visible)
-		return;
+	cache->plane.pixel_blend_mode = plane_state->hw.pixel_blend_mode;
 
 	cache->fb.format = fb->format;
 	cache->fb.stride = fb->pitches[0];
 
-	cache->vma = plane_state->vma;
-	cache->flags = plane_state->flags;
-	if (WARN_ON(cache->flags & PLANE_HAS_FENCE && !cache->vma->fence))
-		cache->flags &= ~PLANE_HAS_FENCE;
+	WARN_ON(plane_state->flags & PLANE_HAS_FENCE &&
+		!plane_state->vma->fence);
+
+	if (plane_state->flags & PLANE_HAS_FENCE &&
+	    plane_state->vma->fence)
+		cache->fence_id = plane_state->vma->fence->id;
+	else
+		cache->fence_id = -1;
+}
+
+static bool intel_fbc_cfb_size_changed(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	return intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache) >
+		fbc->compressed_fb.size * fbc->threshold;
 }
 
 static bool intel_fbc_can_activate(struct intel_crtc *crtc)
@@ -704,6 +687,11 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_state_cache *cache = &fbc->state_cache;
 
+	if (!cache->plane.visible) {
+		fbc->no_fbc_reason = "primary plane not visible";
+		return false;
+	}
+
 	/* We don't need to use a state cache here since this information is
 	 * global for all CRTC.
 	 */
@@ -712,11 +700,6 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 		return false;
 	}
 
-	if (!cache->vma) {
-		fbc->no_fbc_reason = "primary plane not visible";
-		return false;
-	}
-
 	if (cache->crtc.mode_flags & DRM_MODE_FLAG_INTERLACE) {
 		fbc->no_fbc_reason = "incompatible mode";
 		return false;
@@ -740,7 +723,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	 * For now this will effecively disable FBC with 90/270 degree
 	 * rotation.
 	 */
-	if (!(cache->flags & PLANE_HAS_FENCE)) {
+	if (cache->fence_id < 0) {
 		fbc->no_fbc_reason = "framebuffer not tiled or fenced";
 		return false;
 	}
@@ -783,8 +766,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	 * we didn't get any invalidate/deactivate calls, but this would require
 	 * a lot of tracking just for a specific case. If we conclude it's an
 	 * important case, we can implement it later. */
-	if (intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache) >
-	    fbc->compressed_fb.size * fbc->threshold) {
+	if (intel_fbc_cfb_size_changed(dev_priv)) {
 		fbc->no_fbc_reason = "CFB requirements changed";
 		return false;
 	}
@@ -794,7 +776,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	 * having a Y offset that isn't divisible by 4 causes FIFO underrun
 	 * and screen flicker.
 	 */
-	if (IS_GEN_RANGE(dev_priv, 9, 10) &&
+	if (INTEL_GEN(dev_priv) >= 9 &&
 	    (fbc->state_cache.plane.adjusted_y & 3)) {
 		fbc->no_fbc_reason = "plane Y offset is misaligned";
 		return false;
@@ -837,8 +819,7 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 	 * zero. */
 	memset(params, 0, sizeof(*params));
 
-	params->vma = cache->vma;
-	params->flags = cache->flags;
+	params->fence_id = cache->fence_id;
 
 	params->crtc.pipe = crtc->pipe;
 	params->crtc.i9xx_plane = to_intel_plane(crtc->base.primary)->i9xx_plane;
@@ -849,39 +830,88 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 
 	params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache);
 
-	if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv))
-		params->gen9_wa_cfb_stride = DIV_ROUND_UP(cache->plane.src_w,
-						32 * fbc->threshold) * 8;
+	params->gen9_wa_cfb_stride = cache->gen9_wa_cfb_stride;
+
+	params->plane_visible = cache->plane.visible;
+}
+
+static bool intel_fbc_can_flip_nuke(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_fbc *fbc = &dev_priv->fbc;
+	const struct intel_fbc_state_cache *cache = &fbc->state_cache;
+	const struct intel_fbc_reg_params *params = &fbc->params;
+
+	if (drm_atomic_crtc_needs_modeset(&crtc_state->uapi))
+		return false;
+
+	if (!params->plane_visible)
+		return false;
+
+	if (!intel_fbc_can_activate(crtc))
+		return false;
+
+	if (params->fb.format != cache->fb.format)
+		return false;
+
+	if (params->fb.stride != cache->fb.stride)
+		return false;
+
+	if (params->cfb_size != intel_fbc_calculate_cfb_size(dev_priv, cache))
+		return false;
+
+	if (params->gen9_wa_cfb_stride != cache->gen9_wa_cfb_stride)
+		return false;
+
+	return true;
 }
 
-void intel_fbc_pre_update(struct intel_crtc *crtc,
-			  struct intel_crtc_state *crtc_state,
-			  struct intel_plane_state *plane_state)
+bool intel_fbc_pre_update(struct intel_crtc *crtc,
+			  const struct intel_crtc_state *crtc_state,
+			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	const char *reason = "update pending";
+	bool need_vblank_wait = false;
 
 	if (!fbc_supported(dev_priv))
-		return;
+		return need_vblank_wait;
 
 	mutex_lock(&fbc->lock);
 
-	if (!multiple_pipes_ok(crtc, plane_state)) {
-		reason = "more than one pipe active";
-		goto deactivate;
-	}
-
-	if (!fbc->enabled || fbc->crtc != crtc)
+	if (fbc->crtc != crtc)
 		goto unlock;
 
 	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
 	fbc->flip_pending = true;
 
-deactivate:
-	intel_fbc_deactivate(dev_priv, reason);
+	if (!intel_fbc_can_flip_nuke(crtc_state)) {
+		intel_fbc_deactivate(dev_priv, reason);
+
+		/*
+		 * Display WA #1198: glk+
+		 * Need an extra vblank wait between FBC disable and most plane
+		 * updates. Bspec says this is only needed for plane disable, but
+		 * that is not true. Touching most plane registers will cause the
+		 * corruption to appear. Also SKL/derivatives do not seem to be
+		 * affected.
+		 *
+		 * TODO: could optimize this a bit by sampling the frame
+		 * counter when we disable FBC (if it was already done earlier)
+		 * and skipping the extra vblank wait before the plane update
+		 * if at least one frame has already passed.
+		 */
+		if (fbc->activated &&
+		    (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)))
+			need_vblank_wait = true;
+		fbc->activated = false;
+	}
 unlock:
 	mutex_unlock(&fbc->lock);
+
+	return need_vblank_wait;
 }
 
 /**
@@ -897,14 +927,13 @@ static void __intel_fbc_disable(struct drm_i915_private *dev_priv)
 	struct intel_crtc *crtc = fbc->crtc;
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
-	WARN_ON(!fbc->enabled);
+	WARN_ON(!fbc->crtc);
 	WARN_ON(fbc->active);
 
 	DRM_DEBUG_KMS("Disabling FBC on pipe %c\n", pipe_name(crtc->pipe));
 
 	__intel_fbc_cleanup_cfb(dev_priv);
 
-	fbc->enabled = false;
 	fbc->crtc = NULL;
 }
 
@@ -915,11 +944,10 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-	if (!fbc->enabled || fbc->crtc != crtc)
+	if (fbc->crtc != crtc)
 		return;
 
 	fbc->flip_pending = false;
-	WARN_ON(fbc->active);
 
 	if (!i915_modparams.enable_fbc) {
 		intel_fbc_deactivate(dev_priv, "disabled at runtime per module param");
@@ -933,10 +961,9 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 	if (!intel_fbc_can_activate(crtc))
 		return;
 
-	if (!fbc->busy_bits) {
-		intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
+	if (!fbc->busy_bits)
 		intel_fbc_hw_activate(dev_priv);
-	} else
+	else
 		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 }
 
@@ -955,7 +982,7 @@ void intel_fbc_post_update(struct intel_crtc *crtc)
 
 static unsigned int intel_fbc_get_frontbuffer_bit(struct intel_fbc *fbc)
 {
-	if (fbc->enabled)
+	if (fbc->crtc)
 		return to_intel_plane(fbc->crtc->base.primary)->frontbuffer_bit;
 	else
 		return fbc->possible_framebuffer_bits;
@@ -977,7 +1004,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
 
 	fbc->busy_bits |= intel_fbc_get_frontbuffer_bit(fbc) & frontbuffer_bits;
 
-	if (fbc->enabled && fbc->busy_bits)
+	if (fbc->crtc && fbc->busy_bits)
 		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 
 	mutex_unlock(&fbc->lock);
@@ -998,7 +1025,7 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv,
 	if (origin == ORIGIN_GTT || origin == ORIGIN_FLIP)
 		goto out;
 
-	if (!fbc->busy_bits && fbc->enabled &&
+	if (!fbc->busy_bits && fbc->crtc &&
 	    (frontbuffer_bits & intel_fbc_get_frontbuffer_bit(fbc))) {
 		if (fbc->active)
 			intel_fbc_recompress(dev_priv);
@@ -1047,12 +1074,12 @@ void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv,
 	 * to pipe or plane A. */
 	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
 		struct intel_crtc_state *crtc_state;
-		struct intel_crtc *crtc = to_intel_crtc(plane_state->base.crtc);
+		struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc);
 
 		if (!plane->has_fbc)
 			continue;
 
-		if (!plane_state->base.visible)
+		if (!plane_state->uapi.visible)
 			continue;
 
 		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
@@ -1081,42 +1108,53 @@ out:
  * intel_fbc_disable in the middle, as long as it is deactivated.
  */
 void intel_fbc_enable(struct intel_crtc *crtc,
-		      struct intel_crtc_state *crtc_state,
-		      struct intel_plane_state *plane_state)
+		      const struct intel_crtc_state *crtc_state,
+		      const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_state_cache *cache = &fbc->state_cache;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 
 	if (!fbc_supported(dev_priv))
 		return;
 
 	mutex_lock(&fbc->lock);
 
-	if (fbc->enabled) {
-		WARN_ON(fbc->crtc == NULL);
-		if (fbc->crtc == crtc) {
-			WARN_ON(!crtc_state->enable_fbc);
-			WARN_ON(fbc->active);
-		}
-		goto out;
-	}
+	if (fbc->crtc) {
+		if (fbc->crtc != crtc ||
+		    !intel_fbc_cfb_size_changed(dev_priv))
+			goto out;
 
-	if (!crtc_state->enable_fbc)
-		goto out;
+		__intel_fbc_disable(dev_priv);
+	}
 
 	WARN_ON(fbc->active);
-	WARN_ON(fbc->crtc != NULL);
 
 	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
-	if (intel_fbc_alloc_cfb(crtc)) {
+
+	/* FIXME crtc_state->enable_fbc lies :( */
+	if (!cache->plane.visible)
+		goto out;
+
+	if (intel_fbc_alloc_cfb(dev_priv,
+				intel_fbc_calculate_cfb_size(dev_priv, cache),
+				fb->format->cpp[0])) {
+		cache->plane.visible = false;
 		fbc->no_fbc_reason = "not enough stolen memory";
 		goto out;
 	}
 
+	if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
+	    fb->modifier != I915_FORMAT_MOD_X_TILED)
+		cache->gen9_wa_cfb_stride =
+			DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
+	else
+		cache->gen9_wa_cfb_stride = 0;
+
 	DRM_DEBUG_KMS("Enabling FBC on pipe %c\n", pipe_name(crtc->pipe));
 	fbc->no_fbc_reason = "FBC enabled but not active yet\n";
 
-	fbc->enabled = true;
 	fbc->crtc = crtc;
 out:
 	mutex_unlock(&fbc->lock);
@@ -1156,7 +1194,7 @@ void intel_fbc_global_disable(struct drm_i915_private *dev_priv)
 		return;
 
 	mutex_lock(&fbc->lock);
-	if (fbc->enabled) {
+	if (fbc->crtc) {
 		WARN_ON(fbc->crtc->active);
 		__intel_fbc_disable(dev_priv);
 	}
@@ -1172,7 +1210,7 @@ static void intel_fbc_underrun_work_fn(struct work_struct *work)
 	mutex_lock(&fbc->lock);
 
 	/* Maybe we were scheduled twice. */
-	if (fbc->underrun_detected || !fbc->enabled)
+	if (fbc->underrun_detected || !fbc->crtc)
 		goto out;
 
 	DRM_DEBUG_KMS("Disabling FBC due to FIFO underrun.\n");
@@ -1244,28 +1282,6 @@ void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *dev_priv)
 	schedule_work(&fbc->underrun_work);
 }
 
-/**
- * intel_fbc_init_pipe_state - initialize FBC's CRTC visibility tracking
- * @dev_priv: i915 device instance
- *
- * The FBC code needs to track CRTC visibility since the older platforms can't
- * have FBC enabled while multiple pipes are used. This function does the
- * initial setup at driver load to make sure FBC is matching the real hardware.
- */
-void intel_fbc_init_pipe_state(struct drm_i915_private *dev_priv)
-{
-	struct intel_crtc *crtc;
-
-	/* Don't even bother tracking anything if we don't need. */
-	if (!no_fbc_on_multiple_pipes(dev_priv))
-		return;
-
-	for_each_intel_crtc(&dev_priv->drm, crtc)
-		if (intel_crtc_active(crtc) &&
-		    crtc->base.primary->state->visible)
-			dev_priv->fbc.visible_pipes_mask |= (1 << crtc->pipe);
-}
-
 /*
  * The DDX driver changes its behavior depending on the value it reads from
  * i915.enable_fbc, so sanitize it by translating the default value into either
@@ -1283,10 +1299,6 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
 	if (!HAS_FBC(dev_priv))
 		return 0;
 
-	/* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */
-	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
-		return 0;
-
 	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
 		return 1;
 
@@ -1317,7 +1329,6 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 
 	INIT_WORK(&fbc->underrun_work, intel_fbc_underrun_work_fn);
 	mutex_init(&fbc->lock);
-	fbc->enabled = false;
 	fbc->active = false;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.h b/drivers/gpu/drm/i915/display/intel_fbc.h
index 50272eda8d43..c8a5e5098687 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.h
+++ b/drivers/gpu/drm/i915/display/intel_fbc.h
@@ -19,15 +19,14 @@ struct intel_plane_state;
 void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv,
 			   struct intel_atomic_state *state);
 bool intel_fbc_is_active(struct drm_i915_private *dev_priv);
-void intel_fbc_pre_update(struct intel_crtc *crtc,
-			  struct intel_crtc_state *crtc_state,
-			  struct intel_plane_state *plane_state);
+bool intel_fbc_pre_update(struct intel_crtc *crtc,
+			  const struct intel_crtc_state *crtc_state,
+			  const struct intel_plane_state *plane_state);
 void intel_fbc_post_update(struct intel_crtc *crtc);
 void intel_fbc_init(struct drm_i915_private *dev_priv);
-void intel_fbc_init_pipe_state(struct drm_i915_private *dev_priv);
 void intel_fbc_enable(struct intel_crtc *crtc,
-		      struct intel_crtc_state *crtc_state,
-		      struct intel_plane_state *plane_state);
+		      const struct intel_crtc_state *crtc_state,
+		      const struct intel_plane_state *plane_state);
 void intel_fbc_disable(struct intel_crtc *crtc);
 void intel_fbc_global_disable(struct drm_i915_private *dev_priv);
 void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 48c960ca12fb..1e98e432c9fa 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -100,7 +100,7 @@ static int intel_fbdev_pan_display(struct fb_var_screeninfo *var,
 	return ret;
 }
 
-static struct fb_ops intelfb_ops = {
+static const struct fb_ops intelfb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_set_par = intel_fbdev_set_par,
diff --git a/drivers/gpu/drm/i915/display/intel_fifo_underrun.c b/drivers/gpu/drm/i915/display/intel_fifo_underrun.c
index ab61f88d1d33..6c83b350525d 100644
--- a/drivers/gpu/drm/i915/display/intel_fifo_underrun.c
+++ b/drivers/gpu/drm/i915/display/intel_fifo_underrun.c
@@ -126,8 +126,8 @@ static void i9xx_set_fifo_underrun_reporting(struct drm_device *dev,
 	}
 }
 
-static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev,
-						 enum pipe pipe, bool enable)
+static void ilk_set_fifo_underrun_reporting(struct drm_device *dev,
+					    enum pipe pipe, bool enable)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 bit = (pipe == PIPE_A) ?
@@ -139,7 +139,7 @@ static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev,
 		ilk_disable_display_irq(dev_priv, bit);
 }
 
-static void ivybridge_check_fifo_underruns(struct intel_crtc *crtc)
+static void ivb_check_fifo_underruns(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
@@ -157,9 +157,9 @@ static void ivybridge_check_fifo_underruns(struct intel_crtc *crtc)
 	DRM_ERROR("fifo underrun on pipe %c\n", pipe_name(pipe));
 }
 
-static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
-						  enum pipe pipe,
-						  bool enable, bool old)
+static void ivb_set_fifo_underrun_reporting(struct drm_device *dev,
+					    enum pipe pipe, bool enable,
+					    bool old)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	if (enable) {
@@ -180,8 +180,8 @@ static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
 	}
 }
 
-static void broadwell_set_fifo_underrun_reporting(struct drm_device *dev,
-						  enum pipe pipe, bool enable)
+static void bdw_set_fifo_underrun_reporting(struct drm_device *dev,
+					    enum pipe pipe, bool enable)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
@@ -264,11 +264,11 @@ static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
 	if (HAS_GMCH(dev_priv))
 		i9xx_set_fifo_underrun_reporting(dev, pipe, enable, old);
 	else if (IS_GEN_RANGE(dev_priv, 5, 6))
-		ironlake_set_fifo_underrun_reporting(dev, pipe, enable);
+		ilk_set_fifo_underrun_reporting(dev, pipe, enable);
 	else if (IS_GEN(dev_priv, 7))
-		ivybridge_set_fifo_underrun_reporting(dev, pipe, enable, old);
+		ivb_set_fifo_underrun_reporting(dev, pipe, enable, old);
 	else if (INTEL_GEN(dev_priv) >= 8)
-		broadwell_set_fifo_underrun_reporting(dev, pipe, enable);
+		bdw_set_fifo_underrun_reporting(dev, pipe, enable);
 
 	return old;
 }
@@ -427,7 +427,7 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv)
 		if (HAS_GMCH(dev_priv))
 			i9xx_check_fifo_underruns(crtc);
 		else if (IS_GEN(dev_priv, 7))
-			ivybridge_check_fifo_underruns(crtc);
+			ivb_check_fifo_underruns(crtc);
 	}
 
 	spin_unlock_irq(&dev_priv->irq_lock);
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index a448815d8fc2..0fdbd39f6641 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -1870,7 +1870,7 @@ static bool is_hdcp2_supported(struct drm_i915_private *dev_priv)
 		return false;
 
 	return (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv) ||
-		IS_KABYLAKE(dev_priv));
+		IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv));
 }
 
 void intel_hdcp_component_init(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index f56fffc474fa..93ac0f296852 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -85,16 +85,17 @@ assert_hdmi_transcoder_func_disabled(struct drm_i915_private *dev_priv,
 	     "HDMI transcoder function enabled, expecting disabled\n");
 }
 
-struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder)
+struct intel_hdmi *enc_to_intel_hdmi(struct intel_encoder *encoder)
 {
 	struct intel_digital_port *intel_dig_port =
-		container_of(encoder, struct intel_digital_port, base.base);
+		container_of(&encoder->base, struct intel_digital_port,
+			     base.base);
 	return &intel_dig_port->hdmi;
 }
 
-static struct intel_hdmi *intel_attached_hdmi(struct drm_connector *connector)
+static struct intel_hdmi *intel_attached_hdmi(struct intel_connector *connector)
 {
-	return enc_to_intel_hdmi(&intel_attached_encoder(connector)->base);
+	return enc_to_intel_hdmi(intel_attached_encoder(connector));
 }
 
 static u32 g4x_infoframe_index(unsigned int type)
@@ -285,7 +286,7 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 	int i;
@@ -321,7 +322,7 @@ static void ibx_read_infoframe(struct intel_encoder *encoder,
 			       void *frame, ssize_t len)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	u32 val, *data = frame;
 	int i;
 
@@ -340,7 +341,7 @@ static u32 ibx_infoframes_enabled(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(pipe_config->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(pipe_config->uapi.crtc)->pipe;
 	i915_reg_t reg = TVIDEO_DIP_CTL(pipe);
 	u32 val = I915_READ(reg);
 
@@ -362,7 +363,7 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 	int i;
@@ -401,7 +402,7 @@ static void cpt_read_infoframe(struct intel_encoder *encoder,
 			       void *frame, ssize_t len)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	u32 val, *data = frame;
 	int i;
 
@@ -420,7 +421,7 @@ static u32 cpt_infoframes_enabled(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(pipe_config->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(pipe_config->uapi.crtc)->pipe;
 	u32 val = I915_READ(TVIDEO_DIP_CTL(pipe));
 
 	if ((val & VIDEO_DIP_ENABLE) == 0)
@@ -438,7 +439,7 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 	int i;
@@ -474,7 +475,7 @@ static void vlv_read_infoframe(struct intel_encoder *encoder,
 			       void *frame, ssize_t len)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	u32 val, *data = frame;
 	int i;
 
@@ -493,7 +494,7 @@ static u32 vlv_infoframes_enabled(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(pipe_config->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(pipe_config->uapi.crtc)->pipe;
 	u32 val = I915_READ(VLV_TVIDEO_DIP_CTL(pipe));
 
 	if ((val & VIDEO_DIP_ENABLE) == 0)
@@ -602,7 +603,7 @@ u32 intel_hdmi_infoframes_enabled(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	u32 val, ret = 0;
 	int i;
 
@@ -646,7 +647,7 @@ static void intel_write_infoframe(struct intel_encoder *encoder,
 				  enum hdmi_infoframe_type type,
 				  const union hdmi_infoframe *frame)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	u8 buffer[VIDEO_DIP_DATA_SIZE];
 	ssize_t len;
 
@@ -675,7 +676,7 @@ void intel_read_infoframe(struct intel_encoder *encoder,
 			  enum hdmi_infoframe_type type,
 			  union hdmi_infoframe *frame)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	u8 buffer[VIDEO_DIP_DATA_SIZE];
 	int ret;
 
@@ -708,7 +709,7 @@ intel_hdmi_compute_avi_infoframe(struct intel_encoder *encoder,
 {
 	struct hdmi_avi_infoframe *frame = &crtc_state->infoframes.avi.avi;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	struct drm_connector *connector = conn_state->connector;
 	int ret;
 
@@ -804,7 +805,7 @@ intel_hdmi_compute_hdmi_infoframe(struct intel_encoder *encoder,
 
 	ret = drm_hdmi_vendor_infoframe_from_display_mode(frame,
 							  conn_state->connector,
-							  &crtc_state->base.adjusted_mode);
+							  &crtc_state->hw.adjusted_mode);
 	if (WARN_ON(ret))
 		return false;
 
@@ -855,7 +856,7 @@ static void g4x_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	i915_reg_t reg = VIDEO_DIP_CTL;
 	u32 val = I915_READ(reg);
@@ -965,7 +966,7 @@ static bool intel_hdmi_set_gcp_infoframe(struct intel_encoder *encoder,
 					 const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg;
 
 	if ((crtc_state->infoframes.enable &
@@ -990,7 +991,7 @@ void intel_hdmi_read_gcp_infoframe(struct intel_encoder *encoder,
 				   struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg;
 
 	if ((crtc_state->infoframes.enable &
@@ -1027,7 +1028,7 @@ static void intel_hdmi_compute_gcp_infoframe(struct intel_encoder *encoder,
 
 	/* Enable default_phase whenever the display mode is suitably aligned */
 	if (gcp_default_phase_possible(crtc_state->pipe_bpp,
-				       &crtc_state->base.adjusted_mode))
+				       &crtc_state->hw.adjusted_mode))
 		crtc_state->infoframes.gcp |= GCP_DEFAULT_PHASE_ENABLE;
 }
 
@@ -1037,8 +1038,8 @@ static void ibx_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
@@ -1096,8 +1097,8 @@ static void cpt_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 
@@ -1145,8 +1146,8 @@ static void vlv_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 	u32 port = VIDEO_DIP_PORT(encoder->port);
@@ -1736,9 +1737,9 @@ static void intel_hdmi_prepare(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
-	const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	u32 hdmi_val;
 
 	intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
@@ -1774,7 +1775,7 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	intel_wakeref_t wakeref;
 	bool ret;
 
@@ -1793,7 +1794,7 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 static void intel_hdmi_get_config(struct intel_encoder *encoder,
 				  struct intel_crtc_state *pipe_config)
 {
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tmp, flags = 0;
@@ -1829,7 +1830,7 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder,
 	    tmp & HDMI_COLOR_RANGE_16_235)
 		pipe_config->limited_color_range = true;
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	if ((tmp & SDVO_COLOR_FORMAT_MASK) == HDMI_COLOR_FORMAT_12bpc)
 		dotclock = pipe_config->port_clock * 2 / 3;
@@ -1839,7 +1840,7 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder,
 	if (pipe_config->pixel_multiplier)
 		dotclock /= pipe_config->pixel_multiplier;
 
-	pipe_config->base.adjusted_mode.crtc_clock = dotclock;
+	pipe_config->hw.adjusted_mode.crtc_clock = dotclock;
 
 	pipe_config->lane_count = 4;
 
@@ -1860,7 +1861,7 @@ static void intel_enable_hdmi_audio(struct intel_encoder *encoder,
 				    const struct intel_crtc_state *pipe_config,
 				    const struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 
 	WARN_ON(!pipe_config->has_hdmi_sink);
 	DRM_DEBUG_DRIVER("Enabling HDMI audio on pipe %c\n",
@@ -1874,7 +1875,7 @@ static void g4x_enable_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	u32 temp;
 
 	temp = I915_READ(intel_hdmi->hdmi_reg);
@@ -1896,7 +1897,7 @@ static void ibx_enable_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	u32 temp;
 
 	temp = I915_READ(intel_hdmi->hdmi_reg);
@@ -1946,8 +1947,8 @@ static void cpt_enable_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	enum pipe pipe = crtc->pipe;
 	u32 temp;
 
@@ -2007,10 +2008,10 @@ static void intel_disable_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct intel_digital_port *intel_dig_port =
 		hdmi_to_dig_port(intel_hdmi);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	u32 temp;
 
 	temp = I915_READ(intel_hdmi->hdmi_reg);
@@ -2160,7 +2161,7 @@ static enum drm_mode_status
 intel_hdmi_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
-	struct intel_hdmi *hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector));
 	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum drm_mode_status status;
@@ -2210,12 +2211,12 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
 				     int bpc)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->base.crtc->dev);
-	struct drm_atomic_state *state = crtc_state->base.state;
+		to_i915(crtc_state->uapi.crtc->dev);
+	struct drm_atomic_state *state = crtc_state->uapi.state;
 	struct drm_connector_state *connector_state;
 	struct drm_connector *connector;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int i;
 
 	if (HAS_GMCH(dev_priv))
@@ -2240,7 +2241,7 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
 	for_each_new_connector_in_state(state, connector, connector_state, i) {
 		const struct drm_display_info *info = &connector->display_info;
 
-		if (connector_state->crtc != crtc_state->base.crtc)
+		if (connector_state->crtc != crtc_state->uapi.crtc)
 			continue;
 
 		if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420) {
@@ -2281,7 +2282,7 @@ static bool
 intel_hdmi_ycbcr420_config(struct drm_connector *connector,
 			   struct intel_crtc_state *config)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(config->uapi.crtc);
 
 	if (!connector->ycbcr_420_allowed) {
 		DRM_ERROR("Platform doesn't support YCBCR420 output\n");
@@ -2316,7 +2317,7 @@ static int intel_hdmi_compute_bpc(struct intel_encoder *encoder,
 				  struct intel_crtc_state *crtc_state,
 				  int clock, bool force_dvi)
 {
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	int bpc;
 
 	for (bpc = 12; bpc >= 10; bpc -= 2) {
@@ -2334,9 +2335,9 @@ static int intel_hdmi_compute_clock(struct intel_encoder *encoder,
 				    struct intel_crtc_state *crtc_state,
 				    bool force_dvi)
 {
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int bpc, clock = adjusted_mode->crtc_clock;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
@@ -2378,7 +2379,7 @@ static bool intel_hdmi_limited_color_range(const struct intel_crtc_state *crtc_s
 	const struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	/*
 	 * Our YCbCr output is always limited range.
@@ -2404,9 +2405,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config,
 			      struct drm_connector_state *conn_state)
 {
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	struct drm_connector *connector = conn_state->connector;
 	struct drm_scdc *scdc = &connector->display_info.hdmi.scdc;
 	struct intel_digital_connector_state *intel_conn_state =
@@ -2451,8 +2452,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (ret)
 		return ret;
 
-	/* Set user selected PAR to incoming mode's member */
-	adjusted_mode->picture_aspect_ratio = conn_state->picture_aspect_ratio;
+	if (conn_state->picture_aspect_ratio)
+		adjusted_mode->picture_aspect_ratio =
+			conn_state->picture_aspect_ratio;
 
 	pipe_config->lane_count = 4;
 
@@ -2495,7 +2497,7 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 static void
 intel_hdmi_unset_edid(struct drm_connector *connector)
 {
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(to_intel_connector(connector));
 
 	intel_hdmi->has_hdmi_sink = false;
 	intel_hdmi->has_audio = false;
@@ -2511,7 +2513,7 @@ static void
 intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_hdmi *hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector));
 	enum port port = hdmi_to_dig_port(hdmi)->base.port;
 	struct i2c_adapter *adapter =
 		intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
@@ -2558,7 +2560,7 @@ static bool
 intel_hdmi_set_edid(struct drm_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(to_intel_connector(connector));
 	intel_wakeref_t wakeref;
 	struct edid *edid;
 	bool connected = false;
@@ -2599,7 +2601,7 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 {
 	enum drm_connector_status status = connector_status_disconnected;
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(to_intel_connector(connector));
 	struct intel_encoder *encoder = &hdmi_to_dig_port(intel_hdmi)->base;
 	intel_wakeref_t wakeref;
 
@@ -2662,7 +2664,7 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder,
 				  const struct drm_connector_state *conn_state)
 {
 	struct intel_digital_port *intel_dig_port =
-		enc_to_dig_port(&encoder->base);
+		enc_to_dig_port(encoder);
 
 	intel_hdmi_prepare(encoder, pipe_config);
 
@@ -2675,7 +2677,7 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
 	vlv_phy_pre_encoder_enable(encoder, pipe_config);
@@ -2745,7 +2747,7 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
@@ -2771,7 +2773,7 @@ static struct i2c_adapter *
 intel_hdmi_get_i2c_adapter(struct drm_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(to_intel_connector(connector));
 
 	return intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus);
 }
@@ -2815,7 +2817,7 @@ intel_hdmi_connector_register(struct drm_connector *connector)
 
 static void intel_hdmi_destroy(struct drm_connector *connector)
 {
-	struct cec_notifier *n = intel_attached_hdmi(connector)->cec_notifier;
+	struct cec_notifier *n = intel_attached_hdmi(to_intel_connector(connector))->cec_notifier;
 
 	cec_notifier_conn_unregister(n);
 
@@ -2872,7 +2874,6 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
 		intel_attach_colorspace_property(connector);
 
 	drm_connector_attach_content_type_property(connector);
-	connector->state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		drm_object_attach_property(&connector->base,
@@ -2906,7 +2907,7 @@ bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder,
 				       bool scrambling)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct drm_scrambling *sink_scrambling =
 		&connector->display_info.hdmi.scdc.scrambling;
 	struct i2c_adapter *adapter =
@@ -3131,20 +3132,29 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i2c_adapter *ddc;
 	enum port port = intel_encoder->port;
 	struct cec_connector_info conn_info;
 
 	DRM_DEBUG_KMS("Adding HDMI connector on [ENCODER:%d:%s]\n",
 		      intel_encoder->base.base.id, intel_encoder->base.name);
 
+	if (INTEL_GEN(dev_priv) < 12 && WARN_ON(port == PORT_A))
+		return;
+
 	if (WARN(intel_dig_port->max_lanes < 4,
 		 "Not enough lanes (%d) for HDMI on [ENCODER:%d:%s]\n",
 		 intel_dig_port->max_lanes, intel_encoder->base.base.id,
 		 intel_encoder->base.name))
 		return;
 
-	drm_connector_init(dev, connector, &intel_hdmi_connector_funcs,
-			   DRM_MODE_CONNECTOR_HDMIA);
+	intel_hdmi->ddc_bus = intel_hdmi_ddc_pin(dev_priv, port);
+	ddc = intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus);
+
+	drm_connector_init_with_ddc(dev, connector,
+				    &intel_hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    ddc);
 	drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs);
 
 	connector->interlace_allowed = 1;
@@ -3154,10 +3164,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		connector->ycbcr_420_allowed = true;
 
-	intel_hdmi->ddc_bus = intel_hdmi_ddc_pin(dev_priv, port);
-
-	if (WARN_ON(port == PORT_A))
-		return;
 	intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port);
 
 	if (HAS_DDI(dev_priv))
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h
index cf1ea5427639..d3659d0b408b 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.h
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.h
@@ -29,7 +29,7 @@ void intel_hdmi_init(struct drm_i915_private *dev_priv, i915_reg_t hdmi_reg,
 		     enum port port);
 void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 			       struct intel_connector *intel_connector);
-struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder);
+struct intel_hdmi *enc_to_intel_hdmi(struct intel_encoder *encoder);
 int intel_hdmi_compute_config(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config,
 			      struct drm_connector_state *conn_state);
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index fc29046d48ea..99d3a3c7989e 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -302,7 +302,7 @@ intel_encoder_hotplug(struct intel_encoder *encoder,
 static bool intel_encoder_has_hpd_pulse(struct intel_encoder *encoder)
 {
 	return intel_encoder_is_dig_port(encoder) &&
-		enc_to_dig_port(&encoder->base)->hpd_pulse != NULL;
+		enc_to_dig_port(encoder)->hpd_pulse != NULL;
 }
 
 static void i915_digport_work_func(struct work_struct *work)
@@ -335,7 +335,7 @@ static void i915_digport_work_func(struct work_struct *work)
 		if (!long_hpd && !short_hpd)
 			continue;
 
-		dig_port = enc_to_dig_port(&encoder->base);
+		dig_port = enc_to_dig_port(encoder);
 
 		ret = dig_port->hpd_pulse(dig_port, long_hpd);
 		if (ret == IRQ_NONE) {
diff --git a/drivers/gpu/drm/i915/display/intel_lspcon.c b/drivers/gpu/drm/i915/display/intel_lspcon.c
index f8f1308643a9..d807c5648c87 100644
--- a/drivers/gpu/drm/i915/display/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/display/intel_lspcon.c
@@ -189,7 +189,7 @@ void lspcon_ycbcr420_config(struct drm_connector *connector,
 {
 	const struct drm_display_info *info = &connector->display_info;
 	const struct drm_display_mode *adjusted_mode =
-					&crtc_state->base.adjusted_mode;
+					&crtc_state->hw.adjusted_mode;
 
 	if (drm_mode_is_420_only(info, adjusted_mode) &&
 	    connector->ycbcr_420_allowed) {
@@ -434,8 +434,8 @@ void lspcon_write_infoframe(struct intel_encoder *encoder,
 			    const void *frame, ssize_t len)
 {
 	bool ret;
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_lspcon *lspcon = enc_to_intel_lspcon(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_lspcon *lspcon = enc_to_intel_lspcon(encoder);
 
 	/* LSPCON only needs AVI IF */
 	if (type != HDMI_INFOFRAME_TYPE_AVI)
@@ -472,10 +472,10 @@ void lspcon_set_infoframes(struct intel_encoder *encoder,
 	ssize_t ret;
 	union hdmi_infoframe frame;
 	u8 buf[VIDEO_DIP_DATA_SIZE];
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct intel_lspcon *lspcon = &dig_port->lspcon;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	if (!lspcon->active) {
 		DRM_ERROR("Writing infoframes while LSPCON disabled ?\n");
@@ -522,7 +522,7 @@ u32 lspcon_infoframes_enabled(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config)
 {
 	/* FIXME actually read this from the hw */
-	return enc_to_intel_lspcon(&encoder->base)->active;
+	return enc_to_intel_lspcon(encoder)->active;
 }
 
 void lspcon_resume(struct intel_lspcon *lspcon)
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index b1bc78623647..10696bb99dcf 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -135,7 +135,7 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 	else
 		flags |= DRM_MODE_FLAG_PVSYNC;
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	if (INTEL_GEN(dev_priv) < 5)
 		pipe_config->gmch_pfit.lvds_border_bits =
@@ -148,7 +148,7 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 		pipe_config->gmch_pfit.control |= tmp & PANEL_8TO6_DITHER_ENABLE;
 	}
 
-	pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock;
+	pipe_config->hw.adjusted_mode.crtc_clock = pipe_config->port_clock;
 }
 
 static void intel_lvds_pps_get_hw_state(struct drm_i915_private *dev_priv,
@@ -230,8 +230,8 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder,
 {
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	enum pipe pipe = crtc->pipe;
 	u32 temp;
 
@@ -392,8 +392,8 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 		to_lvds_encoder(&intel_encoder->base);
 	struct intel_connector *intel_connector =
 		lvds_encoder->attached_connector;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	unsigned int lvds_bpp;
 
 	/* Should never happen!! */
diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c
index 969ade623691..e59b4992ba1b 100644
--- a/drivers/gpu/drm/i915/display/intel_opregion.c
+++ b/drivers/gpu/drm/i915/display/intel_opregion.c
@@ -941,6 +941,13 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv)
 	if (mboxes & MBOX_ACPI) {
 		DRM_DEBUG_DRIVER("Public ACPI methods supported\n");
 		opregion->acpi = base + OPREGION_ACPI_OFFSET;
+		/*
+		 * Indicate we handle monitor hotplug events ourselves so we do
+		 * not need ACPI notifications for them. Disabling these avoids
+		 * triggering the AML code doing the notifation, which may be
+		 * broken as Windows also seems to disable these.
+		 */
+		opregion->acpi->chpd = 1;
 	}
 
 	if (mboxes & MBOX_SWSCI) {
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 8a98a1aa7adc..e40c3a0e2cd7 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -677,8 +677,8 @@ static void update_colorkey(struct intel_overlay *overlay,
 	if (overlay->color_key_enabled)
 		flags |= DST_KEY_ENABLE;
 
-	if (state->base.visible)
-		format = state->base.fb->format->format;
+	if (state->uapi.visible)
+		format = state->hw.fb->format->format;
 
 	switch (format) {
 	case DRM_FORMAT_C8:
@@ -767,10 +767,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 
 	atomic_inc(&dev_priv->gpu_error.pending_fb_pin);
 
-	i915_gem_object_lock(new_bo);
 	vma = i915_gem_object_pin_to_display_plane(new_bo,
 						   0, NULL, PIN_MAPPABLE);
-	i915_gem_object_unlock(new_bo);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out_pin_section;
@@ -1335,12 +1333,14 @@ err_put_bo:
 void intel_overlay_setup(struct drm_i915_private *dev_priv)
 {
 	struct intel_overlay *overlay;
+	struct intel_engine_cs *engine;
 	int ret;
 
 	if (!HAS_OVERLAY(dev_priv))
 		return;
 
-	if (!HAS_ENGINE(dev_priv, RCS0))
+	engine = dev_priv->engine[RCS0];
+	if (!engine || !engine->kernel_context)
 		return;
 
 	overlay = kzalloc(sizeof(*overlay), GFP_KERNEL);
@@ -1348,7 +1348,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv)
 		return;
 
 	overlay->i915 = dev_priv;
-	overlay->context = dev_priv->engine[RCS0]->kernel_context;
+	overlay->context = engine->kernel_context;
 	GEM_BUG_ON(!overlay->context);
 
 	overlay->color_key = 0x0101fe;
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index bc14e9c0285a..7b3ec6eb3382 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -178,7 +178,7 @@ intel_pch_panel_fitting(struct intel_crtc *intel_crtc,
 			struct intel_crtc_state *pipe_config,
 			int fitting_mode)
 {
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int x = 0, y = 0, width = 0, height = 0;
 
 	/* Native modes don't need fitting */
@@ -300,7 +300,7 @@ static inline u32 panel_fitter_scaling(u32 source, u32 target)
 static void i965_scale_aspect(struct intel_crtc_state *pipe_config,
 			      u32 *pfit_control)
 {
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	u32 scaled_width = adjusted_mode->crtc_hdisplay *
 		pipe_config->pipe_src_h;
 	u32 scaled_height = pipe_config->pipe_src_w *
@@ -321,7 +321,7 @@ static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config,
 			      u32 *pfit_control, u32 *pfit_pgm_ratios,
 			      u32 *border)
 {
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	u32 scaled_width = adjusted_mode->crtc_hdisplay *
 		pipe_config->pipe_src_h;
 	u32 scaled_height = pipe_config->pipe_src_w *
@@ -380,7 +380,7 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	u32 pfit_control = 0, pfit_pgm_ratios = 0, border = 0;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 
 	/* Native modes don't need fitting */
 	if (adjusted_mode->crtc_hdisplay == pipe_config->pipe_src_w &&
@@ -1047,7 +1047,7 @@ static void vlv_enable_backlight(const struct intel_crtc_state *crtc_state,
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 	u32 ctl, ctl2;
 
 	ctl2 = I915_READ(VLV_BLC_PWM_CTL2(pipe));
@@ -1077,7 +1077,7 @@ static void bxt_enable_backlight(const struct intel_crtc_state *crtc_state,
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 	u32 pwm_ctl, val;
 
 	/* Controller 1 uses the utility pin. */
@@ -1189,7 +1189,7 @@ void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 
 	if (!panel->backlight.present)
 		return;
@@ -1840,13 +1840,22 @@ static int pwm_setup_backlight(struct intel_connector *connector,
 			       enum pipe pipe)
 {
 	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_panel *panel = &connector->panel;
+	const char *desc;
 	int retval;
 
-	/* Get the PWM chip for backlight control */
-	panel->backlight.pwm = pwm_get(dev->dev, "pwm_backlight");
+	/* Get the right PWM chip for DSI backlight according to VBT */
+	if (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC) {
+		panel->backlight.pwm = pwm_get(dev->dev, "pwm_pmic_backlight");
+		desc = "PMIC";
+	} else {
+		panel->backlight.pwm = pwm_get(dev->dev, "pwm_soc_backlight");
+		desc = "SoC";
+	}
+
 	if (IS_ERR(panel->backlight.pwm)) {
-		DRM_ERROR("Failed to own the pwm chip\n");
+		DRM_ERROR("Failed to get the %s PWM chip\n", desc);
 		panel->backlight.pwm = NULL;
 		return -ENODEV;
 	}
@@ -1873,6 +1882,7 @@ static int pwm_setup_backlight(struct intel_connector *connector,
 				 CRC_PMIC_PWM_PERIOD_NS);
 	panel->backlight.enabled = panel->backlight.level != 0;
 
+	DRM_INFO("Using %s PWM for LCD backlight control\n", desc);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_pipe_crc.c b/drivers/gpu/drm/i915/display/intel_pipe_crc.c
index 6260a2082719..520408e83681 100644
--- a/drivers/gpu/drm/i915/display/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/display/intel_pipe_crc.c
@@ -98,7 +98,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv,
 			break;
 		case INTEL_OUTPUT_DP:
 		case INTEL_OUTPUT_EDP:
-			dig_port = enc_to_dig_port(&encoder->base);
+			dig_port = enc_to_dig_port(encoder);
 			switch (dig_port->base.port) {
 			case PORT_B:
 				*source = INTEL_PIPE_CRC_SOURCE_DP_B;
@@ -309,13 +309,13 @@ retry:
 		goto put_state;
 	}
 
-	pipe_config->base.mode_changed = pipe_config->has_psr;
+	pipe_config->uapi.mode_changed = pipe_config->has_psr;
 	pipe_config->crc_enabled = enable;
 
 	if (IS_HASWELL(dev_priv) &&
-	    pipe_config->base.active && crtc->pipe == PIPE_A &&
+	    pipe_config->hw.active && crtc->pipe == PIPE_A &&
 	    pipe_config->cpu_transcoder == TRANSCODER_EDP)
-		pipe_config->base.mode_changed = true;
+		pipe_config->uapi.mode_changed = true;
 
 	ret = drm_atomic_commit(state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 6a9f322d3fca..89c9cf5f38d2 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -26,6 +26,7 @@
 #include "display/intel_dp.h"
 
 #include "i915_drv.h"
+#include "intel_atomic.h"
 #include "intel_display_types.h"
 #include "intel_psr.h"
 #include "intel_sprite.h"
@@ -401,7 +402,9 @@ static void intel_psr_enable_sink(struct intel_dp *intel_dp)
 	/* Enable ALPM at sink for psr2 */
 	if (dev_priv->psr.psr2_enabled) {
 		drm_dp_dpcd_writeb(&intel_dp->aux, DP_RECEIVER_ALPM_CONFIG,
-				   DP_ALPM_ENABLE);
+				   DP_ALPM_ENABLE |
+				   DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE);
+
 		dpcd_val |= DP_PSR_ENABLE_PSR2 | DP_PSR_IRQ_HPD_WITH_CRC_ERRORS;
 	} else {
 		if (dev_priv->psr.link_standby)
@@ -536,11 +539,11 @@ transcoder_has_psr2(struct drm_i915_private *dev_priv, enum transcoder trans)
 
 static u32 intel_get_frame_time_us(const struct intel_crtc_state *cstate)
 {
-	if (!cstate || !cstate->base.active)
+	if (!cstate || !cstate->hw.active)
 		return 0;
 
 	return DIV_ROUND_UP(1000 * 1000,
-			    drm_mode_vrefresh(&cstate->base.adjusted_mode));
+			    drm_mode_vrefresh(&cstate->hw.adjusted_mode));
 }
 
 static void psr2_program_idle_frames(struct drm_i915_private *dev_priv,
@@ -605,9 +608,9 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	int crtc_hdisplay = crtc_state->base.adjusted_mode.crtc_hdisplay;
-	int crtc_vdisplay = crtc_state->base.adjusted_mode.crtc_vdisplay;
-	int psr_max_h = 0, psr_max_v = 0;
+	int crtc_hdisplay = crtc_state->hw.adjusted_mode.crtc_hdisplay;
+	int crtc_vdisplay = crtc_state->hw.adjusted_mode.crtc_vdisplay;
+	int psr_max_h = 0, psr_max_v = 0, max_bpp = 0;
 
 	if (!dev_priv->psr.sink_psr2_support)
 		return false;
@@ -631,12 +634,15 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 	if (INTEL_GEN(dev_priv) >= 12) {
 		psr_max_h = 5120;
 		psr_max_v = 3200;
+		max_bpp = 30;
 	} else if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
 		psr_max_h = 4096;
 		psr_max_v = 2304;
+		max_bpp = 24;
 	} else if (IS_GEN(dev_priv, 9)) {
 		psr_max_h = 3640;
 		psr_max_v = 2304;
+		max_bpp = 24;
 	}
 
 	if (crtc_hdisplay > psr_max_h || crtc_vdisplay > psr_max_v) {
@@ -646,6 +652,12 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 		return false;
 	}
 
+	if (crtc_state->pipe_bpp > max_bpp) {
+		DRM_DEBUG_KMS("PSR2 not enabled, pipe bpp %d > max supported %d\n",
+			      crtc_state->pipe_bpp, max_bpp);
+		return false;
+	}
+
 	/*
 	 * HW sends SU blocks of size four scan lines, which means the starting
 	 * X coordinate and Y granularity requirements will always be met. We
@@ -672,7 +684,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int psr_setup_time;
 
 	if (!CAN_PSR(dev_priv))
@@ -792,7 +804,7 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 
 	dev_priv->psr.psr2_enabled = intel_psr2_enabled(dev_priv, crtc_state);
 	dev_priv->psr.busy_frontbuffer_bits = 0;
-	dev_priv->psr.pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	dev_priv->psr.pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 	dev_priv->psr.dc3co_enabled = !!crtc_state->dc3co_exitline;
 	dev_priv->psr.dc3co_exit_delay = intel_get_frame_time_us(crtc_state);
 	dev_priv->psr.transcoder = crtc_state->cpu_transcoder;
@@ -924,6 +936,9 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 	/* Disable PSR on Sink */
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
 
+	if (dev_priv->psr.psr2_enabled)
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_RECEIVER_ALPM_CONFIG, 0);
+
 	dev_priv->psr.enabled = false;
 }
 
@@ -1039,7 +1054,7 @@ unlock:
 int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state,
 			    u32 *out_value)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!dev_priv->psr.enabled || !new_crtc_state->has_psr)
@@ -1096,7 +1111,7 @@ static int intel_psr_fastset_force(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = &dev_priv->drm;
 	struct drm_modeset_acquire_ctx ctx;
 	struct drm_atomic_state *state;
-	struct drm_crtc *crtc;
+	struct intel_crtc *crtc;
 	int err;
 
 	state = drm_atomic_state_alloc(dev);
@@ -1107,21 +1122,18 @@ static int intel_psr_fastset_force(struct drm_i915_private *dev_priv)
 	state->acquire_ctx = &ctx;
 
 retry:
-	drm_for_each_crtc(crtc, dev) {
-		struct drm_crtc_state *crtc_state;
-		struct intel_crtc_state *intel_crtc_state;
+	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			intel_atomic_get_crtc_state(state, crtc);
 
-		crtc_state = drm_atomic_get_crtc_state(state, crtc);
 		if (IS_ERR(crtc_state)) {
 			err = PTR_ERR(crtc_state);
 			goto error;
 		}
 
-		intel_crtc_state = to_intel_crtc_state(crtc_state);
-
-		if (crtc_state->active && intel_crtc_state->has_psr) {
+		if (crtc_state->hw.active && crtc_state->has_psr) {
 			/* Mark mode as changed to trigger a pipe->update() */
-			crtc_state->mode_changed = true;
+			crtc_state->uapi.mode_changed = true;
 			break;
 		}
 	}
@@ -1379,11 +1391,80 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	mutex_init(&dev_priv->psr.lock);
 }
 
-void intel_psr_short_pulse(struct intel_dp *intel_dp)
+static int psr_get_status_and_error_status(struct intel_dp *intel_dp,
+					   u8 *status, u8 *error_status)
+{
+	struct drm_dp_aux *aux = &intel_dp->aux;
+	int ret;
+
+	ret = drm_dp_dpcd_readb(aux, DP_PSR_STATUS, status);
+	if (ret != 1)
+		return ret;
+
+	ret = drm_dp_dpcd_readb(aux, DP_PSR_ERROR_STATUS, error_status);
+	if (ret != 1)
+		return ret;
+
+	*status = *status & DP_PSR_SINK_STATE_MASK;
+
+	return 0;
+}
+
+static void psr_alpm_check(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	struct drm_dp_aux *aux = &intel_dp->aux;
+	struct i915_psr *psr = &dev_priv->psr;
+	u8 val;
+	int r;
+
+	if (!psr->psr2_enabled)
+		return;
+
+	r = drm_dp_dpcd_readb(aux, DP_RECEIVER_ALPM_STATUS, &val);
+	if (r != 1) {
+		DRM_ERROR("Error reading ALPM status\n");
+		return;
+	}
+
+	if (val & DP_ALPM_LOCK_TIMEOUT_ERROR) {
+		intel_psr_disable_locked(intel_dp);
+		psr->sink_not_reliable = true;
+		DRM_DEBUG_KMS("ALPM lock timeout error, disabling PSR\n");
+
+		/* Clearing error */
+		drm_dp_dpcd_writeb(aux, DP_RECEIVER_ALPM_STATUS, val);
+	}
+}
+
+static void psr_capability_changed_check(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	struct i915_psr *psr = &dev_priv->psr;
 	u8 val;
+	int r;
+
+	r = drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_ESI, &val);
+	if (r != 1) {
+		DRM_ERROR("Error reading DP_PSR_ESI\n");
+		return;
+	}
+
+	if (val & DP_PSR_CAPS_CHANGE) {
+		intel_psr_disable_locked(intel_dp);
+		psr->sink_not_reliable = true;
+		DRM_DEBUG_KMS("Sink PSR capability changed, disabling PSR\n");
+
+		/* Clearing it */
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ESI, val);
+	}
+}
+
+void intel_psr_short_pulse(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	struct i915_psr *psr = &dev_priv->psr;
+	u8 status, error_status;
 	const u8 errors = DP_PSR_RFB_STORAGE_ERROR |
 			  DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR |
 			  DP_PSR_LINK_CRC_ERROR;
@@ -1396,38 +1477,34 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp)
 	if (!psr->enabled || psr->dp != intel_dp)
 		goto exit;
 
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) != 1) {
-		DRM_ERROR("PSR_STATUS dpcd read failed\n");
+	if (psr_get_status_and_error_status(intel_dp, &status, &error_status)) {
+		DRM_ERROR("Error reading PSR status or error status\n");
 		goto exit;
 	}
 
-	if ((val & DP_PSR_SINK_STATE_MASK) == DP_PSR_SINK_INTERNAL_ERROR) {
-		DRM_DEBUG_KMS("PSR sink internal error, disabling PSR\n");
+	if (status == DP_PSR_SINK_INTERNAL_ERROR || (error_status & errors)) {
 		intel_psr_disable_locked(intel_dp);
 		psr->sink_not_reliable = true;
 	}
 
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_ERROR_STATUS, &val) != 1) {
-		DRM_ERROR("PSR_ERROR_STATUS dpcd read failed\n");
-		goto exit;
-	}
-
-	if (val & DP_PSR_RFB_STORAGE_ERROR)
+	if (status == DP_PSR_SINK_INTERNAL_ERROR && !error_status)
+		DRM_DEBUG_KMS("PSR sink internal error, disabling PSR\n");
+	if (error_status & DP_PSR_RFB_STORAGE_ERROR)
 		DRM_DEBUG_KMS("PSR RFB storage error, disabling PSR\n");
-	if (val & DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR)
+	if (error_status & DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR)
 		DRM_DEBUG_KMS("PSR VSC SDP uncorrectable error, disabling PSR\n");
-	if (val & DP_PSR_LINK_CRC_ERROR)
+	if (error_status & DP_PSR_LINK_CRC_ERROR)
 		DRM_DEBUG_KMS("PSR Link CRC error, disabling PSR\n");
 
-	if (val & ~errors)
+	if (error_status & ~errors)
 		DRM_ERROR("PSR_ERROR_STATUS unhandled errors %x\n",
-			  val & ~errors);
-	if (val & errors) {
-		intel_psr_disable_locked(intel_dp);
-		psr->sink_not_reliable = true;
-	}
+			  error_status & ~errors);
 	/* clear status register */
-	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ERROR_STATUS, val);
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ERROR_STATUS, error_status);
+
+	psr_alpm_check(intel_dp);
+	psr_capability_changed_check(intel_dp);
+
 exit:
 	mutex_unlock(&psr->lock);
 }
@@ -1446,3 +1523,27 @@ bool intel_psr_enabled(struct intel_dp *intel_dp)
 
 	return ret;
 }
+
+void intel_psr_atomic_check(struct drm_connector *connector,
+			    struct drm_connector_state *old_state,
+			    struct drm_connector_state *new_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
+	struct intel_connector *intel_connector;
+	struct intel_digital_port *dig_port;
+	struct drm_crtc_state *crtc_state;
+
+	if (!CAN_PSR(dev_priv) || !new_state->crtc ||
+	    dev_priv->psr.initially_probed)
+		return;
+
+	intel_connector = to_intel_connector(connector);
+	dig_port = enc_to_dig_port(intel_connector->encoder);
+	if (dev_priv->psr.dp != &dig_port->dp)
+		return;
+
+	crtc_state = drm_atomic_get_new_crtc_state(new_state->state,
+						   new_state->crtc);
+	crtc_state->mode_changed = true;
+	dev_priv->psr.initially_probed = true;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h
index 46e4de8b8cd5..c58a1d438808 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.h
+++ b/drivers/gpu/drm/i915/display/intel_psr.h
@@ -8,6 +8,8 @@
 
 #include "intel_frontbuffer.h"
 
+struct drm_connector;
+struct drm_connector_state;
 struct drm_i915_private;
 struct intel_crtc_state;
 struct intel_dp;
@@ -35,5 +37,8 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp);
 int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state,
 			    u32 *out_value);
 bool intel_psr_enabled(struct intel_dp *intel_dp);
+void intel_psr_atomic_check(struct drm_connector *connector,
+			    struct drm_connector_state *old_state,
+			    struct drm_connector_state *new_state);
 
 #endif /* __INTEL_PSR_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 5b7f4baf7348..e8819fd21e03 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -180,7 +180,7 @@ static struct intel_sdvo *to_sdvo(struct intel_encoder *encoder)
 	return container_of(encoder, struct intel_sdvo, base);
 }
 
-static struct intel_sdvo *intel_attached_sdvo(struct drm_connector *connector)
+static struct intel_sdvo *intel_attached_sdvo(struct intel_connector *connector)
 {
 	return to_sdvo(intel_attached_encoder(connector));
 }
@@ -1087,7 +1087,7 @@ static bool intel_sdvo_compute_avi_infoframe(struct intel_sdvo *intel_sdvo,
 {
 	struct hdmi_avi_infoframe *frame = &crtc_state->infoframes.avi.avi;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int ret;
 
 	if (!crtc_state->has_hdmi_sink)
@@ -1276,8 +1276,8 @@ static int intel_sdvo_compute_config(struct intel_encoder *encoder,
 		to_intel_sdvo_connector_state(conn_state);
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(conn_state->connector);
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct drm_display_mode *mode = &pipe_config->base.mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct drm_display_mode *mode = &pipe_config->hw.mode;
 
 	DRM_DEBUG_KMS("forcing bpc to 8 for SDVO\n");
 	pipe_config->pipe_bpp = 8*3;
@@ -1349,9 +1349,9 @@ static int intel_sdvo_compute_config(struct intel_encoder *encoder,
 	if (IS_TV(intel_sdvo_connector))
 		i9xx_adjust_sdvo_tv_clock(pipe_config);
 
-	/* Set user selected PAR to incoming mode's member */
-	if (intel_sdvo_connector->is_hdmi)
-		adjusted_mode->picture_aspect_ratio = conn_state->picture_aspect_ratio;
+	if (conn_state->picture_aspect_ratio)
+		adjusted_mode->picture_aspect_ratio =
+			conn_state->picture_aspect_ratio;
 
 	if (!intel_sdvo_compute_avi_infoframe(intel_sdvo,
 					      pipe_config, conn_state)) {
@@ -1429,13 +1429,13 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder,
 				  const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	const struct intel_sdvo_connector_state *sdvo_state =
 		to_intel_sdvo_connector_state(conn_state);
 	const struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(conn_state->connector);
-	const struct drm_display_mode *mode = &crtc_state->base.mode;
+	const struct drm_display_mode *mode = &crtc_state->hw.mode;
 	struct intel_sdvo *intel_sdvo = to_sdvo(intel_encoder);
 	u32 sdvox;
 	struct intel_sdvo_in_out_map in_out;
@@ -1551,7 +1551,7 @@ static bool intel_sdvo_connector_get_hw_state(struct intel_connector *connector)
 {
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(&connector->base);
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(&connector->base);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
 	u16 active_outputs = 0;
 
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
@@ -1629,7 +1629,7 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 			flags |= DRM_MODE_FLAG_NVSYNC;
 	}
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	/*
 	 * pixel multiplier readout is tricky: Only on i915g/gm it is stored in
@@ -1649,7 +1649,7 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 	if (pipe_config->pixel_multiplier)
 		dotclock /= pipe_config->pixel_multiplier;
 
-	pipe_config->base.adjusted_mode.crtc_clock = dotclock;
+	pipe_config->hw.adjusted_mode.crtc_clock = dotclock;
 
 	/* Cross check the port pixel multiplier with the sdvo encoder state. */
 	if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_CLOCK_RATE_MULT,
@@ -1701,7 +1701,7 @@ static void intel_sdvo_enable_audio(struct intel_sdvo *intel_sdvo,
 				    const struct drm_connector_state *conn_state)
 {
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	struct drm_connector *connector = conn_state->connector;
 	u8 *eld = connector->eld;
 
@@ -1723,7 +1723,7 @@ static void intel_disable_sdvo(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	u32 temp;
 
 	if (old_crtc_state->has_audio)
@@ -1785,7 +1785,7 @@ static void intel_enable_sdvo(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	u32 temp;
 	bool input1, input2;
 	int i;
@@ -1823,7 +1823,7 @@ static enum drm_mode_status
 intel_sdvo_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(connector);
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
@@ -1941,7 +1941,7 @@ intel_sdvo_multifunc_encoder(struct intel_sdvo *intel_sdvo)
 static struct edid *
 intel_sdvo_get_edid(struct drm_connector *connector)
 {
-	struct intel_sdvo *sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	return drm_get_edid(connector, &sdvo->ddc);
 }
 
@@ -1959,7 +1959,7 @@ intel_sdvo_get_analog_edid(struct drm_connector *connector)
 static enum drm_connector_status
 intel_sdvo_tmds_sink_detect(struct drm_connector *connector)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(connector);
 	enum drm_connector_status status;
@@ -2028,7 +2028,7 @@ static enum drm_connector_status
 intel_sdvo_detect(struct drm_connector *connector, bool force)
 {
 	u16 response;
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector);
 	enum drm_connector_status ret;
 
@@ -2175,7 +2175,7 @@ static const struct drm_display_mode sdvo_tv_modes[] = {
 
 static void intel_sdvo_get_tv_modes(struct drm_connector *connector)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	const struct drm_connector_state *conn_state = connector->state;
 	struct intel_sdvo_sdtv_resolution_request tv_res;
 	u32 reply = 0, format_map = 0;
@@ -2215,7 +2215,7 @@ static void intel_sdvo_get_tv_modes(struct drm_connector *connector)
 
 static void intel_sdvo_get_lvds_modes(struct drm_connector *connector)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct drm_display_mode *newmode;
 
@@ -2379,7 +2379,7 @@ intel_sdvo_connector_atomic_set_property(struct drm_connector *connector,
 static int
 intel_sdvo_connector_register(struct drm_connector *connector)
 {
-	struct intel_sdvo *sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	int ret;
 
 	ret = intel_connector_register(connector);
@@ -2394,7 +2394,7 @@ intel_sdvo_connector_register(struct drm_connector *connector)
 static void
 intel_sdvo_connector_unregister(struct drm_connector *connector)
 {
-	struct intel_sdvo *sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *sdvo = intel_attached_sdvo(to_intel_connector(connector));
 
 	sysfs_remove_link(&connector->kdev->kobj,
 			  sdvo->ddc.dev.kobj.name);
@@ -2654,7 +2654,6 @@ intel_sdvo_add_hdmi_properties(struct intel_sdvo *intel_sdvo,
 		intel_attach_broadcast_rgb_property(&connector->base.base);
 	}
 	intel_attach_aspect_ratio_property(&connector->base.base);
-	connector->base.base.state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
 }
 
 static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void)
@@ -2933,7 +2932,7 @@ static void intel_sdvo_output_cleanup(struct intel_sdvo *intel_sdvo)
 
 	list_for_each_entry_safe(connector, tmp,
 				 &dev->mode_config.connector_list, head) {
-		if (intel_attached_encoder(connector) == &intel_sdvo->base) {
+		if (intel_attached_encoder(to_intel_connector(connector)) == &intel_sdvo->base) {
 			drm_connector_unregister(connector);
 			intel_connector_destroy(connector);
 		}
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 72fda0430062..fca77ec1e0dd 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -81,9 +81,9 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
  */
 void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	const struct drm_display_mode *adjusted_mode = &new_crtc_state->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &new_crtc_state->hw.adjusted_mode;
 	long timeout = msecs_to_jiffies_timeout(1);
 	int scanline, min, max, vblank_start;
 	wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
@@ -120,7 +120,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 
 	crtc->debug.min_vbl = min;
 	crtc->debug.max_vbl = max;
-	trace_i915_pipe_update_start(crtc);
+	trace_intel_pipe_update_start(crtc);
 
 	for (;;) {
 		/*
@@ -173,7 +173,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 	crtc->debug.start_vbl_time = ktime_get();
 	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
 
-	trace_i915_pipe_update_vblank_evaded(crtc);
+	trace_intel_pipe_update_vblank_evaded(crtc);
 	return;
 
 irq_disable:
@@ -190,27 +190,28 @@ irq_disable:
  */
 void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 	int scanline_end = intel_get_crtc_scanline(crtc);
 	u32 end_vbl_count = intel_crtc_get_vblank_counter(crtc);
 	ktime_t end_vbl_time = ktime_get();
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end);
+	trace_intel_pipe_update_end(crtc, end_vbl_count, scanline_end);
 
 	/* We're still in the vblank-evade critical section, this can't race.
 	 * Would be slightly nice to just grab the vblank count and arm the
 	 * event outside of the critical section - the spinlock might spin for a
 	 * while ... */
-	if (new_crtc_state->base.event) {
+	if (new_crtc_state->uapi.event) {
 		WARN_ON(drm_crtc_vblank_get(&crtc->base) != 0);
 
 		spin_lock(&crtc->base.dev->event_lock);
-		drm_crtc_arm_vblank_event(&crtc->base, new_crtc_state->base.event);
+		drm_crtc_arm_vblank_event(&crtc->base,
+				          new_crtc_state->uapi.event);
 		spin_unlock(&crtc->base.dev->event_lock);
 
-		new_crtc_state->base.event = NULL;
+		new_crtc_state->uapi.event = NULL;
 	}
 
 	local_irq_enable();
@@ -239,9 +240,9 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state)
 
 int intel_plane_check_stride(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	u32 stride, max_stride;
 
 	/*
@@ -251,7 +252,7 @@ int intel_plane_check_stride(const struct intel_plane_state *plane_state)
 	 * kick in due the plane being invisible.
 	 */
 	if (intel_plane_can_remap(plane_state) &&
-	    !plane_state->base.visible)
+	    !plane_state->uapi.visible)
 		return 0;
 
 	/* FIXME other color planes? */
@@ -271,10 +272,10 @@ int intel_plane_check_stride(const struct intel_plane_state *plane_state)
 
 int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	struct drm_rect *src = &plane_state->base.src;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	struct drm_rect *src = &plane_state->uapi.src;
 	u32 src_x, src_y, src_w, src_h, hsub, vsub;
-	bool rotated = drm_rotation_90_or_270(plane_state->base.rotation);
+	bool rotated = drm_rotation_90_or_270(plane_state->hw.rotation);
 
 	/*
 	 * Hardware doesn't handle subpixel coordinates.
@@ -327,8 +328,8 @@ skl_plane_ratio(const struct intel_crtc_state *crtc_state,
 		const struct intel_plane_state *plane_state,
 		unsigned int *num, unsigned int *den)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 
 	if (fb->format->cpp[0] == 8) {
 		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
@@ -347,7 +348,7 @@ skl_plane_ratio(const struct intel_crtc_state *crtc_state,
 static int skl_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
 			       const struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev);
+	struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev);
 	unsigned int pixel_rate = crtc_state->pixel_rate;
 	unsigned int src_w, src_h, dst_w, dst_h;
 	unsigned int num, den;
@@ -358,10 +359,10 @@ static int skl_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		den *= 2;
 
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	dst_w = drm_rect_width(&plane_state->base.dst);
-	dst_h = drm_rect_height(&plane_state->base.dst);
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->uapi.dst);
+	dst_h = drm_rect_height(&plane_state->uapi.dst);
 
 	/* Downscaling limits the maximum pixel rate */
 	dst_w = min(src_w, dst_w);
@@ -395,28 +396,28 @@ skl_program_scaler(struct intel_plane *plane,
 		   const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	int scaler_id = plane_state->scaler_id;
 	const struct intel_scaler *scaler =
 		&crtc_state->scaler_state.scalers[scaler_id];
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	u32 crtc_w = drm_rect_width(&plane_state->base.dst);
-	u32 crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	u32 crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	u32 crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	u16 y_hphase, uv_rgb_hphase;
 	u16 y_vphase, uv_rgb_vphase;
 	int hscale, vscale;
 
-	hscale = drm_rect_calc_hscale(&plane_state->base.src,
-				      &plane_state->base.dst,
+	hscale = drm_rect_calc_hscale(&plane_state->uapi.src,
+				      &plane_state->uapi.dst,
 				      0, INT_MAX);
-	vscale = drm_rect_calc_vscale(&plane_state->base.src,
-				      &plane_state->base.dst,
+	vscale = drm_rect_calc_vscale(&plane_state->uapi.src,
+				      &plane_state->uapi.dst,
 				      0, INT_MAX);
 
 	/* TODO: handle sub-pixel coordinates */
-	if (drm_format_info_is_yuv_semiplanar(fb->format) &&
+	if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
 	    !icl_is_hdr_plane(dev_priv, plane->id)) {
 		y_hphase = skl_scaler_calc_phase(1, hscale, false);
 		y_vphase = skl_scaler_calc_phase(1, vscale, false);
@@ -541,10 +542,10 @@ icl_program_input_csc(struct intel_plane *plane,
 	};
 	const u16 *csc;
 
-	if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
-		csc = input_csc_matrix[plane_state->base.color_encoding];
+	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+		csc = input_csc_matrix[plane_state->hw.color_encoding];
 	else
-		csc = input_csc_matrix_lr[plane_state->base.color_encoding];
+		csc = input_csc_matrix_lr[plane_state->hw.color_encoding];
 
 	I915_WRITE_FW(PLANE_INPUT_CSC_COEFF(pipe, plane_id, 0), ROFF(csc[0]) |
 		      GOFF(csc[1]));
@@ -558,7 +559,7 @@ icl_program_input_csc(struct intel_plane *plane,
 
 	I915_WRITE_FW(PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 0),
 		      PREOFF_YUV_TO_RGB_HI);
-	if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 		I915_WRITE_FW(PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1), 0);
 	else
 		I915_WRITE_FW(PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1),
@@ -574,7 +575,7 @@ static void
 skl_program_plane(struct intel_plane *plane,
 		  const struct intel_crtc_state *crtc_state,
 		  const struct intel_plane_state *plane_state,
-		  int color_plane, bool slave, u32 plane_ctl)
+		  int color_plane)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum plane_id plane_id = plane->id;
@@ -582,19 +583,21 @@ skl_program_plane(struct intel_plane *plane,
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 surf_addr = plane_state->color_plane[color_plane].offset;
 	u32 stride = skl_plane_stride(plane_state, color_plane);
-	u32 aux_stride = skl_plane_stride(plane_state, 1);
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	int aux_plane = intel_main_to_aux_plane(fb, color_plane);
+	u32 aux_dist = plane_state->color_plane[aux_plane].offset - surf_addr;
+	u32 aux_stride = skl_plane_stride(plane_state, aux_plane);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
 	u32 x = plane_state->color_plane[color_plane].x;
 	u32 y = plane_state->color_plane[color_plane].y;
-	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	struct intel_plane *linked = plane_state->planar_linked_plane;
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	u8 alpha = plane_state->base.alpha >> 8;
+	u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
+	u8 alpha = plane_state->hw.alpha >> 8;
 	u32 plane_color_ctl = 0;
 	unsigned long irqflags;
 	u32 keymsk, keymax;
+	u32 plane_ctl = plane_state->ctl;
 
 	plane_ctl |= skl_plane_ctl_crtc(crtc_state);
 
@@ -623,29 +626,13 @@ skl_program_plane(struct intel_plane *plane,
 	I915_WRITE_FW(PLANE_STRIDE(pipe, plane_id), stride);
 	I915_WRITE_FW(PLANE_POS(pipe, plane_id), (crtc_y << 16) | crtc_x);
 	I915_WRITE_FW(PLANE_SIZE(pipe, plane_id), (src_h << 16) | src_w);
-	I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id),
-		      (plane_state->color_plane[1].offset - surf_addr) | aux_stride);
 
-	if (icl_is_hdr_plane(dev_priv, plane_id)) {
-		u32 cus_ctl = 0;
-
-		if (linked) {
-			/* Enable and use MPEG-2 chroma siting */
-			cus_ctl = PLANE_CUS_ENABLE |
-				PLANE_CUS_HPHASE_0 |
-				PLANE_CUS_VPHASE_SIGN_NEGATIVE |
-				PLANE_CUS_VPHASE_0_25;
-
-			if (linked->id == PLANE_SPRITE5)
-				cus_ctl |= PLANE_CUS_PLANE_7;
-			else if (linked->id == PLANE_SPRITE4)
-				cus_ctl |= PLANE_CUS_PLANE_6;
-			else
-				MISSING_CASE(linked->id);
-		}
+	if (INTEL_GEN(dev_priv) < 12)
+		aux_dist |= aux_stride;
+	I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id), aux_dist);
 
-		I915_WRITE_FW(PLANE_CUS_CTL(pipe, plane_id), cus_ctl);
-	}
+	if (icl_is_hdr_plane(dev_priv, plane_id))
+		I915_WRITE_FW(PLANE_CUS_CTL(pipe, plane_id), plane_state->cus_ctl);
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		I915_WRITE_FW(PLANE_COLOR_CTL(pipe, plane_id), plane_color_ctl);
@@ -675,7 +662,7 @@ skl_program_plane(struct intel_plane *plane,
 	I915_WRITE_FW(PLANE_SURF(pipe, plane_id),
 		      intel_plane_ggtt_offset(plane_state) + surf_addr);
 
-	if (!slave && plane_state->scaler_id >= 0)
+	if (plane_state->scaler_id >= 0)
 		skl_program_scaler(plane, crtc_state, plane_state);
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
@@ -688,24 +675,12 @@ skl_update_plane(struct intel_plane *plane,
 {
 	int color_plane = 0;
 
-	if (plane_state->planar_linked_plane) {
-		/* Program the UV plane */
+	if (plane_state->planar_linked_plane && !plane_state->planar_slave)
+		/* Program the UV plane on planar master */
 		color_plane = 1;
-	}
 
-	skl_program_plane(plane, crtc_state, plane_state,
-			  color_plane, false, plane_state->ctl);
-}
-
-static void
-icl_update_slave(struct intel_plane *plane,
-		 const struct intel_crtc_state *crtc_state,
-		 const struct intel_plane_state *plane_state)
-{
-	skl_program_plane(plane, crtc_state, plane_state, 0, true,
-			  plane_state->ctl | PLANE_CTL_YUV420_Y_PLANE);
+	skl_program_plane(plane, crtc_state, plane_state, color_plane);
 }
-
 static void
 skl_disable_plane(struct intel_plane *plane,
 		  const struct intel_crtc_state *crtc_state)
@@ -765,9 +740,9 @@ static void i9xx_plane_linear_gamma(u16 gamma[8])
 static void
 chv_update_csc(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum plane_id plane_id = plane->id;
 	/*
 	 * |r|   | c0 c1 c2 |   |cr|
@@ -793,7 +768,7 @@ chv_update_csc(const struct intel_plane_state *plane_state)
 			    0, 4096,  7601,
 		},
 	};
-	const s16 *csc = csc_matrix[plane_state->base.color_encoding];
+	const s16 *csc = csc_matrix[plane_state->hw.color_encoding];
 
 	/* Seems RGB data bypasses the CSC always */
 	if (!fb->format->is_yuv)
@@ -824,15 +799,15 @@ chv_update_csc(const struct intel_plane_state *plane_state)
 static void
 vlv_update_clrc(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	enum plane_id plane_id = plane->id;
 	int contrast, brightness, sh_scale, sh_sin, sh_cos;
 
 	if (fb->format->is_yuv &&
-	    plane_state->base.color_range == DRM_COLOR_YCBCR_LIMITED_RANGE) {
+	    plane_state->hw.color_range == DRM_COLOR_YCBCR_LIMITED_RANGE) {
 		/*
 		 * Expand limited range to full range:
 		 * Contrast is applied first and is used to expand Y range.
@@ -866,7 +841,7 @@ vlv_plane_ratio(const struct intel_crtc_state *crtc_state,
 		unsigned int *num, unsigned int *den)
 {
 	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	/*
@@ -952,8 +927,8 @@ static u32 vlv_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 sprctl;
 
@@ -972,6 +947,9 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_VYUY:
 		sprctl |= SP_FORMAT_YUV422 | SP_YUV_ORDER_VYUY;
 		break;
+	case DRM_FORMAT_C8:
+		sprctl |= SP_FORMAT_8BPP;
+		break;
 	case DRM_FORMAT_RGB565:
 		sprctl |= SP_FORMAT_BGR565;
 		break;
@@ -987,6 +965,12 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_ABGR2101010:
 		sprctl |= SP_FORMAT_RGBA1010102;
 		break;
+	case DRM_FORMAT_XRGB2101010:
+		sprctl |= SP_FORMAT_BGRX1010102;
+		break;
+	case DRM_FORMAT_ARGB2101010:
+		sprctl |= SP_FORMAT_BGRA1010102;
+		break;
 	case DRM_FORMAT_XBGR8888:
 		sprctl |= SP_FORMAT_RGBX8888;
 		break;
@@ -998,7 +982,7 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 		return 0;
 	}
 
-	if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+	if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 		sprctl |= SP_YUV_FORMAT_BT709;
 
 	if (fb->modifier == I915_FORMAT_MOD_X_TILED)
@@ -1018,9 +1002,9 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 
 static void vlv_update_gamma(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	enum plane_id plane_id = plane->id;
 	u16 gamma[8];
@@ -1052,10 +1036,10 @@ vlv_update_plane(struct intel_plane *plane,
 	u32 sprsurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	u32 crtc_w = drm_rect_width(&plane_state->base.dst);
-	u32 crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	u32 crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	u32 crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	u32 x = plane_state->color_plane[0].x;
 	u32 y = plane_state->color_plane[0].y;
 	unsigned long irqflags;
@@ -1150,7 +1134,7 @@ static void ivb_plane_ratio(const struct intel_crtc_state *crtc_state,
 			    unsigned int *num, unsigned int *den)
 {
 	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	if (hweight8(active_planes) == 2) {
@@ -1186,7 +1170,7 @@ static void ivb_plane_ratio_scaling(const struct intel_crtc_state *crtc_state,
 				    const struct intel_plane_state *plane_state,
 				    unsigned int *num, unsigned int *den)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	switch (cpp) {
@@ -1244,8 +1228,8 @@ static int ivb_sprite_min_cdclk(const struct intel_crtc_state *crtc_state,
 	 */
 	pixel_rate = crtc_state->pixel_rate;
 
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	dst_w = drm_rect_width(&plane_state->base.dst);
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->uapi.dst);
 
 	if (src_w != dst_w)
 		ivb_plane_ratio_scaling(crtc_state, plane_state, &num, &den);
@@ -1264,7 +1248,7 @@ static void hsw_plane_ratio(const struct intel_crtc_state *crtc_state,
 			    unsigned int *num, unsigned int *den)
 {
 	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	if (hweight8(active_planes) == 2) {
@@ -1319,8 +1303,8 @@ static u32 ivb_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 static bool ivb_need_sprite_gamma(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 
 	return fb->format->cpp[0] == 8 &&
 		(IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv));
@@ -1330,9 +1314,9 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 sprctl;
 
@@ -1348,6 +1332,12 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XRGB8888:
 		sprctl |= SPRITE_FORMAT_RGBX888;
 		break;
+	case DRM_FORMAT_XBGR2101010:
+		sprctl |= SPRITE_FORMAT_RGBX101010 | SPRITE_RGB_ORDER_RGBX;
+		break;
+	case DRM_FORMAT_XRGB2101010:
+		sprctl |= SPRITE_FORMAT_RGBX101010;
+		break;
 	case DRM_FORMAT_XBGR16161616F:
 		sprctl |= SPRITE_FORMAT_RGBX161616 | SPRITE_RGB_ORDER_RGBX;
 		break;
@@ -1374,10 +1364,10 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	if (!ivb_need_sprite_gamma(plane_state))
 		sprctl |= SPRITE_INT_GAMMA_DISABLE;
 
-	if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+	if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 		sprctl |= SPRITE_YUV_TO_RGB_CSC_FORMAT_BT709;
 
-	if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 		sprctl |= SPRITE_YUV_RANGE_CORRECTION_DISABLE;
 
 	if (fb->modifier == I915_FORMAT_MOD_X_TILED)
@@ -1421,7 +1411,7 @@ static void ivb_sprite_linear_gamma(const struct intel_plane_state *plane_state,
 
 static void ivb_update_gamma(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 	u16 gamma[18];
@@ -1460,14 +1450,14 @@ ivb_update_plane(struct intel_plane *plane,
 	u32 sprsurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	u32 crtc_w = drm_rect_width(&plane_state->base.dst);
-	u32 crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	u32 crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	u32 crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	u32 x = plane_state->color_plane[0].x;
 	u32 y = plane_state->color_plane[0].y;
-	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	u32 sprctl, sprscale = 0;
 	unsigned long irqflags;
 
@@ -1566,7 +1556,7 @@ ivb_plane_get_hw_state(struct intel_plane *plane,
 static int g4x_sprite_min_cdclk(const struct intel_crtc_state *crtc_state,
 				const struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int hscale, pixel_rate;
 	unsigned int limit, decimate;
 
@@ -1580,8 +1570,8 @@ static int g4x_sprite_min_cdclk(const struct intel_crtc_state *crtc_state,
 	pixel_rate = crtc_state->pixel_rate;
 
 	/* Horizontal downscaling limits the maximum pixel rate */
-	hscale = drm_rect_calc_hscale(&plane_state->base.src,
-				      &plane_state->base.dst,
+	hscale = drm_rect_calc_hscale(&plane_state->uapi.src,
+				      &plane_state->uapi.dst,
 				      0, INT_MAX);
 	if (hscale < 0x10000)
 		return pixel_rate;
@@ -1635,9 +1625,9 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 dvscntr;
 
@@ -1653,6 +1643,12 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XRGB8888:
 		dvscntr |= DVS_FORMAT_RGBX888;
 		break;
+	case DRM_FORMAT_XBGR2101010:
+		dvscntr |= DVS_FORMAT_RGBX101010 | DVS_RGB_ORDER_XBGR;
+		break;
+	case DRM_FORMAT_XRGB2101010:
+		dvscntr |= DVS_FORMAT_RGBX101010;
+		break;
 	case DRM_FORMAT_XBGR16161616F:
 		dvscntr |= DVS_FORMAT_RGBX161616 | DVS_RGB_ORDER_XBGR;
 		break;
@@ -1676,10 +1672,10 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 		return 0;
 	}
 
-	if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+	if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 		dvscntr |= DVS_YUV_FORMAT_BT709;
 
-	if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 		dvscntr |= DVS_YUV_RANGE_CORRECTION_DISABLE;
 
 	if (fb->modifier == I915_FORMAT_MOD_X_TILED)
@@ -1698,9 +1694,9 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 
 static void g4x_update_gamma(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	u16 gamma[8];
 	int i;
@@ -1730,9 +1726,9 @@ static void ilk_sprite_linear_gamma(u16 gamma[17])
 
 static void ilk_update_gamma(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	u16 gamma[17];
 	int i;
@@ -1766,14 +1762,14 @@ g4x_update_plane(struct intel_plane *plane,
 	u32 dvssurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	u32 crtc_w = drm_rect_width(&plane_state->base.dst);
-	u32 crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	u32 crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	u32 crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	u32 x = plane_state->color_plane[0].x;
 	u32 y = plane_state->color_plane[0].y;
-	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	u32 dvscntr, dvsscale = 0;
 	unsigned long irqflags;
 
@@ -1886,12 +1882,12 @@ static int
 g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 			 struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	const struct drm_rect *src = &plane_state->base.src;
-	const struct drm_rect *dst = &plane_state->base.dst;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	const struct drm_rect *src = &plane_state->uapi.src;
+	const struct drm_rect *dst = &plane_state->uapi.dst;
 	int src_x, src_w, src_h, crtc_w, crtc_h;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	unsigned int stride = plane_state->color_plane[0].stride;
 	unsigned int cpp = fb->format->cpp[0];
 	unsigned int width_bytes;
@@ -1947,13 +1943,13 @@ static int
 g4x_sprite_check(struct intel_crtc_state *crtc_state,
 		 struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	int min_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int max_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int ret;
 
-	if (intel_fb_scalable(plane_state->base.fb)) {
+	if (intel_fb_scalable(plane_state->hw.fb)) {
 		if (INTEL_GEN(dev_priv) < 7) {
 			min_scale = 1;
 			max_scale = 16 << 16;
@@ -1963,8 +1959,8 @@ g4x_sprite_check(struct intel_crtc_state *crtc_state,
 		}
 	}
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  min_scale, max_scale,
 						  true, true);
 	if (ret)
@@ -1974,7 +1970,7 @@ g4x_sprite_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = intel_plane_check_src_coordinates(plane_state);
@@ -1995,9 +1991,9 @@ g4x_sprite_check(struct intel_crtc_state *crtc_state,
 
 int chv_plane_check_rotation(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	unsigned int rotation = plane_state->base.rotation;
+	unsigned int rotation = plane_state->hw.rotation;
 
 	/* CHV ignores the mirror bit when the rotate bit is set :( */
 	if (IS_CHERRYVIEW(dev_priv) &&
@@ -2020,8 +2016,8 @@ vlv_sprite_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  true, true);
@@ -2032,7 +2028,7 @@ vlv_sprite_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = intel_plane_check_src_coordinates(plane_state);
@@ -2047,10 +2043,10 @@ vlv_sprite_check(struct intel_crtc_state *crtc_state,
 static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	struct drm_format_name_buf format_name;
 
 	if (!fb)
@@ -2105,12 +2101,14 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 	}
 
 	/* Y-tiling is not supported in IF-ID Interlace mode */
-	if (crtc_state->base.enable &&
-	    crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE &&
+	if (crtc_state->hw.enable &&
+	    crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE &&
 	    (fb->modifier == I915_FORMAT_MOD_Y_TILED ||
 	     fb->modifier == I915_FORMAT_MOD_Yf_TILED ||
 	     fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
-	     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS)) {
+	     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
+	     fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+	     fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS)) {
 		DRM_DEBUG_KMS("Y/Yf tiling not supported in IF-ID mode\n");
 		return -EINVAL;
 	}
@@ -2122,9 +2120,9 @@ static int skl_plane_check_dst_coordinates(const struct intel_crtc_state *crtc_s
 					   const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_w = drm_rect_width(&plane_state->base.dst);
+		to_i915(plane_state->uapi.plane->dev);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_w = drm_rect_width(&plane_state->uapi.dst);
 	int pipe_src_w = crtc_state->pipe_src_w;
 
 	/*
@@ -2150,12 +2148,13 @@ static int skl_plane_check_dst_coordinates(const struct intel_crtc_state *crtc_s
 
 static int skl_plane_check_nv12_rotation(const struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
-	int src_w = drm_rect_width(&plane_state->base.src) >> 16;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
+	int src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
 
 	/* Display WA #1106 */
-	if (drm_format_info_is_yuv_semiplanar(fb->format) && src_w & 3 &&
+	if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
+	    src_w & 3 &&
 	    (rotation == DRM_MODE_ROTATE_270 ||
 	     rotation == (DRM_MODE_REFLECT_X | DRM_MODE_ROTATE_90))) {
 		DRM_DEBUG_KMS("src width must be multiple of 4 for rotated planar YUV\n");
@@ -2175,7 +2174,7 @@ static int skl_plane_max_scale(struct drm_i915_private *dev_priv,
 	 * FIXME need to properly check this later.
 	 */
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv) ||
-	    !drm_format_info_is_yuv_semiplanar(fb->format))
+	    !intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		return 0x30000 - 1;
 	else
 		return 0x20000 - 1;
@@ -2184,9 +2183,9 @@ static int skl_plane_max_scale(struct drm_i915_private *dev_priv,
 static int skl_plane_check(struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int min_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int max_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int ret;
@@ -2201,8 +2200,8 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 		max_scale = skl_plane_max_scale(dev_priv, fb);
 	}
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  min_scale, max_scale,
 						  true, true);
 	if (ret)
@@ -2212,7 +2211,7 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = skl_plane_check_dst_coordinates(crtc_state, plane_state);
@@ -2228,8 +2227,8 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 		return ret;
 
 	/* HW only has 8 bits pixel precision, disable plane if invisible */
-	if (!(plane_state->base.alpha >> 8))
-		plane_state->base.visible = false;
+	if (!(plane_state->hw.alpha >> 8))
+		plane_state->uapi.visible = false;
 
 	plane_state->ctl = skl_plane_ctl(crtc_state, plane_state);
 
@@ -2237,6 +2236,15 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 		plane_state->color_ctl = glk_plane_color_ctl(crtc_state,
 							     plane_state);
 
+	if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
+	    icl_is_hdr_plane(dev_priv, plane->id))
+		/* Enable and use MPEG-2 chroma siting */
+		plane_state->cus_ctl = PLANE_CUS_ENABLE |
+			PLANE_CUS_HPHASE_0 |
+			PLANE_CUS_VPHASE_SIGN_NEGATIVE | PLANE_CUS_VPHASE_0_25;
+	else
+		plane_state->cus_ctl = 0;
+
 	return 0;
 }
 
@@ -2248,7 +2256,7 @@ static bool has_dst_key_in_primary_plane(struct drm_i915_private *dev_priv)
 static void intel_plane_set_ckey(struct intel_plane_state *plane_state,
 				 const struct drm_intel_sprite_colorkey *set)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 
@@ -2375,6 +2383,8 @@ static const u64 i9xx_plane_format_modifiers[] = {
 static const u32 snb_plane_formats[] = {
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_XBGR2101010,
 	DRM_FORMAT_XRGB16161616F,
 	DRM_FORMAT_XBGR16161616F,
 	DRM_FORMAT_YUYV,
@@ -2384,12 +2394,30 @@ static const u32 snb_plane_formats[] = {
 };
 
 static const u32 vlv_plane_formats[] = {
+	DRM_FORMAT_C8,
 	DRM_FORMAT_RGB565,
-	DRM_FORMAT_ABGR8888,
-	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
+};
+
+static const u32 chv_pipe_b_sprite_formats[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_RGB565,
 	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
 	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
@@ -2462,6 +2490,8 @@ static const u32 icl_sdr_y_plane_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
@@ -2483,6 +2513,8 @@ static const u32 icl_sdr_uv_plane_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
@@ -2508,6 +2540,8 @@ static const u32 icl_hdr_plane_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_XRGB16161616F,
 	DRM_FORMAT_XBGR16161616F,
 	DRM_FORMAT_ARGB16161616F,
@@ -2546,7 +2580,17 @@ static const u64 skl_plane_format_modifiers_ccs[] = {
 	DRM_FORMAT_MOD_INVALID
 };
 
-static const u64 gen12_plane_format_modifiers_noccs[] = {
+static const u64 gen12_plane_format_modifiers_mc_ccs[] = {
+	I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS,
+	I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS,
+	I915_FORMAT_MOD_Y_TILED,
+	I915_FORMAT_MOD_X_TILED,
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
+static const u64 gen12_plane_format_modifiers_rc_ccs[] = {
+	I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS,
 	I915_FORMAT_MOD_Y_TILED,
 	I915_FORMAT_MOD_X_TILED,
 	DRM_FORMAT_MOD_LINEAR,
@@ -2593,6 +2637,8 @@ static bool snb_sprite_format_mod_supported(struct drm_plane *_plane,
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
 	case DRM_FORMAT_XRGB16161616F:
 	case DRM_FORMAT_XBGR16161616F:
 	case DRM_FORMAT_YUYV:
@@ -2620,6 +2666,7 @@ static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane,
 	}
 
 	switch (format) {
+	case DRM_FORMAT_C8:
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_ABGR8888:
 	case DRM_FORMAT_ARGB8888:
@@ -2627,6 +2674,8 @@ static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR2101010:
 	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -2671,6 +2720,8 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -2703,13 +2754,25 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	}
 }
 
+static bool gen12_plane_supports_mc_ccs(enum plane_id plane_id)
+{
+	return plane_id < PLANE_SPRITE4;
+}
+
 static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 					     u32 format, u64 modifier)
 {
+	struct intel_plane *plane = to_intel_plane(_plane);
+
 	switch (modifier) {
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		if (!gen12_plane_supports_mc_ccs(plane->id))
+			return false;
+		/* fall through */
 	case DRM_FORMAT_MOD_LINEAR:
 	case I915_FORMAT_MOD_X_TILED:
 	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
 		break;
 	default:
 		return false;
@@ -2720,9 +2783,9 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_ABGR8888:
-	case DRM_FORMAT_RGB565:
-	case DRM_FORMAT_XRGB2101010:
-	case DRM_FORMAT_XBGR2101010:
+		if (is_ccs_modifier(modifier))
+			return true;
+		/* fall through */
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -2731,6 +2794,14 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_P010:
 	case DRM_FORMAT_P012:
 	case DRM_FORMAT_P016:
+		if (modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS)
+			return true;
+		/* fall through */
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_XVYU2101010:
 	case DRM_FORMAT_C8:
 	case DRM_FORMAT_XBGR16161616F:
@@ -2864,6 +2935,14 @@ static const u32 *icl_get_plane_formats(struct drm_i915_private *dev_priv,
 	}
 }
 
+static const u64 *gen12_get_plane_modifiers(enum plane_id plane_id)
+{
+	if (gen12_plane_supports_mc_ccs(plane_id))
+		return gen12_plane_format_modifiers_mc_ccs;
+	else
+		return gen12_plane_format_modifiers_rc_ccs;
+}
+
 static bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
 			      enum pipe pipe, enum plane_id plane_id)
 {
@@ -2916,8 +2995,6 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 	plane->get_hw_state = skl_plane_get_hw_state;
 	plane->check_plane = skl_plane_check;
 	plane->min_cdclk = skl_plane_min_cdclk;
-	if (icl_is_nv12_y_plane(plane_id))
-		plane->update_slave = icl_update_slave;
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		formats = icl_get_plane_formats(dev_priv, pipe,
@@ -2929,13 +3006,11 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 		formats = skl_get_plane_formats(dev_priv, pipe,
 						plane_id, &num_formats);
 
+	plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
 	if (INTEL_GEN(dev_priv) >= 12) {
-		/* TODO: Implement support for gen-12 CCS modifiers */
-		plane->has_ccs = false;
-		modifiers = gen12_plane_format_modifiers_noccs;
+		modifiers = gen12_get_plane_modifiers(plane_id);
 		plane_funcs = &gen12_plane_funcs;
 	} else {
-		plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
 		if (plane->has_ccs)
 			modifiers = skl_plane_format_modifiers_ccs;
 		else
@@ -3025,8 +3100,13 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane->check_plane = vlv_sprite_check;
 		plane->min_cdclk = vlv_plane_min_cdclk;
 
-		formats = vlv_plane_formats;
-		num_formats = ARRAY_SIZE(vlv_plane_formats);
+		if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) {
+			formats = chv_pipe_b_sprite_formats;
+			num_formats = ARRAY_SIZE(chv_pipe_b_sprite_formats);
+		} else {
+			formats = vlv_plane_formats;
+			num_formats = ARRAY_SIZE(vlv_plane_formats);
+		}
 		modifiers = i9xx_plane_format_modifiers;
 
 		plane_funcs = &vlv_sprite_funcs;
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index 9983fadf6c28..c75e0ceecee6 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -898,7 +898,7 @@ static struct intel_tv *enc_to_tv(struct intel_encoder *encoder)
 	return container_of(encoder, struct intel_tv, base);
 }
 
-static struct intel_tv *intel_attached_tv(struct drm_connector *connector)
+static struct intel_tv *intel_attached_tv(struct intel_connector *connector)
 {
 	return enc_to_tv(intel_attached_encoder(connector));
 }
@@ -924,7 +924,7 @@ intel_enable_tv(struct intel_encoder *encoder,
 
 	/* Prevents vblank waits from timing out in intel_tv_detect_type() */
 	intel_wait_for_vblank(dev_priv,
-			      to_intel_crtc(pipe_config->base.crtc)->pipe);
+			      to_intel_crtc(pipe_config->uapi.crtc)->pipe);
 
 	I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE);
 }
@@ -1085,7 +1085,7 @@ intel_tv_get_config(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 	struct drm_display_mode mode = {};
 	u32 tv_ctl, hctl1, hctl3, vctl1, vctl2, tmp;
 	struct tv_mode tv_mode = {};
@@ -1188,7 +1188,7 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 		to_intel_tv_connector_state(conn_state);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state);
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 	int hdisplay = adjusted_mode->crtc_hdisplay;
 	int vdisplay = adjusted_mode->crtc_vdisplay;
 
@@ -1417,7 +1417,7 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder,
 				const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct intel_tv *intel_tv = enc_to_tv(encoder);
 	const struct intel_tv_connector_state *tv_conn_state =
 		to_intel_tv_connector_state(conn_state);
@@ -1527,7 +1527,7 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder,
 			   ((video_levels->black << TV_BLACK_LEVEL_SHIFT) |
 			    (video_levels->blank << TV_BLANK_LEVEL_SHIFT)));
 
-	assert_pipe_disabled(dev_priv, intel_crtc->pipe);
+	assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder);
 
 	/* Filter ctl must be set before TV_WIN_SIZE */
 	tv_filter_ctl = TV_AUTO_SCALE;
@@ -1662,7 +1662,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
  */
 static void intel_tv_find_better_format(struct drm_connector *connector)
 {
-	struct intel_tv *intel_tv = intel_attached_tv(connector);
+	struct intel_tv *intel_tv = intel_attached_tv(to_intel_connector(connector));
 	const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state);
 	int i;
 
@@ -1689,7 +1689,7 @@ intel_tv_detect(struct drm_connector *connector,
 		struct drm_modeset_acquire_ctx *ctx,
 		bool force)
 {
-	struct intel_tv *intel_tv = intel_attached_tv(connector);
+	struct intel_tv *intel_tv = intel_attached_tv(to_intel_connector(connector));
 	enum drm_connector_status status;
 	int type;
 
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index 69a7cb1fa121..4d0c23b29248 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -115,6 +115,7 @@ enum bdb_block_id {
 	BDB_MIPI_CONFIG			= 52,
 	BDB_MIPI_SEQUENCE		= 53,
 	BDB_COMPRESSION_PARAMETERS	= 56,
+	BDB_GENERIC_DTD			= 58,
 	BDB_SKIP			= 254, /* VBIOS private block, ignore */
 };
 
@@ -368,7 +369,7 @@ struct child_device_config {
 			u16 dtd_buf_ptr;			/* 161 */
 			u8 edidless_efp:1;			/* 161 */
 			u8 compression_enable:1;		/* 198 */
-			u8 compression_method:1;		/* 198 */
+			u8 compression_method_cps:1;		/* 198 */
 			u8 ganged_edp:1;			/* 202 */
 			u8 reserved0:4;
 			u8 compression_structure_index:4;	/* 198 */
@@ -793,6 +794,35 @@ struct bdb_lfp_backlight_data {
 } __packed;
 
 /*
+ * Block 44 - LFP Power Conservation Features Block
+ */
+
+struct als_data_entry {
+	u16 backlight_adjust;
+	u16 lux;
+} __packed;
+
+struct agressiveness_profile_entry {
+	u8 dpst_agressiveness : 4;
+	u8 lace_agressiveness : 4;
+} __packed;
+
+struct bdb_lfp_power {
+	u8 lfp_feature_bits;
+	struct als_data_entry als[5];
+	u8 lace_aggressiveness_profile;
+	u16 dpst;
+	u16 psr;
+	u16 drrs;
+	u16 lace_support;
+	u16 adt;
+	u16 dmrrs;
+	u16 adb;
+	u16 lace_enabled_status;
+	struct agressiveness_profile_entry aggressivenes[16];
+} __packed;
+
+/*
  * Block 52 - MIPI Configuration Block
  */
 
@@ -863,4 +893,34 @@ struct bdb_compression_parameters {
 	struct dsc_compression_parameters_entry data[16];
 } __packed;
 
+/*
+ * Block 58 - Generic DTD Block
+ */
+
+struct generic_dtd_entry {
+	u32 pixel_clock;
+	u16 hactive;
+	u16 hblank;
+	u16 hfront_porch;
+	u16 hsync;
+	u16 vactive;
+	u16 vblank;
+	u16 vfront_porch;
+	u16 vsync;
+	u16 width_mm;
+	u16 height_mm;
+
+	/* Flags */
+	u8 rsvd_flags:6;
+	u8 vsync_positive_polarity:1;
+	u8 hsync_positive_polarity:1;
+
+	u8 rsvd[3];
+} __packed;
+
+struct bdb_generic_dtd {
+	u16 gdtd_size;
+	struct generic_dtd_entry dtd[];	/* up to 24 DTD's */
+} __packed;
+
 #endif /* _INTEL_VBT_DEFS_H_ */
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index 896b0c334f5e..9e6aaa302e40 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -10,6 +10,7 @@
 
 #include "i915_drv.h"
 #include "intel_display_types.h"
+#include "intel_dsi.h"
 #include "intel_vdsc.h"
 
 enum ROW_INDEX_BPP {
@@ -30,10 +31,8 @@ enum COLUMN_INDEX_BPC {
 	MAX_COLUMN_INDEX
 };
 
-#define DSC_SUPPORTED_VERSION_MIN		1
-
 /* From DSC_v1.11 spec, rc_parameter_Set syntax element typically constant */
-static u16 rc_buf_thresh[] = {
+static const u16 rc_buf_thresh[] = {
 	896, 1792, 2688, 3584, 4480, 5376, 6272, 6720, 7168, 7616,
 	7744, 7872, 8000, 8064
 };
@@ -53,7 +52,7 @@ struct rc_parameters {
  * Selected Rate Control Related Parameter Recommended Values
  * from DSC_v1.11 spec & C Model release: DSC_model_20161212
  */
-static struct rc_parameters rc_params[][MAX_COLUMN_INDEX] = {
+static const struct rc_parameters rc_parameters[][MAX_COLUMN_INDEX] = {
 {
 	/* 6BPP/8BPC */
 	{ 768, 15, 6144, 3, 13, 11, 11, {
@@ -319,63 +318,84 @@ static int get_column_index_for_rc_params(u8 bits_per_component)
 	}
 }
 
-int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
-				struct intel_crtc_state *pipe_config)
+static const struct rc_parameters *get_rc_params(u16 compressed_bpp,
+						 u8 bits_per_component)
+{
+	int row_index, column_index;
+
+	row_index = get_row_index_for_rc_params(compressed_bpp);
+	if (row_index < 0)
+		return NULL;
+
+	column_index = get_column_index_for_rc_params(bits_per_component);
+	if (column_index < 0)
+		return NULL;
+
+	return &rc_parameters[row_index][column_index];
+}
+
+bool intel_dsc_source_support(struct intel_encoder *encoder,
+			      const struct intel_crtc_state *crtc_state)
+{
+	const struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+	enum pipe pipe = crtc->pipe;
+
+	if (!INTEL_INFO(i915)->display.has_dsc)
+		return false;
+
+	/* On TGL, DSC is supported on all Pipes */
+	if (INTEL_GEN(i915) >= 12)
+		return true;
+
+	if (INTEL_GEN(i915) >= 10 &&
+	    (pipe != PIPE_A ||
+	     (cpu_transcoder == TRANSCODER_EDP ||
+	      cpu_transcoder == TRANSCODER_DSI_0 ||
+	      cpu_transcoder == TRANSCODER_DSI_1)))
+		return true;
+
+	return false;
+}
+
+static bool is_pipe_dsc(const struct intel_crtc_state *crtc_state)
+{
+	const struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+
+	if (INTEL_GEN(i915) >= 12)
+		return true;
+
+	if (cpu_transcoder == TRANSCODER_EDP ||
+	    cpu_transcoder == TRANSCODER_DSI_0 ||
+	    cpu_transcoder == TRANSCODER_DSI_1)
+		return false;
+
+	/* There's no pipe A DSC engine on ICL */
+	WARN_ON(crtc->pipe == PIPE_A);
+
+	return true;
+}
+
+int intel_dsc_compute_params(struct intel_encoder *encoder,
+			     struct intel_crtc_state *pipe_config)
 {
 	struct drm_dsc_config *vdsc_cfg = &pipe_config->dsc.config;
 	u16 compressed_bpp = pipe_config->dsc.compressed_bpp;
+	const struct rc_parameters *rc_params;
 	u8 i = 0;
-	int row_index = 0;
-	int column_index = 0;
-	u8 line_buf_depth = 0;
 
-	vdsc_cfg->pic_width = pipe_config->base.adjusted_mode.crtc_hdisplay;
-	vdsc_cfg->pic_height = pipe_config->base.adjusted_mode.crtc_vdisplay;
+	vdsc_cfg->pic_width = pipe_config->hw.adjusted_mode.crtc_hdisplay;
+	vdsc_cfg->pic_height = pipe_config->hw.adjusted_mode.crtc_vdisplay;
 	vdsc_cfg->slice_width = DIV_ROUND_UP(vdsc_cfg->pic_width,
 					     pipe_config->dsc.slice_count);
-	/*
-	 * Slice Height of 8 works for all currently available panels. So start
-	 * with that if pic_height is an integral multiple of 8.
-	 * Eventually add logic to try multiple slice heights.
-	 */
-	if (vdsc_cfg->pic_height % 8 == 0)
-		vdsc_cfg->slice_height = 8;
-	else if (vdsc_cfg->pic_height % 4 == 0)
-		vdsc_cfg->slice_height = 4;
-	else
-		vdsc_cfg->slice_height = 2;
-
-	/* Values filled from DSC Sink DPCD */
-	vdsc_cfg->dsc_version_major =
-		(intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] &
-		 DP_DSC_MAJOR_MASK) >> DP_DSC_MAJOR_SHIFT;
-	vdsc_cfg->dsc_version_minor =
-		min(DSC_SUPPORTED_VERSION_MIN,
-		    (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] &
-		     DP_DSC_MINOR_MASK) >> DP_DSC_MINOR_SHIFT);
-
-	vdsc_cfg->convert_rgb = intel_dp->dsc_dpcd[DP_DSC_DEC_COLOR_FORMAT_CAP - DP_DSC_SUPPORT] &
-		DP_DSC_RGB;
-
-	line_buf_depth = drm_dp_dsc_sink_line_buf_depth(intel_dp->dsc_dpcd);
-	if (!line_buf_depth) {
-		DRM_DEBUG_KMS("DSC Sink Line Buffer Depth invalid\n");
-		return -EINVAL;
-	}
-	if (vdsc_cfg->dsc_version_minor == 2)
-		vdsc_cfg->line_buf_depth = (line_buf_depth == DSC_1_2_MAX_LINEBUF_DEPTH_BITS) ?
-			DSC_1_2_MAX_LINEBUF_DEPTH_VAL : line_buf_depth;
-	else
-		vdsc_cfg->line_buf_depth = (line_buf_depth > DSC_1_1_MAX_LINEBUF_DEPTH_BITS) ?
-			DSC_1_1_MAX_LINEBUF_DEPTH_BITS : line_buf_depth;
 
 	/* Gen 11 does not support YCbCr */
 	vdsc_cfg->simple_422 = false;
 	/* Gen 11 does not support VBR */
 	vdsc_cfg->vbr_enable = false;
-	vdsc_cfg->block_pred_enable =
-			intel_dp->dsc_dpcd[DP_DSC_BLK_PREDICTION_SUPPORT - DP_DSC_SUPPORT] &
-		DP_DSC_BLK_PREDICTION_IS_SUPPORTED;
 
 	/* Gen 11 only supports integral values of bpp */
 	vdsc_cfg->bits_per_pixel = compressed_bpp << 4;
@@ -399,39 +419,29 @@ int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
 		vdsc_cfg->rc_buf_thresh[13] = 0x7D;
 	}
 
-	row_index = get_row_index_for_rc_params(compressed_bpp);
-	column_index =
-		get_column_index_for_rc_params(vdsc_cfg->bits_per_component);
-
-	if (row_index < 0 || column_index < 0)
+	rc_params = get_rc_params(compressed_bpp, vdsc_cfg->bits_per_component);
+	if (!rc_params)
 		return -EINVAL;
 
-	vdsc_cfg->first_line_bpg_offset =
-		rc_params[row_index][column_index].first_line_bpg_offset;
-	vdsc_cfg->initial_xmit_delay =
-		rc_params[row_index][column_index].initial_xmit_delay;
-	vdsc_cfg->initial_offset =
-		rc_params[row_index][column_index].initial_offset;
-	vdsc_cfg->flatness_min_qp =
-		rc_params[row_index][column_index].flatness_min_qp;
-	vdsc_cfg->flatness_max_qp =
-		rc_params[row_index][column_index].flatness_max_qp;
-	vdsc_cfg->rc_quant_incr_limit0 =
-		rc_params[row_index][column_index].rc_quant_incr_limit0;
-	vdsc_cfg->rc_quant_incr_limit1 =
-		rc_params[row_index][column_index].rc_quant_incr_limit1;
+	vdsc_cfg->first_line_bpg_offset = rc_params->first_line_bpg_offset;
+	vdsc_cfg->initial_xmit_delay = rc_params->initial_xmit_delay;
+	vdsc_cfg->initial_offset = rc_params->initial_offset;
+	vdsc_cfg->flatness_min_qp = rc_params->flatness_min_qp;
+	vdsc_cfg->flatness_max_qp = rc_params->flatness_max_qp;
+	vdsc_cfg->rc_quant_incr_limit0 = rc_params->rc_quant_incr_limit0;
+	vdsc_cfg->rc_quant_incr_limit1 = rc_params->rc_quant_incr_limit1;
 
 	for (i = 0; i < DSC_NUM_BUF_RANGES; i++) {
 		vdsc_cfg->rc_range_params[i].range_min_qp =
-			rc_params[row_index][column_index].rc_range_params[i].range_min_qp;
+			rc_params->rc_range_params[i].range_min_qp;
 		vdsc_cfg->rc_range_params[i].range_max_qp =
-			rc_params[row_index][column_index].rc_range_params[i].range_max_qp;
+			rc_params->rc_range_params[i].range_max_qp;
 		/*
 		 * Range BPG Offset uses 2's complement and is only a 6 bits. So
 		 * mask it to get only 6 bits.
 		 */
 		vdsc_cfg->rc_range_params[i].range_bpg_offset =
-			rc_params[row_index][column_index].rc_range_params[i].range_bpg_offset &
+			rc_params->rc_range_params[i].range_bpg_offset &
 			DSC_RANGE_BPG_OFFSET_MASK;
 	}
 
@@ -453,41 +463,42 @@ int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
 	vdsc_cfg->initial_scale_value = (vdsc_cfg->rc_model_size << 3) /
 		(vdsc_cfg->rc_model_size - vdsc_cfg->initial_offset);
 
-	return drm_dsc_compute_rc_parameters(vdsc_cfg);
+	return 0;
 }
 
 enum intel_display_power_domain
 intel_dsc_power_domain(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *i915 = to_i915(crtc_state->base.crtc->dev);
-	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	/*
-	 * On ICL VDSC/joining for eDP transcoder uses a separate power well,
-	 * PW2. This requires POWER_DOMAIN_TRANSCODER_VDSC_PW2 power domain.
-	 * For any other transcoder, VDSC/joining uses the power well associated
-	 * with the pipe/transcoder in use. Hence another reference on the
-	 * transcoder power domain will suffice.
+	 * VDSC/joining uses a separate power well, PW2, and requires
+	 * POWER_DOMAIN_TRANSCODER_VDSC_PW2 power domain in two cases:
+	 *
+	 *  - ICL eDP/DSI transcoder
+	 *  - TGL pipe A
 	 *
-	 * On TGL we have the same mapping, but for transcoder A (the special
-	 * TRANSCODER_EDP is gone).
+	 * For any other pipe, VDSC/joining uses the power well associated with
+	 * the pipe in use. Hence another reference on the pipe power domain
+	 * will suffice. (Except no VDSC/joining on ICL pipe A.)
 	 */
-	if (INTEL_GEN(i915) >= 12 && cpu_transcoder == TRANSCODER_A)
-		return POWER_DOMAIN_TRANSCODER_VDSC_PW2;
-	else if (cpu_transcoder == TRANSCODER_EDP)
+	if (INTEL_GEN(i915) >= 12 && pipe == PIPE_A)
 		return POWER_DOMAIN_TRANSCODER_VDSC_PW2;
+	else if (is_pipe_dsc(crtc_state))
+		return POWER_DOMAIN_PIPE(pipe);
 	else
-		return POWER_DOMAIN_TRANSCODER(cpu_transcoder);
+		return POWER_DOMAIN_TRANSCODER_VDSC_PW2;
 }
 
-static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
-						const struct intel_crtc_state *crtc_state)
+static void intel_dsc_pps_configure(struct intel_encoder *encoder,
+				    const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	enum pipe pipe = crtc->pipe;
-	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 pps_val = 0;
 	u32 rc_buf_thresh_dword[4];
 	u32 rc_range_params_dword[8];
@@ -508,7 +519,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	if (vdsc_cfg->vbr_enable)
 		pps_val |= DSC_VBR_ENABLE;
 	DRM_INFO("PPS0 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_0, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -527,7 +538,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val = 0;
 	pps_val |= DSC_BPP(vdsc_cfg->bits_per_pixel);
 	DRM_INFO("PPS1 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_1, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -547,7 +558,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_PIC_HEIGHT(vdsc_cfg->pic_height) |
 		DSC_PIC_WIDTH(vdsc_cfg->pic_width / num_vdsc_instances);
 	DRM_INFO("PPS2 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_2, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -567,7 +578,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_SLICE_HEIGHT(vdsc_cfg->slice_height) |
 		DSC_SLICE_WIDTH(vdsc_cfg->slice_width);
 	DRM_INFO("PPS3 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_3, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -587,7 +598,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_INITIAL_XMIT_DELAY(vdsc_cfg->initial_xmit_delay) |
 		DSC_INITIAL_DEC_DELAY(vdsc_cfg->initial_dec_delay);
 	DRM_INFO("PPS4 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_4, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -607,7 +618,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_SCALE_INC_INT(vdsc_cfg->scale_increment_interval) |
 		DSC_SCALE_DEC_INT(vdsc_cfg->scale_decrement_interval);
 	DRM_INFO("PPS5 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_5, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -629,7 +640,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DSC_FLATNESS_MIN_QP(vdsc_cfg->flatness_min_qp) |
 		DSC_FLATNESS_MAX_QP(vdsc_cfg->flatness_max_qp);
 	DRM_INFO("PPS6 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_6, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -649,7 +660,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_SLICE_BPG_OFFSET(vdsc_cfg->slice_bpg_offset) |
 		DSC_NFL_BPG_OFFSET(vdsc_cfg->nfl_bpg_offset);
 	DRM_INFO("PPS7 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_7, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -669,7 +680,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_FINAL_OFFSET(vdsc_cfg->final_offset) |
 		DSC_INITIAL_OFFSET(vdsc_cfg->initial_offset);
 	DRM_INFO("PPS8 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_8, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -689,7 +700,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_RC_MODEL_SIZE(DSC_RC_MODEL_SIZE_CONST) |
 		DSC_RC_EDGE_FACTOR(DSC_RC_EDGE_FACTOR_CONST);
 	DRM_INFO("PPS9 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_9, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -711,7 +722,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DSC_RC_TARGET_OFF_HIGH(DSC_RC_TGT_OFFSET_HI_CONST) |
 		DSC_RC_TARGET_OFF_LOW(DSC_RC_TGT_OFFSET_LO_CONST);
 	DRM_INFO("PPS10 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_10, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -734,7 +745,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DSC_SLICE_ROW_PER_FRAME(vdsc_cfg->pic_height /
 					vdsc_cfg->slice_height);
 	DRM_INFO("PPS16 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_16, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -758,7 +769,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DRM_INFO(" RC_BUF_THRESH%d = 0x%08x\n", i,
 			 rc_buf_thresh_dword[i / 4]);
 	}
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_RC_BUF_THRESH_0, rc_buf_thresh_dword[0]);
 		I915_WRITE(DSCA_RC_BUF_THRESH_0_UDW, rc_buf_thresh_dword[1]);
 		I915_WRITE(DSCA_RC_BUF_THRESH_1, rc_buf_thresh_dword[2]);
@@ -807,7 +818,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DRM_INFO(" RC_RANGE_PARAM_%d = 0x%08x\n", i,
 			 rc_range_params_dword[i / 2]);
 	}
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_RC_RANGE_PARAMETERS_0,
 			   rc_range_params_dword[0]);
 		I915_WRITE(DSCA_RC_RANGE_PARAMETERS_0_UDW,
@@ -880,10 +891,77 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	}
 }
 
-static void intel_dp_write_dsc_pps_sdp(struct intel_encoder *encoder,
-				       const struct intel_crtc_state *crtc_state)
+void intel_dsc_get_config(struct intel_encoder *encoder,
+			  struct intel_crtc_state *crtc_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	enum pipe pipe = crtc->pipe;
+	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
+	u32 dss_ctl1, dss_ctl2, val;
+
+	if (!intel_dsc_source_support(encoder, crtc_state))
+		return;
+
+	power_domain = intel_dsc_power_domain(crtc_state);
+
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
+		return;
+
+	if (!is_pipe_dsc(crtc_state)) {
+		dss_ctl1 = I915_READ(DSS_CTL1);
+		dss_ctl2 = I915_READ(DSS_CTL2);
+	} else {
+		dss_ctl1 = I915_READ(ICL_PIPE_DSS_CTL1(pipe));
+		dss_ctl2 = I915_READ(ICL_PIPE_DSS_CTL2(pipe));
+	}
+
+	crtc_state->dsc.compression_enable = dss_ctl2 & LEFT_BRANCH_VDSC_ENABLE;
+	if (!crtc_state->dsc.compression_enable)
+		goto out;
+
+	crtc_state->dsc.dsc_split = (dss_ctl2 & RIGHT_BRANCH_VDSC_ENABLE) &&
+		(dss_ctl1 & JOINER_ENABLE);
+
+	/* FIXME: add more state readout as needed */
+
+	/* PPS1 */
+	if (!is_pipe_dsc(crtc_state))
+		val = I915_READ(DSCA_PICTURE_PARAMETER_SET_1);
+	else
+		val = I915_READ(ICL_DSC0_PICTURE_PARAMETER_SET_1(pipe));
+	vdsc_cfg->bits_per_pixel = val;
+	crtc_state->dsc.compressed_bpp = vdsc_cfg->bits_per_pixel >> 4;
+out:
+	intel_display_power_put(dev_priv, power_domain, wakeref);
+}
+
+static void intel_dsc_dsi_pps_write(struct intel_encoder *encoder,
+				    const struct intel_crtc_state *crtc_state)
+{
+	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct mipi_dsi_device *dsi;
+	struct drm_dsc_picture_parameter_set pps;
+	enum port port;
+
+	drm_dsc_pps_payload_pack(&pps, vdsc_cfg);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		dsi = intel_dsi->dsi_hosts[port]->device;
+
+		mipi_dsi_picture_parameter_set(dsi, &pps);
+		mipi_dsi_compression_mode(dsi, true);
+	}
+}
+
+static void intel_dsc_dp_pps_write(struct intel_encoder *encoder,
+				   const struct intel_crtc_state *crtc_state)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	struct drm_dsc_pps_infoframe dp_dsc_pps_sdp;
@@ -902,7 +980,7 @@ static void intel_dp_write_dsc_pps_sdp(struct intel_encoder *encoder,
 void intel_dsc_enable(struct intel_encoder *encoder,
 		      const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum pipe pipe = crtc->pipe;
 	i915_reg_t dss_ctl1_reg, dss_ctl2_reg;
@@ -916,11 +994,14 @@ void intel_dsc_enable(struct intel_encoder *encoder,
 	intel_display_power_get(dev_priv,
 				intel_dsc_power_domain(crtc_state));
 
-	intel_configure_pps_for_dsc_encoder(encoder, crtc_state);
+	intel_dsc_pps_configure(encoder, crtc_state);
 
-	intel_dp_write_dsc_pps_sdp(encoder, crtc_state);
+	if (encoder->type == INTEL_OUTPUT_DSI)
+		intel_dsc_dsi_pps_write(encoder, crtc_state);
+	else
+		intel_dsc_dp_pps_write(encoder, crtc_state);
 
-	if (crtc_state->cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		dss_ctl1_reg = DSS_CTL1;
 		dss_ctl2_reg = DSS_CTL2;
 	} else {
@@ -938,7 +1019,7 @@ void intel_dsc_enable(struct intel_encoder *encoder,
 
 void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	i915_reg_t dss_ctl1_reg, dss_ctl2_reg;
@@ -947,7 +1028,7 @@ void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state)
 	if (!old_crtc_state->dsc.compression_enable)
 		return;
 
-	if (old_crtc_state->cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(old_crtc_state)) {
 		dss_ctl1_reg = DSS_CTL1;
 		dss_ctl2_reg = DSS_CTL2;
 	} else {
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h
index 90d3f6017fcb..e56a3254c214 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.h
@@ -6,15 +6,20 @@
 #ifndef __INTEL_VDSC_H__
 #define __INTEL_VDSC_H__
 
+#include <linux/types.h>
+
 struct intel_encoder;
 struct intel_crtc_state;
-struct intel_dp;
 
+bool intel_dsc_source_support(struct intel_encoder *encoder,
+			      const struct intel_crtc_state *crtc_state);
 void intel_dsc_enable(struct intel_encoder *encoder,
 		      const struct intel_crtc_state *crtc_state);
 void intel_dsc_disable(const struct intel_crtc_state *crtc_state);
-int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
-				struct intel_crtc_state *pipe_config);
+int intel_dsc_compute_params(struct intel_encoder *encoder,
+			     struct intel_crtc_state *pipe_config);
+void intel_dsc_get_config(struct intel_encoder *encoder,
+			  struct intel_crtc_state *crtc_state);
 enum intel_display_power_domain
 intel_dsc_power_domain(const struct intel_crtc_state *crtc_state);
 
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 0ca49b1604c6..daf4fc3dab6f 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -23,7 +23,6 @@
  * Author: Jani Nikula <jani.nikula@intel.com>
  */
 
-#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 
 #include <drm/drm_atomic_helper.h>
@@ -261,9 +260,9 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder,
 	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
 						   base);
 	struct intel_connector *intel_connector = intel_dsi->attached_connector;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int ret;
 
 	DRM_DEBUG_KMS("\n");
@@ -319,7 +318,7 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder,
 static bool glk_dsi_enable_io(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 tmp;
 	bool cold_boot = false;
@@ -367,7 +366,7 @@ static bool glk_dsi_enable_io(struct intel_encoder *encoder)
 static void glk_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -438,7 +437,7 @@ static void glk_dsi_device_ready(struct intel_encoder *encoder)
 static void bxt_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -465,7 +464,7 @@ static void bxt_dsi_device_ready(struct intel_encoder *encoder)
 static void vlv_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -516,7 +515,7 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder)
 static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -546,7 +545,7 @@ static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
 static void glk_dsi_disable_mipi_io(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 tmp;
 
@@ -579,7 +578,7 @@ static void glk_dsi_clear_device_ready(struct intel_encoder *encoder)
 static void vlv_dsi_clear_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	DRM_DEBUG_KMS("\n");
@@ -624,8 +623,8 @@ static void intel_dsi_port_enable(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
@@ -681,7 +680,7 @@ static void intel_dsi_port_disable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -745,8 +744,8 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *pipe_config,
 				 const struct drm_connector_state *conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	struct drm_crtc *crtc = pipe_config->base.crtc;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct drm_crtc *crtc = pipe_config->uapi.crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum pipe pipe = intel_crtc->pipe;
@@ -793,9 +792,6 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 	if (!IS_GEMINILAKE(dev_priv))
 		intel_dsi_prepare(encoder, pipe_config);
 
-	/* Power on, try both CRC pmic gpio and VBT */
-	if (intel_dsi->gpio_panel)
-		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 1);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
 	intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
 
@@ -850,7 +846,7 @@ static void intel_dsi_disable(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	DRM_DEBUG_KMS("\n");
@@ -882,16 +878,22 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 }
 
 static void intel_dsi_post_disable(struct intel_encoder *encoder,
-				   const struct intel_crtc_state *pipe_config,
-				   const struct drm_connector_state *conn_state)
+				   const struct intel_crtc_state *old_crtc_state,
+				   const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
 	DRM_DEBUG_KMS("\n");
 
+	if (IS_GEN9_LP(dev_priv)) {
+		intel_crtc_vblank_off(old_crtc_state);
+
+		skl_scaler_disable(old_crtc_state);
+	}
+
 	if (is_vid_mode(intel_dsi)) {
 		for_each_dsi_port(port, intel_dsi->ports)
 			vlv_dsi_wait_for_fifo_empty(intel_dsi, port);
@@ -939,11 +941,8 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder,
 	/* Assert reset */
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET);
 
-	/* Power off, try both CRC pmic gpio and VBT */
 	intel_dsi_msleep(intel_dsi, intel_dsi->panel_off_delay);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_OFF);
-	if (intel_dsi->gpio_panel)
-		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 0);
 
 	/*
 	 * FIXME As we do with eDP, just make a note of the time here
@@ -956,7 +955,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	intel_wakeref_t wakeref;
 	enum port port;
 	bool active = false;
@@ -1032,10 +1031,10 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+					&pipe_config->hw.adjusted_mode;
 	struct drm_display_mode *adjusted_mode_sw;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	unsigned int lane_count = intel_dsi->lane_count;
 	unsigned int bpp, fmt;
 	enum port port;
@@ -1045,7 +1044,7 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 				crtc_hblank_start_sw, crtc_hblank_end_sw;
 
 	/* FIXME: hw readout should not depend on SW state */
-	adjusted_mode_sw = &crtc->config->base.adjusted_mode;
+	adjusted_mode_sw = &crtc->config->hw.adjusted_mode;
 
 	/*
 	 * Atleast one port is active as encoder->get_config called only if
@@ -1204,7 +1203,7 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 	}
 
 	if (pclk) {
-		pipe_config->base.adjusted_mode.crtc_clock = pclk;
+		pipe_config->hw.adjusted_mode.crtc_clock = pclk;
 		pipe_config->port_clock = pclk;
 	}
 }
@@ -1228,7 +1227,7 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(encoder));
 	enum port port;
 	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 	unsigned int lane_count = intel_dsi->lane_count;
@@ -1315,9 +1314,9 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(encoder));
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	enum port port;
 	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 	u32 val, tmp;
@@ -1506,7 +1505,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
 static void intel_dsi_unprepare(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -1533,12 +1532,9 @@ static void intel_dsi_unprepare(struct intel_encoder *encoder)
 
 static void intel_dsi_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-
-	/* dispose of the gpios */
-	if (intel_dsi->gpio_panel)
-		gpiod_put(intel_dsi->gpio_panel);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(encoder));
 
+	intel_dsi_vbt_gpio_cleanup(intel_dsi);
 	intel_encoder_destroy(encoder);
 }
 
@@ -1819,6 +1815,7 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 	struct drm_connector *connector;
 	struct drm_display_mode *current_mode, *fixed_mode;
 	enum port port;
+	enum pipe pipe;
 
 	DRM_DEBUG_KMS("\n");
 
@@ -1917,20 +1914,8 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 
 	vlv_dphy_param_init(intel_dsi);
 
-	/*
-	 * In case of BYT with CRC PMIC, we need to use GPIO for
-	 * Panel control.
-	 */
-	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
-	    (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC)) {
-		intel_dsi->gpio_panel =
-			gpiod_get(dev->dev, "panel", GPIOD_OUT_HIGH);
-
-		if (IS_ERR(intel_dsi->gpio_panel)) {
-			DRM_ERROR("Failed to own gpio for panel control\n");
-			intel_dsi->gpio_panel = NULL;
-		}
-	}
+	intel_dsi_vbt_gpio_init(intel_dsi,
+				intel_dsi_get_hw_state(intel_encoder, &pipe));
 
 	drm_connector_init(dev, connector, &intel_dsi_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
index 95f39cd0ce02..6b89e67b120f 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
@@ -117,7 +117,7 @@ int vlv_dsi_pll_compute(struct intel_encoder *encoder,
 			struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	int ret;
 	u32 dsi_clk;
 
@@ -255,7 +255,7 @@ u32 vlv_dsi_get_pclk(struct intel_encoder *encoder,
 		     struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 	u32 dsi_clock, pclk;
 	u32 pll_ctl, pll_div;
@@ -321,7 +321,7 @@ u32 bxt_dsi_get_pclk(struct intel_encoder *encoder,
 	u32 pclk;
 	u32 dsi_clk;
 	u32 dsi_ratio;
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 
@@ -341,7 +341,7 @@ void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 temp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
 	temp = I915_READ(MIPI_CTRL(port));
 	temp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
@@ -455,7 +455,7 @@ int bxt_dsi_pll_compute(struct intel_encoder *encoder,
 			struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u8 dsi_ratio, dsi_ratio_min, dsi_ratio_max;
 	u32 dsi_clk;
 
@@ -503,7 +503,7 @@ void bxt_dsi_pll_enable(struct intel_encoder *encoder,
 			const struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
diff --git a/drivers/gpu/drm/i915/gem/Makefile b/drivers/gpu/drm/i915/gem/Makefile
deleted file mode 100644
index 7e73aa587967..000000000000
--- a/drivers/gpu/drm/i915/gem/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index 18ee708585a9..34be4c0ee7c5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -27,27 +27,24 @@ static void __do_clflush(struct drm_i915_gem_object *obj)
 static int clflush_work(struct dma_fence_work *base)
 {
 	struct clflush *clflush = container_of(base, typeof(*clflush), base);
-	struct drm_i915_gem_object *obj = fetch_and_zero(&clflush->obj);
+	struct drm_i915_gem_object *obj = clflush->obj;
 	int err;
 
 	err = i915_gem_object_pin_pages(obj);
 	if (err)
-		goto put;
+		return err;
 
 	__do_clflush(obj);
 	i915_gem_object_unpin_pages(obj);
 
-put:
-	i915_gem_object_put(obj);
-	return err;
+	return 0;
 }
 
 static void clflush_release(struct dma_fence_work *base)
 {
 	struct clflush *clflush = container_of(base, typeof(*clflush), base);
 
-	if (clflush->obj)
-		i915_gem_object_put(clflush->obj);
+	i915_gem_object_put(clflush->obj);
 }
 
 static const struct dma_fence_work_ops clflush_ops = {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 42385277c684..a2e57e62af30 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -69,7 +69,10 @@
 
 #include <drm/i915_drm.h>
 
+#include "gt/gen6_ppgtt.h"
+#include "gt/intel_context.h"
 #include "gt/intel_engine_heartbeat.h"
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_lrc_reg.h"
 #include "gt/intel_ring.h"
@@ -169,12 +172,80 @@ lookup_user_engine(struct i915_gem_context *ctx,
 	return i915_gem_context_get_engine(ctx, idx);
 }
 
+static struct i915_address_space *
+context_get_vm_rcu(struct i915_gem_context *ctx)
+{
+	GEM_BUG_ON(!rcu_access_pointer(ctx->vm));
+
+	do {
+		struct i915_address_space *vm;
+
+		/*
+		 * We do not allow downgrading from full-ppgtt [to a shared
+		 * global gtt], so ctx->vm cannot become NULL.
+		 */
+		vm = rcu_dereference(ctx->vm);
+		if (!kref_get_unless_zero(&vm->ref))
+			continue;
+
+		/*
+		 * This ppgtt may have be reallocated between
+		 * the read and the kref, and reassigned to a third
+		 * context. In order to avoid inadvertent sharing
+		 * of this ppgtt with that third context (and not
+		 * src), we have to confirm that we have the same
+		 * ppgtt after passing through the strong memory
+		 * barrier implied by a successful
+		 * kref_get_unless_zero().
+		 *
+		 * Once we have acquired the current ppgtt of ctx,
+		 * we no longer care if it is released from ctx, as
+		 * it cannot be reallocated elsewhere.
+		 */
+
+		if (vm == rcu_access_pointer(ctx->vm))
+			return rcu_pointer_handoff(vm);
+
+		i915_vm_put(vm);
+	} while (1);
+}
+
+static void intel_context_set_gem(struct intel_context *ce,
+				  struct i915_gem_context *ctx)
+{
+	GEM_BUG_ON(rcu_access_pointer(ce->gem_context));
+	RCU_INIT_POINTER(ce->gem_context, ctx);
+
+	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))
+		ce->ring = __intel_context_ring_size(SZ_16K);
+
+	if (rcu_access_pointer(ctx->vm)) {
+		struct i915_address_space *vm;
+
+		rcu_read_lock();
+		vm = context_get_vm_rcu(ctx); /* hmm */
+		rcu_read_unlock();
+
+		i915_vm_put(ce->vm);
+		ce->vm = vm;
+	}
+
+	GEM_BUG_ON(ce->timeline);
+	if (ctx->timeline)
+		ce->timeline = intel_timeline_get(ctx->timeline);
+
+	if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
+	    intel_engine_has_semaphores(ce->engine))
+		__set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
+}
+
 static void __free_engines(struct i915_gem_engines *e, unsigned int count)
 {
 	while (count--) {
 		if (!e->engines[count])
 			continue;
 
+		RCU_INIT_POINTER(e->engines[count]->gem_context, NULL);
 		intel_context_put(e->engines[count]);
 	}
 	kfree(e);
@@ -211,12 +282,14 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
 		GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES);
 		GEM_BUG_ON(e->engines[engine->legacy_idx]);
 
-		ce = intel_context_create(ctx, engine);
+		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			__free_engines(e, e->num_engines + 1);
 			return ERR_CAST(ce);
 		}
 
+		intel_context_set_gem(ce, ctx);
+
 		e->engines[engine->legacy_idx] = ce;
 		e->num_engines = max(e->num_engines, engine->legacy_idx);
 	}
@@ -236,14 +309,10 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	free_engines(rcu_access_pointer(ctx->engines));
 	mutex_destroy(&ctx->engines_mutex);
 
-	kfree(ctx->jump_whitelist);
-
 	if (ctx->timeline)
 		intel_timeline_put(ctx->timeline);
 
-	kfree(ctx->name);
 	put_pid(ctx->pid);
-
 	mutex_destroy(&ctx->mutex);
 
 	kfree_rcu(ctx, rcu);
@@ -389,15 +458,6 @@ static void kill_context(struct i915_gem_context *ctx)
 	struct intel_context *ce;
 
 	/*
-	 * If we are already banned, it was due to a guilty request causing
-	 * a reset and the entire context being evicted from the GPU.
-	 */
-	if (i915_gem_context_is_banned(ctx))
-		return;
-
-	i915_gem_context_set_banned(ctx);
-
-	/*
 	 * Map the user's engine back to the actual engines; one virtual
 	 * engine will be mapped to multiple engines, and using ctx->engine[]
 	 * the same engine may be have multiple instances in the user's map.
@@ -407,6 +467,9 @@ static void kill_context(struct i915_gem_context *ctx)
 	for_each_gem_engine(ce, __context_engines_static(ctx), it) {
 		struct intel_engine_cs *engine;
 
+		if (intel_context_set_banned(ce))
+			continue;
+
 		/*
 		 * Check the current active state of this context; if we
 		 * are currently executing on the GPU we need to evict
@@ -427,11 +490,29 @@ static void kill_context(struct i915_gem_context *ctx)
 	}
 }
 
+static void set_closed_name(struct i915_gem_context *ctx)
+{
+	char *s;
+
+	/* Replace '[]' with '<>' to indicate closed in debug prints */
+
+	s = strrchr(ctx->name, '[');
+	if (!s)
+		return;
+
+	*s = '<';
+
+	s = strchr(s + 1, ']');
+	if (s)
+		*s = '>';
+}
+
 static void context_close(struct i915_gem_context *ctx)
 {
 	struct i915_address_space *vm;
 
 	i915_gem_context_set_closed(ctx);
+	set_closed_name(ctx);
 
 	mutex_lock(&ctx->mutex);
 
@@ -529,9 +610,6 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
-	ctx->jump_whitelist = NULL;
-	ctx->jump_whitelist_cmds = 0;
-
 	spin_lock(&i915->gem.contexts.lock);
 	list_add_tail(&ctx->link, &i915->gem.contexts.list);
 	spin_unlock(&i915->gem.contexts.lock);
@@ -628,7 +706,7 @@ i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
 	if (HAS_FULL_PPGTT(i915)) {
 		struct i915_ppgtt *ppgtt;
 
-		ppgtt = i915_ppgtt_create(i915);
+		ppgtt = i915_ppgtt_create(&i915->gt);
 		if (IS_ERR(ppgtt)) {
 			DRM_DEBUG_DRIVER("PPGTT setup failed (%ld)\n",
 					 PTR_ERR(ppgtt));
@@ -661,37 +739,6 @@ i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
 	return ctx;
 }
 
-static void
-destroy_kernel_context(struct i915_gem_context **ctxp)
-{
-	struct i915_gem_context *ctx;
-
-	/* Keep the context ref so that we can free it immediately ourselves */
-	ctx = i915_gem_context_get(fetch_and_zero(ctxp));
-	GEM_BUG_ON(!i915_gem_context_is_kernel(ctx));
-
-	context_close(ctx);
-	i915_gem_context_free(ctx);
-}
-
-struct i915_gem_context *
-i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio)
-{
-	struct i915_gem_context *ctx;
-
-	ctx = i915_gem_create_context(i915, 0);
-	if (IS_ERR(ctx))
-		return ctx;
-
-	i915_gem_context_clear_bannable(ctx);
-	i915_gem_context_set_persistence(ctx);
-	ctx->sched.priority = I915_USER_PRIORITY(prio);
-
-	GEM_BUG_ON(!i915_gem_context_is_kernel(ctx));
-
-	return ctx;
-}
-
 static void init_contexts(struct i915_gem_contexts *gc)
 {
 	spin_lock_init(&gc->lock);
@@ -701,41 +748,19 @@ static void init_contexts(struct i915_gem_contexts *gc)
 	init_llist_head(&gc->free_list);
 }
 
-int i915_gem_init_contexts(struct drm_i915_private *i915)
+void i915_gem_init__contexts(struct drm_i915_private *i915)
 {
-	struct i915_gem_context *ctx;
-
-	/* Reassure ourselves we are only called once */
-	GEM_BUG_ON(i915->kernel_context);
-
 	init_contexts(&i915->gem.contexts);
-
-	/* lowest priority; idle task */
-	ctx = i915_gem_context_create_kernel(i915, I915_PRIORITY_MIN);
-	if (IS_ERR(ctx)) {
-		DRM_ERROR("Failed to create default global context\n");
-		return PTR_ERR(ctx);
-	}
-	i915->kernel_context = ctx;
-
 	DRM_DEBUG_DRIVER("%s context support initialized\n",
 			 DRIVER_CAPS(i915)->has_logical_contexts ?
 			 "logical" : "fake");
-	return 0;
 }
 
 void i915_gem_driver_release__contexts(struct drm_i915_private *i915)
 {
-	destroy_kernel_context(&i915->kernel_context);
 	flush_work(&i915->gem.contexts.free_work);
 }
 
-static int context_idr_cleanup(int id, void *p, void *data)
-{
-	context_close(p);
-	return 0;
-}
-
 static int vm_idr_cleanup(int id, void *p, void *data)
 {
 	i915_vm_put(p);
@@ -743,7 +768,8 @@ static int vm_idr_cleanup(int id, void *p, void *data)
 }
 
 static int gem_context_register(struct i915_gem_context *ctx,
-				struct drm_i915_file_private *fpriv)
+				struct drm_i915_file_private *fpriv,
+				u32 *id)
 {
 	struct i915_address_space *vm;
 	int ret;
@@ -757,24 +783,14 @@ static int gem_context_register(struct i915_gem_context *ctx,
 	mutex_unlock(&ctx->mutex);
 
 	ctx->pid = get_task_pid(current, PIDTYPE_PID);
-	ctx->name = kasprintf(GFP_KERNEL, "%s[%d]",
-			      current->comm, pid_nr(ctx->pid));
-	if (!ctx->name) {
-		ret = -ENOMEM;
-		goto err_pid;
-	}
+	snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
+		 current->comm, pid_nr(ctx->pid));
 
 	/* And finally expose ourselves to userspace via the idr */
-	mutex_lock(&fpriv->context_idr_lock);
-	ret = idr_alloc(&fpriv->context_idr, ctx, 0, 0, GFP_KERNEL);
-	mutex_unlock(&fpriv->context_idr_lock);
-	if (ret >= 0)
-		goto out;
+	ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL);
+	if (ret)
+		put_pid(fetch_and_zero(&ctx->pid));
 
-	kfree(fetch_and_zero(&ctx->name));
-err_pid:
-	put_pid(fetch_and_zero(&ctx->pid));
-out:
 	return ret;
 }
 
@@ -784,11 +800,11 @@ int i915_gem_context_open(struct drm_i915_private *i915,
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct i915_gem_context *ctx;
 	int err;
+	u32 id;
 
-	mutex_init(&file_priv->context_idr_lock);
-	mutex_init(&file_priv->vm_idr_lock);
+	xa_init_flags(&file_priv->context_xa, XA_FLAGS_ALLOC);
 
-	idr_init(&file_priv->context_idr);
+	mutex_init(&file_priv->vm_idr_lock);
 	idr_init_base(&file_priv->vm_idr, 1);
 
 	ctx = i915_gem_create_context(i915, 0);
@@ -797,22 +813,19 @@ int i915_gem_context_open(struct drm_i915_private *i915,
 		goto err;
 	}
 
-	err = gem_context_register(ctx, file_priv);
+	err = gem_context_register(ctx, file_priv, &id);
 	if (err < 0)
 		goto err_ctx;
 
-	GEM_BUG_ON(i915_gem_context_is_kernel(ctx));
-	GEM_BUG_ON(err > 0);
-
+	GEM_BUG_ON(id);
 	return 0;
 
 err_ctx:
 	context_close(ctx);
 err:
 	idr_destroy(&file_priv->vm_idr);
-	idr_destroy(&file_priv->context_idr);
+	xa_destroy(&file_priv->context_xa);
 	mutex_destroy(&file_priv->vm_idr_lock);
-	mutex_destroy(&file_priv->context_idr_lock);
 	return err;
 }
 
@@ -820,10 +833,12 @@ void i915_gem_context_close(struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct drm_i915_private *i915 = file_priv->dev_priv;
+	struct i915_gem_context *ctx;
+	unsigned long idx;
 
-	idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
-	idr_destroy(&file_priv->context_idr);
-	mutex_destroy(&file_priv->context_idr_lock);
+	xa_for_each(&file_priv->context_xa, idx, ctx)
+		context_close(ctx);
+	xa_destroy(&file_priv->context_xa);
 
 	idr_for_each(&file_priv->vm_idr, vm_idr_cleanup, NULL);
 	idr_destroy(&file_priv->vm_idr);
@@ -847,7 +862,7 @@ int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (args->flags)
 		return -EINVAL;
 
-	ppgtt = i915_ppgtt_create(i915);
+	ppgtt = i915_ppgtt_create(&i915->gt);
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
@@ -1012,7 +1027,7 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
 		return -ENODEV;
 
 	rcu_read_lock();
-	vm = i915_vm_get(ctx->vm);
+	vm = context_get_vm_rcu(ctx);
 	rcu_read_unlock();
 
 	ret = mutex_lock_interruptible(&file_priv->vm_idr_lock);
@@ -1049,7 +1064,7 @@ static void set_ppgtt_barrier(void *data)
 
 static int emit_ppgtt_update(struct i915_request *rq, void *data)
 {
-	struct i915_address_space *vm = rq->hw_context->vm;
+	struct i915_address_space *vm = rq->context->vm;
 	struct intel_engine_cs *engine = rq->engine;
 	u32 base = engine->mmio_base;
 	u32 *cs;
@@ -1096,9 +1111,6 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 		}
 		*cs++ = MI_NOOP;
 		intel_ring_advance(rq, cs);
-	} else {
-		/* ppGTT is not part of the legacy context image */
-		gen6_ppgtt_pin(i915_vm_to_ppgtt(vm));
 	}
 
 	return 0;
@@ -1106,10 +1118,20 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 
 static bool skip_ppgtt_update(struct intel_context *ce, void *data)
 {
+	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))
+		return true;
+
 	if (HAS_LOGICAL_RING_CONTEXTS(ce->engine->i915))
-		return !ce->state;
-	else
-		return !atomic_read(&ce->pin_count);
+		return false;
+
+	if (!atomic_read(&ce->pin_count))
+		return true;
+
+	/* ppGTT is not part of the legacy context image */
+	if (gen6_ppgtt_pin(i915_vm_to_ppgtt(ce->vm)))
+		return true;
+
+	return false;
 }
 
 static int set_ppgtt(struct drm_i915_file_private *file_priv,
@@ -1214,12 +1236,14 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 	 * image, or into the registers directory, does not stick). Pristine
 	 * and idle contexts will be configured on pinning.
 	 */
-	if (!intel_context_is_pinned(ce))
+	if (!intel_context_pin_if_active(ce))
 		return 0;
 
-	rq = i915_request_create(ce->engine->kernel_context);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
+	rq = intel_engine_create_kernel_request(ce->engine);
+	if (IS_ERR(rq)) {
+		ret = PTR_ERR(rq);
+		goto out_unpin;
+	}
 
 	/* Serialise with the remote context */
 	ret = intel_context_prepare_remote_request(ce, rq);
@@ -1227,6 +1251,8 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 		ret = gen8_emit_rpcs_config(rq, ce, sseu);
 
 	i915_request_add(rq);
+out_unpin:
+	intel_context_unpin(ce);
 	return ret;
 }
 
@@ -1485,12 +1511,14 @@ set_engines__load_balance(struct i915_user_extension __user *base, void *data)
 		}
 	}
 
-	ce = intel_execlists_create_virtual(set->ctx, siblings, n);
+	ce = intel_execlists_create_virtual(siblings, n);
 	if (IS_ERR(ce)) {
 		err = PTR_ERR(ce);
 		goto out_siblings;
 	}
 
+	intel_context_set_gem(ce, set->ctx);
+
 	if (cmpxchg(&set->engines->engines[idx], NULL, ce)) {
 		intel_context_put(ce);
 		err = -EEXIST;
@@ -1660,12 +1688,14 @@ set_engines(struct i915_gem_context *ctx,
 			return -ENOENT;
 		}
 
-		ce = intel_context_create(ctx, engine);
+		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			__free_engines(set.engines, n);
 			return PTR_ERR(ce);
 		}
 
+		intel_context_set_gem(ce, ctx);
+
 		set.engines->engines[n] = ce;
 	}
 	set.engines->num_engines = num_engines;
@@ -1806,6 +1836,44 @@ set_persistence(struct i915_gem_context *ctx,
 	return __context_set_persistence(ctx, args->value);
 }
 
+static void __apply_priority(struct intel_context *ce, void *arg)
+{
+	struct i915_gem_context *ctx = arg;
+
+	if (!intel_engine_has_semaphores(ce->engine))
+		return;
+
+	if (ctx->sched.priority >= I915_PRIORITY_NORMAL)
+		intel_context_set_use_semaphores(ce);
+	else
+		intel_context_clear_use_semaphores(ce);
+}
+
+static int set_priority(struct i915_gem_context *ctx,
+			const struct drm_i915_gem_context_param *args)
+{
+	s64 priority = args->value;
+
+	if (args->size)
+		return -EINVAL;
+
+	if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
+		return -ENODEV;
+
+	if (priority > I915_CONTEXT_MAX_USER_PRIORITY ||
+	    priority < I915_CONTEXT_MIN_USER_PRIORITY)
+		return -EINVAL;
+
+	if (priority > I915_CONTEXT_DEFAULT_PRIORITY &&
+	    !capable(CAP_SYS_NICE))
+		return -EPERM;
+
+	ctx->sched.priority = I915_USER_PRIORITY(priority);
+	context_apply_all(ctx, __apply_priority, ctx);
+
+	return 0;
+}
+
 static int ctx_setparam(struct drm_i915_file_private *fpriv,
 			struct i915_gem_context *ctx,
 			struct drm_i915_gem_context_param *args)
@@ -1852,23 +1920,7 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 		break;
 
 	case I915_CONTEXT_PARAM_PRIORITY:
-		{
-			s64 priority = args->value;
-
-			if (args->size)
-				ret = -EINVAL;
-			else if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
-				ret = -ENODEV;
-			else if (priority > I915_CONTEXT_MAX_USER_PRIORITY ||
-				 priority < I915_CONTEXT_MIN_USER_PRIORITY)
-				ret = -EINVAL;
-			else if (priority > I915_CONTEXT_DEFAULT_PRIORITY &&
-				 !capable(CAP_SYS_NICE))
-				ret = -EPERM;
-			else
-				ctx->sched.priority =
-					I915_USER_PRIORITY(priority);
-		}
+		ret = set_priority(ctx, args);
 		break;
 
 	case I915_CONTEXT_PARAM_SSEU:
@@ -1948,20 +2000,23 @@ static int clone_engines(struct i915_gem_context *dst,
 		 */
 		if (intel_engine_is_virtual(engine))
 			clone->engines[n] =
-				intel_execlists_clone_virtual(dst, engine);
+				intel_execlists_clone_virtual(engine);
 		else
-			clone->engines[n] = intel_context_create(dst, engine);
+			clone->engines[n] = intel_context_create(engine);
 		if (IS_ERR_OR_NULL(clone->engines[n])) {
 			__free_engines(clone, n);
 			goto err_unlock;
 		}
+
+		intel_context_set_gem(clone->engines[n], dst);
 	}
 	clone->num_engines = n;
 
 	user_engines = i915_gem_context_user_engines(src);
 	i915_gem_context_unlock_engines(src);
 
-	free_engines(dst->engines);
+	/* Serialised by constructor */
+	free_engines(__context_engines_static(dst));
 	RCU_INIT_POINTER(dst->engines, clone);
 	if (user_engines)
 		i915_gem_context_set_user_engines(dst);
@@ -1996,7 +2051,8 @@ static int clone_sseu(struct i915_gem_context *dst,
 	unsigned long n;
 	int err;
 
-	clone = dst->engines; /* no locking required; sole access */
+	/* no locking required; sole access under constructor*/
+	clone = __context_engines_static(dst);
 	if (e->num_engines != clone->num_engines) {
 		err = -EINVAL;
 		goto unlock;
@@ -2041,47 +2097,21 @@ static int clone_vm(struct i915_gem_context *dst,
 	struct i915_address_space *vm;
 	int err = 0;
 
-	rcu_read_lock();
-	do {
-		vm = rcu_dereference(src->vm);
-		if (!vm)
-			break;
-
-		if (!kref_get_unless_zero(&vm->ref))
-			continue;
-
-		/*
-		 * This ppgtt may have be reallocated between
-		 * the read and the kref, and reassigned to a third
-		 * context. In order to avoid inadvertent sharing
-		 * of this ppgtt with that third context (and not
-		 * src), we have to confirm that we have the same
-		 * ppgtt after passing through the strong memory
-		 * barrier implied by a successful
-		 * kref_get_unless_zero().
-		 *
-		 * Once we have acquired the current ppgtt of src,
-		 * we no longer care if it is released from src, as
-		 * it cannot be reallocated elsewhere.
-		 */
-
-		if (vm == rcu_access_pointer(src->vm))
-			break;
+	if (!rcu_access_pointer(src->vm))
+		return 0;
 
-		i915_vm_put(vm);
-	} while (1);
+	rcu_read_lock();
+	vm = context_get_vm_rcu(src);
 	rcu_read_unlock();
 
-	if (vm) {
-		if (!mutex_lock_interruptible(&dst->mutex)) {
-			__assign_ppgtt(dst, vm);
-			mutex_unlock(&dst->mutex);
-		} else {
-			err = -EINTR;
-		}
-		i915_vm_put(vm);
+	if (!mutex_lock_interruptible(&dst->mutex)) {
+		__assign_ppgtt(dst, vm);
+		mutex_unlock(&dst->mutex);
+	} else {
+		err = -EINTR;
 	}
 
+	i915_vm_put(vm);
 	return err;
 }
 
@@ -2153,6 +2183,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_gem_context_create_ext *args = data;
 	struct create_ext ext_data;
 	int ret;
+	u32 id;
 
 	if (!DRIVER_CAPS(i915)->has_logical_contexts)
 		return -ENODEV;
@@ -2184,11 +2215,11 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 			goto err_ctx;
 	}
 
-	ret = gem_context_register(ext_data.ctx, ext_data.fpriv);
+	ret = gem_context_register(ext_data.ctx, ext_data.fpriv, &id);
 	if (ret < 0)
 		goto err_ctx;
 
-	args->ctx_id = ret;
+	args->ctx_id = id;
 	DRM_DEBUG("HW context %d created\n", args->ctx_id);
 
 	return 0;
@@ -2211,11 +2242,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 	if (!args->ctx_id)
 		return -ENOENT;
 
-	if (mutex_lock_interruptible(&file_priv->context_idr_lock))
-		return -EINTR;
-
-	ctx = idr_remove(&file_priv->context_idr, args->ctx_id);
-	mutex_unlock(&file_priv->context_idr_lock);
+	ctx = xa_erase(&file_priv->context_xa, args->ctx_id);
 	if (!ctx)
 		return -ENOENT;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 18e50a769a6e..3ae61a355d87 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -13,7 +13,6 @@
 
 #include "i915_drv.h"
 #include "i915_gem.h"
-#include "i915_gem_gtt.h"
 #include "i915_scheduler.h"
 #include "intel_device_info.h"
 
@@ -91,26 +90,6 @@ static inline void i915_gem_context_clear_persistence(struct i915_gem_context *c
 	clear_bit(UCONTEXT_PERSISTENCE, &ctx->user_flags);
 }
 
-static inline bool i915_gem_context_is_banned(const struct i915_gem_context *ctx)
-{
-	return test_bit(CONTEXT_BANNED, &ctx->flags);
-}
-
-static inline void i915_gem_context_set_banned(struct i915_gem_context *ctx)
-{
-	set_bit(CONTEXT_BANNED, &ctx->flags);
-}
-
-static inline bool i915_gem_context_force_single_submission(const struct i915_gem_context *ctx)
-{
-	return test_bit(CONTEXT_FORCE_SINGLE_SUBMISSION, &ctx->flags);
-}
-
-static inline void i915_gem_context_set_force_single_submission(struct i915_gem_context *ctx)
-{
-	__set_bit(CONTEXT_FORCE_SINGLE_SUBMISSION, &ctx->flags);
-}
-
 static inline bool
 i915_gem_context_user_engines(const struct i915_gem_context *ctx)
 {
@@ -129,31 +108,8 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx)
 	clear_bit(CONTEXT_USER_ENGINES, &ctx->flags);
 }
 
-static inline bool
-i915_gem_context_nopreempt(const struct i915_gem_context *ctx)
-{
-	return test_bit(CONTEXT_NOPREEMPT, &ctx->flags);
-}
-
-static inline void
-i915_gem_context_set_nopreempt(struct i915_gem_context *ctx)
-{
-	set_bit(CONTEXT_NOPREEMPT, &ctx->flags);
-}
-
-static inline void
-i915_gem_context_clear_nopreempt(struct i915_gem_context *ctx)
-{
-	clear_bit(CONTEXT_NOPREEMPT, &ctx->flags);
-}
-
-static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
-{
-	return !ctx->file_priv;
-}
-
 /* i915_gem_context.c */
-int __must_check i915_gem_init_contexts(struct drm_i915_private *i915);
+void i915_gem_init__contexts(struct drm_i915_private *i915);
 void i915_gem_driver_release__contexts(struct drm_i915_private *i915);
 
 int i915_gem_context_open(struct drm_i915_private *i915,
@@ -178,9 +134,6 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 int i915_gem_context_reset_stats_ioctl(struct drm_device *dev, void *data,
 				       struct drm_file *file);
 
-struct i915_gem_context *
-i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio);
-
 static inline struct i915_gem_context *
 i915_gem_context_get(struct i915_gem_context *ctx)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 3870dd5daaa0..017ca803ab47 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -100,15 +100,6 @@ struct i915_gem_context {
 	 */
 	struct pid *pid;
 
-	/**
-	 * @name: arbitrary name
-	 *
-	 * A name is constructed for the context from the creator's process
-	 * name, pid and user handle in order to uniquely identify the
-	 * context in messages.
-	 */
-	const char *name;
-
 	/** link: place with &drm_i915_private.context_list */
 	struct list_head link;
 	struct llist_node free_link;
@@ -143,11 +134,8 @@ struct i915_gem_context {
 	 * @flags: small set of booleans
 	 */
 	unsigned long flags;
-#define CONTEXT_BANNED			0
-#define CONTEXT_CLOSED			1
-#define CONTEXT_FORCE_SINGLE_SUBMISSION	2
-#define CONTEXT_USER_ENGINES		3
-#define CONTEXT_NOPREEMPT		4
+#define CONTEXT_CLOSED			0
+#define CONTEXT_USER_ENGINES		1
 
 	struct mutex mutex;
 
@@ -177,12 +165,14 @@ struct i915_gem_context {
 	 */
 	struct radix_tree_root handles_vma;
 
-	/** jump_whitelist: Bit array for tracking cmds during cmdparsing
-	 *  Guarded by struct_mutex
+	/**
+	 * @name: arbitrary name, used for user debug
+	 *
+	 * A name is constructed for the context from the creator's process
+	 * name, pid and user handle in order to uniquely identify the
+	 * context in messages.
 	 */
-	unsigned long *jump_whitelist;
-	/** jump_whitelist_cmds: No of cmd slots available */
-	u32 jump_whitelist_cmds;
+	char name[TASK_COMM_LEN + 8];
 };
 
 #endif /* __I915_GEM_CONTEXT_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index eaea49d08eb5..372b57ca0efc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -93,40 +93,6 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	i915_gem_object_unpin_map(obj);
 }
 
-static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
-	struct page *page;
-
-	if (page_num >= obj->base.size >> PAGE_SHIFT)
-		return NULL;
-
-	if (!i915_gem_object_has_struct_page(obj))
-		return NULL;
-
-	if (i915_gem_object_pin_pages(obj))
-		return NULL;
-
-	/* Synchronisation is left to the caller (via .begin_cpu_access()) */
-	page = i915_gem_object_get_page(obj, page_num);
-	if (IS_ERR(page))
-		goto err_unpin;
-
-	return kmap(page);
-
-err_unpin:
-	i915_gem_object_unpin_pages(obj);
-	return NULL;
-}
-
-static void i915_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
-{
-	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
-
-	kunmap(virt_to_page(addr));
-	i915_gem_object_unpin_pages(obj);
-}
-
 static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
@@ -195,8 +161,6 @@ static const struct dma_buf_ops i915_dmabuf_ops =  {
 	.map_dma_buf = i915_gem_map_dma_buf,
 	.unmap_dma_buf = i915_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
-	.map = i915_gem_dmabuf_kmap,
-	.unmap = i915_gem_dmabuf_kunmap,
 	.mmap = i915_gem_dmabuf_mmap,
 	.vmap = i915_gem_dmabuf_vmap,
 	.vunmap = i915_gem_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index f86400a191b0..0cc40e77bbd2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -12,6 +12,8 @@
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
 #include "i915_vma.h"
+#include "i915_gem_lmem.h"
+#include "i915_gem_mman.h"
 
 static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj)
 {
@@ -148,9 +150,17 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	GEM_BUG_ON((obj->write_domain & ~I915_GEM_DOMAIN_GTT) != 0);
 	obj->read_domains |= I915_GEM_DOMAIN_GTT;
 	if (write) {
+		struct i915_vma *vma;
+
 		obj->read_domains = I915_GEM_DOMAIN_GTT;
 		obj->write_domain = I915_GEM_DOMAIN_GTT;
 		obj->mm.dirty = true;
+
+		spin_lock(&obj->vma.lock);
+		for_each_ggtt_vma(vma, obj)
+			if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
+				i915_vma_set_ggtt_write(vma);
+		spin_unlock(&obj->vma.lock);
 	}
 
 	i915_gem_object_unpin_pages(obj);
@@ -175,138 +185,34 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 				    enum i915_cache_level cache_level)
 {
-	struct i915_vma *vma;
 	int ret;
 
-	assert_object_held(obj);
-
 	if (obj->cache_level == cache_level)
 		return 0;
 
-	/* Inspect the list of currently bound VMA and unbind any that would
-	 * be invalid given the new cache-level. This is principally to
-	 * catch the issue of the CS prefetch crossing page boundaries and
-	 * reading an invalid PTE on older architectures.
-	 */
-restart:
-	list_for_each_entry(vma, &obj->vma.list, obj_link) {
-		if (!drm_mm_node_allocated(&vma->node))
-			continue;
-
-		if (i915_vma_is_pinned(vma)) {
-			DRM_DEBUG("can not change the cache level of pinned objects\n");
-			return -EBUSY;
-		}
-
-		if (!i915_vma_is_closed(vma) &&
-		    i915_gem_valid_gtt_space(vma, cache_level))
-			continue;
-
-		ret = i915_vma_unbind(vma);
-		if (ret)
-			return ret;
-
-		/* As unbinding may affect other elements in the
-		 * obj->vma_list (due to side-effects from retiring
-		 * an active vma), play safe and restart the iterator.
-		 */
-		goto restart;
-	}
+	ret = i915_gem_object_wait(obj,
+				   I915_WAIT_INTERRUPTIBLE |
+				   I915_WAIT_ALL,
+				   MAX_SCHEDULE_TIMEOUT);
+	if (ret)
+		return ret;
 
-	/* We can reuse the existing drm_mm nodes but need to change the
-	 * cache-level on the PTE. We could simply unbind them all and
-	 * rebind with the correct cache-level on next use. However since
-	 * we already have a valid slot, dma mapping, pages etc, we may as
-	 * rewrite the PTE in the belief that doing so tramples upon less
-	 * state and so involves less work.
-	 */
-	if (atomic_read(&obj->bind_count)) {
-		struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	ret = i915_gem_object_lock_interruptible(obj);
+	if (ret)
+		return ret;
 
-		/* Before we change the PTE, the GPU must not be accessing it.
-		 * If we wait upon the object, we know that all the bound
-		 * VMA are no longer active.
-		 */
-		ret = i915_gem_object_wait(obj,
-					   I915_WAIT_INTERRUPTIBLE |
-					   I915_WAIT_ALL,
-					   MAX_SCHEDULE_TIMEOUT);
-		if (ret)
-			return ret;
-
-		if (!HAS_LLC(i915) && cache_level != I915_CACHE_NONE) {
-			intel_wakeref_t wakeref =
-				intel_runtime_pm_get(&i915->runtime_pm);
-
-			/*
-			 * Access to snoopable pages through the GTT is
-			 * incoherent and on some machines causes a hard
-			 * lockup. Relinquish the CPU mmaping to force
-			 * userspace to refault in the pages and we can
-			 * then double check if the GTT mapping is still
-			 * valid for that pointer access.
-			 */
-			ret = mutex_lock_interruptible(&i915->ggtt.vm.mutex);
-			if (ret) {
-				intel_runtime_pm_put(&i915->runtime_pm,
-						     wakeref);
-				return ret;
-			}
-
-			if (obj->userfault_count)
-				__i915_gem_object_release_mmap(obj);
-
-			/*
-			 * As we no longer need a fence for GTT access,
-			 * we can relinquish it now (and so prevent having
-			 * to steal a fence from someone else on the next
-			 * fence request). Note GPU activity would have
-			 * dropped the fence as all snoopable access is
-			 * supposed to be linear.
-			 */
-			for_each_ggtt_vma(vma, obj) {
-				ret = i915_vma_revoke_fence(vma);
-				if (ret)
-					break;
-			}
-			mutex_unlock(&i915->ggtt.vm.mutex);
-			intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-			if (ret)
-				return ret;
-		} else {
-			/*
-			 * We either have incoherent backing store and
-			 * so no GTT access or the architecture is fully
-			 * coherent. In such cases, existing GTT mmaps
-			 * ignore the cache bit in the PTE and we can
-			 * rewrite it without confusing the GPU or having
-			 * to force userspace to fault back in its mmaps.
-			 */
-		}
-
-		list_for_each_entry(vma, &obj->vma.list, obj_link) {
-			if (!drm_mm_node_allocated(&vma->node))
-				continue;
-
-			/* Wait for an earlier async bind, need to rewrite it */
-			ret = i915_vma_sync(vma);
-			if (ret)
-				return ret;
-
-			ret = i915_vma_bind(vma, cache_level, PIN_UPDATE, NULL);
-			if (ret)
-				return ret;
-		}
+	/* Always invalidate stale cachelines */
+	if (obj->cache_level != cache_level) {
+		i915_gem_object_set_cache_coherency(obj, cache_level);
+		obj->cache_dirty = true;
 	}
 
-	list_for_each_entry(vma, &obj->vma.list, obj_link) {
-		if (i915_vm_has_cache_coloring(vma->vm))
-			vma->node.color = cache_level;
-	}
-	i915_gem_object_set_cache_coherency(obj, cache_level);
-	obj->cache_dirty = true; /* Always invalidate stale cachelines */
+	i915_gem_object_unlock(obj);
 
-	return 0;
+	/* The cache-level will be applied when each vma is rebound. */
+	return i915_gem_object_unbind(obj,
+				      I915_GEM_OBJECT_UNBIND_ACTIVE |
+				      I915_GEM_OBJECT_UNBIND_BARRIER);
 }
 
 int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
@@ -387,20 +293,7 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	if (obj->cache_level == level)
-		goto out;
-
-	ret = i915_gem_object_wait(obj,
-				   I915_WAIT_INTERRUPTIBLE,
-				   MAX_SCHEDULE_TIMEOUT);
-	if (ret)
-		goto out;
-
-	ret = i915_gem_object_lock_interruptible(obj);
-	if (ret == 0) {
-		ret = i915_gem_object_set_cache_level(obj, level);
-		i915_gem_object_unlock(obj);
-	}
+	ret = i915_gem_object_set_cache_level(obj, level);
 
 out:
 	i915_gem_object_put(obj);
@@ -419,10 +312,13 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     const struct i915_ggtt_view *view,
 				     unsigned int flags)
 {
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 	int ret;
 
-	assert_object_held(obj);
+	/* Frame buffer must be in LMEM (no migration yet) */
+	if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj))
+		return ERR_PTR(-EINVAL);
 
 	/*
 	 * The display engine is not coherent with the LLC cache on gen6.  As
@@ -435,7 +331,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 * with that bit in the PTE to main memory with just one PIPE_CONTROL.
 	 */
 	ret = i915_gem_object_set_cache_level(obj,
-					      HAS_WT(to_i915(obj->base.dev)) ?
+					      HAS_WT(i915) ?
 					      I915_CACHE_WT : I915_CACHE_NONE);
 	if (ret)
 		return ERR_PTR(ret);
@@ -462,13 +358,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 
 	vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
 
-	__i915_gem_object_flush_for_display(obj);
-
-	/*
-	 * It should now be out of any other write domains, and we can update
-	 * the domain values for our changes.
-	 */
-	obj->read_domains |= I915_GEM_DOMAIN_GTT;
+	i915_gem_object_flush_if_display(obj);
 
 	return vma;
 }
@@ -479,8 +369,11 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 	struct i915_vma *vma;
 
 	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+	if (!atomic_read(&obj->bind_count))
+		return;
 
 	mutex_lock(&i915->ggtt.vm.mutex);
+	spin_lock(&obj->vma.lock);
 	for_each_ggtt_vma(vma, obj) {
 		if (!drm_mm_node_allocated(&vma->node))
 			continue;
@@ -488,6 +381,7 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 		GEM_BUG_ON(vma->vm != &i915->ggtt.vm);
 		list_move_tail(&vma->vm_link, &vma->vm->bound_list);
 	}
+	spin_unlock(&obj->vma.lock);
 	mutex_unlock(&i915->ggtt.vm.mutex);
 
 	if (i915_gem_object_is_shrinkable(obj)) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index bc3a67226163..d5a0f5ae4a8b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -25,6 +25,7 @@
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
 #include "i915_gem_ioctls.h"
+#include "i915_sw_fence_work.h"
 #include "i915_trace.h"
 
 enum {
@@ -228,6 +229,7 @@ struct i915_execbuffer {
 
 	struct i915_request *request; /** our request to build */
 	struct i915_vma *batch; /** identity of the batch obj/vma */
+	struct i915_vma *trampoline; /** trampoline used for chaining */
 
 	/** actual size of execobj[] as we may extend it for the cmdparser */
 	unsigned int buffer_count;
@@ -253,7 +255,6 @@ struct i915_execbuffer {
 		bool has_fence : 1;
 		bool needs_unfenced : 1;
 
-		struct intel_context *ce;
 		struct i915_request *rq;
 		u32 *rq_cmd;
 		unsigned int rq_size;
@@ -277,25 +278,6 @@ struct i915_execbuffer {
 
 #define exec_entry(EB, VMA) (&(EB)->exec[(VMA)->exec_flags - (EB)->flags])
 
-/*
- * Used to convert any address to canonical form.
- * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS,
- * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the
- * addresses to be in a canonical form:
- * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct
- * canonical form [63:48] == [47]."
- */
-#define GEN8_HIGH_ADDRESS_BIT 47
-static inline u64 gen8_canonical_addr(u64 address)
-{
-	return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT);
-}
-
-static inline u64 gen8_noncanonical_addr(u64 address)
-{
-	return address & GENMASK_ULL(GEN8_HIGH_ADDRESS_BIT, 0);
-}
-
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 {
 	return intel_engine_requires_cmd_parser(eb->engine) ||
@@ -748,9 +730,6 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 	unsigned int i, batch;
 	int err;
 
-	if (unlikely(i915_gem_context_is_banned(eb->gem_context)))
-		return -EIO;
-
 	INIT_LIST_HEAD(&eb->relocs);
 	INIT_LIST_HEAD(&eb->unbound);
 
@@ -886,9 +865,6 @@ static void eb_destroy(const struct i915_execbuffer *eb)
 {
 	GEM_BUG_ON(eb->reloc_cache.rq);
 
-	if (eb->reloc_cache.ce)
-		intel_context_put(eb->reloc_cache.ce);
-
 	if (eb->lut_size > 0)
 		kfree(eb->buckets);
 }
@@ -912,7 +888,6 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->has_fence = cache->gen < 4;
 	cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
 	cache->node.flags = 0;
-	cache->ce = NULL;
 	cache->rq = NULL;
 	cache->rq_size = 0;
 }
@@ -1182,7 +1157,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	if (err)
 		goto err_unmap;
 
-	rq = intel_context_create_request(cache->ce);
+	rq = i915_request_create(eb->context);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_unpin;
@@ -1246,36 +1221,9 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 	if (unlikely(!cache->rq)) {
 		int err;
 
-		/* If we need to copy for the cmdparser, we will stall anyway */
-		if (eb_use_cmdparser(eb))
-			return ERR_PTR(-EWOULDBLOCK);
-
 		if (!intel_engine_can_store_dword(eb->engine))
 			return ERR_PTR(-ENODEV);
 
-		if (!cache->ce) {
-			struct intel_context *ce;
-
-			/*
-			 * The CS pre-parser can pre-fetch commands across
-			 * memory sync points and starting gen12 it is able to
-			 * pre-fetch across BB_START and BB_END boundaries
-			 * (within the same context). We therefore use a
-			 * separate context gen12+ to guarantee that the reloc
-			 * writes land before the parser gets to the target
-			 * memory location.
-			 */
-			if (cache->gen >= 12)
-				ce = intel_context_create(eb->context->gem_context,
-							  eb->engine);
-			else
-				ce = intel_context_get(eb->context);
-			if (IS_ERR(ce))
-				return ERR_CAST(ce);
-
-			cache->ce = ce;
-		}
-
 		err = __reloc_gpu_alloc(eb, vma, len);
 		if (unlikely(err))
 			return ERR_PTR(err);
@@ -1943,15 +1891,15 @@ err_skip:
 	return err;
 }
 
-static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
+static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 {
 	if (exec->flags & __I915_EXEC_ILLEGAL_FLAGS)
-		return false;
+		return -EINVAL;
 
 	/* Kernel clipping was a DRI1 misfeature */
 	if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) {
 		if (exec->num_cliprects || exec->cliprects_ptr)
-			return false;
+			return -EINVAL;
 	}
 
 	if (exec->DR4 == 0xffffffff) {
@@ -1959,12 +1907,12 @@ static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 		exec->DR4 = 0;
 	}
 	if (exec->DR1 || exec->DR4)
-		return false;
+		return -EINVAL;
 
 	if ((exec->batch_start_offset | exec->batch_len) & 0x7)
-		return false;
+		return -EINVAL;
 
-	return true;
+	return 0;
 }
 
 static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
@@ -1993,99 +1941,179 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 }
 
 static struct i915_vma *
-shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj)
+shadow_batch_pin(struct drm_i915_gem_object *obj,
+		 struct i915_address_space *vm,
+		 unsigned int flags)
 {
-	struct drm_i915_private *dev_priv = eb->i915;
-	struct i915_vma * const vma = *eb->vma;
-	struct i915_address_space *vm;
-	u64 flags;
+	struct i915_vma *vma;
+	int err;
 
-	/*
-	 * PPGTT backed shadow buffers must be mapped RO, to prevent
-	 * post-scan tampering
-	 */
-	if (CMDPARSER_USES_GGTT(dev_priv)) {
-		flags = PIN_GLOBAL;
-		vm = &dev_priv->ggtt.vm;
-	} else if (vma->vm->has_read_only) {
-		flags = PIN_USER;
-		vm = vma->vm;
-		i915_gem_object_set_readonly(obj);
-	} else {
-		DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
-		return ERR_PTR(-EINVAL);
-	}
+	vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(vma))
+		return vma;
+
+	err = i915_vma_pin(vma, 0, 0, flags);
+	if (err)
+		return ERR_PTR(err);
 
-	return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags);
+	return vma;
 }
 
-static struct i915_vma *eb_parse(struct i915_execbuffer *eb)
+struct eb_parse_work {
+	struct dma_fence_work base;
+	struct intel_engine_cs *engine;
+	struct i915_vma *batch;
+	struct i915_vma *shadow;
+	struct i915_vma *trampoline;
+	unsigned int batch_offset;
+	unsigned int batch_length;
+};
+
+static int __eb_parse(struct dma_fence_work *work)
 {
-	struct intel_engine_pool_node *pool;
-	struct i915_vma *vma;
-	u64 batch_start;
-	u64 shadow_batch_start;
+	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
+
+	return intel_engine_cmd_parser(pw->engine,
+				       pw->batch,
+				       pw->batch_offset,
+				       pw->batch_length,
+				       pw->shadow,
+				       pw->trampoline);
+}
+
+static const struct dma_fence_work_ops eb_parse_ops = {
+	.name = "eb_parse",
+	.work = __eb_parse,
+};
+
+static int eb_parse_pipeline(struct i915_execbuffer *eb,
+			     struct i915_vma *shadow,
+			     struct i915_vma *trampoline)
+{
+	struct eb_parse_work *pw;
 	int err;
 
-	pool = intel_engine_get_pool(eb->engine, eb->batch_len);
-	if (IS_ERR(pool))
-		return ERR_CAST(pool);
+	pw = kzalloc(sizeof(*pw), GFP_KERNEL);
+	if (!pw)
+		return -ENOMEM;
 
-	vma = shadow_batch_pin(eb, pool->obj);
-	if (IS_ERR(vma))
-		goto err;
+	dma_fence_work_init(&pw->base, &eb_parse_ops);
 
-	batch_start = gen8_canonical_addr(eb->batch->node.start) +
-		      eb->batch_start_offset;
+	pw->engine = eb->engine;
+	pw->batch = eb->batch;
+	pw->batch_offset = eb->batch_start_offset;
+	pw->batch_length = eb->batch_len;
+	pw->shadow = shadow;
+	pw->trampoline = trampoline;
 
-	shadow_batch_start = gen8_canonical_addr(vma->node.start);
+	dma_resv_lock(pw->batch->resv, NULL);
 
-	err = intel_engine_cmd_parser(eb->gem_context,
-				      eb->engine,
-				      eb->batch->obj,
-				      batch_start,
-				      eb->batch_start_offset,
-				      eb->batch_len,
-				      pool->obj,
-				      shadow_batch_start);
+	err = dma_resv_reserve_shared(pw->batch->resv, 1);
+	if (err)
+		goto err_batch_unlock;
 
-	if (err) {
-		i915_vma_unpin(vma);
+	/* Wait for all writes (and relocs) into the batch to complete */
+	err = i915_sw_fence_await_reservation(&pw->base.chain,
+					      pw->batch->resv, NULL, false,
+					      0, I915_FENCE_GFP);
+	if (err < 0)
+		goto err_batch_unlock;
+
+	/* Keep the batch alive and unwritten as we parse */
+	dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma);
+
+	dma_resv_unlock(pw->batch->resv);
 
+	/* Force execution to wait for completion of the parser */
+	dma_resv_lock(shadow->resv, NULL);
+	dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
+	dma_resv_unlock(shadow->resv);
+
+	dma_fence_work_commit(&pw->base);
+	return 0;
+
+err_batch_unlock:
+	dma_resv_unlock(pw->batch->resv);
+	kfree(pw);
+	return err;
+}
+
+static int eb_parse(struct i915_execbuffer *eb)
+{
+	struct intel_engine_pool_node *pool;
+	struct i915_vma *shadow, *trampoline;
+	unsigned int len;
+	int err;
+
+	if (!eb_use_cmdparser(eb))
+		return 0;
+
+	len = eb->batch_len;
+	if (!CMDPARSER_USES_GGTT(eb->i915)) {
 		/*
-		 * Unsafe GGTT-backed buffers can still be submitted safely
-		 * as non-secure.
-		 * For PPGTT backing however, we have no choice but to forcibly
-		 * reject unsafe buffers
+		 * ppGTT backed shadow buffers must be mapped RO, to prevent
+		 * post-scan tampering
 		 */
-		if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES))
-			/* Execute original buffer non-secure */
-			vma = NULL;
-		else
-			vma = ERR_PTR(err);
+		if (!eb->context->vm->has_read_only) {
+			DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
+			return -EINVAL;
+		}
+	} else {
+		len += I915_CMD_PARSER_TRAMPOLINE_SIZE;
+	}
+
+	pool = intel_engine_get_pool(eb->engine, len);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+
+	shadow = shadow_batch_pin(pool->obj, eb->context->vm, PIN_USER);
+	if (IS_ERR(shadow)) {
+		err = PTR_ERR(shadow);
 		goto err;
 	}
+	i915_gem_object_set_readonly(shadow->obj);
+
+	trampoline = NULL;
+	if (CMDPARSER_USES_GGTT(eb->i915)) {
+		trampoline = shadow;
+
+		shadow = shadow_batch_pin(pool->obj,
+					  &eb->engine->gt->ggtt->vm,
+					  PIN_GLOBAL);
+		if (IS_ERR(shadow)) {
+			err = PTR_ERR(shadow);
+			shadow = trampoline;
+			goto err_shadow;
+		}
+
+		eb->batch_flags |= I915_DISPATCH_SECURE;
+	}
+
+	err = eb_parse_pipeline(eb, shadow, trampoline);
+	if (err)
+		goto err_trampoline;
 
-	eb->vma[eb->buffer_count] = i915_vma_get(vma);
+	eb->vma[eb->buffer_count] = i915_vma_get(shadow);
 	eb->flags[eb->buffer_count] =
 		__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF;
-	vma->exec_flags = &eb->flags[eb->buffer_count];
+	shadow->exec_flags = &eb->flags[eb->buffer_count];
 	eb->buffer_count++;
 
+	eb->trampoline = trampoline;
 	eb->batch_start_offset = 0;
-	eb->batch = vma;
+	eb->batch = shadow;
 
-	if (CMDPARSER_USES_GGTT(eb->i915))
-		eb->batch_flags |= I915_DISPATCH_SECURE;
-
-	/* eb->batch_len unchanged */
-
-	vma->private = pool;
-	return vma;
+	shadow->private = pool;
+	return 0;
 
+err_trampoline:
+	if (trampoline)
+		i915_vma_unpin(trampoline);
+err_shadow:
+	i915_vma_unpin(shadow);
 err:
 	intel_engine_pool_put(pool);
-	return vma;
+	return err;
 }
 
 static void
@@ -2134,8 +2162,18 @@ static int eb_submit(struct i915_execbuffer *eb)
 	if (err)
 		return err;
 
-	if (i915_gem_context_nopreempt(eb->gem_context))
-		eb->request->flags |= I915_REQUEST_NOPREEMPT;
+	if (eb->trampoline) {
+		GEM_BUG_ON(eb->batch_start_offset);
+		err = eb->engine->emit_bb_start(eb->request,
+						eb->trampoline->node.start +
+						eb->batch_len,
+						0, 0);
+		if (err)
+			return err;
+	}
+
+	if (intel_context_nopreempt(eb->context))
+		__set_bit(I915_FENCE_FLAG_NOPREEMPT, &eb->request->fence.flags);
 
 	return 0;
 }
@@ -2220,6 +2258,9 @@ static int __eb_pin_engine(struct i915_execbuffer *eb, struct intel_context *ce)
 	if (err)
 		return err;
 
+	if (unlikely(intel_context_is_banned(ce)))
+		return -EIO;
+
 	/*
 	 * Pinning the contexts may generate requests in order to acquire
 	 * GGTT space, so do this first before we reserve a seqno for
@@ -2515,6 +2556,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.buffer_count = args->buffer_count;
 	eb.batch_start_offset = args->batch_start_offset;
 	eb.batch_len = args->batch_len;
+	eb.trampoline = NULL;
 
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
@@ -2606,15 +2648,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (eb.batch_len == 0)
 		eb.batch_len = eb.batch->size - eb.batch_start_offset;
 
-	if (eb_use_cmdparser(&eb)) {
-		struct i915_vma *vma;
-
-		vma = eb_parse(&eb);
-		if (IS_ERR(vma)) {
-			err = PTR_ERR(vma);
-			goto err_vma;
-		}
-	}
+	err = eb_parse(&eb);
+	if (err)
+		goto err_vma;
 
 	/*
 	 * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
@@ -2720,6 +2756,8 @@ err_batch_unpin:
 err_vma:
 	if (eb.exec)
 		eb_release_vmas(&eb);
+	if (eb.trampoline)
+		i915_vma_unpin(eb.trampoline);
 	mutex_unlock(&dev->struct_mutex);
 err_engine:
 	eb_unpin_engine(&eb);
@@ -2789,8 +2827,9 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 	exec2.flags = I915_EXEC_RENDER;
 	i915_execbuffer2_set_context_id(exec2, 0);
 
-	if (!i915_gem_check_execbuffer(&exec2))
-		return -EINVAL;
+	err = i915_gem_check_execbuffer(&exec2);
+	if (err)
+		return err;
 
 	/* Copy in the exec list from userland */
 	exec_list = kvmalloc_array(count, sizeof(*exec_list),
@@ -2867,8 +2906,9 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	if (!i915_gem_check_execbuffer(args))
-		return -EINVAL;
+	err = i915_gem_check_execbuffer(args);
+	if (err)
+		return err;
 
 	/* Allocate an extra slot for use by the command parser */
 	exec2_list = kvmalloc_array(count + 1, eb_element_size(),
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h b/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
index ddc7f2a52b3e..87d8b27f426d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
@@ -28,8 +28,8 @@ int i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
 			   struct drm_file *file);
 int i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
-int i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
-			    struct drm_file *file);
+int i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data,
+			       struct drm_file *file);
 int i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file);
 int i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
index 0e2bf6b7e143..70543c83df06 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
@@ -16,46 +16,6 @@ const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
 	.release = i915_gem_object_release_memory_region,
 };
 
-/* XXX: Time to vfunc your life up? */
-void __iomem *
-i915_gem_object_lmem_io_map_page(struct drm_i915_gem_object *obj,
-				 unsigned long n)
-{
-	resource_size_t offset;
-
-	offset = i915_gem_object_get_dma_address(obj, n);
-	offset -= obj->mm.region->region.start;
-
-	return io_mapping_map_wc(&obj->mm.region->iomap, offset, PAGE_SIZE);
-}
-
-void __iomem *
-i915_gem_object_lmem_io_map_page_atomic(struct drm_i915_gem_object *obj,
-					unsigned long n)
-{
-	resource_size_t offset;
-
-	offset = i915_gem_object_get_dma_address(obj, n);
-	offset -= obj->mm.region->region.start;
-
-	return io_mapping_map_atomic_wc(&obj->mm.region->iomap, offset);
-}
-
-void __iomem *
-i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
-			    unsigned long n,
-			    unsigned long size)
-{
-	resource_size_t offset;
-
-	GEM_BUG_ON(!i915_gem_object_is_contiguous(obj));
-
-	offset = i915_gem_object_get_dma_address(obj, n);
-	offset -= obj->mm.region->region.start;
-
-	return io_mapping_map_wc(&obj->mm.region->iomap, offset, size);
-}
-
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
 {
 	return obj->ops == &i915_gem_lmem_obj_ops;
@@ -79,9 +39,6 @@ __i915_gem_lmem_object_create(struct intel_memory_region *mem,
 	struct drm_i915_private *i915 = mem->i915;
 	struct drm_i915_gem_object *obj;
 
-	if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
-		return ERR_PTR(-E2BIG);
-
 	obj = i915_gem_object_alloc();
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
index 7c176b8b7d2f..fc3f15580fe3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
@@ -14,14 +14,6 @@ struct intel_memory_region;
 
 extern const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops;
 
-void __iomem *i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
-					  unsigned long n, unsigned long size);
-void __iomem *i915_gem_object_lmem_io_map_page(struct drm_i915_gem_object *obj,
-					       unsigned long n);
-void __iomem *
-i915_gem_object_lmem_io_map_page_atomic(struct drm_i915_gem_object *obj,
-					unsigned long n);
-
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
 
 struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index e3002849844b..b9fdac2f9003 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -4,7 +4,9 @@
  * Copyright © 2014-2016 Intel Corporation
  */
 
+#include <linux/anon_inodes.h>
 #include <linux/mman.h>
+#include <linux/pfn_t.h>
 #include <linux/sizes.h>
 
 #include "gt/intel_gt.h"
@@ -14,7 +16,9 @@
 #include "i915_gem_gtt.h"
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
+#include "i915_gem_mman.h"
 #include "i915_trace.h"
+#include "i915_user_extensions.h"
 #include "i915_vma.h"
 
 static inline bool
@@ -144,6 +148,9 @@ static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
  * 3 - Remove implicit set-domain(GTT) and synchronisation on initial
  *     pagefault; swapin remains transparent.
  *
+ * 4 - Support multiple fault handlers per object depending on object's
+ *     backing storage (a.k.a. MMAP_OFFSET).
+ *
  * Restrictions:
  *
  *  * snoopable objects cannot be accessed via the GTT. It can cause machine
@@ -171,7 +178,7 @@ static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
  */
 int i915_gem_mmap_gtt_version(void)
 {
-	return 3;
+	return 4;
 }
 
 static inline struct i915_ggtt_view
@@ -197,29 +204,80 @@ compute_partial_view(const struct drm_i915_gem_object *obj,
 	return view;
 }
 
-/**
- * i915_gem_fault - fault a page into the GTT
- * @vmf: fault info
- *
- * The fault handler is set up by drm_gem_mmap() when a object is GTT mapped
- * from userspace.  The fault handler takes care of binding the object to
- * the GTT (if needed), allocating and programming a fence register (again,
- * only if needed based on whether the old reg is still valid or the object
- * is tiled) and inserting a new PTE into the faulting process.
- *
- * Note that the faulting process may involve evicting existing objects
- * from the GTT and/or fence registers to make room.  So performance may
- * suffer if the GTT working set is large or there are few fence registers
- * left.
- *
- * The current feature set supported by i915_gem_fault() and thus GTT mmaps
- * is exposed via I915_PARAM_MMAP_GTT_VERSION (see i915_gem_mmap_gtt_version).
- */
-vm_fault_t i915_gem_fault(struct vm_fault *vmf)
+static vm_fault_t i915_error_to_vmf_fault(int err)
+{
+	switch (err) {
+	default:
+		WARN_ONCE(err, "unhandled error in %s: %i\n", __func__, err);
+		/* fallthrough */
+	case -EIO: /* shmemfs failure from swap device */
+	case -EFAULT: /* purged object */
+	case -ENODEV: /* bad object, how did you get here! */
+	case -ENXIO: /* unable to access backing store (on device) */
+		return VM_FAULT_SIGBUS;
+
+	case -ENOSPC: /* shmemfs allocation failure */
+	case -ENOMEM: /* our allocation failure */
+		return VM_FAULT_OOM;
+
+	case 0:
+	case -EAGAIN:
+	case -ERESTARTSYS:
+	case -EINTR:
+	case -EBUSY:
+		/*
+		 * EBUSY is ok: this just means that another thread
+		 * already did the job.
+		 */
+		return VM_FAULT_NOPAGE;
+	}
+}
+
+static vm_fault_t vm_fault_cpu(struct vm_fault *vmf)
+{
+	struct vm_area_struct *area = vmf->vma;
+	struct i915_mmap_offset *mmo = area->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
+	resource_size_t iomap;
+	int err;
+
+	/* Sanity check that we allow writing into this object */
+	if (unlikely(i915_gem_object_is_readonly(obj) &&
+		     area->vm_flags & VM_WRITE))
+		return VM_FAULT_SIGBUS;
+
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
+		goto out;
+
+	iomap = -1;
+	if (!i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_STRUCT_PAGE)) {
+		iomap = obj->mm.region->iomap.base;
+		iomap -= obj->mm.region->region.start;
+	}
+
+	/* PTEs are revoked in obj->ops->put_pages() */
+	err = remap_io_sg(area,
+			  area->vm_start, area->vm_end - area->vm_start,
+			  obj->mm.pages->sgl, iomap);
+
+	if (area->vm_flags & VM_WRITE) {
+		GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+		obj->mm.dirty = true;
+	}
+
+	i915_gem_object_unpin_pages(obj);
+
+out:
+	return i915_error_to_vmf_fault(err);
+}
+
+static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 {
 #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT)
 	struct vm_area_struct *area = vmf->vma;
-	struct drm_i915_gem_object *obj = to_intel_bo(area->vm_private_data);
+	struct i915_mmap_offset *mmo = area->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct intel_runtime_pm *rpm = &i915->runtime_pm;
@@ -312,6 +370,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		list_add(&obj->userfault_link, &i915->ggtt.userfault_list);
 	mutex_unlock(&i915->ggtt.vm.mutex);
 
+	/* Track the mmo associated with the fenced vma */
+	vma->mmo = mmo;
+
 	if (IS_ACTIVE(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND))
 		intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
@@ -332,67 +393,36 @@ err_rpm:
 	intel_runtime_pm_put(rpm, wakeref);
 	i915_gem_object_unpin_pages(obj);
 err:
-	switch (ret) {
-	default:
-		WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
-		/* fallthrough */
-	case -EIO: /* shmemfs failure from swap device */
-	case -EFAULT: /* purged object */
-	case -ENODEV: /* bad object, how did you get here! */
-		return VM_FAULT_SIGBUS;
-
-	case -ENOSPC: /* shmemfs allocation failure */
-	case -ENOMEM: /* our allocation failure */
-		return VM_FAULT_OOM;
-
-	case 0:
-	case -EAGAIN:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	}
+	return i915_error_to_vmf_fault(ret);
 }
 
-void __i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
+void __i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
 
 	GEM_BUG_ON(!obj->userfault_count);
 
-	obj->userfault_count = 0;
-	list_del(&obj->userfault_link);
-	drm_vma_node_unmap(&obj->base.vma_node,
-			   obj->base.dev->anon_inode->i_mapping);
-
 	for_each_ggtt_vma(vma, obj)
-		i915_vma_unset_userfault(vma);
+		i915_vma_revoke_mmap(vma);
+
+	GEM_BUG_ON(obj->userfault_count);
 }
 
-/**
- * i915_gem_object_release_mmap - remove physical page mappings
- * @obj: obj in question
- *
- * Preserve the reservation of the mmapping with the DRM core code, but
- * relinquish ownership of the pages back to the system.
- *
+/*
  * It is vital that we remove the page mapping if we have mapped a tiled
  * object through the GTT and then lose the fence register due to
  * resource pressure. Similarly if the object has been moved out of the
  * aperture, than pages mapped into userspace must be revoked. Removing the
  * mapping will then trigger a page fault on the next user access, allowing
- * fixup by i915_gem_fault().
+ * fixup by vm_fault_gtt().
  */
-void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
+static void i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	intel_wakeref_t wakeref;
 
-	/* Serialisation between user GTT access and our code depends upon
+	/*
+	 * Serialisation between user GTT access and our code depends upon
 	 * revoking the CPU's PTE whilst the mutex is held. The next user
 	 * pagefault then has to wait until we release the mutex.
 	 *
@@ -406,9 +436,10 @@ void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
 	if (!obj->userfault_count)
 		goto out;
 
-	__i915_gem_object_release_mmap(obj);
+	__i915_gem_object_release_mmap_gtt(obj);
 
-	/* Ensure that the CPU's PTE are revoked and there are not outstanding
+	/*
+	 * Ensure that the CPU's PTE are revoked and there are not outstanding
 	 * memory transactions from userspace before we return. The TLB
 	 * flushing implied above by changing the PTE above *should* be
 	 * sufficient, an extra barrier here just provides us with a bit
@@ -422,54 +453,151 @@ out:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
 
-static int create_mmap_offset(struct drm_i915_gem_object *obj)
+void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj)
+{
+	struct i915_mmap_offset *mmo;
+
+	spin_lock(&obj->mmo.lock);
+	list_for_each_entry(mmo, &obj->mmo.offsets, offset) {
+		/*
+		 * vma_node_unmap for GTT mmaps handled already in
+		 * __i915_gem_object_release_mmap_gtt
+		 */
+		if (mmo->mmap_type == I915_MMAP_TYPE_GTT)
+			continue;
+
+		spin_unlock(&obj->mmo.lock);
+		drm_vma_node_unmap(&mmo->vma_node,
+				   obj->base.dev->anon_inode->i_mapping);
+		spin_lock(&obj->mmo.lock);
+	}
+	spin_unlock(&obj->mmo.lock);
+}
+
+/**
+ * i915_gem_object_release_mmap - remove physical page mappings
+ * @obj: obj in question
+ *
+ * Preserve the reservation of the mmapping with the DRM core code, but
+ * relinquish ownership of the pages back to the system.
+ */
+void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
+{
+	i915_gem_object_release_mmap_gtt(obj);
+	i915_gem_object_release_mmap_offset(obj);
+}
+
+static struct i915_mmap_offset *
+mmap_offset_attach(struct drm_i915_gem_object *obj,
+		   enum i915_mmap_type mmap_type,
+		   struct drm_file *file)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct intel_gt *gt = &i915->gt;
+	struct i915_mmap_offset *mmo;
 	int err;
 
-	err = drm_gem_create_mmap_offset(&obj->base);
+	mmo = kmalloc(sizeof(*mmo), GFP_KERNEL);
+	if (!mmo)
+		return ERR_PTR(-ENOMEM);
+
+	mmo->obj = obj;
+	mmo->dev = obj->base.dev;
+	mmo->file = file;
+	mmo->mmap_type = mmap_type;
+	drm_vma_node_reset(&mmo->vma_node);
+
+	err = drm_vma_offset_add(mmo->dev->vma_offset_manager, &mmo->vma_node,
+				 obj->base.size / PAGE_SIZE);
 	if (likely(!err))
-		return 0;
+		goto out;
 
 	/* Attempt to reap some mmap space from dead objects */
-	err = intel_gt_retire_requests_timeout(gt, MAX_SCHEDULE_TIMEOUT);
+	err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT);
 	if (err)
-		return err;
+		goto err;
 
 	i915_gem_drain_freed_objects(i915);
-	return drm_gem_create_mmap_offset(&obj->base);
+	err = drm_vma_offset_add(mmo->dev->vma_offset_manager, &mmo->vma_node,
+				 obj->base.size / PAGE_SIZE);
+	if (err)
+		goto err;
+
+out:
+	if (file)
+		drm_vma_node_allow(&mmo->vma_node, file);
+
+	spin_lock(&obj->mmo.lock);
+	list_add(&mmo->offset, &obj->mmo.offsets);
+	spin_unlock(&obj->mmo.lock);
+
+	return mmo;
+
+err:
+	kfree(mmo);
+	return ERR_PTR(err);
 }
 
-int
-i915_gem_mmap_gtt(struct drm_file *file,
-		  struct drm_device *dev,
-		  u32 handle,
-		  u64 *offset)
+static int
+__assign_mmap_offset(struct drm_file *file,
+		     u32 handle,
+		     enum i915_mmap_type mmap_type,
+		     u64 *offset)
 {
 	struct drm_i915_gem_object *obj;
-	int ret;
+	struct i915_mmap_offset *mmo;
+	int err;
 
 	obj = i915_gem_object_lookup(file, handle);
 	if (!obj)
 		return -ENOENT;
 
-	if (i915_gem_object_never_bind_ggtt(obj)) {
-		ret = -ENODEV;
+	if (mmap_type == I915_MMAP_TYPE_GTT &&
+	    i915_gem_object_never_bind_ggtt(obj)) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	if (mmap_type != I915_MMAP_TYPE_GTT &&
+	    !i915_gem_object_type_has(obj,
+				      I915_GEM_OBJECT_HAS_STRUCT_PAGE |
+				      I915_GEM_OBJECT_HAS_IOMEM)) {
+		err = -ENODEV;
 		goto out;
 	}
 
-	ret = create_mmap_offset(obj);
-	if (ret == 0)
-		*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
+	mmo = mmap_offset_attach(obj, mmap_type, file);
+	if (IS_ERR(mmo)) {
+		err = PTR_ERR(mmo);
+		goto out;
+	}
 
+	*offset = drm_vma_node_offset_addr(&mmo->vma_node);
+	err = 0;
 out:
 	i915_gem_object_put(obj);
-	return ret;
+	return err;
+}
+
+int
+i915_gem_dumb_mmap_offset(struct drm_file *file,
+			  struct drm_device *dev,
+			  u32 handle,
+			  u64 *offset)
+{
+	enum i915_mmap_type mmap_type;
+
+	if (boot_cpu_has(X86_FEATURE_PAT))
+		mmap_type = I915_MMAP_TYPE_WC;
+	else if (!i915_ggtt_has_aperture(&to_i915(dev)->ggtt))
+		return -ENODEV;
+	else
+		mmap_type = I915_MMAP_TYPE_GTT;
+
+	return __assign_mmap_offset(file, handle, mmap_type, offset);
 }
 
 /**
- * i915_gem_mmap_gtt_ioctl - prepare an object for GTT mmap'ing
+ * i915_gem_mmap_offset_ioctl - prepare an object for GTT mmap'ing
  * @dev: DRM device
  * @data: GTT mapping ioctl data
  * @file: GEM object info
@@ -484,12 +612,237 @@ out:
  * userspace.
  */
 int
-i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
-			struct drm_file *file)
+i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data,
+			   struct drm_file *file)
+{
+	struct drm_i915_private *i915 = to_i915(dev);
+	struct drm_i915_gem_mmap_offset *args = data;
+	enum i915_mmap_type type;
+	int err;
+
+	/*
+	 * Historically we failed to check args.pad and args.offset
+	 * and so we cannot use those fields for user input and we cannot
+	 * add -EINVAL for them as the ABI is fixed, i.e. old userspace
+	 * may be feeding in garbage in those fields.
+	 *
+	 * if (args->pad) return -EINVAL; is verbotten!
+	 */
+
+	err = i915_user_extensions(u64_to_user_ptr(args->extensions),
+				   NULL, 0, NULL);
+	if (err)
+		return err;
+
+	switch (args->flags) {
+	case I915_MMAP_OFFSET_GTT:
+		if (!i915_ggtt_has_aperture(&i915->ggtt))
+			return -ENODEV;
+		type = I915_MMAP_TYPE_GTT;
+		break;
+
+	case I915_MMAP_OFFSET_WC:
+		if (!boot_cpu_has(X86_FEATURE_PAT))
+			return -ENODEV;
+		type = I915_MMAP_TYPE_WC;
+		break;
+
+	case I915_MMAP_OFFSET_WB:
+		type = I915_MMAP_TYPE_WB;
+		break;
+
+	case I915_MMAP_OFFSET_UC:
+		if (!boot_cpu_has(X86_FEATURE_PAT))
+			return -ENODEV;
+		type = I915_MMAP_TYPE_UC;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return __assign_mmap_offset(file, args->handle, type, &args->offset);
+}
+
+static void vm_open(struct vm_area_struct *vma)
 {
-	struct drm_i915_gem_mmap_gtt *args = data;
+	struct i915_mmap_offset *mmo = vma->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
 
-	return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset);
+	GEM_BUG_ON(!obj);
+	i915_gem_object_get(obj);
+}
+
+static void vm_close(struct vm_area_struct *vma)
+{
+	struct i915_mmap_offset *mmo = vma->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
+
+	GEM_BUG_ON(!obj);
+	i915_gem_object_put(obj);
+}
+
+static const struct vm_operations_struct vm_ops_gtt = {
+	.fault = vm_fault_gtt,
+	.open = vm_open,
+	.close = vm_close,
+};
+
+static const struct vm_operations_struct vm_ops_cpu = {
+	.fault = vm_fault_cpu,
+	.open = vm_open,
+	.close = vm_close,
+};
+
+static int singleton_release(struct inode *inode, struct file *file)
+{
+	struct drm_i915_private *i915 = file->private_data;
+
+	cmpxchg(&i915->gem.mmap_singleton, file, NULL);
+	drm_dev_put(&i915->drm);
+
+	return 0;
+}
+
+static const struct file_operations singleton_fops = {
+	.owner = THIS_MODULE,
+	.release = singleton_release,
+};
+
+static struct file *mmap_singleton(struct drm_i915_private *i915)
+{
+	struct file *file;
+
+	rcu_read_lock();
+	file = i915->gem.mmap_singleton;
+	if (file && !get_file_rcu(file))
+		file = NULL;
+	rcu_read_unlock();
+	if (file)
+		return file;
+
+	file = anon_inode_getfile("i915.gem", &singleton_fops, i915, O_RDWR);
+	if (IS_ERR(file))
+		return file;
+
+	/* Everyone shares a single global address space */
+	file->f_mapping = i915->drm.anon_inode->i_mapping;
+
+	smp_store_mb(i915->gem.mmap_singleton, file);
+	drm_dev_get(&i915->drm);
+
+	return file;
+}
+
+/*
+ * This overcomes the limitation in drm_gem_mmap's assignment of a
+ * drm_gem_object as the vma->vm_private_data. Since we need to
+ * be able to resolve multiple mmap offsets which could be tied
+ * to a single gem object.
+ */
+int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct drm_vma_offset_node *node;
+	struct drm_file *priv = filp->private_data;
+	struct drm_device *dev = priv->minor->dev;
+	struct i915_mmap_offset *mmo = NULL;
+	struct drm_gem_object *obj = NULL;
+	struct file *anon;
+
+	if (drm_dev_is_unplugged(dev))
+		return -ENODEV;
+
+	drm_vma_offset_lock_lookup(dev->vma_offset_manager);
+	node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager,
+						  vma->vm_pgoff,
+						  vma_pages(vma));
+	if (likely(node)) {
+		mmo = container_of(node, struct i915_mmap_offset,
+				   vma_node);
+		/*
+		 * In our dependency chain, the drm_vma_offset_node
+		 * depends on the validity of the mmo, which depends on
+		 * the gem object. However the only reference we have
+		 * at this point is the mmo (as the parent of the node).
+		 * Try to check if the gem object was at least cleared.
+		 */
+		if (!mmo || !mmo->obj) {
+			drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
+			return -EINVAL;
+		}
+		/*
+		 * Skip 0-refcnted objects as it is in the process of being
+		 * destroyed and will be invalid when the vma manager lock
+		 * is released.
+		 */
+		obj = &mmo->obj->base;
+		if (!kref_get_unless_zero(&obj->refcount))
+			obj = NULL;
+	}
+	drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
+	if (!obj)
+		return -EINVAL;
+
+	if (!drm_vma_node_is_allowed(node, priv)) {
+		drm_gem_object_put_unlocked(obj);
+		return -EACCES;
+	}
+
+	if (i915_gem_object_is_readonly(to_intel_bo(obj))) {
+		if (vma->vm_flags & VM_WRITE) {
+			drm_gem_object_put_unlocked(obj);
+			return -EINVAL;
+		}
+		vma->vm_flags &= ~VM_MAYWRITE;
+	}
+
+	anon = mmap_singleton(to_i915(obj->dev));
+	if (IS_ERR(anon)) {
+		drm_gem_object_put_unlocked(obj);
+		return PTR_ERR(anon);
+	}
+
+	vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_private_data = mmo;
+
+	/*
+	 * We keep the ref on mmo->obj, not vm_file, but we require
+	 * vma->vm_file->f_mapping, see vma_link(), for later revocation.
+	 * Our userspace is accustomed to having per-file resource cleanup
+	 * (i.e. contexts, objects and requests) on their close(fd), which
+	 * requires avoiding extraneous references to their filp, hence why
+	 * we prefer to use an anonymous file for their mmaps.
+	 */
+	fput(vma->vm_file);
+	vma->vm_file = anon;
+
+	switch (mmo->mmap_type) {
+	case I915_MMAP_TYPE_WC:
+		vma->vm_page_prot =
+			pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+		vma->vm_ops = &vm_ops_cpu;
+		break;
+
+	case I915_MMAP_TYPE_WB:
+		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+		vma->vm_ops = &vm_ops_cpu;
+		break;
+
+	case I915_MMAP_TYPE_UC:
+		vma->vm_page_prot =
+			pgprot_noncached(vm_get_page_prot(vma->vm_flags));
+		vma->vm_ops = &vm_ops_cpu;
+		break;
+
+	case I915_MMAP_TYPE_GTT:
+		vma->vm_page_prot =
+			pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+		vma->vm_ops = &vm_ops_gtt;
+		break;
+	}
+	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+
+	return 0;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.h b/drivers/gpu/drm/i915/gem/i915_gem_mman.h
new file mode 100644
index 000000000000..862e01b7cb69
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.h
@@ -0,0 +1,31 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __I915_GEM_MMAN_H__
+#define __I915_GEM_MMAN_H__
+
+#include <linux/mm_types.h>
+#include <linux/types.h>
+
+struct drm_device;
+struct drm_file;
+struct drm_i915_gem_object;
+struct file;
+struct i915_mmap_offset;
+struct mutex;
+
+int i915_gem_mmap_gtt_version(void);
+int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma);
+
+int i915_gem_dumb_mmap_offset(struct drm_file *file_priv,
+			      struct drm_device *dev,
+			      u32 handle, u64 *offset);
+
+void __i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj);
+void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj);
+void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index a596548c07bf..46bacc82ddc4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -22,11 +22,14 @@
  *
  */
 
+#include <linux/sched/mm.h>
+
 #include "display/intel_frontbuffer.h"
 #include "gt/intel_gt.h"
 #include "i915_drv.h"
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
+#include "i915_gem_mman.h"
 #include "i915_gem_object.h"
 #include "i915_globals.h"
 #include "i915_trace.h"
@@ -59,6 +62,9 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 
 	INIT_LIST_HEAD(&obj->lut_list);
 
+	spin_lock_init(&obj->mmo.lock);
+	INIT_LIST_HEAD(&obj->mmo.offsets);
+
 	init_rcu_head(&obj->rcu);
 
 	obj->ops = ops;
@@ -95,6 +101,7 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file)
 	struct drm_i915_gem_object *obj = to_intel_bo(gem);
 	struct drm_i915_file_private *fpriv = file->driver_priv;
 	struct i915_lut_handle *lut, *ln;
+	struct i915_mmap_offset *mmo;
 	LIST_HEAD(close);
 
 	i915_gem_object_lock(obj);
@@ -109,6 +116,17 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file)
 	}
 	i915_gem_object_unlock(obj);
 
+	spin_lock(&obj->mmo.lock);
+	list_for_each_entry(mmo, &obj->mmo.offsets, offset) {
+		if (mmo->file != file)
+			continue;
+
+		spin_unlock(&obj->mmo.lock);
+		drm_vma_node_revoke(&mmo->vma_node, file);
+		spin_lock(&obj->mmo.lock);
+	}
+	spin_unlock(&obj->mmo.lock);
+
 	list_for_each_entry_safe(lut, ln, &close, obj_link) {
 		struct i915_gem_context *ctx = lut->ctx;
 		struct i915_vma *vma;
@@ -156,6 +174,8 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 	llist_for_each_entry_safe(obj, on, freed, freed) {
+		struct i915_mmap_offset *mmo, *mn;
+
 		trace_i915_gem_object_destroy(obj);
 
 		if (!list_empty(&obj->vma.list)) {
@@ -174,19 +194,28 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 				GEM_BUG_ON(vma->obj != obj);
 				spin_unlock(&obj->vma.lock);
 
-				i915_vma_destroy(vma);
+				__i915_vma_put(vma);
 
 				spin_lock(&obj->vma.lock);
 			}
 			spin_unlock(&obj->vma.lock);
 		}
 
+		i915_gem_object_release_mmap(obj);
+
+		list_for_each_entry_safe(mmo, mn, &obj->mmo.offsets, offset) {
+			drm_vma_offset_remove(obj->base.dev->vma_offset_manager,
+					      &mmo->vma_node);
+			kfree(mmo);
+		}
+		INIT_LIST_HEAD(&obj->mmo.offsets);
+
 		GEM_BUG_ON(atomic_read(&obj->bind_count));
 		GEM_BUG_ON(obj->userfault_count);
 		GEM_BUG_ON(!list_empty(&obj->lut_list));
 
 		atomic_set(&obj->mm.pages_pin_count, 0);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 		GEM_BUG_ON(i915_gem_object_has_pages(obj));
 		bitmap_free(obj->bit_17);
 
@@ -277,18 +306,14 @@ i915_gem_object_flush_write_domain(struct drm_i915_gem_object *obj,
 
 	switch (obj->write_domain) {
 	case I915_GEM_DOMAIN_GTT:
-		for_each_ggtt_vma(vma, obj)
-			intel_gt_flush_ggtt_writes(vma->vm->gt);
-
-		i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
-
+		spin_lock(&obj->vma.lock);
 		for_each_ggtt_vma(vma, obj) {
-			if (vma->iomap)
-				continue;
-
-			i915_vma_unset_ggtt_write(vma);
+			if (i915_vma_unset_ggtt_write(vma))
+				intel_gt_flush_ggtt_writes(vma->vm->gt);
 		}
+		spin_unlock(&obj->vma.lock);
 
+		i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
 		break;
 
 	case I915_GEM_DOMAIN_WC:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 4b93591fd5c7..db70a3306e59 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -16,6 +16,7 @@
 #include "display/intel_frontbuffer.h"
 #include "i915_gem_object_types.h"
 #include "i915_gem_gtt.h"
+#include "i915_vma_types.h"
 
 void i915_gem_init__objects(struct drm_i915_private *i915);
 
@@ -132,13 +133,13 @@ void i915_gem_object_unlock_fence(struct drm_i915_gem_object *obj,
 static inline void
 i915_gem_object_set_readonly(struct drm_i915_gem_object *obj)
 {
-	obj->base.vma_node.readonly = true;
+	obj->flags |= I915_BO_READONLY;
 }
 
 static inline bool
 i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj)
 {
-	return obj->base.vma_node.readonly;
+	return obj->flags & I915_BO_READONLY;
 }
 
 static inline bool
@@ -271,10 +272,27 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 int ____i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
 int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
 
+enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock/struct_mutex */
+	I915_MM_NORMAL = 0,
+	/*
+	 * Only used by struct_mutex, when called "recursively" from
+	 * direct-reclaim-esque. Safe because there is only every one
+	 * struct_mutex in the entire system.
+	 */
+	I915_MM_SHRINKER = 1,
+	/*
+	 * Used for obj->mm.lock when allocating pages. Safe because the object
+	 * isn't yet on any LRU, and therefore the shrinker can't deadlock on
+	 * it. As soon as the object has pages, obj->mm.lock nests within
+	 * fs_reclaim.
+	 */
+	I915_MM_GET_PAGES = 1,
+};
+
 static inline int __must_check
 i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
 {
-	might_lock(&obj->mm.lock);
+	might_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 
 	if (atomic_inc_not_zero(&obj->mm.pages_pin_count))
 		return 0;
@@ -317,13 +335,7 @@ i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
 	__i915_gem_object_unpin_pages(obj);
 }
 
-enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock/struct_mutex */
-	I915_MM_NORMAL = 0,
-	I915_MM_SHRINKER /* called "recursively" from direct-reclaim-esque */
-};
-
-int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
-				enum i915_mm_subclass subclass);
+int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj);
 void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
 void i915_gem_object_writeback(struct drm_i915_gem_object *obj);
 
@@ -376,9 +388,6 @@ static inline void i915_gem_object_unpin_map(struct drm_i915_gem_object *obj)
 	i915_gem_object_unpin_pages(obj);
 }
 
-void __i915_gem_object_release_mmap(struct drm_i915_gem_object *obj);
-void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj);
-
 void
 i915_gem_object_flush_write_domain(struct drm_i915_gem_object *obj,
 				   unsigned int flush_domains);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index e3f3944fbd90..88e268633fdc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -63,6 +63,23 @@ struct drm_i915_gem_object_ops {
 	void (*release)(struct drm_i915_gem_object *obj);
 };
 
+enum i915_mmap_type {
+	I915_MMAP_TYPE_GTT = 0,
+	I915_MMAP_TYPE_WC,
+	I915_MMAP_TYPE_WB,
+	I915_MMAP_TYPE_UC,
+};
+
+struct i915_mmap_offset {
+	struct drm_device *dev;
+	struct drm_vma_offset_node vma_node;
+	struct drm_i915_gem_object *obj;
+	struct drm_file *file;
+	enum i915_mmap_type mmap_type;
+
+	struct list_head offset;
+};
+
 struct drm_i915_gem_object {
 	struct drm_gem_object base;
 
@@ -118,12 +135,18 @@ struct drm_i915_gem_object {
 	unsigned int userfault_count;
 	struct list_head userfault_link;
 
+	struct {
+		spinlock_t lock; /* Protects access to mmo offsets */
+		struct list_head offsets;
+	} mmo;
+
 	I915_SELFTEST_DECLARE(struct list_head st_link);
 
 	unsigned long flags;
 #define I915_BO_ALLOC_CONTIGUOUS BIT(0)
 #define I915_BO_ALLOC_VOLATILE   BIT(1)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | I915_BO_ALLOC_VOLATILE)
+#define I915_BO_READONLY         BIT(2)
 
 	/*
 	 * Is the object to be mapped as read-only to the GPU
@@ -162,7 +185,11 @@ struct drm_i915_gem_object {
 	atomic_t bind_count;
 
 	struct {
-		struct mutex lock; /* protects the pages and their use */
+		/*
+		 * Protects the pages and their use. Do not use directly, but
+		 * instead go through the pin/unpin interfaces.
+		 */
+		struct mutex lock;
 		atomic_t pages_pin_count;
 		atomic_t shrink_pin;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 29f4c2850745..54aca5c9101e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -8,6 +8,7 @@
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
 #include "i915_gem_lmem.h"
+#include "i915_gem_mman.h"
 
 void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 				 struct sg_table *pages,
@@ -106,7 +107,7 @@ int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 {
 	int err;
 
-	err = mutex_lock_interruptible(&obj->mm.lock);
+	err = mutex_lock_interruptible_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 	if (err)
 		return err;
 
@@ -157,9 +158,7 @@ static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj)
 
 static void unmap_object(struct drm_i915_gem_object *obj, void *ptr)
 {
-	if (i915_gem_object_is_lmem(obj))
-		io_mapping_unmap((void __force __iomem *)ptr);
-	else if (is_vmalloc_addr(ptr))
+	if (is_vmalloc_addr(ptr))
 		vunmap(ptr);
 	else
 		kunmap(kmap_to_page(ptr));
@@ -190,8 +189,7 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	return pages;
 }
 
-int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
-				enum i915_mm_subclass subclass)
+int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 {
 	struct sg_table *pages;
 	int err;
@@ -202,12 +200,14 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
 	GEM_BUG_ON(atomic_read(&obj->bind_count));
 
 	/* May be called by shrinker from within get_pages() (on another bo) */
-	mutex_lock_nested(&obj->mm.lock, subclass);
+	mutex_lock(&obj->mm.lock);
 	if (unlikely(atomic_read(&obj->mm.pages_pin_count))) {
 		err = -EBUSY;
 		goto unlock;
 	}
 
+	i915_gem_object_release_mmap_offset(obj);
+
 	/*
 	 * ->put_pages might need to allocate memory for the bit17 swizzle
 	 * array, hence protect them from being reaped by removing them from gtt
@@ -234,46 +234,44 @@ unlock:
 	return err;
 }
 
+static inline pte_t iomap_pte(resource_size_t base,
+			      dma_addr_t offset,
+			      pgprot_t prot)
+{
+	return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot));
+}
+
 /* The 'mapping' part of i915_gem_object_pin_map() below */
 static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
 				 enum i915_map_type type)
 {
-	unsigned long n_pages = obj->base.size >> PAGE_SHIFT;
+	unsigned long n_pte = obj->base.size >> PAGE_SHIFT;
 	struct sg_table *sgt = obj->mm.pages;
-	struct sgt_iter sgt_iter;
-	struct page *page;
-	struct page *stack_pages[32];
-	struct page **pages = stack_pages;
-	unsigned long i = 0;
+	pte_t *stack[32], **mem;
+	struct vm_struct *area;
 	pgprot_t pgprot;
-	void *addr;
-
-	if (i915_gem_object_is_lmem(obj)) {
-		void __iomem *io;
-
-		if (type != I915_MAP_WC)
-			return NULL;
 
-		io = i915_gem_object_lmem_io_map(obj, 0, obj->base.size);
-		return (void __force *)io;
-	}
+	if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
+		return NULL;
 
 	/* A single page can always be kmapped */
-	if (n_pages == 1 && type == I915_MAP_WB)
+	if (n_pte == 1 && type == I915_MAP_WB)
 		return kmap(sg_page(sgt->sgl));
 
-	if (n_pages > ARRAY_SIZE(stack_pages)) {
+	mem = stack;
+	if (n_pte > ARRAY_SIZE(stack)) {
 		/* Too big for stack -- allocate temporary array instead */
-		pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
-		if (!pages)
+		mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
+		if (!mem)
 			return NULL;
 	}
 
-	for_each_sgt_page(page, sgt_iter, sgt)
-		pages[i++] = page;
-
-	/* Check that we have the expected number of pages */
-	GEM_BUG_ON(i != n_pages);
+	area = alloc_vm_area(obj->base.size, mem);
+	if (!area) {
+		if (mem != stack)
+			kvfree(mem);
+		return NULL;
+	}
 
 	switch (type) {
 	default:
@@ -286,12 +284,31 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
 		pgprot = pgprot_writecombine(PAGE_KERNEL_IO);
 		break;
 	}
-	addr = vmap(pages, n_pages, 0, pgprot);
 
-	if (pages != stack_pages)
-		kvfree(pages);
+	if (i915_gem_object_has_struct_page(obj)) {
+		struct sgt_iter iter;
+		struct page *page;
+		pte_t **ptes = mem;
+
+		for_each_sgt_page(page, iter, sgt)
+			**ptes++ = mk_pte(page, pgprot);
+	} else {
+		resource_size_t iomap;
+		struct sgt_iter iter;
+		pte_t **ptes = mem;
+		dma_addr_t addr;
+
+		iomap = obj->mm.region->iomap.base;
+		iomap -= obj->mm.region->region.start;
+
+		for_each_sgt_daddr(addr, iter, sgt)
+			**ptes++ = iomap_pte(iomap, addr, pgprot);
+	}
+
+	if (mem != stack)
+		kvfree(mem);
 
-	return addr;
+	return area->addr;
 }
 
 /* get, pin, and map the pages of the object into kernel space */
@@ -308,7 +325,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	if (!i915_gem_object_type_has(obj, flags))
 		return ERR_PTR(-ENXIO);
 
-	err = mutex_lock_interruptible(&obj->mm.lock);
+	err = mutex_lock_interruptible_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 	if (err)
 		return ERR_PTR(err);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 8043ff63d73f..b1b7c1b3038a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -164,7 +164,7 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
 	if (err)
 		return err;
 
-	mutex_lock(&obj->mm.lock);
+	mutex_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 
 	if (obj->mm.madv != I915_MADV_WILLNEED) {
 		err = -EFAULT;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index f88ee1317bb4..c8264eb036bf 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -13,7 +13,7 @@
 
 void i915_gem_suspend(struct drm_i915_private *i915)
 {
-	GEM_TRACE("\n");
+	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
 
 	intel_wakeref_auto(&i915->ggtt.userfault_wakeref, 0);
 	flush_workqueue(i915->wq);
@@ -99,30 +99,12 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 
 void i915_gem_resume(struct drm_i915_private *i915)
 {
-	GEM_TRACE("\n");
-
-	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
-
-	if (intel_gt_init_hw(&i915->gt))
-		goto err_wedged;
+	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
 
 	/*
 	 * As we didn't flush the kernel context before suspend, we cannot
 	 * guarantee that the context image is complete. So let's just reset
 	 * it and start again.
 	 */
-	if (intel_gt_resume(&i915->gt))
-		goto err_wedged;
-
-out_unlock:
-	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
-	return;
-
-err_wedged:
-	if (!intel_gt_is_wedged(&i915->gt)) {
-		dev_err(i915->drm.dev,
-			"Failed to re-initialize GPU, declaring it wedged!\n");
-		intel_gt_set_wedged(&i915->gt);
-	}
-	goto out_unlock;
+	intel_gt_resume(&i915->gt);
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index 2f7bcfb9c964..1515384d7e0e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -85,7 +85,7 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 		}
 
 		prev_end = offset + block_size;
-	};
+	}
 
 	sg_page_sizes |= sg->length;
 	sg_mark_end(sg);
@@ -107,7 +107,10 @@ void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
 {
 	INIT_LIST_HEAD(&obj->mm.blocks);
 	obj->mm.region = intel_memory_region_get(mem);
+
 	obj->flags |= flags;
+	if (obj->base.size <= mem->min_page_size)
+		obj->flags |= I915_BO_ALLOC_CONTIGUOUS;
 
 	mutex_lock(&mem->objects.lock);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 4d69c3fc3439..a2a980d9d241 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -594,6 +594,8 @@ static int init_shmem(struct intel_memory_region *mem)
 			 err);
 	}
 
+	intel_memory_region_set_name(mem, "system");
+
 	return 0; /* Don't error, we can simply fallback to the kernel mnt */
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index f2418a1cfe68..f7e4b39c734f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -57,7 +57,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj,
 		flags = I915_GEM_OBJECT_UNBIND_ACTIVE;
 
 	if (i915_gem_object_unbind(obj, flags) == 0)
-		__i915_gem_object_put_pages(obj, I915_MM_SHRINKER);
+		__i915_gem_object_put_pages(obj);
 
 	return !i915_gem_object_has_pages(obj);
 }
@@ -209,8 +209,7 @@ i915_gem_shrink(struct drm_i915_private *i915,
 
 			if (unsafe_drop_pages(obj, shrink)) {
 				/* May arrive from get_pages on another bo */
-				mutex_lock_nested(&obj->mm.lock,
-						  I915_MM_SHRINKER);
+				mutex_lock(&obj->mm.lock);
 				if (!i915_gem_object_has_pages(obj)) {
 					try_to_writeback(obj, shrink);
 					count += obj->base.size >> PAGE_SHIFT;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index a2d49c04e6a4..451f3078d60d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -26,48 +26,49 @@
  * for is a boon.
  */
 
-int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
+int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *i915,
 					 struct drm_mm_node *node, u64 size,
 					 unsigned alignment, u64 start, u64 end)
 {
 	int ret;
 
-	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+	if (!drm_mm_initialized(&i915->mm.stolen))
 		return -ENODEV;
 
 	/* WaSkipStolenMemoryFirstPage:bdw+ */
-	if (INTEL_GEN(dev_priv) >= 8 && start < 4096)
+	if (INTEL_GEN(i915) >= 8 && start < 4096)
 		start = 4096;
 
-	mutex_lock(&dev_priv->mm.stolen_lock);
-	ret = drm_mm_insert_node_in_range(&dev_priv->mm.stolen, node,
+	mutex_lock(&i915->mm.stolen_lock);
+	ret = drm_mm_insert_node_in_range(&i915->mm.stolen, node,
 					  size, alignment, 0,
 					  start, end, DRM_MM_INSERT_BEST);
-	mutex_unlock(&dev_priv->mm.stolen_lock);
+	mutex_unlock(&i915->mm.stolen_lock);
 
 	return ret;
 }
 
-int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv,
+int i915_gem_stolen_insert_node(struct drm_i915_private *i915,
 				struct drm_mm_node *node, u64 size,
 				unsigned alignment)
 {
-	return i915_gem_stolen_insert_node_in_range(dev_priv, node, size,
+	return i915_gem_stolen_insert_node_in_range(i915, node, size,
 						    alignment, 0, U64_MAX);
 }
 
-void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
+void i915_gem_stolen_remove_node(struct drm_i915_private *i915,
 				 struct drm_mm_node *node)
 {
-	mutex_lock(&dev_priv->mm.stolen_lock);
+	mutex_lock(&i915->mm.stolen_lock);
 	drm_mm_remove_node(node);
-	mutex_unlock(&dev_priv->mm.stolen_lock);
+	mutex_unlock(&i915->mm.stolen_lock);
 }
 
-static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
+static int i915_adjust_stolen(struct drm_i915_private *i915,
 			      struct resource *dsm)
 {
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
 	struct resource *r;
 
 	if (dsm->start == 0 || dsm->end <= dsm->start)
@@ -79,14 +80,14 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 	 */
 
 	/* Make sure we don't clobber the GTT if it's within stolen memory */
-	if (INTEL_GEN(dev_priv) <= 4 &&
-	    !IS_G33(dev_priv) && !IS_PINEVIEW(dev_priv) && !IS_G4X(dev_priv)) {
+	if (INTEL_GEN(i915) <= 4 &&
+	    !IS_G33(i915) && !IS_PINEVIEW(i915) && !IS_G4X(i915)) {
 		struct resource stolen[2] = {*dsm, *dsm};
 		struct resource ggtt_res;
 		resource_size_t ggtt_start;
 
-		ggtt_start = I915_READ(PGTBL_CTL);
-		if (IS_GEN(dev_priv, 4))
+		ggtt_start = intel_uncore_read(uncore, PGTBL_CTL);
+		if (IS_GEN(i915, 4))
 			ggtt_start = (ggtt_start & PGTBL_ADDRESS_LO_MASK) |
 				     (ggtt_start & PGTBL_ADDRESS_HI_MASK) << 28;
 		else
@@ -120,7 +121,7 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 	 * kernel. So if the region is already marked as busy, something
 	 * is seriously wrong.
 	 */
-	r = devm_request_mem_region(dev_priv->drm.dev, dsm->start,
+	r = devm_request_mem_region(i915->drm.dev, dsm->start,
 				    resource_size(dsm),
 				    "Graphics Stolen Memory");
 	if (r == NULL) {
@@ -133,14 +134,14 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 		 * reservation starting from 1 instead of 0.
 		 * There's also BIOS with off-by-one on the other end.
 		 */
-		r = devm_request_mem_region(dev_priv->drm.dev, dsm->start + 1,
+		r = devm_request_mem_region(i915->drm.dev, dsm->start + 1,
 					    resource_size(dsm) - 2,
 					    "Graphics Stolen Memory");
 		/*
 		 * GEN3 firmware likes to smash pci bridges into the stolen
 		 * range. Apparently this works.
 		 */
-		if (r == NULL && !IS_GEN(dev_priv, 3)) {
+		if (!r && !IS_GEN(i915, 3)) {
 			DRM_ERROR("conflict detected with stolen region: %pR\n",
 				  dsm);
 
@@ -151,25 +152,27 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
-static void i915_gem_cleanup_stolen(struct drm_i915_private *dev_priv)
+static void i915_gem_cleanup_stolen(struct drm_i915_private *i915)
 {
-	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+	if (!drm_mm_initialized(&i915->mm.stolen))
 		return;
 
-	drm_mm_takedown(&dev_priv->mm.stolen);
+	drm_mm_takedown(&i915->mm.stolen);
 }
 
-static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void g4x_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u32 reg_val = I915_READ(IS_GM45(dev_priv) ?
-				CTG_STOLEN_RESERVED :
-				ELK_STOLEN_RESERVED);
-	resource_size_t stolen_top = dev_priv->dsm.end + 1;
+	u32 reg_val = intel_uncore_read(uncore,
+					IS_GM45(i915) ?
+					CTG_STOLEN_RESERVED :
+					ELK_STOLEN_RESERVED);
+	resource_size_t stolen_top = i915->dsm.end + 1;
 
 	DRM_DEBUG_DRIVER("%s_STOLEN_RESERVED = %08x\n",
-			 IS_GM45(dev_priv) ? "CTG" : "ELK", reg_val);
+			 IS_GM45(i915) ? "CTG" : "ELK", reg_val);
 
 	if ((reg_val & G4X_STOLEN_RESERVED_ENABLE) == 0)
 		return;
@@ -178,7 +181,7 @@ static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	 * Whether ILK really reuses the ELK register for this is unclear.
 	 * Let's see if we catch anyone with this supposedly enabled on ILK.
 	 */
-	WARN(IS_GEN(dev_priv, 5), "ILK stolen reserved found? 0x%08x\n",
+	WARN(IS_GEN(i915, 5), "ILK stolen reserved found? 0x%08x\n",
 	     reg_val);
 
 	if (!(reg_val & G4X_STOLEN_RESERVED_ADDR2_MASK))
@@ -190,11 +193,12 @@ static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	*size = stolen_top - *base;
 }
 
-static void gen6_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void gen6_get_stolen_reserved(struct drm_i915_private *i915,
+				     struct intel_uncore *uncore,
 				     resource_size_t *base,
 				     resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -222,12 +226,13 @@ static void gen6_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void vlv_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void vlv_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
-	resource_size_t stolen_top = dev_priv->dsm.end + 1;
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
+	resource_size_t stolen_top = i915->dsm.end + 1;
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -250,11 +255,12 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	*base = stolen_top - *size;
 }
 
-static void gen7_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void gen7_get_stolen_reserved(struct drm_i915_private *i915,
+				     struct intel_uncore *uncore,
 				     resource_size_t *base,
 				     resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -276,11 +282,12 @@ static void gen7_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void chv_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void chv_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -308,12 +315,13 @@ static void chv_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void bdw_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
-	resource_size_t stolen_top = dev_priv->dsm.end + 1;
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
+	resource_size_t stolen_top = i915->dsm.end + 1;
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -328,10 +336,11 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
 }
 
 static void icl_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u64 reg_val = intel_uncore_read64(&i915->uncore, GEN6_STOLEN_RESERVED);
+	u64 reg_val = intel_uncore_read64(uncore, GEN6_STOLEN_RESERVED);
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
 
@@ -356,22 +365,23 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915,
 	}
 }
 
-static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
+static int i915_gem_init_stolen(struct drm_i915_private *i915)
 {
+	struct intel_uncore *uncore = &i915->uncore;
 	resource_size_t reserved_base, stolen_top;
 	resource_size_t reserved_total, reserved_size;
 
-	mutex_init(&dev_priv->mm.stolen_lock);
+	mutex_init(&i915->mm.stolen_lock);
 
-	if (intel_vgpu_active(dev_priv)) {
-		dev_notice(dev_priv->drm.dev,
+	if (intel_vgpu_active(i915)) {
+		dev_notice(i915->drm.dev,
 			   "%s, disabling use of stolen memory\n",
 			   "iGVT-g active");
 		return 0;
 	}
 
-	if (intel_vtd_active() && INTEL_GEN(dev_priv) < 8) {
-		dev_notice(dev_priv->drm.dev,
+	if (intel_vtd_active() && INTEL_GEN(i915) < 8) {
+		dev_notice(i915->drm.dev,
 			   "%s, disabling use of stolen memory\n",
 			   "DMAR active");
 		return 0;
@@ -380,58 +390,59 @@ static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 	if (resource_size(&intel_graphics_stolen_res) == 0)
 		return 0;
 
-	dev_priv->dsm = intel_graphics_stolen_res;
+	i915->dsm = intel_graphics_stolen_res;
 
-	if (i915_adjust_stolen(dev_priv, &dev_priv->dsm))
+	if (i915_adjust_stolen(i915, &i915->dsm))
 		return 0;
 
-	GEM_BUG_ON(dev_priv->dsm.start == 0);
-	GEM_BUG_ON(dev_priv->dsm.end <= dev_priv->dsm.start);
+	GEM_BUG_ON(i915->dsm.start == 0);
+	GEM_BUG_ON(i915->dsm.end <= i915->dsm.start);
 
-	stolen_top = dev_priv->dsm.end + 1;
+	stolen_top = i915->dsm.end + 1;
 	reserved_base = stolen_top;
 	reserved_size = 0;
 
-	switch (INTEL_GEN(dev_priv)) {
+	switch (INTEL_GEN(i915)) {
 	case 2:
 	case 3:
 		break;
 	case 4:
-		if (!IS_G4X(dev_priv))
+		if (!IS_G4X(i915))
 			break;
 		/* fall through */
 	case 5:
-		g4x_get_stolen_reserved(dev_priv,
+		g4x_get_stolen_reserved(i915, uncore,
 					&reserved_base, &reserved_size);
 		break;
 	case 6:
-		gen6_get_stolen_reserved(dev_priv,
+		gen6_get_stolen_reserved(i915, uncore,
 					 &reserved_base, &reserved_size);
 		break;
 	case 7:
-		if (IS_VALLEYVIEW(dev_priv))
-			vlv_get_stolen_reserved(dev_priv,
+		if (IS_VALLEYVIEW(i915))
+			vlv_get_stolen_reserved(i915, uncore,
 						&reserved_base, &reserved_size);
 		else
-			gen7_get_stolen_reserved(dev_priv,
+			gen7_get_stolen_reserved(i915, uncore,
 						 &reserved_base, &reserved_size);
 		break;
 	case 8:
 	case 9:
 	case 10:
-		if (IS_LP(dev_priv))
-			chv_get_stolen_reserved(dev_priv,
+		if (IS_LP(i915))
+			chv_get_stolen_reserved(i915, uncore,
 						&reserved_base, &reserved_size);
 		else
-			bdw_get_stolen_reserved(dev_priv,
+			bdw_get_stolen_reserved(i915, uncore,
 						&reserved_base, &reserved_size);
 		break;
 	default:
-		MISSING_CASE(INTEL_GEN(dev_priv));
+		MISSING_CASE(INTEL_GEN(i915));
 		/* fall-through */
 	case 11:
 	case 12:
-		icl_get_stolen_reserved(dev_priv, &reserved_base,
+		icl_get_stolen_reserved(i915, uncore,
+					&reserved_base,
 					&reserved_size);
 		break;
 	}
@@ -448,12 +459,12 @@ static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 		reserved_size = 0;
 	}
 
-	dev_priv->dsm_reserved =
-		(struct resource) DEFINE_RES_MEM(reserved_base, reserved_size);
+	i915->dsm_reserved =
+		(struct resource)DEFINE_RES_MEM(reserved_base, reserved_size);
 
-	if (!resource_contains(&dev_priv->dsm, &dev_priv->dsm_reserved)) {
+	if (!resource_contains(&i915->dsm, &i915->dsm_reserved)) {
 		DRM_ERROR("Stolen reserved area %pR outside stolen memory %pR\n",
-			  &dev_priv->dsm_reserved, &dev_priv->dsm);
+			  &i915->dsm_reserved, &i915->dsm);
 		return 0;
 	}
 
@@ -462,14 +473,14 @@ static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 	reserved_total = stolen_top - reserved_base;
 
 	DRM_DEBUG_DRIVER("Memory reserved for graphics device: %lluK, usable: %lluK\n",
-			 (u64)resource_size(&dev_priv->dsm) >> 10,
-			 ((u64)resource_size(&dev_priv->dsm) - reserved_total) >> 10);
+			 (u64)resource_size(&i915->dsm) >> 10,
+			 ((u64)resource_size(&i915->dsm) - reserved_total) >> 10);
 
-	dev_priv->stolen_usable_size =
-		resource_size(&dev_priv->dsm) - reserved_total;
+	i915->stolen_usable_size =
+		resource_size(&i915->dsm) - reserved_total;
 
 	/* Basic memrange allocator for stolen space. */
-	drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->stolen_usable_size);
+	drm_mm_init(&i915->mm.stolen, 0, i915->stolen_usable_size);
 
 	return 0;
 }
@@ -478,11 +489,11 @@ static struct sg_table *
 i915_pages_create_for_stolen(struct drm_device *dev,
 			     resource_size_t offset, resource_size_t size)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct sg_table *st;
 	struct scatterlist *sg;
 
-	GEM_BUG_ON(range_overflows(offset, size, resource_size(&dev_priv->dsm)));
+	GEM_BUG_ON(range_overflows(offset, size, resource_size(&i915->dsm)));
 
 	/* We hide that we have no struct page backing our stolen object
 	 * by wrapping the contiguous physical allocation with a fake
@@ -502,7 +513,7 @@ i915_pages_create_for_stolen(struct drm_device *dev,
 	sg->offset = 0;
 	sg->length = size;
 
-	sg_dma_address(sg) = (dma_addr_t)dev_priv->dsm.start + offset;
+	sg_dma_address(sg) = (dma_addr_t)i915->dsm.start + offset;
 	sg_dma_len(sg) = size;
 
 	return st;
@@ -533,16 +544,15 @@ static void i915_gem_object_put_pages_stolen(struct drm_i915_gem_object *obj,
 static void
 i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct drm_mm_node *stolen = fetch_and_zero(&obj->stolen);
 
 	GEM_BUG_ON(!stolen);
 
-	i915_gem_stolen_remove_node(dev_priv, stolen);
-	kfree(stolen);
+	i915_gem_object_release_memory_region(obj);
 
-	if (obj->mm.region)
-		i915_gem_object_release_memory_region(obj);
+	i915_gem_stolen_remove_node(i915, stolen);
+	kfree(stolen);
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
@@ -552,9 +562,8 @@ static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
 };
 
 static struct drm_i915_gem_object *
-__i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
-				struct drm_mm_node *stolen,
-				struct intel_memory_region *mem)
+__i915_gem_object_create_stolen(struct intel_memory_region *mem,
+				struct drm_mm_node *stolen)
 {
 	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
@@ -565,20 +574,19 @@ __i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 	if (!obj)
 		goto err;
 
-	drm_gem_private_object_init(&dev_priv->drm, &obj->base, stolen->size);
+	drm_gem_private_object_init(&mem->i915->drm, &obj->base, stolen->size);
 	i915_gem_object_init(obj, &i915_gem_object_stolen_ops, &lock_class);
 
 	obj->stolen = stolen;
 	obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
-	cache_level = HAS_LLC(dev_priv) ? I915_CACHE_LLC : I915_CACHE_NONE;
+	cache_level = HAS_LLC(mem->i915) ? I915_CACHE_LLC : I915_CACHE_NONE;
 	i915_gem_object_set_cache_coherency(obj, cache_level);
 
 	err = i915_gem_object_pin_pages(obj);
 	if (err)
 		goto cleanup;
 
-	if (mem)
-		i915_gem_object_init_memory_region(obj, mem, 0);
+	i915_gem_object_init_memory_region(obj, mem, 0);
 
 	return obj;
 
@@ -593,12 +601,12 @@ _i915_gem_object_create_stolen(struct intel_memory_region *mem,
 			       resource_size_t size,
 			       unsigned int flags)
 {
-	struct drm_i915_private *dev_priv = mem->i915;
+	struct drm_i915_private *i915 = mem->i915;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
 	int ret;
 
-	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+	if (!drm_mm_initialized(&i915->mm.stolen))
 		return ERR_PTR(-ENODEV);
 
 	if (size == 0)
@@ -608,35 +616,37 @@ _i915_gem_object_create_stolen(struct intel_memory_region *mem,
 	if (!stolen)
 		return ERR_PTR(-ENOMEM);
 
-	ret = i915_gem_stolen_insert_node(dev_priv, stolen, size, 4096);
+	ret = i915_gem_stolen_insert_node(i915, stolen, size, 4096);
 	if (ret) {
 		obj = ERR_PTR(ret);
 		goto err_free;
 	}
 
-	obj = __i915_gem_object_create_stolen(dev_priv, stolen, mem);
+	obj = __i915_gem_object_create_stolen(mem, stolen);
 	if (IS_ERR(obj))
 		goto err_remove;
 
 	return obj;
 
 err_remove:
-	i915_gem_stolen_remove_node(dev_priv, stolen);
+	i915_gem_stolen_remove_node(i915, stolen);
 err_free:
 	kfree(stolen);
 	return obj;
 }
 
 struct drm_i915_gem_object *
-i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
+i915_gem_object_create_stolen(struct drm_i915_private *i915,
 			      resource_size_t size)
 {
-	return i915_gem_object_create_region(dev_priv->mm.regions[INTEL_REGION_STOLEN],
+	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_STOLEN],
 					     size, I915_BO_ALLOC_CONTIGUOUS);
 }
 
 static int init_stolen(struct intel_memory_region *mem)
 {
+	intel_memory_region_set_name(mem, "stolen");
+
 	/*
 	 * Initialise stolen early so that we may reserve preallocated
 	 * objects for the BIOS to KMS transition.
@@ -665,18 +675,19 @@ struct intel_memory_region *i915_gem_stolen_setup(struct drm_i915_private *i915)
 }
 
 struct drm_i915_gem_object *
-i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv,
+i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915,
 					       resource_size_t stolen_offset,
 					       resource_size_t gtt_offset,
 					       resource_size_t size)
 {
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct intel_memory_region *mem = i915->mm.regions[INTEL_REGION_STOLEN];
+	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
 	struct i915_vma *vma;
 	int ret;
 
-	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+	if (!drm_mm_initialized(&i915->mm.stolen))
 		return ERR_PTR(-ENODEV);
 
 	DRM_DEBUG_DRIVER("creating preallocated stolen object: stolen_offset=%pa, gtt_offset=%pa, size=%pa\n",
@@ -694,19 +705,19 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 
 	stolen->start = stolen_offset;
 	stolen->size = size;
-	mutex_lock(&dev_priv->mm.stolen_lock);
-	ret = drm_mm_reserve_node(&dev_priv->mm.stolen, stolen);
-	mutex_unlock(&dev_priv->mm.stolen_lock);
+	mutex_lock(&i915->mm.stolen_lock);
+	ret = drm_mm_reserve_node(&i915->mm.stolen, stolen);
+	mutex_unlock(&i915->mm.stolen_lock);
 	if (ret) {
 		DRM_DEBUG_DRIVER("failed to allocate stolen space\n");
 		kfree(stolen);
 		return ERR_PTR(ret);
 	}
 
-	obj = __i915_gem_object_create_stolen(dev_priv, stolen, NULL);
+	obj = __i915_gem_object_create_stolen(mem, stolen);
 	if (IS_ERR(obj)) {
 		DRM_DEBUG_DRIVER("failed to allocate stolen object\n");
-		i915_gem_stolen_remove_node(dev_priv, stolen);
+		i915_gem_stolen_remove_node(i915, stolen);
 		kfree(stolen);
 		return obj;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index 1fa592d82af5..6c7825a2dc2a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -11,6 +11,7 @@
 #include "i915_drv.h"
 #include "i915_gem.h"
 #include "i915_gem_ioctls.h"
+#include "i915_gem_mman.h"
 #include "i915_gem_object.h"
 
 /**
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 0dbb44d30885..580319b7bf1a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -129,9 +129,10 @@ userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 		spin_unlock(&mn->lock);
 
 		ret = i915_gem_object_unbind(obj,
-					     I915_GEM_OBJECT_UNBIND_ACTIVE);
+					     I915_GEM_OBJECT_UNBIND_ACTIVE |
+					     I915_GEM_OBJECT_UNBIND_BARRIER);
 		if (ret == 0)
-			ret = __i915_gem_object_put_pages(obj, I915_MM_SHRINKER);
+			ret = __i915_gem_object_put_pages(obj);
 		i915_gem_object_put(obj);
 		if (ret)
 			return ret;
@@ -460,31 +461,36 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 		unsigned int flags = 0;
+		int locked = 0;
 
 		if (!i915_gem_object_is_readonly(obj))
 			flags |= FOLL_WRITE;
 
 		ret = -EFAULT;
 		if (mmget_not_zero(mm)) {
-			down_read(&mm->mmap_sem);
 			while (pinned < npages) {
+				if (!locked) {
+					down_read(&mm->mmap_sem);
+					locked = 1;
+				}
 				ret = get_user_pages_remote
 					(work->task, mm,
 					 obj->userptr.ptr + pinned * PAGE_SIZE,
 					 npages - pinned,
 					 flags,
-					 pvec + pinned, NULL, NULL);
+					 pvec + pinned, NULL, &locked);
 				if (ret < 0)
 					break;
 
 				pinned += ret;
 			}
-			up_read(&mm->mmap_sem);
+			if (locked)
+				up_read(&mm->mmap_sem);
 			mmput(mm);
 		}
 	}
 
-	mutex_lock(&obj->mm.lock);
+	mutex_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 	if (obj->userptr.work == &work->work) {
 		struct sg_table *pages = ERR_PTR(ret);
 
@@ -774,15 +780,11 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		return -EFAULT;
 
 	if (args->flags & I915_USERPTR_READ_ONLY) {
-		struct i915_address_space *vm;
-
 		/*
 		 * On almost all of the older hw, we cannot tell the GPU that
 		 * a page is readonly.
 		 */
-		vm = rcu_dereference_protected(dev_priv->kernel_context->vm,
-					       true); /* static vm */
-		if (!vm || !vm->has_read_only)
+		if (!dev_priv->gt.vm->has_read_only)
 			return -ENODEV;
 	}
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
index 892d12db6c49..fa16f2c3f3ac 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
@@ -12,10 +12,14 @@ static void huge_free_pages(struct drm_i915_gem_object *obj,
 			    struct sg_table *pages)
 {
 	unsigned long nreal = obj->scratch / PAGE_SIZE;
-	struct scatterlist *sg;
+	struct sgt_iter sgt_iter;
+	struct page *page;
 
-	for (sg = pages->sgl; sg && nreal--; sg = __sg_next(sg))
-		__free_page(sg_page(sg));
+	for_each_sgt_page(page, sgt_iter, pages) {
+		__free_page(page);
+		if (!--nreal)
+			break;
+	}
 
 	sg_free_table(pages);
 	kfree(pages);
@@ -70,7 +74,6 @@ static int huge_get_pages(struct drm_i915_gem_object *obj)
 
 err:
 	huge_free_pages(obj, pages);
-
 	return -ENOMEM;
 #undef GFP
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.h b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.h
index 549c1394bcdc..b8cf31b7bf14 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.h
@@ -7,6 +7,12 @@
 #ifndef __HUGE_GEM_OBJECT_H
 #define __HUGE_GEM_OBJECT_H
 
+#include <linux/types.h>
+
+#include "gem/i915_gem_object_types.h"
+
+struct drm_i915_private;
+
 struct drm_i915_gem_object *
 huge_gem_object(struct drm_i915_private *i915,
 		phys_addr_t phys_size,
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 688c49a24f32..9311250d7d6f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -517,7 +517,7 @@ static int igt_mock_memory_region_huge_pages(void *arg)
 			i915_vma_unpin(vma);
 			i915_vma_close(vma);
 
-			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -650,7 +650,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 		i915_vma_close(vma);
 
 		i915_gem_object_unpin_pages(obj);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 		i915_gem_object_put(obj);
 	}
 
@@ -678,7 +678,7 @@ static void close_object_list(struct list_head *objects,
 
 		list_del(&obj->st_link);
 		i915_gem_object_unpin_pages(obj);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 		i915_gem_object_put(obj);
 	}
 }
@@ -948,7 +948,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 			i915_vma_close(vma);
 
 			i915_gem_object_unpin_pages(obj);
-			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -1017,38 +1017,33 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	return err;
 }
 
-static int __cpu_check_lmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
+static int __cpu_check_vmap(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 {
-	unsigned long n;
+	unsigned long n = obj->base.size >> PAGE_SHIFT;
+	u32 *ptr;
 	int err;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_wc_domain(obj, false);
-	i915_gem_object_unlock(obj);
+	err = i915_gem_object_wait(obj, 0, MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
-	err = i915_gem_object_pin_pages(obj);
-	if (err)
-		return err;
+	ptr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
 
-	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
-		u32 __iomem *base;
-		u32 read_val;
-
-		base = i915_gem_object_lmem_io_map_page_atomic(obj, n);
-
-		read_val = ioread32(base + dword);
-		io_mapping_unmap_atomic(base);
-		if (read_val != val) {
-			pr_err("n=%lu base[%u]=%u, val=%u\n",
-			       n, dword, read_val, val);
+	ptr += dword;
+	while (n--) {
+		if (*ptr != val) {
+			pr_err("base[%u]=%08x, val=%08x\n",
+			       dword, *ptr, val);
 			err = -EINVAL;
 			break;
 		}
+
+		ptr += PAGE_SIZE / sizeof(*ptr);
 	}
 
-	i915_gem_object_unpin_pages(obj);
+	i915_gem_object_unpin_map(obj);
 	return err;
 }
 
@@ -1056,10 +1051,8 @@ static int cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 {
 	if (i915_gem_object_has_struct_page(obj))
 		return __cpu_check_shmem(obj, dword, val);
-	else if (i915_gem_object_is_lmem(obj))
-		return __cpu_check_lmem(obj, dword, val);
-
-	return -ENODEV;
+	else
+		return __cpu_check_vmap(obj, dword, val);
 }
 
 static int __igt_write_huge(struct intel_context *ce,
@@ -1110,8 +1103,7 @@ static int __igt_write_huge(struct intel_context *ce,
 out_vma_unpin:
 	i915_vma_unpin(vma);
 out_vma_close:
-	i915_vma_destroy(vma);
-
+	__i915_vma_put(vma);
 	return err;
 }
 
@@ -1301,7 +1293,7 @@ static int igt_ppgtt_exhaust_huge(void *arg)
 			}
 
 			i915_gem_object_unpin_pages(obj);
-			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -1420,7 +1412,7 @@ try_again:
 
 		err = i915_gem_object_pin_pages(obj);
 		if (err) {
-			if (err == -ENXIO) {
+			if (err == -ENXIO || err == -E2BIG) {
 				i915_gem_object_put(obj);
 				size >>= 1;
 				goto try_again;
@@ -1442,7 +1434,7 @@ try_again:
 		}
 out_unpin:
 		i915_gem_object_unpin_pages(obj);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 out_put:
 		i915_gem_object_put(obj);
 
@@ -1530,7 +1522,7 @@ static int igt_ppgtt_sanity_check(void *arg)
 			err = igt_write_huge(ctx, obj);
 
 			i915_gem_object_unpin_pages(obj);
-			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 
 			if (err) {
@@ -1873,7 +1865,7 @@ int i915_gem_huge_page_mock_selftests(void)
 	mkwrite_device_info(dev_priv)->ppgtt_type = INTEL_PPGTT_FULL;
 	mkwrite_device_info(dev_priv)->ppgtt_size = 48;
 
-	ppgtt = i915_ppgtt_create(dev_priv);
+	ppgtt = i915_ppgtt_create(&dev_priv->gt);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
@@ -1912,9 +1904,9 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ppgtt_smoke_huge),
 		SUBTEST(igt_ppgtt_sanity_check),
 	};
-	struct drm_file *file;
 	struct i915_gem_context *ctx;
 	struct i915_address_space *vm;
+	struct file *file;
 	int err;
 
 	if (!HAS_PPGTT(i915)) {
@@ -1944,6 +1936,6 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 	err = i915_subtests(tests, ctx);
 
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index da8edee4fe0a..b972be165e85 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -24,6 +24,7 @@ static int __igt_client_fill(struct intel_engine_cs *engine)
 
 	prandom_seed_state(&prng, i915_selftest.random_seed);
 
+	intel_engine_pm_get(engine);
 	do {
 		const u32 max_block_size = S16_MAX * PAGE_SIZE;
 		u32 sz = min_t(u64, ce->vm->total >> 4, prandom_u32_state(&prng));
@@ -99,6 +100,7 @@ err_put:
 err_flush:
 	if (err == -ENOMEM)
 		err = 0;
+	intel_engine_pm_put(engine);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 2b29f6b4e1dd..3f6079e1dfb6 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -6,6 +6,7 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_ring.h"
@@ -200,7 +201,7 @@ static int gpu_set(struct context *ctx, unsigned long offset, u32 v)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	rq = i915_request_create(ctx->engine->kernel_context);
+	rq = intel_engine_create_kernel_request(ctx->engine);
 	if (IS_ERR(rq)) {
 		i915_vma_unpin(vma);
 		return PTR_ERR(rq);
@@ -324,8 +325,12 @@ static int igt_gem_coherency(void *arg)
 	values = offsets + ncachelines;
 
 	ctx.engine = random_engine(i915, &prng);
-	GEM_BUG_ON(!ctx.engine);
+	if (!ctx.engine) {
+		err = -ENODEV;
+		goto out_free;
+	}
 	pr_info("%s: using %s\n", __func__, ctx.engine->name);
+	intel_engine_pm_get(ctx.engine);
 
 	for (over = igt_coherency_mode; over->name; over++) {
 		if (!over->set)
@@ -352,7 +357,7 @@ static int igt_gem_coherency(void *arg)
 					ctx.obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 					if (IS_ERR(ctx.obj)) {
 						err = PTR_ERR(ctx.obj);
-						goto free;
+						goto out_pm;
 					}
 
 					i915_random_reorder(offsets, ncachelines, &prng);
@@ -403,13 +408,15 @@ static int igt_gem_coherency(void *arg)
 			}
 		}
 	}
-free:
+out_pm:
+	intel_engine_pm_put(ctx.engine);
+out_free:
 	kfree(offsets);
 	return err;
 
 put_object:
 	i915_gem_object_put(ctx.obj);
-	goto free;
+	goto out_pm;
 }
 
 int i915_gem_coherency_live_selftests(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 62fabc023a83..7fc46861a54d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -7,6 +7,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
 #include "gt/intel_reset.h"
@@ -26,6 +27,12 @@
 
 #define DW_PER_PAGE (PAGE_SIZE / sizeof(u32))
 
+static inline struct i915_address_space *ctx_vm(struct i915_gem_context *ctx)
+{
+	/* single threaded, private ctx */
+	return rcu_dereference_protected(ctx->vm, true);
+}
+
 static int live_nop_switch(void *arg)
 {
 	const unsigned int nctx = 1024;
@@ -33,7 +40,7 @@ static int live_nop_switch(void *arg)
 	struct intel_engine_cs *engine;
 	struct i915_gem_context **ctx;
 	struct igt_live_test t;
-	struct drm_file *file;
+	struct file *file;
 	unsigned long n;
 	int err = -ENODEV;
 
@@ -67,25 +74,34 @@ static int live_nop_switch(void *arg)
 	}
 
 	for_each_uabi_engine(engine, i915) {
-		struct i915_request *rq;
+		struct i915_request *rq = NULL;
 		unsigned long end_time, prime;
 		ktime_t times[2] = {};
 
 		times[0] = ktime_get_raw();
 		for (n = 0; n < nctx; n++) {
-			rq = igt_request_alloc(ctx[n], engine);
-			if (IS_ERR(rq)) {
-				err = PTR_ERR(rq);
+			struct i915_request *this;
+
+			this = igt_request_alloc(ctx[n], engine);
+			if (IS_ERR(this)) {
+				err = PTR_ERR(this);
 				goto out_file;
 			}
-			i915_request_add(rq);
+			if (rq) {
+				i915_request_await_dma_fence(this, &rq->fence);
+				i915_request_put(rq);
+			}
+			rq = i915_request_get(this);
+			i915_request_add(this);
 		}
 		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 			pr_err("Failed to populated %d contexts\n", nctx);
 			intel_gt_set_wedged(&i915->gt);
+			i915_request_put(rq);
 			err = -EIO;
 			goto out_file;
 		}
+		i915_request_put(rq);
 
 		times[1] = ktime_get_raw();
 
@@ -100,13 +116,21 @@ static int live_nop_switch(void *arg)
 		for_each_prime_number_from(prime, 2, 8192) {
 			times[1] = ktime_get_raw();
 
+			rq = NULL;
 			for (n = 0; n < prime; n++) {
-				rq = igt_request_alloc(ctx[n % nctx], engine);
-				if (IS_ERR(rq)) {
-					err = PTR_ERR(rq);
+				struct i915_request *this;
+
+				this = igt_request_alloc(ctx[n % nctx], engine);
+				if (IS_ERR(this)) {
+					err = PTR_ERR(this);
 					goto out_file;
 				}
 
+				if (rq) { /* Force submission order */
+					i915_request_await_dma_fence(this, &rq->fence);
+					i915_request_put(rq);
+				}
+
 				/*
 				 * This space is left intentionally blank.
 				 *
@@ -121,14 +145,18 @@ static int live_nop_switch(void *arg)
 				 * for latency.
 				 */
 
-				i915_request_add(rq);
+				rq = i915_request_get(this);
+				i915_request_add(this);
 			}
+			GEM_BUG_ON(!rq);
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				pr_err("Switching between %ld contexts timed out\n",
 				       prime);
 				intel_gt_set_wedged(&i915->gt);
+				i915_request_put(rq);
 				break;
 			}
+			i915_request_put(rq);
 
 			times[1] = ktime_sub(ktime_get_raw(), times[1]);
 			if (prime == 2)
@@ -149,7 +177,7 @@ static int live_nop_switch(void *arg)
 	}
 
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -255,7 +283,7 @@ static int live_parallel_switch(void *arg)
 	int (* const *fn)(void *arg);
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
-	struct drm_file *file;
+	struct file *file;
 	int n, m, count;
 	int err = 0;
 
@@ -309,7 +337,7 @@ static int live_parallel_switch(void *arg)
 			if (!data[m].ce[0])
 				continue;
 
-			ce = intel_context_create(ctx, data[m].ce[0]->engine);
+			ce = intel_context_create(data[m].ce[0]->engine);
 			if (IS_ERR(ce))
 				goto out;
 
@@ -377,7 +405,7 @@ out:
 	}
 	kfree(data);
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -502,17 +530,17 @@ out_unmap:
 	return err;
 }
 
-static int file_add_object(struct drm_file *file,
-			    struct drm_i915_gem_object *obj)
+static int file_add_object(struct file *file, struct drm_i915_gem_object *obj)
 {
 	int err;
 
 	GEM_BUG_ON(obj->base.handle_count);
 
 	/* tie the object to the drm_file for easy reaping */
-	err = idr_alloc(&file->object_idr, &obj->base, 1, 0, GFP_KERNEL);
+	err = idr_alloc(&to_drm_file(file)->object_idr,
+			&obj->base, 1, 0, GFP_KERNEL);
 	if (err < 0)
-		return  err;
+		return err;
 
 	i915_gem_object_get(obj);
 	obj->base.handle_count++;
@@ -521,7 +549,7 @@ static int file_add_object(struct drm_file *file,
 
 static struct drm_i915_gem_object *
 create_test_object(struct i915_address_space *vm,
-		   struct drm_file *file,
+		   struct file *file,
 		   struct list_head *objects)
 {
 	struct drm_i915_gem_object *obj;
@@ -621,9 +649,9 @@ static int igt_ctx_exec(void *arg)
 		unsigned long ncontexts, ndwords, dw;
 		struct i915_request *tq[5] = {};
 		struct igt_live_test t;
-		struct drm_file *file;
 		IGT_TIMEOUT(end_time);
 		LIST_HEAD(objects);
+		struct file *file;
 
 		if (!intel_engine_can_store_dword(engine))
 			continue;
@@ -716,7 +744,7 @@ out_file:
 		if (igt_live_test_end(&t))
 			err = -EIO;
 
-		mock_file_free(i915, file);
+		fput(file);
 		if (err)
 			return err;
 
@@ -733,7 +761,7 @@ static int igt_shared_ctx_exec(void *arg)
 	struct i915_gem_context *parent;
 	struct intel_engine_cs *engine;
 	struct igt_live_test t;
-	struct drm_file *file;
+	struct file *file;
 	int err = 0;
 
 	/*
@@ -786,14 +814,15 @@ static int igt_shared_ctx_exec(void *arg)
 			}
 
 			mutex_lock(&ctx->mutex);
-			__assign_ppgtt(ctx, parent->vm);
+			__assign_ppgtt(ctx, ctx_vm(parent));
 			mutex_unlock(&ctx->mutex);
 
 			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
 			GEM_BUG_ON(IS_ERR(ce));
 
 			if (!obj) {
-				obj = create_test_object(parent->vm, file, &objects);
+				obj = create_test_object(ctx_vm(parent),
+							 file, &objects);
 				if (IS_ERR(obj)) {
 					err = PTR_ERR(obj);
 					intel_context_put(ce);
@@ -854,7 +883,7 @@ out_test:
 	if (igt_live_test_end(&t))
 		err = -EIO;
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -1140,8 +1169,7 @@ out:
 		igt_spinner_end(spin);
 
 	if ((flags & TEST_IDLE) && ret == 0) {
-		ret = intel_gt_wait_for_idle(ce->engine->gt,
-					     MAX_SCHEDULE_TIMEOUT);
+		ret = igt_flush_test(ce->engine->i915);
 		if (ret)
 			return ret;
 
@@ -1163,9 +1191,11 @@ __sseu_test(const char *name,
 	struct igt_spinner *spin = NULL;
 	int ret;
 
+	intel_engine_pm_get(ce->engine);
+
 	ret = __sseu_prepare(name, flags, ce, &spin);
 	if (ret)
-		return ret;
+		goto out_pm;
 
 	ret = intel_context_reconfigure_sseu(ce, sseu);
 	if (ret)
@@ -1180,6 +1210,8 @@ out_spin:
 		igt_spinner_fini(spin);
 		kfree(spin);
 	}
+out_pm:
+	intel_engine_pm_put(ce->engine);
 	return ret;
 }
 
@@ -1232,8 +1264,7 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
 			hweight32(engine->sseu.slice_mask),
 			hweight32(pg_sseu.slice_mask));
 
-		ce = intel_context_create(engine->kernel_context->gem_context,
-					  engine);
+		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			ret = PTR_ERR(ce);
 			goto out_put;
@@ -1311,16 +1342,18 @@ static int igt_ctx_sseu(void *arg)
 static int igt_ctx_readonly(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
+	unsigned long idx, ndwords, dw, num_engines;
 	struct drm_i915_gem_object *obj = NULL;
 	struct i915_request *tq[5] = {};
+	struct i915_gem_engines_iter it;
 	struct i915_address_space *vm;
 	struct i915_gem_context *ctx;
-	unsigned long idx, ndwords, dw;
+	struct intel_context *ce;
 	struct igt_live_test t;
-	struct drm_file *file;
 	I915_RND_STATE(prng);
 	IGT_TIMEOUT(end_time);
 	LIST_HEAD(objects);
+	struct file *file;
 	int err = -ENODEV;
 
 	/*
@@ -1343,21 +1376,21 @@ static int igt_ctx_readonly(void *arg)
 		goto out_file;
 	}
 
-	rcu_read_lock();
-	vm = rcu_dereference(ctx->vm) ?: &i915->ggtt.alias->vm;
+	vm = ctx_vm(ctx) ?: &i915->ggtt.alias->vm;
 	if (!vm || !vm->has_read_only) {
-		rcu_read_unlock();
 		err = 0;
 		goto out_file;
 	}
-	rcu_read_unlock();
+
+	num_engines = 0;
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it)
+		if (intel_engine_can_store_dword(ce->engine))
+			num_engines++;
+	i915_gem_context_unlock_engines(ctx);
 
 	ndwords = 0;
 	dw = 0;
 	while (!time_after(jiffies, end_time)) {
-		struct i915_gem_engines_iter it;
-		struct intel_context *ce;
-
 		for_each_gem_engine(ce,
 				    i915_gem_context_lock_engines(ctx), it) {
 			if (!intel_engine_can_store_dword(ce->engine))
@@ -1380,7 +1413,7 @@ static int igt_ctx_readonly(void *arg)
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       ce->engine->name,
-				       yesno(!!rcu_access_pointer(ctx->vm)),
+				       yesno(!!ctx_vm(ctx)),
 				       err);
 				i915_gem_context_unlock_engines(ctx);
 				goto out_file;
@@ -1400,8 +1433,8 @@ static int igt_ctx_readonly(void *arg)
 		}
 		i915_gem_context_unlock_engines(ctx);
 	}
-	pr_info("Submitted %lu dwords (across %u engines)\n",
-		ndwords, RUNTIME_INFO(i915)->num_engines);
+	pr_info("Submitted %lu dwords (across %lu engines)\n",
+		ndwords, num_engines);
 
 	dw = 0;
 	idx = 0;
@@ -1426,7 +1459,7 @@ out_file:
 	if (igt_live_test_end(&t))
 		err = -EIO;
 
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -1466,7 +1499,7 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto err;
+		goto out;
 	}
 
 	*cmd++ = MI_STORE_DWORD_IMM_GEN4;
@@ -1488,12 +1521,12 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
-		goto err_vm;
+		goto out_vm;
 	}
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_OFFSET_FIXED);
 	if (err)
-		goto err_vm;
+		goto out_vm;
 
 	err = check_scratch(vm, offset);
 	if (err)
@@ -1517,22 +1550,20 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	if (err)
 		goto skip_request;
 
-	i915_vma_unpin_and_release(&vma, 0);
+	i915_vma_unpin(vma);
 
 	i915_request_add(rq);
 
-	i915_vm_put(vm);
-	return 0;
-
+	goto out_vm;
 skip_request:
 	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_unpin:
 	i915_vma_unpin(vma);
-err_vm:
+out_vm:
 	i915_vm_put(vm);
-err:
+out:
 	i915_gem_object_put(obj);
 	return err;
 }
@@ -1560,7 +1591,7 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto err;
+		goto out;
 	}
 
 	memset(cmd, POISON_INUSE, PAGE_SIZE);
@@ -1592,12 +1623,12 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
-		goto err_vm;
+		goto out_vm;
 	}
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_OFFSET_FIXED);
 	if (err)
-		goto err_vm;
+		goto out_vm;
 
 	err = check_scratch(vm, offset);
 	if (err)
@@ -1630,29 +1661,27 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	err = i915_gem_object_set_to_cpu_domain(obj, false);
 	i915_gem_object_unlock(obj);
 	if (err)
-		goto err_vm;
+		goto out_vm;
 
 	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto err_vm;
+		goto out_vm;
 	}
 
 	*value = cmd[result / sizeof(*cmd)];
 	i915_gem_object_unpin_map(obj);
-	i915_gem_object_put(obj);
-
-	return 0;
 
+	goto out_vm;
 skip_request:
 	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_unpin:
 	i915_vma_unpin(vma);
-err_vm:
+out_vm:
 	i915_vm_put(vm);
-err:
+out:
 	i915_gem_object_put(obj);
 	return err;
 }
@@ -1661,11 +1690,11 @@ static int igt_vm_isolation(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_gem_context *ctx_a, *ctx_b;
+	unsigned long num_engines, count;
 	struct intel_engine_cs *engine;
 	struct igt_live_test t;
-	struct drm_file *file;
 	I915_RND_STATE(prng);
-	unsigned long count;
+	struct file *file;
 	u64 vm_total;
 	int err;
 
@@ -1698,14 +1727,15 @@ static int igt_vm_isolation(void *arg)
 	}
 
 	/* We can only test vm isolation, if the vm are distinct */
-	if (ctx_a->vm == ctx_b->vm)
+	if (ctx_vm(ctx_a) == ctx_vm(ctx_b))
 		goto out_file;
 
-	vm_total = ctx_a->vm->total;
-	GEM_BUG_ON(ctx_b->vm->total != vm_total);
+	vm_total = ctx_vm(ctx_a)->total;
+	GEM_BUG_ON(ctx_vm(ctx_b)->total != vm_total);
 	vm_total -= I915_GTT_PAGE_SIZE;
 
 	count = 0;
+	num_engines = 0;
 	for_each_uabi_engine(engine, i915) {
 		IGT_TIMEOUT(end_time);
 		unsigned long this = 0;
@@ -1743,14 +1773,15 @@ static int igt_vm_isolation(void *arg)
 			this++;
 		}
 		count += this;
+		num_engines++;
 	}
-	pr_info("Checked %lu scratch offsets across %d engines\n",
-		count, RUNTIME_INFO(i915)->num_engines);
+	pr_info("Checked %lu scratch offsets across %lu engines\n",
+		count, num_engines);
 
 out_file:
 	if (igt_live_test_end(&t))
 		err = -EIO;
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index d85d1ce273ca..2a52b92586b9 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -254,106 +254,6 @@ err_obj:
 	return err;
 }
 
-static int igt_dmabuf_export_kmap(void *arg)
-{
-	struct drm_i915_private *i915 = arg;
-	struct drm_i915_gem_object *obj;
-	struct dma_buf *dmabuf;
-	void *ptr;
-	int err;
-
-	obj = i915_gem_object_create_shmem(i915, 2 * PAGE_SIZE);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
-
-	dmabuf = i915_gem_prime_export(&obj->base, 0);
-	i915_gem_object_put(obj);
-	if (IS_ERR(dmabuf)) {
-		err = PTR_ERR(dmabuf);
-		pr_err("i915_gem_prime_export failed with err=%d\n", err);
-		return err;
-	}
-
-	ptr = dma_buf_kmap(dmabuf, 0);
-	if (!ptr) {
-		pr_err("dma_buf_kmap failed\n");
-		err = -ENOMEM;
-		goto err;
-	}
-
-	if (memchr_inv(ptr, 0, PAGE_SIZE)) {
-		dma_buf_kunmap(dmabuf, 0, ptr);
-		pr_err("Exported page[0] not initialiased to zero!\n");
-		err = -EINVAL;
-		goto err;
-	}
-
-	memset(ptr, 0xc5, PAGE_SIZE);
-	dma_buf_kunmap(dmabuf, 0, ptr);
-
-	ptr = i915_gem_object_pin_map(obj, I915_MAP_WB);
-	if (IS_ERR(ptr)) {
-		err = PTR_ERR(ptr);
-		pr_err("i915_gem_object_pin_map failed with err=%d\n", err);
-		goto err;
-	}
-	memset(ptr + PAGE_SIZE, 0xaa, PAGE_SIZE);
-	i915_gem_object_flush_map(obj);
-	i915_gem_object_unpin_map(obj);
-
-	ptr = dma_buf_kmap(dmabuf, 1);
-	if (!ptr) {
-		pr_err("dma_buf_kmap failed\n");
-		err = -ENOMEM;
-		goto err;
-	}
-
-	if (memchr_inv(ptr, 0xaa, PAGE_SIZE)) {
-		dma_buf_kunmap(dmabuf, 1, ptr);
-		pr_err("Exported page[1] not set to 0xaa!\n");
-		err = -EINVAL;
-		goto err;
-	}
-
-	memset(ptr, 0xc5, PAGE_SIZE);
-	dma_buf_kunmap(dmabuf, 1, ptr);
-
-	ptr = dma_buf_kmap(dmabuf, 0);
-	if (!ptr) {
-		pr_err("dma_buf_kmap failed\n");
-		err = -ENOMEM;
-		goto err;
-	}
-	if (memchr_inv(ptr, 0xc5, PAGE_SIZE)) {
-		dma_buf_kunmap(dmabuf, 0, ptr);
-		pr_err("Exported page[0] did not retain 0xc5!\n");
-		err = -EINVAL;
-		goto err;
-	}
-	dma_buf_kunmap(dmabuf, 0, ptr);
-
-	ptr = dma_buf_kmap(dmabuf, 2);
-	if (ptr) {
-		pr_err("Erroneously kmapped beyond the end of the object!\n");
-		dma_buf_kunmap(dmabuf, 2, ptr);
-		err = -EINVAL;
-		goto err;
-	}
-
-	ptr = dma_buf_kmap(dmabuf, -1);
-	if (ptr) {
-		pr_err("Erroneously kmapped before the start of the object!\n");
-		dma_buf_kunmap(dmabuf, -1, ptr);
-		err = -EINVAL;
-		goto err;
-	}
-
-	err = 0;
-err:
-	dma_buf_put(dmabuf);
-	return err;
-}
-
 int i915_gem_dmabuf_mock_selftests(void)
 {
 	static const struct i915_subtest tests[] = {
@@ -362,7 +262,6 @@ int i915_gem_dmabuf_mock_selftests(void)
 		SUBTEST(igt_dmabuf_import),
 		SUBTEST(igt_dmabuf_import_ownership),
 		SUBTEST(igt_dmabuf_export_vmap),
-		SUBTEST(igt_dmabuf_export_kmap),
 	};
 	struct drm_i915_private *i915;
 	int err;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 29b2077b73d2..ef7c74cff28a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -6,12 +6,15 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gem/i915_gem_region.h"
 #include "huge_gem_object.h"
 #include "i915_selftest.h"
 #include "selftests/i915_random.h"
 #include "selftests/igt_flush_test.h"
+#include "selftests/igt_mmap.h"
 
 struct tile {
 	unsigned int width;
@@ -161,7 +164,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 	kunmap(p);
 
 out:
-	i915_vma_destroy(vma);
+	__i915_vma_put(vma);
 	return err;
 }
 
@@ -255,7 +258,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj,
 		if (err)
 			return err;
 
-		i915_vma_destroy(vma);
+		__i915_vma_put(vma);
 
 		if (igt_timeout(end_time,
 				"%s: timed out after tiling=%d stride=%d\n",
@@ -535,7 +538,7 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 		if (err)
 			return err;
 
-		rq = i915_request_create(engine->kernel_context);
+		rq = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(rq)) {
 			i915_vma_unpin(vma);
 			return PTR_ERR(rq);
@@ -563,16 +566,16 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 			       int expected)
 {
 	struct drm_i915_gem_object *obj;
-	int err;
+	struct i915_mmap_offset *mmo;
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	err = create_mmap_offset(obj);
+	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
 	i915_gem_object_put(obj);
 
-	return err == expected;
+	return PTR_ERR_OR_ZERO(mmo) == expected;
 }
 
 static void disable_retire_worker(struct drm_i915_private *i915)
@@ -606,28 +609,50 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct drm_mm *mm = &i915->drm.vma_offset_manager->vm_addr_space_mm;
 	struct drm_i915_gem_object *obj;
-	struct drm_mm_node resv, *hole;
-	u64 hole_start, hole_end;
-	int loop, err;
+	struct drm_mm_node *hole, *next;
+	struct i915_mmap_offset *mmo;
+	int loop, err = 0;
 
 	/* Disable background reaper */
 	disable_retire_worker(i915);
 	GEM_BUG_ON(!i915->gt.awake);
+	intel_gt_retire_requests(&i915->gt);
+	i915_gem_drain_freed_objects(i915);
 
 	/* Trim the device mmap space to only a page */
-	memset(&resv, 0, sizeof(resv));
-	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
-		resv.start = hole_start;
-		resv.size = hole_end - hole_start - 1; /* PAGE_SIZE units */
-		mmap_offset_lock(i915);
-		err = drm_mm_reserve_node(mm, &resv);
-		mmap_offset_unlock(i915);
+	mmap_offset_lock(i915);
+	loop = 1; /* PAGE_SIZE units */
+	list_for_each_entry_safe(hole, next, &mm->hole_stack, hole_stack) {
+		struct drm_mm_node *resv;
+
+		resv = kzalloc(sizeof(*resv), GFP_NOWAIT);
+		if (!resv) {
+			err = -ENOMEM;
+			goto out_park;
+		}
+
+		resv->start = drm_mm_hole_node_start(hole) + loop;
+		resv->size = hole->hole_size - loop;
+		resv->color = -1ul;
+		loop = 0;
+
+		if (!resv->size) {
+			kfree(resv);
+			continue;
+		}
+
+		pr_debug("Reserving hole [%llx + %llx]\n",
+			 resv->start, resv->size);
+
+		err = drm_mm_reserve_node(mm, resv);
 		if (err) {
 			pr_err("Failed to trim VMA manager, err=%d\n", err);
+			kfree(resv);
 			goto out_park;
 		}
-		break;
 	}
+	GEM_BUG_ON(!list_is_singular(&mm->hole_stack));
+	mmap_offset_unlock(i915);
 
 	/* Just fits! */
 	if (!assert_mmap_offset(i915, PAGE_SIZE, 0)) {
@@ -650,9 +675,10 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		goto out;
 	}
 
-	err = create_mmap_offset(obj);
-	if (err) {
+	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
+	if (IS_ERR(mmo)) {
 		pr_err("Unable to insert object into reclaimed hole\n");
+		err = PTR_ERR(mmo);
 		goto err_obj;
 	}
 
@@ -684,9 +710,15 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 out:
 	mmap_offset_lock(i915);
-	drm_mm_remove_node(&resv);
-	mmap_offset_unlock(i915);
 out_park:
+	drm_mm_for_each_node_safe(hole, next, mm) {
+		if (hole->color != -1ul)
+			continue;
+
+		drm_mm_remove_node(hole);
+		kfree(hole);
+	}
+	mmap_offset_unlock(i915);
 	restore_retire_worker(i915);
 	return err;
 err_obj:
@@ -694,12 +726,515 @@ err_obj:
 	goto out;
 }
 
+static int gtt_set(struct drm_i915_gem_object *obj)
+{
+	struct i915_vma *vma;
+	void __iomem *map;
+	int err = 0;
+
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	intel_gt_pm_get(vma->vm->gt);
+	map = i915_vma_pin_iomap(vma);
+	i915_vma_unpin(vma);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto out;
+	}
+
+	memset_io(map, POISON_INUSE, obj->base.size);
+	i915_vma_unpin_iomap(vma);
+
+out:
+	intel_gt_pm_put(vma->vm->gt);
+	return err;
+}
+
+static int gtt_check(struct drm_i915_gem_object *obj)
+{
+	struct i915_vma *vma;
+	void __iomem *map;
+	int err = 0;
+
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	intel_gt_pm_get(vma->vm->gt);
+	map = i915_vma_pin_iomap(vma);
+	i915_vma_unpin(vma);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto out;
+	}
+
+	if (memchr_inv((void __force *)map, POISON_FREE, obj->base.size)) {
+		pr_err("%s: Write via mmap did not land in backing store (GTT)\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+	}
+	i915_vma_unpin_iomap(vma);
+
+out:
+	intel_gt_pm_put(vma->vm->gt);
+	return err;
+}
+
+static int wc_set(struct drm_i915_gem_object *obj)
+{
+	void *vaddr;
+
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
+
+	memset(vaddr, POISON_INUSE, obj->base.size);
+	i915_gem_object_flush_map(obj);
+	i915_gem_object_unpin_map(obj);
+
+	return 0;
+}
+
+static int wc_check(struct drm_i915_gem_object *obj)
+{
+	void *vaddr;
+	int err = 0;
+
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
+
+	if (memchr_inv(vaddr, POISON_FREE, obj->base.size)) {
+		pr_err("%s: Write via mmap did not land in backing store (WC)\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+	}
+	i915_gem_object_unpin_map(obj);
+
+	return err;
+}
+
+static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type)
+{
+	if (type == I915_MMAP_TYPE_GTT &&
+	    !i915_ggtt_has_aperture(&to_i915(obj->base.dev)->ggtt))
+		return false;
+
+	if (type != I915_MMAP_TYPE_GTT &&
+	    !i915_gem_object_type_has(obj,
+				      I915_GEM_OBJECT_HAS_STRUCT_PAGE |
+				      I915_GEM_OBJECT_HAS_IOMEM))
+		return false;
+
+	return true;
+}
+
+#define expand32(x) (((x) << 0) | ((x) << 8) | ((x) << 16) | ((x) << 24))
+static int __igt_mmap(struct drm_i915_private *i915,
+		      struct drm_i915_gem_object *obj,
+		      enum i915_mmap_type type)
+{
+	struct i915_mmap_offset *mmo;
+	struct vm_area_struct *area;
+	unsigned long addr;
+	int err, i;
+
+	if (!can_mmap(obj, type))
+		return 0;
+
+	err = wc_set(obj);
+	if (err == -ENXIO)
+		err = gtt_set(obj);
+	if (err)
+		return err;
+
+	mmo = mmap_offset_attach(obj, type, NULL);
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
+
+	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	pr_debug("igt_mmap(%s, %d) @ %lx\n", obj->mm.region->name, type, addr);
+
+	area = find_vma(current->mm, addr);
+	if (!area) {
+		pr_err("%s: Did not create a vm_area_struct for the mmap\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+		goto out_unmap;
+	}
+
+	if (area->vm_private_data != mmo) {
+		pr_err("%s: vm_area_struct did not point back to our mmap_offset object!\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+		goto out_unmap;
+	}
+
+	for (i = 0; i < obj->base.size / sizeof(u32); i++) {
+		u32 __user *ux = u64_to_user_ptr((u64)(addr + i * sizeof(*ux)));
+		u32 x;
+
+		if (get_user(x, ux)) {
+			pr_err("%s: Unable to read from mmap, offset:%zd\n",
+			       obj->mm.region->name, i * sizeof(x));
+			err = -EFAULT;
+			goto out_unmap;
+		}
+
+		if (x != expand32(POISON_INUSE)) {
+			pr_err("%s: Read incorrect value from mmap, offset:%zd, found:%x, expected:%x\n",
+			       obj->mm.region->name,
+			       i * sizeof(x), x, expand32(POISON_INUSE));
+			err = -EINVAL;
+			goto out_unmap;
+		}
+
+		x = expand32(POISON_FREE);
+		if (put_user(x, ux)) {
+			pr_err("%s: Unable to write to mmap, offset:%zd\n",
+			       obj->mm.region->name, i * sizeof(x));
+			err = -EFAULT;
+			goto out_unmap;
+		}
+	}
+
+	if (type == I915_MMAP_TYPE_GTT)
+		intel_gt_flush_ggtt_writes(&i915->gt);
+
+	err = wc_check(obj);
+	if (err == -ENXIO)
+		err = gtt_check(obj);
+out_unmap:
+	vm_munmap(addr, obj->base.size);
+	return err;
+}
+
+static int igt_mmap(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
+
+	for_each_memory_region(mr, i915, id) {
+		unsigned long sizes[] = {
+			PAGE_SIZE,
+			mr->min_page_size,
+			SZ_4M,
+		};
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+			struct drm_i915_gem_object *obj;
+			int err;
+
+			obj = i915_gem_object_create_region(mr, sizes[i], 0);
+			if (obj == ERR_PTR(-ENODEV))
+				continue;
+
+			if (IS_ERR(obj))
+				return PTR_ERR(obj);
+
+			err = __igt_mmap(i915, obj, I915_MMAP_TYPE_GTT);
+			if (err == 0)
+				err = __igt_mmap(i915, obj, I915_MMAP_TYPE_WC);
+
+			i915_gem_object_put(obj);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int __igt_mmap_gpu(struct drm_i915_private *i915,
+			  struct drm_i915_gem_object *obj,
+			  enum i915_mmap_type type)
+{
+	struct intel_engine_cs *engine;
+	struct i915_mmap_offset *mmo;
+	unsigned long addr;
+	u32 __user *ux;
+	u32 bbe;
+	int err;
+
+	/*
+	 * Verify that the mmap access into the backing store aligns with
+	 * that of the GPU, i.e. that mmap is indeed writing into the same
+	 * page as being read by the GPU.
+	 */
+
+	if (!can_mmap(obj, type))
+		return 0;
+
+	err = wc_set(obj);
+	if (err == -ENXIO)
+		err = gtt_set(obj);
+	if (err)
+		return err;
+
+	mmo = mmap_offset_attach(obj, type, NULL);
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
+
+	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	ux = u64_to_user_ptr((u64)addr);
+	bbe = MI_BATCH_BUFFER_END;
+	if (put_user(bbe, ux)) {
+		pr_err("%s: Unable to write to mmap\n", obj->mm.region->name);
+		err = -EFAULT;
+		goto out_unmap;
+	}
+
+	if (type == I915_MMAP_TYPE_GTT)
+		intel_gt_flush_ggtt_writes(&i915->gt);
+
+	for_each_uabi_engine(engine, i915) {
+		struct i915_request *rq;
+		struct i915_vma *vma;
+
+		vma = i915_vma_instance(obj, engine->kernel_context->vm, NULL);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			goto out_unmap;
+		}
+
+		err = i915_vma_pin(vma, 0, 0, PIN_USER);
+		if (err)
+			goto out_unmap;
+
+		rq = i915_request_create(engine->kernel_context);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_unpin;
+		}
+
+		i915_vma_lock(vma);
+		err = i915_request_await_object(rq, vma->obj, false);
+		if (err == 0)
+			err = i915_vma_move_to_active(vma, rq, 0);
+		i915_vma_unlock(vma);
+
+		err = engine->emit_bb_start(rq, vma->node.start, 0, 0);
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+			struct drm_printer p =
+				drm_info_printer(engine->i915->drm.dev);
+
+			pr_err("%s(%s, %s): Failed to execute batch\n",
+			       __func__, engine->name, obj->mm.region->name);
+			intel_engine_dump(engine, &p,
+					  "%s\n", engine->name);
+
+			intel_gt_set_wedged(engine->gt);
+			err = -EIO;
+		}
+		i915_request_put(rq);
+
+out_unpin:
+		i915_vma_unpin(vma);
+		if (err)
+			goto out_unmap;
+	}
+
+out_unmap:
+	vm_munmap(addr, obj->base.size);
+	return err;
+}
+
+static int igt_mmap_gpu(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
+
+	for_each_memory_region(mr, i915, id) {
+		struct drm_i915_gem_object *obj;
+		int err;
+
+		obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0);
+		if (obj == ERR_PTR(-ENODEV))
+			continue;
+
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_GTT);
+		if (err == 0)
+			err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_WC);
+
+		i915_gem_object_put(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int check_present_pte(pte_t *pte, unsigned long addr, void *data)
+{
+	if (!pte_present(*pte) || pte_none(*pte)) {
+		pr_err("missing PTE:%lx\n",
+		       (addr - (unsigned long)data) >> PAGE_SHIFT);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int check_absent_pte(pte_t *pte, unsigned long addr, void *data)
+{
+	if (pte_present(*pte) && !pte_none(*pte)) {
+		pr_err("present PTE:%lx; expected to be revoked\n",
+		       (addr - (unsigned long)data) >> PAGE_SHIFT);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int check_present(unsigned long addr, unsigned long len)
+{
+	return apply_to_page_range(current->mm, addr, len,
+				   check_present_pte, (void *)addr);
+}
+
+static int check_absent(unsigned long addr, unsigned long len)
+{
+	return apply_to_page_range(current->mm, addr, len,
+				   check_absent_pte, (void *)addr);
+}
+
+static int prefault_range(u64 start, u64 len)
+{
+	const char __user *addr, *end;
+	char __maybe_unused c;
+	int err;
+
+	addr = u64_to_user_ptr(start);
+	end = addr + len;
+
+	for (; addr < end; addr += PAGE_SIZE) {
+		err = __get_user(c, addr);
+		if (err)
+			return err;
+	}
+
+	return __get_user(c, end - 1);
+}
+
+static int __igt_mmap_revoke(struct drm_i915_private *i915,
+			     struct drm_i915_gem_object *obj,
+			     enum i915_mmap_type type)
+{
+	struct i915_mmap_offset *mmo;
+	unsigned long addr;
+	int err;
+
+	if (!can_mmap(obj, type))
+		return 0;
+
+	mmo = mmap_offset_attach(obj, type, NULL);
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
+
+	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	err = prefault_range(addr, obj->base.size);
+	if (err)
+		goto out_unmap;
+
+	GEM_BUG_ON(mmo->mmap_type == I915_MMAP_TYPE_GTT &&
+		   !atomic_read(&obj->bind_count));
+
+	err = check_present(addr, obj->base.size);
+	if (err) {
+		pr_err("%s: was not present\n", obj->mm.region->name);
+		goto out_unmap;
+	}
+
+	/*
+	 * After unbinding the object from the GGTT, its address may be reused
+	 * for other objects. Ergo we have to revoke the previous mmap PTE
+	 * access as it no longer points to the same object.
+	 */
+	err = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE);
+	if (err) {
+		pr_err("Failed to unbind object!\n");
+		goto out_unmap;
+	}
+	GEM_BUG_ON(atomic_read(&obj->bind_count));
+
+	if (type != I915_MMAP_TYPE_GTT) {
+		__i915_gem_object_put_pages(obj);
+		if (i915_gem_object_has_pages(obj)) {
+			pr_err("Failed to put-pages object!\n");
+			err = -EINVAL;
+			goto out_unmap;
+		}
+	}
+
+	err = check_absent(addr, obj->base.size);
+	if (err) {
+		pr_err("%s: was not absent\n", obj->mm.region->name);
+		goto out_unmap;
+	}
+
+out_unmap:
+	vm_munmap(addr, obj->base.size);
+	return err;
+}
+
+static int igt_mmap_revoke(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
+
+	for_each_memory_region(mr, i915, id) {
+		struct drm_i915_gem_object *obj;
+		int err;
+
+		obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0);
+		if (obj == ERR_PTR(-ENODEV))
+			continue;
+
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_GTT);
+		if (err == 0)
+			err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_WC);
+
+		i915_gem_object_put(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 int i915_gem_mman_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_partial_tiling),
 		SUBTEST(igt_smoke_tiling),
 		SUBTEST(igt_mmap_offset_exhaustion),
+		SUBTEST(igt_mmap),
+		SUBTEST(igt_mmap_revoke),
+		SUBTEST(igt_mmap_gpu),
 	};
 
 	return i915_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
index e8132aca0bb6..62077fe46715 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
@@ -41,6 +41,7 @@ static int __perf_fill_blt(struct drm_i915_gem_object *obj)
 		if (!engine)
 			return 0;
 
+		intel_engine_pm_get(engine);
 		for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
 			struct intel_context *ce = engine->kernel_context;
 			ktime_t t0, t1;
@@ -49,17 +50,20 @@ static int __perf_fill_blt(struct drm_i915_gem_object *obj)
 
 			err = i915_gem_object_fill_blt(obj, ce, 0);
 			if (err)
-				return err;
+				break;
 
 			err = i915_gem_object_wait(obj,
 						   I915_WAIT_ALL,
 						   MAX_SCHEDULE_TIMEOUT);
 			if (err)
-				return err;
+				break;
 
 			t1 = ktime_get();
 			t[pass] = ktime_sub(t1, t0);
 		}
+		intel_engine_pm_put(engine);
+		if (err)
+			return err;
 
 		sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
 		pr_info("%s: blt %zd KiB fill: %lld MiB/s\n",
@@ -109,6 +113,7 @@ static int __perf_copy_blt(struct drm_i915_gem_object *src,
 		struct intel_engine_cs *engine;
 		ktime_t t[5];
 		int pass;
+		int err = 0;
 
 		engine = intel_engine_lookup_user(i915,
 						  I915_ENGINE_CLASS_COPY,
@@ -116,26 +121,29 @@ static int __perf_copy_blt(struct drm_i915_gem_object *src,
 		if (!engine)
 			return 0;
 
+		intel_engine_pm_get(engine);
 		for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
 			struct intel_context *ce = engine->kernel_context;
 			ktime_t t0, t1;
-			int err;
 
 			t0 = ktime_get();
 
 			err = i915_gem_object_copy_blt(src, dst, ce);
 			if (err)
-				return err;
+				break;
 
 			err = i915_gem_object_wait(dst,
 						   I915_WAIT_ALL,
 						   MAX_SCHEDULE_TIMEOUT);
 			if (err)
-				return err;
+				break;
 
 			t1 = ktime_get();
 			t[pass] = ktime_sub(t1, t0);
 		}
+		intel_engine_pm_put(engine);
+		if (err)
+			return err;
 
 		sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
 		pr_info("%s: blt %zd KiB copy: %lld MiB/s\n",
@@ -186,6 +194,8 @@ err_src:
 
 struct igt_thread_arg {
 	struct drm_i915_private *i915;
+	struct i915_gem_context *ctx;
+	struct file *file;
 	struct rnd_state prng;
 	unsigned int n_cpus;
 };
@@ -198,24 +208,20 @@ static int igt_fill_blt_thread(void *arg)
 	struct drm_i915_gem_object *obj;
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
-	struct drm_file *file;
 	unsigned int prio;
 	IGT_TIMEOUT(end);
 	int err;
 
-	file = mock_file(i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+	ctx = thread->ctx;
+	if (!ctx) {
+		ctx = live_context(i915, thread->file);
+		if (IS_ERR(ctx))
+			return PTR_ERR(ctx);
 
-	ctx = live_context(i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out_file;
+		prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
+		ctx->sched.priority = I915_USER_PRIORITY(prio);
 	}
 
-	prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
-	ctx->sched.priority = I915_USER_PRIORITY(prio);
-
 	ce = i915_gem_context_get_engine(ctx, BCS0);
 	GEM_BUG_ON(IS_ERR(ce));
 
@@ -300,8 +306,6 @@ err_flush:
 		err = 0;
 
 	intel_context_put(ce);
-out_file:
-	mock_file_free(i915, file);
 	return err;
 }
 
@@ -313,24 +317,20 @@ static int igt_copy_blt_thread(void *arg)
 	struct drm_i915_gem_object *src, *dst;
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
-	struct drm_file *file;
 	unsigned int prio;
 	IGT_TIMEOUT(end);
 	int err;
 
-	file = mock_file(i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+	ctx = thread->ctx;
+	if (!ctx) {
+		ctx = live_context(i915, thread->file);
+		if (IS_ERR(ctx))
+			return PTR_ERR(ctx);
 
-	ctx = live_context(i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out_file;
+		prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
+		ctx->sched.priority = I915_USER_PRIORITY(prio);
 	}
 
-	prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
-	ctx->sched.priority = I915_USER_PRIORITY(prio);
-
 	ce = i915_gem_context_get_engine(ctx, BCS0);
 	GEM_BUG_ON(IS_ERR(ce));
 
@@ -431,19 +431,18 @@ err_flush:
 		err = 0;
 
 	intel_context_put(ce);
-out_file:
-	mock_file_free(i915, file);
 	return err;
 }
 
 static int igt_threaded_blt(struct drm_i915_private *i915,
-			    int (*blt_fn)(void *arg))
+			    int (*blt_fn)(void *arg),
+			    unsigned int flags)
+#define SINGLE_CTX BIT(0)
 {
 	struct igt_thread_arg *thread;
 	struct task_struct **tsk;
+	unsigned int n_cpus, i;
 	I915_RND_STATE(prng);
-	unsigned int n_cpus;
-	unsigned int i;
 	int err = 0;
 
 	n_cpus = num_online_cpus() + 1;
@@ -453,13 +452,27 @@ static int igt_threaded_blt(struct drm_i915_private *i915,
 		return 0;
 
 	thread = kcalloc(n_cpus, sizeof(struct igt_thread_arg), GFP_KERNEL);
-	if (!thread) {
-		kfree(tsk);
-		return 0;
+	if (!thread)
+		goto out_tsk;
+
+	thread[0].file = mock_file(i915);
+	if (IS_ERR(thread[0].file)) {
+		err = PTR_ERR(thread[0].file);
+		goto out_thread;
+	}
+
+	if (flags & SINGLE_CTX) {
+		thread[0].ctx = live_context(i915, thread[0].file);
+		if (IS_ERR(thread[0].ctx)) {
+			err = PTR_ERR(thread[0].ctx);
+			goto out_file;
+		}
 	}
 
 	for (i = 0; i < n_cpus; ++i) {
 		thread[i].i915 = i915;
+		thread[i].file = thread[0].file;
+		thread[i].ctx = thread[0].ctx;
 		thread[i].n_cpus = n_cpus;
 		thread[i].prng =
 			I915_RND_STATE_INITIALIZER(prandom_u32_state(&prng));
@@ -488,29 +501,42 @@ static int igt_threaded_blt(struct drm_i915_private *i915,
 		put_task_struct(tsk[i]);
 	}
 
-	kfree(tsk);
+out_file:
+	fput(thread[0].file);
+out_thread:
 	kfree(thread);
-
+out_tsk:
+	kfree(tsk);
 	return err;
 }
 
 static int igt_fill_blt(void *arg)
 {
-	return igt_threaded_blt(arg, igt_fill_blt_thread);
+	return igt_threaded_blt(arg, igt_fill_blt_thread, 0);
+}
+
+static int igt_fill_blt_ctx0(void *arg)
+{
+	return igt_threaded_blt(arg, igt_fill_blt_thread, SINGLE_CTX);
 }
 
 static int igt_copy_blt(void *arg)
 {
-	return igt_threaded_blt(arg, igt_copy_blt_thread);
+	return igt_threaded_blt(arg, igt_copy_blt_thread, 0);
+}
+
+static int igt_copy_blt_ctx0(void *arg)
+{
+	return igt_threaded_blt(arg, igt_copy_blt_thread, SINGLE_CTX);
 }
 
 int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
-		SUBTEST(perf_fill_blt),
-		SUBTEST(perf_copy_blt),
 		SUBTEST(igt_fill_blt),
+		SUBTEST(igt_fill_blt_ctx0),
 		SUBTEST(igt_copy_blt),
+		SUBTEST(igt_copy_blt_ctx0),
 	};
 
 	if (intel_gt_is_wedged(&i915->gt))
@@ -521,3 +547,16 @@ int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
 
 	return i915_live_subtests(tests, i915);
 }
+
+int i915_gem_object_blt_perf_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(perf_fill_blt),
+		SUBTEST(perf_copy_blt),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_live_subtests(tests, i915);
+}
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index 29b8984f0e47..384143aa7776 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -5,6 +5,7 @@
  */
 
 #include "mock_context.h"
+#include "selftests/mock_drm.h"
 #include "selftests/mock_gtt.h"
 
 struct i915_gem_context *
@@ -36,9 +37,7 @@ mock_context(struct drm_i915_private *i915,
 	if (name) {
 		struct i915_ppgtt *ppgtt;
 
-		ctx->name = kstrdup(name, GFP_KERNEL);
-		if (!ctx->name)
-			goto err_put;
+		strncpy(ctx->name, name, sizeof(ctx->name));
 
 		ppgtt = mock_ppgtt(i915, name);
 		if (!ppgtt)
@@ -74,16 +73,17 @@ void mock_init_contexts(struct drm_i915_private *i915)
 }
 
 struct i915_gem_context *
-live_context(struct drm_i915_private *i915, struct drm_file *file)
+live_context(struct drm_i915_private *i915, struct file *file)
 {
 	struct i915_gem_context *ctx;
 	int err;
+	u32 id;
 
 	ctx = i915_gem_create_context(i915, 0);
 	if (IS_ERR(ctx))
 		return ctx;
 
-	err = gem_context_register(ctx, file->driver_priv);
+	err = gem_context_register(ctx, to_drm_file(file)->driver_priv, &id);
 	if (err < 0)
 		goto err_ctx;
 
@@ -97,7 +97,16 @@ err_ctx:
 struct i915_gem_context *
 kernel_context(struct drm_i915_private *i915)
 {
-	return i915_gem_context_create_kernel(i915, I915_PRIORITY_NORMAL);
+	struct i915_gem_context *ctx;
+
+	ctx = i915_gem_create_context(i915, 0);
+	if (IS_ERR(ctx))
+		return ctx;
+
+	i915_gem_context_clear_bannable(ctx);
+	i915_gem_context_set_persistence(ctx);
+
+	return ctx;
 }
 
 void kernel_context_close(struct i915_gem_context *ctx)
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.h b/drivers/gpu/drm/i915/gem/selftests/mock_context.h
index 0b926653914f..fb83d2f09212 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.h
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.h
@@ -7,6 +7,9 @@
 #ifndef __MOCK_CONTEXT_H
 #define __MOCK_CONTEXT_H
 
+struct file;
+struct drm_i915_private;
+
 void mock_init_contexts(struct drm_i915_private *i915);
 
 struct i915_gem_context *
@@ -16,7 +19,7 @@ mock_context(struct drm_i915_private *i915,
 void mock_context_close(struct i915_gem_context *ctx);
 
 struct i915_gem_context *
-live_context(struct drm_i915_private *i915, struct drm_file *file);
+live_context(struct drm_i915_private *i915, struct file *file);
 
 struct i915_gem_context *kernel_context(struct drm_i915_private *i915);
 void kernel_context_close(struct i915_gem_context *ctx);
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
index b9e059d4328a..9272bef57092 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
@@ -76,20 +76,6 @@ static void mock_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	vm_unmap_ram(vaddr, mock->npages);
 }
 
-static void *mock_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	struct mock_dmabuf *mock = to_mock(dma_buf);
-
-	return kmap(mock->pages[page_num]);
-}
-
-static void mock_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
-{
-	struct mock_dmabuf *mock = to_mock(dma_buf);
-
-	return kunmap(mock->pages[page_num]);
-}
-
 static int mock_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
 {
 	return -ENODEV;
@@ -99,8 +85,6 @@ static const struct dma_buf_ops mock_dmabuf_ops =  {
 	.map_dma_buf = mock_map_dma_buf,
 	.unmap_dma_buf = mock_unmap_dma_buf,
 	.release = mock_dmabuf_release,
-	.map = mock_dmabuf_kmap,
-	.unmap = mock_dmabuf_kunmap,
 	.mmap = mock_dmabuf_mmap,
 	.vmap = mock_dmabuf_vmap,
 	.vunmap = mock_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.h b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.h
index f0f8bbd82dfc..22818bbb139d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.h
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.h
@@ -14,7 +14,7 @@ struct mock_dmabuf {
 	struct page *pages[];
 };
 
-static struct mock_dmabuf *to_mock(struct dma_buf *buf)
+static inline struct mock_dmabuf *to_mock(struct dma_buf *buf)
 {
 	return buf->priv;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_gem_object.h b/drivers/gpu/drm/i915/gem/selftests/mock_gem_object.h
index 370360b4a148..688511afa883 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_gem_object.h
@@ -7,6 +7,8 @@
 #ifndef __MOCK_GEM_OBJECT_H__
 #define __MOCK_GEM_OBJECT_H__
 
+#include "gem/i915_gem_object_types.h"
+
 struct mock_object {
 	struct drm_i915_gem_object base;
 };
diff --git a/drivers/gpu/drm/i915/gt/Makefile b/drivers/gpu/drm/i915/gt/Makefile
deleted file mode 100644
index 7e73aa587967..000000000000
--- a/drivers/gpu/drm/i915/gt/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
diff --git a/drivers/gpu/drm/i915/gt/debugfs_engines.c b/drivers/gpu/drm/i915/gt/debugfs_engines.c
new file mode 100644
index 000000000000..6a5e9ab20b94
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_engines.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <drm/drm_print.h>
+
+#include "debugfs_engines.h"
+#include "debugfs_gt.h"
+#include "i915_drv.h" /* for_each_engine! */
+#include "intel_engine.h"
+
+static int engines_show(struct seq_file *m, void *data)
+{
+	struct intel_gt *gt = m->private;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct drm_printer p;
+
+	p = drm_seq_file_printer(m);
+	for_each_engine(engine, gt, id)
+		intel_engine_dump(engine, &p, "%s\n", engine->name);
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(engines);
+
+void debugfs_engines_register(struct intel_gt *gt, struct dentry *root)
+{
+	static const struct debugfs_gt_file files[] = {
+		{ "engines", &engines_fops },
+	};
+
+	debugfs_gt_register_files(gt, root, files, ARRAY_SIZE(files));
+}
diff --git a/drivers/gpu/drm/i915/gt/debugfs_engines.h b/drivers/gpu/drm/i915/gt/debugfs_engines.h
new file mode 100644
index 000000000000..f69257eaa1cc
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_engines.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef DEBUGFS_ENGINES_H
+#define DEBUGFS_ENGINES_H
+
+struct intel_gt;
+struct dentry;
+
+void debugfs_engines_register(struct intel_gt *gt, struct dentry *root);
+
+#endif /* DEBUGFS_ENGINES_H */
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.c b/drivers/gpu/drm/i915/gt/debugfs_gt.c
new file mode 100644
index 000000000000..75255aaacaed
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/debugfs.h>
+
+#include "debugfs_engines.h"
+#include "debugfs_gt.h"
+#include "debugfs_gt_pm.h"
+#include "i915_drv.h"
+
+void debugfs_gt_register(struct intel_gt *gt)
+{
+	struct dentry *root;
+
+	if (!gt->i915->drm.primary->debugfs_root)
+		return;
+
+	root = debugfs_create_dir("gt", gt->i915->drm.primary->debugfs_root);
+	if (IS_ERR(root))
+		return;
+
+	debugfs_engines_register(gt, root);
+	debugfs_gt_pm_register(gt, root);
+}
+
+void debugfs_gt_register_files(struct intel_gt *gt,
+			       struct dentry *root,
+			       const struct debugfs_gt_file *files,
+			       unsigned long count)
+{
+	while (count--) {
+		if (!files->eval || files->eval(gt))
+			debugfs_create_file(files->name,
+					    0444, root, gt,
+					    files->fops);
+
+		files++;
+	}
+}
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.h b/drivers/gpu/drm/i915/gt/debugfs_gt.h
new file mode 100644
index 000000000000..4ea0f06cda8f
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef DEBUGFS_GT_H
+#define DEBUGFS_GT_H
+
+#include <linux/file.h>
+
+struct intel_gt;
+
+#define DEFINE_GT_DEBUGFS_ATTRIBUTE(__name)				\
+	static int __name ## _open(struct inode *inode, struct file *file) \
+{									\
+	return single_open(file, __name ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __name ## _fops = {			\
+	.owner = THIS_MODULE,						\
+	.open = __name ## _open,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+	.release = single_release,					\
+}
+
+void debugfs_gt_register(struct intel_gt *gt);
+
+struct debugfs_gt_file {
+	const char *name;
+	const struct file_operations *fops;
+	bool (*eval)(const struct intel_gt *gt);
+};
+
+void debugfs_gt_register_files(struct intel_gt *gt,
+			       struct dentry *root,
+			       const struct debugfs_gt_file *files,
+			       unsigned long count);
+
+#endif /* DEBUGFS_GT_H */
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
new file mode 100644
index 000000000000..059c9e5c002e
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
@@ -0,0 +1,601 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/seq_file.h>
+
+#include "debugfs_gt.h"
+#include "debugfs_gt_pm.h"
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_llc.h"
+#include "intel_rc6.h"
+#include "intel_rps.h"
+#include "intel_runtime_pm.h"
+#include "intel_sideband.h"
+#include "intel_uncore.h"
+
+static int fw_domains_show(struct seq_file *m, void *data)
+{
+	struct intel_gt *gt = m->private;
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_uncore_forcewake_domain *fw_domain;
+	unsigned int tmp;
+
+	seq_printf(m, "user.bypass_count = %u\n",
+		   uncore->user_forcewake_count);
+
+	for_each_fw_domain(fw_domain, uncore, tmp)
+		seq_printf(m, "%s.wake_count = %u\n",
+			   intel_uncore_forcewake_domain_to_str(fw_domain->id),
+			   READ_ONCE(fw_domain->wake_count));
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(fw_domains);
+
+static void print_rc6_res(struct seq_file *m,
+			  const char *title,
+			  const i915_reg_t reg)
+{
+	struct intel_gt *gt = m->private;
+	intel_wakeref_t wakeref;
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+		seq_printf(m, "%s %u (%llu us)\n", title,
+			   intel_uncore_read(gt->uncore, reg),
+			   intel_rc6_residency_us(&gt->rc6, reg));
+}
+
+static int vlv_drpc(struct seq_file *m)
+{
+	struct intel_gt *gt = m->private;
+	struct intel_uncore *uncore = gt->uncore;
+	u32 rcctl1, pw_status;
+
+	pw_status = intel_uncore_read(uncore, VLV_GTLC_PW_STATUS);
+	rcctl1 = intel_uncore_read(uncore, GEN6_RC_CONTROL);
+
+	seq_printf(m, "RC6 Enabled: %s\n",
+		   yesno(rcctl1 & (GEN7_RC_CTL_TO_MODE |
+					GEN6_RC_CTL_EI_MODE(1))));
+	seq_printf(m, "Render Power Well: %s\n",
+		   (pw_status & VLV_GTLC_PW_RENDER_STATUS_MASK) ? "Up" : "Down");
+	seq_printf(m, "Media Power Well: %s\n",
+		   (pw_status & VLV_GTLC_PW_MEDIA_STATUS_MASK) ? "Up" : "Down");
+
+	print_rc6_res(m, "Render RC6 residency since boot:", VLV_GT_RENDER_RC6);
+	print_rc6_res(m, "Media RC6 residency since boot:", VLV_GT_MEDIA_RC6);
+
+	return fw_domains_show(m, NULL);
+}
+
+static int gen6_drpc(struct seq_file *m)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	u32 gt_core_status, rcctl1, rc6vids = 0;
+	u32 gen9_powergate_enable = 0, gen9_powergate_status = 0;
+
+	gt_core_status = intel_uncore_read_fw(uncore, GEN6_GT_CORE_STATUS);
+
+	rcctl1 = intel_uncore_read(uncore, GEN6_RC_CONTROL);
+	if (INTEL_GEN(i915) >= 9) {
+		gen9_powergate_enable =
+			intel_uncore_read(uncore, GEN9_PG_ENABLE);
+		gen9_powergate_status =
+			intel_uncore_read(uncore, GEN9_PWRGT_DOMAIN_STATUS);
+	}
+
+	if (INTEL_GEN(i915) <= 7)
+		sandybridge_pcode_read(i915, GEN6_PCODE_READ_RC6VIDS,
+				       &rc6vids, NULL);
+
+	seq_printf(m, "RC1e Enabled: %s\n",
+		   yesno(rcctl1 & GEN6_RC_CTL_RC1e_ENABLE));
+	seq_printf(m, "RC6 Enabled: %s\n",
+		   yesno(rcctl1 & GEN6_RC_CTL_RC6_ENABLE));
+	if (INTEL_GEN(i915) >= 9) {
+		seq_printf(m, "Render Well Gating Enabled: %s\n",
+			   yesno(gen9_powergate_enable & GEN9_RENDER_PG_ENABLE));
+		seq_printf(m, "Media Well Gating Enabled: %s\n",
+			   yesno(gen9_powergate_enable & GEN9_MEDIA_PG_ENABLE));
+	}
+	seq_printf(m, "Deep RC6 Enabled: %s\n",
+		   yesno(rcctl1 & GEN6_RC_CTL_RC6p_ENABLE));
+	seq_printf(m, "Deepest RC6 Enabled: %s\n",
+		   yesno(rcctl1 & GEN6_RC_CTL_RC6pp_ENABLE));
+	seq_puts(m, "Current RC state: ");
+	switch (gt_core_status & GEN6_RCn_MASK) {
+	case GEN6_RC0:
+		if (gt_core_status & GEN6_CORE_CPD_STATE_MASK)
+			seq_puts(m, "Core Power Down\n");
+		else
+			seq_puts(m, "on\n");
+		break;
+	case GEN6_RC3:
+		seq_puts(m, "RC3\n");
+		break;
+	case GEN6_RC6:
+		seq_puts(m, "RC6\n");
+		break;
+	case GEN6_RC7:
+		seq_puts(m, "RC7\n");
+		break;
+	default:
+		seq_puts(m, "Unknown\n");
+		break;
+	}
+
+	seq_printf(m, "Core Power Down: %s\n",
+		   yesno(gt_core_status & GEN6_CORE_CPD_STATE_MASK));
+	if (INTEL_GEN(i915) >= 9) {
+		seq_printf(m, "Render Power Well: %s\n",
+			   (gen9_powergate_status &
+			    GEN9_PWRGT_RENDER_STATUS_MASK) ? "Up" : "Down");
+		seq_printf(m, "Media Power Well: %s\n",
+			   (gen9_powergate_status &
+			    GEN9_PWRGT_MEDIA_STATUS_MASK) ? "Up" : "Down");
+	}
+
+	/* Not exactly sure what this is */
+	print_rc6_res(m, "RC6 \"Locked to RPn\" residency since boot:",
+		      GEN6_GT_GFX_RC6_LOCKED);
+	print_rc6_res(m, "RC6 residency since boot:", GEN6_GT_GFX_RC6);
+	print_rc6_res(m, "RC6+ residency since boot:", GEN6_GT_GFX_RC6p);
+	print_rc6_res(m, "RC6++ residency since boot:", GEN6_GT_GFX_RC6pp);
+
+	if (INTEL_GEN(i915) <= 7) {
+		seq_printf(m, "RC6   voltage: %dmV\n",
+			   GEN6_DECODE_RC6_VID(((rc6vids >> 0) & 0xff)));
+		seq_printf(m, "RC6+  voltage: %dmV\n",
+			   GEN6_DECODE_RC6_VID(((rc6vids >> 8) & 0xff)));
+		seq_printf(m, "RC6++ voltage: %dmV\n",
+			   GEN6_DECODE_RC6_VID(((rc6vids >> 16) & 0xff)));
+	}
+
+	return fw_domains_show(m, NULL);
+}
+
+static int ilk_drpc(struct seq_file *m)
+{
+	struct intel_gt *gt = m->private;
+	struct intel_uncore *uncore = gt->uncore;
+	u32 rgvmodectl, rstdbyctl;
+	u16 crstandvid;
+
+	rgvmodectl = intel_uncore_read(uncore, MEMMODECTL);
+	rstdbyctl = intel_uncore_read(uncore, RSTDBYCTL);
+	crstandvid = intel_uncore_read16(uncore, CRSTANDVID);
+
+	seq_printf(m, "HD boost: %s\n", yesno(rgvmodectl & MEMMODE_BOOST_EN));
+	seq_printf(m, "Boost freq: %d\n",
+		   (rgvmodectl & MEMMODE_BOOST_FREQ_MASK) >>
+		   MEMMODE_BOOST_FREQ_SHIFT);
+	seq_printf(m, "HW control enabled: %s\n",
+		   yesno(rgvmodectl & MEMMODE_HWIDLE_EN));
+	seq_printf(m, "SW control enabled: %s\n",
+		   yesno(rgvmodectl & MEMMODE_SWMODE_EN));
+	seq_printf(m, "Gated voltage change: %s\n",
+		   yesno(rgvmodectl & MEMMODE_RCLK_GATE));
+	seq_printf(m, "Starting frequency: P%d\n",
+		   (rgvmodectl & MEMMODE_FSTART_MASK) >> MEMMODE_FSTART_SHIFT);
+	seq_printf(m, "Max P-state: P%d\n",
+		   (rgvmodectl & MEMMODE_FMAX_MASK) >> MEMMODE_FMAX_SHIFT);
+	seq_printf(m, "Min P-state: P%d\n", (rgvmodectl & MEMMODE_FMIN_MASK));
+	seq_printf(m, "RS1 VID: %d\n", (crstandvid & 0x3f));
+	seq_printf(m, "RS2 VID: %d\n", ((crstandvid >> 8) & 0x3f));
+	seq_printf(m, "Render standby enabled: %s\n",
+		   yesno(!(rstdbyctl & RCX_SW_EXIT)));
+	seq_puts(m, "Current RS state: ");
+	switch (rstdbyctl & RSX_STATUS_MASK) {
+	case RSX_STATUS_ON:
+		seq_puts(m, "on\n");
+		break;
+	case RSX_STATUS_RC1:
+		seq_puts(m, "RC1\n");
+		break;
+	case RSX_STATUS_RC1E:
+		seq_puts(m, "RC1E\n");
+		break;
+	case RSX_STATUS_RS1:
+		seq_puts(m, "RS1\n");
+		break;
+	case RSX_STATUS_RS2:
+		seq_puts(m, "RS2 (RC6)\n");
+		break;
+	case RSX_STATUS_RS3:
+		seq_puts(m, "RC3 (RC6+)\n");
+		break;
+	default:
+		seq_puts(m, "unknown\n");
+		break;
+	}
+
+	return 0;
+}
+
+static int drpc_show(struct seq_file *m, void *unused)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	intel_wakeref_t wakeref;
+	int err = -ENODEV;
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref) {
+		if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
+			err = vlv_drpc(m);
+		else if (INTEL_GEN(i915) >= 6)
+			err = gen6_drpc(m);
+		else
+			err = ilk_drpc(m);
+	}
+
+	return err;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(drpc);
+
+static int frequency_show(struct seq_file *m, void *unused)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_rps *rps = &gt->rps;
+	intel_wakeref_t wakeref;
+
+	wakeref = intel_runtime_pm_get(uncore->rpm);
+
+	if (IS_GEN(i915, 5)) {
+		u16 rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);
+		u16 rgvstat = intel_uncore_read16(uncore, MEMSTAT_ILK);
+
+		seq_printf(m, "Requested P-state: %d\n", (rgvswctl >> 8) & 0xf);
+		seq_printf(m, "Requested VID: %d\n", rgvswctl & 0x3f);
+		seq_printf(m, "Current VID: %d\n", (rgvstat & MEMSTAT_VID_MASK) >>
+			   MEMSTAT_VID_SHIFT);
+		seq_printf(m, "Current P-state: %d\n",
+			   (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT);
+	} else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		u32 rpmodectl, freq_sts;
+
+		rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL);
+		seq_printf(m, "Video Turbo Mode: %s\n",
+			   yesno(rpmodectl & GEN6_RP_MEDIA_TURBO));
+		seq_printf(m, "HW control enabled: %s\n",
+			   yesno(rpmodectl & GEN6_RP_ENABLE));
+		seq_printf(m, "SW control enabled: %s\n",
+			   yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) ==
+				  GEN6_RP_MEDIA_SW_MODE));
+
+		vlv_punit_get(i915);
+		freq_sts = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
+		vlv_punit_put(i915);
+
+		seq_printf(m, "PUNIT_REG_GPU_FREQ_STS: 0x%08x\n", freq_sts);
+		seq_printf(m, "DDR freq: %d MHz\n", i915->mem_freq);
+
+		seq_printf(m, "actual GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, (freq_sts >> 8) & 0xff));
+
+		seq_printf(m, "current GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->cur_freq));
+
+		seq_printf(m, "max GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->max_freq));
+
+		seq_printf(m, "min GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->min_freq));
+
+		seq_printf(m, "idle GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->idle_freq));
+
+		seq_printf(m, "efficient (RPe) frequency: %d MHz\n",
+			   intel_gpu_freq(rps, rps->efficient_freq));
+	} else if (INTEL_GEN(i915) >= 6) {
+		u32 rp_state_limits;
+		u32 gt_perf_status;
+		u32 rp_state_cap;
+		u32 rpmodectl, rpinclimit, rpdeclimit;
+		u32 rpstat, cagf, reqf;
+		u32 rpupei, rpcurup, rpprevup;
+		u32 rpdownei, rpcurdown, rpprevdown;
+		u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask;
+		int max_freq;
+
+		rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS);
+		if (IS_GEN9_LP(i915)) {
+			rp_state_cap = intel_uncore_read(uncore, BXT_RP_STATE_CAP);
+			gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS);
+		} else {
+			rp_state_cap = intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
+			gt_perf_status = intel_uncore_read(uncore, GEN6_GT_PERF_STATUS);
+		}
+
+		/* RPSTAT1 is in the GT power well */
+		intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+
+		reqf = intel_uncore_read(uncore, GEN6_RPNSWREQ);
+		if (INTEL_GEN(i915) >= 9) {
+			reqf >>= 23;
+		} else {
+			reqf &= ~GEN6_TURBO_DISABLE;
+			if (IS_HASWELL(i915) || IS_BROADWELL(i915))
+				reqf >>= 24;
+			else
+				reqf >>= 25;
+		}
+		reqf = intel_gpu_freq(rps, reqf);
+
+		rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL);
+		rpinclimit = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD);
+		rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD);
+
+		rpstat = intel_uncore_read(uncore, GEN6_RPSTAT1);
+		rpupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK;
+		rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK;
+		rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK;
+		rpdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
+		rpcurdown = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
+		rpprevdown = intel_uncore_read(uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
+		cagf = intel_rps_read_actual_frequency(rps);
+
+		intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+
+		if (INTEL_GEN(i915) >= 11) {
+			pm_ier = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE);
+			pm_imr = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK);
+			/*
+			 * The equivalent to the PM ISR & IIR cannot be read
+			 * without affecting the current state of the system
+			 */
+			pm_isr = 0;
+			pm_iir = 0;
+		} else if (INTEL_GEN(i915) >= 8) {
+			pm_ier = intel_uncore_read(uncore, GEN8_GT_IER(2));
+			pm_imr = intel_uncore_read(uncore, GEN8_GT_IMR(2));
+			pm_isr = intel_uncore_read(uncore, GEN8_GT_ISR(2));
+			pm_iir = intel_uncore_read(uncore, GEN8_GT_IIR(2));
+		} else {
+			pm_ier = intel_uncore_read(uncore, GEN6_PMIER);
+			pm_imr = intel_uncore_read(uncore, GEN6_PMIMR);
+			pm_isr = intel_uncore_read(uncore, GEN6_PMISR);
+			pm_iir = intel_uncore_read(uncore, GEN6_PMIIR);
+		}
+		pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK);
+
+		seq_printf(m, "Video Turbo Mode: %s\n",
+			   yesno(rpmodectl & GEN6_RP_MEDIA_TURBO));
+		seq_printf(m, "HW control enabled: %s\n",
+			   yesno(rpmodectl & GEN6_RP_ENABLE));
+		seq_printf(m, "SW control enabled: %s\n",
+			   yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) ==
+				  GEN6_RP_MEDIA_SW_MODE));
+
+		seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n",
+			   pm_ier, pm_imr, pm_mask);
+		if (INTEL_GEN(i915) <= 10)
+			seq_printf(m, "PM ISR=0x%08x IIR=0x%08x\n",
+				   pm_isr, pm_iir);
+		seq_printf(m, "pm_intrmsk_mbz: 0x%08x\n",
+			   rps->pm_intrmsk_mbz);
+		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
+		seq_printf(m, "Render p-state ratio: %d\n",
+			   (gt_perf_status & (INTEL_GEN(i915) >= 9 ? 0x1ff00 : 0xff00)) >> 8);
+		seq_printf(m, "Render p-state VID: %d\n",
+			   gt_perf_status & 0xff);
+		seq_printf(m, "Render p-state limit: %d\n",
+			   rp_state_limits & 0xff);
+		seq_printf(m, "RPSTAT1: 0x%08x\n", rpstat);
+		seq_printf(m, "RPMODECTL: 0x%08x\n", rpmodectl);
+		seq_printf(m, "RPINCLIMIT: 0x%08x\n", rpinclimit);
+		seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
+		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
+		seq_printf(m, "CAGF: %dMHz\n", cagf);
+		seq_printf(m, "RP CUR UP EI: %d (%dus)\n",
+			   rpupei, GT_PM_INTERVAL_TO_US(i915, rpupei));
+		seq_printf(m, "RP CUR UP: %d (%dus)\n",
+			   rpcurup, GT_PM_INTERVAL_TO_US(i915, rpcurup));
+		seq_printf(m, "RP PREV UP: %d (%dus)\n",
+			   rpprevup, GT_PM_INTERVAL_TO_US(i915, rpprevup));
+		seq_printf(m, "Up threshold: %d%%\n",
+			   rps->power.up_threshold);
+
+		seq_printf(m, "RP CUR DOWN EI: %d (%dus)\n",
+			   rpdownei, GT_PM_INTERVAL_TO_US(i915, rpdownei));
+		seq_printf(m, "RP CUR DOWN: %d (%dus)\n",
+			   rpcurdown, GT_PM_INTERVAL_TO_US(i915, rpcurdown));
+		seq_printf(m, "RP PREV DOWN: %d (%dus)\n",
+			   rpprevdown, GT_PM_INTERVAL_TO_US(i915, rpprevdown));
+		seq_printf(m, "Down threshold: %d%%\n",
+			   rps->power.down_threshold);
+
+		max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 0 :
+			    rp_state_cap >> 16) & 0xff;
+		max_freq *= (IS_GEN9_BC(i915) ||
+			     INTEL_GEN(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+		seq_printf(m, "Lowest (RPN) frequency: %dMHz\n",
+			   intel_gpu_freq(rps, max_freq));
+
+		max_freq = (rp_state_cap & 0xff00) >> 8;
+		max_freq *= (IS_GEN9_BC(i915) ||
+			     INTEL_GEN(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+		seq_printf(m, "Nominal (RP1) frequency: %dMHz\n",
+			   intel_gpu_freq(rps, max_freq));
+
+		max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 16 :
+			    rp_state_cap >> 0) & 0xff;
+		max_freq *= (IS_GEN9_BC(i915) ||
+			     INTEL_GEN(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
+			   intel_gpu_freq(rps, max_freq));
+		seq_printf(m, "Max overclocked frequency: %dMHz\n",
+			   intel_gpu_freq(rps, rps->max_freq));
+
+		seq_printf(m, "Current freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->cur_freq));
+		seq_printf(m, "Actual freq: %d MHz\n", cagf);
+		seq_printf(m, "Idle freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->idle_freq));
+		seq_printf(m, "Min freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->min_freq));
+		seq_printf(m, "Boost freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->boost_freq));
+		seq_printf(m, "Max freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->max_freq));
+		seq_printf(m,
+			   "efficient (RPe) frequency: %d MHz\n",
+			   intel_gpu_freq(rps, rps->efficient_freq));
+	} else {
+		seq_puts(m, "no P-state info available\n");
+	}
+
+	seq_printf(m, "Current CD clock frequency: %d kHz\n", i915->cdclk.hw.cdclk);
+	seq_printf(m, "Max CD clock frequency: %d kHz\n", i915->max_cdclk_freq);
+	seq_printf(m, "Max pixel clock frequency: %d kHz\n", i915->max_dotclk_freq);
+
+	intel_runtime_pm_put(uncore->rpm, wakeref);
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(frequency);
+
+static int llc_show(struct seq_file *m, void *data)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	const bool edram = INTEL_GEN(i915) > 8;
+	struct intel_rps *rps = &gt->rps;
+	unsigned int max_gpu_freq, min_gpu_freq;
+	intel_wakeref_t wakeref;
+	int gpu_freq, ia_freq;
+
+	seq_printf(m, "LLC: %s\n", yesno(HAS_LLC(i915)));
+	seq_printf(m, "%s: %uMB\n", edram ? "eDRAM" : "eLLC",
+		   i915->edram_size_mb);
+
+	min_gpu_freq = rps->min_freq;
+	max_gpu_freq = rps->max_freq;
+	if (IS_GEN9_BC(i915) || INTEL_GEN(i915) >= 10) {
+		/* Convert GT frequency to 50 HZ units */
+		min_gpu_freq /= GEN9_FREQ_SCALER;
+		max_gpu_freq /= GEN9_FREQ_SCALER;
+	}
+
+	seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
+
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+	for (gpu_freq = min_gpu_freq; gpu_freq <= max_gpu_freq; gpu_freq++) {
+		ia_freq = gpu_freq;
+		sandybridge_pcode_read(i915,
+				       GEN6_PCODE_READ_MIN_FREQ_TABLE,
+				       &ia_freq, NULL);
+		seq_printf(m, "%d\t\t%d\t\t\t\t%d\n",
+			   intel_gpu_freq(rps,
+					  (gpu_freq *
+					   (IS_GEN9_BC(i915) ||
+					    INTEL_GEN(i915) >= 10 ?
+					    GEN9_FREQ_SCALER : 1))),
+			   ((ia_freq >> 0) & 0xff) * 100,
+			   ((ia_freq >> 8) & 0xff) * 100);
+	}
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+
+	return 0;
+}
+
+static bool llc_eval(const struct intel_gt *gt)
+{
+	return HAS_LLC(gt->i915);
+}
+
+DEFINE_GT_DEBUGFS_ATTRIBUTE(llc);
+
+static const char *rps_power_to_str(unsigned int power)
+{
+	static const char * const strings[] = {
+		[LOW_POWER] = "low power",
+		[BETWEEN] = "mixed",
+		[HIGH_POWER] = "high power",
+	};
+
+	if (power >= ARRAY_SIZE(strings) || !strings[power])
+		return "unknown";
+
+	return strings[power];
+}
+
+static int rps_boost_show(struct seq_file *m, void *data)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_rps *rps = &gt->rps;
+
+	seq_printf(m, "RPS enabled? %d\n", rps->enabled);
+	seq_printf(m, "GPU busy? %s\n", yesno(gt->awake));
+	seq_printf(m, "Boosts outstanding? %d\n",
+		   atomic_read(&rps->num_waiters));
+	seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive));
+	seq_printf(m, "Frequency requested %d, actual %d\n",
+		   intel_gpu_freq(rps, rps->cur_freq),
+		   intel_rps_read_actual_frequency(rps));
+	seq_printf(m, "  min hard:%d, soft:%d; max soft:%d, hard:%d\n",
+		   intel_gpu_freq(rps, rps->min_freq),
+		   intel_gpu_freq(rps, rps->min_freq_softlimit),
+		   intel_gpu_freq(rps, rps->max_freq_softlimit),
+		   intel_gpu_freq(rps, rps->max_freq));
+	seq_printf(m, "  idle:%d, efficient:%d, boost:%d\n",
+		   intel_gpu_freq(rps, rps->idle_freq),
+		   intel_gpu_freq(rps, rps->efficient_freq),
+		   intel_gpu_freq(rps, rps->boost_freq));
+
+	seq_printf(m, "Wait boosts: %d\n", atomic_read(&rps->boosts));
+
+	if (INTEL_GEN(i915) >= 6 && rps->enabled && gt->awake) {
+		struct intel_uncore *uncore = gt->uncore;
+		u32 rpup, rpupei;
+		u32 rpdown, rpdownei;
+
+		intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+		rpup = intel_uncore_read_fw(uncore, GEN6_RP_CUR_UP) & GEN6_RP_EI_MASK;
+		rpupei = intel_uncore_read_fw(uncore, GEN6_RP_CUR_UP_EI) & GEN6_RP_EI_MASK;
+		rpdown = intel_uncore_read_fw(uncore, GEN6_RP_CUR_DOWN) & GEN6_RP_EI_MASK;
+		rpdownei = intel_uncore_read_fw(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_RP_EI_MASK;
+		intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+
+		seq_printf(m, "\nRPS Autotuning (current \"%s\" window):\n",
+			   rps_power_to_str(rps->power.mode));
+		seq_printf(m, "  Avg. up: %d%% [above threshold? %d%%]\n",
+			   rpup && rpupei ? 100 * rpup / rpupei : 0,
+			   rps->power.up_threshold);
+		seq_printf(m, "  Avg. down: %d%% [below threshold? %d%%]\n",
+			   rpdown && rpdownei ? 100 * rpdown / rpdownei : 0,
+			   rps->power.down_threshold);
+	} else {
+		seq_puts(m, "\nRPS Autotuning inactive\n");
+	}
+
+	return 0;
+}
+
+static bool rps_eval(const struct intel_gt *gt)
+{
+	return HAS_RPS(gt->i915);
+}
+
+DEFINE_GT_DEBUGFS_ATTRIBUTE(rps_boost);
+
+void debugfs_gt_pm_register(struct intel_gt *gt, struct dentry *root)
+{
+	static const struct debugfs_gt_file files[] = {
+		{ "drpc", &drpc_fops, NULL },
+		{ "frequency", &frequency_fops, NULL },
+		{ "forcewake", &fw_domains_fops, NULL },
+		{ "llc", &llc_fops, llc_eval },
+		{ "rps_boost", &rps_boost_fops, rps_eval },
+	};
+
+	debugfs_gt_register_files(gt, root, files, ARRAY_SIZE(files));
+}
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h
new file mode 100644
index 000000000000..4cf5f5c9da7d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef DEBUGFS_GT_PM_H
+#define DEBUGFS_GT_PM_H
+
+struct intel_gt;
+struct dentry;
+
+void debugfs_gt_pm_register(struct intel_gt *gt, struct dentry *root);
+
+#endif /* DEBUGFS_GT_PM_H */
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
new file mode 100644
index 000000000000..f4fec7eb4064
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/log2.h>
+
+#include "gen6_ppgtt.h"
+#include "i915_scatterlist.h"
+#include "i915_trace.h"
+#include "i915_vgpu.h"
+#include "intel_gt.h"
+
+/* Write pde (index) from the page directory @pd to the page table @pt */
+static inline void gen6_write_pde(const struct gen6_ppgtt *ppgtt,
+				  const unsigned int pde,
+				  const struct i915_page_table *pt)
+{
+	/* Caller needs to make sure the write completes if necessary */
+	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
+		  ppgtt->pd_addr + pde);
+}
+
+void gen7_ppgtt_enable(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	u32 ecochk;
+
+	intel_uncore_rmw(uncore, GAC_ECO_BITS, 0, ECOBITS_PPGTT_CACHE64B);
+
+	ecochk = intel_uncore_read(uncore, GAM_ECOCHK);
+	if (IS_HASWELL(i915)) {
+		ecochk |= ECOCHK_PPGTT_WB_HSW;
+	} else {
+		ecochk |= ECOCHK_PPGTT_LLC_IVB;
+		ecochk &= ~ECOCHK_PPGTT_GFDT_IVB;
+	}
+	intel_uncore_write(uncore, GAM_ECOCHK, ecochk);
+
+	for_each_engine(engine, gt, id) {
+		/* GFX_MODE is per-ring on gen7+ */
+		ENGINE_WRITE(engine,
+			     RING_MODE_GEN7,
+			     _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+	}
+}
+
+void gen6_ppgtt_enable(struct intel_gt *gt)
+{
+	struct intel_uncore *uncore = gt->uncore;
+
+	intel_uncore_rmw(uncore,
+			 GAC_ECO_BITS,
+			 0,
+			 ECOBITS_SNB_BIT | ECOBITS_PPGTT_CACHE64B);
+
+	intel_uncore_rmw(uncore,
+			 GAB_CTL,
+			 0,
+			 GAB_CTL_CONT_AFTER_PAGEFAULT);
+
+	intel_uncore_rmw(uncore,
+			 GAM_ECOCHK,
+			 0,
+			 ECOCHK_SNB_BIT | ECOCHK_PPGTT_CACHE64B);
+
+	if (HAS_PPGTT(uncore->i915)) /* may be disabled for VT-d */
+		intel_uncore_write(uncore,
+				   GFX_MODE,
+				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+}
+
+/* PPGTT support for Sandybdrige/Gen6 and later */
+static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
+				   u64 start, u64 length)
+{
+	struct gen6_ppgtt * const ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
+	const unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+	const gen6_pte_t scratch_pte = vm->scratch[0].encode;
+	unsigned int pde = first_entry / GEN6_PTES;
+	unsigned int pte = first_entry % GEN6_PTES;
+	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+
+	while (num_entries) {
+		struct i915_page_table * const pt =
+			i915_pt_entry(ppgtt->base.pd, pde++);
+		const unsigned int count = min(num_entries, GEN6_PTES - pte);
+		gen6_pte_t *vaddr;
+
+		GEM_BUG_ON(px_base(pt) == px_base(&vm->scratch[1]));
+
+		num_entries -= count;
+
+		GEM_BUG_ON(count > atomic_read(&pt->used));
+		if (!atomic_sub_return(count, &pt->used))
+			ppgtt->scan_for_unused_pt = true;
+
+		/*
+		 * Note that the hw doesn't support removing PDE on the fly
+		 * (they are cached inside the context with no means to
+		 * invalidate the cache), so we can only reset the PTE
+		 * entries back to scratch.
+		 */
+
+		vaddr = kmap_atomic_px(pt);
+		memset32(vaddr + pte, scratch_pte, count);
+		kunmap_atomic(vaddr);
+
+		pte = 0;
+	}
+}
+
+static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
+				      struct i915_vma *vma,
+				      enum i915_cache_level cache_level,
+				      u32 flags)
+{
+	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+	struct i915_page_directory * const pd = ppgtt->pd;
+	unsigned int first_entry = vma->node.start / I915_GTT_PAGE_SIZE;
+	unsigned int act_pt = first_entry / GEN6_PTES;
+	unsigned int act_pte = first_entry % GEN6_PTES;
+	const u32 pte_encode = vm->pte_encode(0, cache_level, flags);
+	struct sgt_dma iter = sgt_dma(vma);
+	gen6_pte_t *vaddr;
+
+	GEM_BUG_ON(pd->entry[act_pt] == &vm->scratch[1]);
+
+	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
+	do {
+		GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
+		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
+
+		iter.dma += I915_GTT_PAGE_SIZE;
+		if (iter.dma == iter.max) {
+			iter.sg = __sg_next(iter.sg);
+			if (!iter.sg)
+				break;
+
+			iter.dma = sg_dma_address(iter.sg);
+			iter.max = iter.dma + iter.sg->length;
+		}
+
+		if (++act_pte == GEN6_PTES) {
+			kunmap_atomic(vaddr);
+			vaddr = kmap_atomic_px(i915_pt_entry(pd, ++act_pt));
+			act_pte = 0;
+		}
+	} while (1);
+	kunmap_atomic(vaddr);
+
+	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+}
+
+static void gen6_flush_pd(struct gen6_ppgtt *ppgtt, u64 start, u64 end)
+{
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	struct i915_page_table *pt;
+	unsigned int pde;
+
+	start = round_down(start, SZ_64K);
+	end = round_up(end, SZ_64K) - start;
+
+	mutex_lock(&ppgtt->flush);
+
+	gen6_for_each_pde(pt, pd, start, end, pde)
+		gen6_write_pde(ppgtt, pde, pt);
+
+	mb();
+	ioread32(ppgtt->pd_addr + pde - 1);
+	gen6_ggtt_invalidate(ppgtt->base.vm.gt->ggtt);
+	mb();
+
+	mutex_unlock(&ppgtt->flush);
+}
+
+static int gen6_alloc_va_range(struct i915_address_space *vm,
+			       u64 start, u64 length)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	struct i915_page_table *pt, *alloc = NULL;
+	intel_wakeref_t wakeref;
+	u64 from = start;
+	unsigned int pde;
+	int ret = 0;
+
+	wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
+
+	spin_lock(&pd->lock);
+	gen6_for_each_pde(pt, pd, start, length, pde) {
+		const unsigned int count = gen6_pte_count(start, length);
+
+		if (px_base(pt) == px_base(&vm->scratch[1])) {
+			spin_unlock(&pd->lock);
+
+			pt = fetch_and_zero(&alloc);
+			if (!pt)
+				pt = alloc_pt(vm);
+			if (IS_ERR(pt)) {
+				ret = PTR_ERR(pt);
+				goto unwind_out;
+			}
+
+			fill32_px(pt, vm->scratch[0].encode);
+
+			spin_lock(&pd->lock);
+			if (pd->entry[pde] == &vm->scratch[1]) {
+				pd->entry[pde] = pt;
+			} else {
+				alloc = pt;
+				pt = pd->entry[pde];
+			}
+		}
+
+		atomic_add(count, &pt->used);
+	}
+	spin_unlock(&pd->lock);
+
+	if (i915_vma_is_bound(ppgtt->vma, I915_VMA_GLOBAL_BIND))
+		gen6_flush_pd(ppgtt, from, start);
+
+	goto out;
+
+unwind_out:
+	gen6_ppgtt_clear_range(vm, from, start - from);
+out:
+	if (alloc)
+		free_px(vm, alloc);
+	intel_runtime_pm_put(&vm->i915->runtime_pm, wakeref);
+	return ret;
+}
+
+static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
+{
+	struct i915_address_space * const vm = &ppgtt->base.vm;
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	int ret;
+
+	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
+	if (ret)
+		return ret;
+
+	vm->scratch[0].encode =
+		vm->pte_encode(px_dma(&vm->scratch[0]),
+			       I915_CACHE_NONE, PTE_READ_ONLY);
+
+	if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[1])))) {
+		cleanup_scratch_page(vm);
+		return -ENOMEM;
+	}
+
+	fill32_px(&vm->scratch[1], vm->scratch[0].encode);
+	memset_p(pd->entry, &vm->scratch[1], I915_PDES);
+
+	return 0;
+}
+
+static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)
+{
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	struct i915_page_dma * const scratch =
+		px_base(&ppgtt->base.vm.scratch[1]);
+	struct i915_page_table *pt;
+	u32 pde;
+
+	gen6_for_all_pdes(pt, pd, pde)
+		if (px_base(pt) != scratch)
+			free_px(&ppgtt->base.vm, pt);
+}
+
+static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
+
+	__i915_vma_put(ppgtt->vma);
+
+	gen6_ppgtt_free_pd(ppgtt);
+	free_scratch(vm);
+
+	mutex_destroy(&ppgtt->flush);
+	mutex_destroy(&ppgtt->pin_mutex);
+	kfree(ppgtt->base.pd);
+}
+
+static int pd_vma_set_pages(struct i915_vma *vma)
+{
+	vma->pages = ERR_PTR(-ENODEV);
+	return 0;
+}
+
+static void pd_vma_clear_pages(struct i915_vma *vma)
+{
+	GEM_BUG_ON(!vma->pages);
+
+	vma->pages = NULL;
+}
+
+static int pd_vma_bind(struct i915_vma *vma,
+		       enum i915_cache_level cache_level,
+		       u32 unused)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vma->vm);
+	struct gen6_ppgtt *ppgtt = vma->private;
+	u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE;
+
+	px_base(ppgtt->base.pd)->ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);
+	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
+
+	gen6_flush_pd(ppgtt, 0, ppgtt->base.vm.total);
+	return 0;
+}
+
+static void pd_vma_unbind(struct i915_vma *vma)
+{
+	struct gen6_ppgtt *ppgtt = vma->private;
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	struct i915_page_dma * const scratch =
+		px_base(&ppgtt->base.vm.scratch[1]);
+	struct i915_page_table *pt;
+	unsigned int pde;
+
+	if (!ppgtt->scan_for_unused_pt)
+		return;
+
+	/* Free all no longer used page tables */
+	gen6_for_all_pdes(pt, ppgtt->base.pd, pde) {
+		if (px_base(pt) == scratch || atomic_read(&pt->used))
+			continue;
+
+		free_px(&ppgtt->base.vm, pt);
+		pd->entry[pde] = scratch;
+	}
+
+	ppgtt->scan_for_unused_pt = false;
+}
+
+static const struct i915_vma_ops pd_vma_ops = {
+	.set_pages = pd_vma_set_pages,
+	.clear_pages = pd_vma_clear_pages,
+	.bind_vma = pd_vma_bind,
+	.unbind_vma = pd_vma_unbind,
+};
+
+static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
+{
+	struct i915_ggtt *ggtt = ppgtt->base.vm.gt->ggtt;
+	struct i915_vma *vma;
+
+	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
+	GEM_BUG_ON(size > ggtt->vm.total);
+
+	vma = i915_vma_alloc();
+	if (!vma)
+		return ERR_PTR(-ENOMEM);
+
+	i915_active_init(&vma->active, NULL, NULL);
+
+	kref_init(&vma->ref);
+	mutex_init(&vma->pages_mutex);
+	vma->vm = i915_vm_get(&ggtt->vm);
+	vma->ops = &pd_vma_ops;
+	vma->private = ppgtt;
+
+	vma->size = size;
+	vma->fence_size = size;
+	atomic_set(&vma->flags, I915_VMA_GGTT);
+	vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */
+
+	INIT_LIST_HEAD(&vma->obj_link);
+	INIT_LIST_HEAD(&vma->closed_link);
+
+	return vma;
+}
+
+int gen6_ppgtt_pin(struct i915_ppgtt *base)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
+	int err;
+
+	GEM_BUG_ON(!atomic_read(&ppgtt->base.vm.open));
+
+	/*
+	 * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
+	 * which will be pinned into every active context.
+	 * (When vma->pin_count becomes atomic, I expect we will naturally
+	 * need a larger, unpacked, type and kill this redundancy.)
+	 */
+	if (atomic_add_unless(&ppgtt->pin_count, 1, 0))
+		return 0;
+
+	if (mutex_lock_interruptible(&ppgtt->pin_mutex))
+		return -EINTR;
+
+	/*
+	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
+	 * allocator works in address space sizes, so it's multiplied by page
+	 * size. We allocate at the top of the GTT to avoid fragmentation.
+	 */
+	err = 0;
+	if (!atomic_read(&ppgtt->pin_count))
+		err = i915_ggtt_pin(ppgtt->vma, GEN6_PD_ALIGN, PIN_HIGH);
+	if (!err)
+		atomic_inc(&ppgtt->pin_count);
+	mutex_unlock(&ppgtt->pin_mutex);
+
+	return err;
+}
+
+void gen6_ppgtt_unpin(struct i915_ppgtt *base)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
+
+	GEM_BUG_ON(!atomic_read(&ppgtt->pin_count));
+	if (atomic_dec_and_test(&ppgtt->pin_count))
+		i915_vma_unpin(ppgtt->vma);
+}
+
+void gen6_ppgtt_unpin_all(struct i915_ppgtt *base)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
+
+	if (!atomic_read(&ppgtt->pin_count))
+		return;
+
+	i915_vma_unpin(ppgtt->vma);
+	atomic_set(&ppgtt->pin_count, 0);
+}
+
+struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
+{
+	struct i915_ggtt * const ggtt = gt->ggtt;
+	struct gen6_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&ppgtt->flush);
+	mutex_init(&ppgtt->pin_mutex);
+
+	ppgtt_init(&ppgtt->base, gt);
+	ppgtt->base.vm.top = 1;
+
+	ppgtt->base.vm.bind_async_flags = I915_VMA_LOCAL_BIND;
+	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
+	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
+	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
+	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
+
+	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
+
+	ppgtt->base.pd = __alloc_pd(sizeof(*ppgtt->base.pd));
+	if (!ppgtt->base.pd) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	err = gen6_ppgtt_init_scratch(ppgtt);
+	if (err)
+		goto err_pd;
+
+	ppgtt->vma = pd_vma_create(ppgtt, GEN6_PD_SIZE);
+	if (IS_ERR(ppgtt->vma)) {
+		err = PTR_ERR(ppgtt->vma);
+		goto err_scratch;
+	}
+
+	return &ppgtt->base;
+
+err_scratch:
+	free_scratch(&ppgtt->base.vm);
+err_pd:
+	kfree(ppgtt->base.pd);
+err_free:
+	mutex_destroy(&ppgtt->pin_mutex);
+	kfree(ppgtt);
+	return ERR_PTR(err);
+}
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h
new file mode 100644
index 000000000000..72e481806c96
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __GEN6_PPGTT_H__
+#define __GEN6_PPGTT_H__
+
+#include "intel_gtt.h"
+
+struct gen6_ppgtt {
+	struct i915_ppgtt base;
+
+	struct mutex flush;
+	struct i915_vma *vma;
+	gen6_pte_t __iomem *pd_addr;
+
+	atomic_t pin_count;
+	struct mutex pin_mutex;
+
+	bool scan_for_unused_pt;
+};
+
+static inline u32 gen6_pte_index(u32 addr)
+{
+	return i915_pte_index(addr, GEN6_PDE_SHIFT);
+}
+
+static inline u32 gen6_pte_count(u32 addr, u32 length)
+{
+	return i915_pte_count(addr, length, GEN6_PDE_SHIFT);
+}
+
+static inline u32 gen6_pde_index(u32 addr)
+{
+	return i915_pde_index(addr, GEN6_PDE_SHIFT);
+}
+
+#define __to_gen6_ppgtt(base) container_of(base, struct gen6_ppgtt, base)
+
+static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base)
+{
+	BUILD_BUG_ON(offsetof(struct gen6_ppgtt, base));
+	return __to_gen6_ppgtt(base);
+}
+
+/*
+ * gen6_for_each_pde() iterates over every pde from start until start+length.
+ * If start and start+length are not perfectly divisible, the macro will round
+ * down and up as needed. Start=0 and length=2G effectively iterates over
+ * every PDE in the system. The macro modifies ALL its parameters except 'pd',
+ * so each of the other parameters should preferably be a simple variable, or
+ * at most an lvalue with no side-effects!
+ */
+#define gen6_for_each_pde(pt, pd, start, length, iter)			\
+	for (iter = gen6_pde_index(start);				\
+	     length > 0 && iter < I915_PDES &&				\
+		     (pt = i915_pt_entry(pd, iter), true);		\
+	     ({ u32 temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT);		\
+		    temp = min(temp - start, length);			\
+		    start += temp, length -= temp; }), ++iter)
+
+#define gen6_for_all_pdes(pt, pd, iter)					\
+	for (iter = 0;							\
+	     iter < I915_PDES &&					\
+		     (pt = i915_pt_entry(pd, iter), true);		\
+	     ++iter)
+
+int gen6_ppgtt_pin(struct i915_ppgtt *base);
+void gen6_ppgtt_unpin(struct i915_ppgtt *base);
+void gen6_ppgtt_unpin_all(struct i915_ppgtt *base);
+void gen6_ppgtt_enable(struct intel_gt *gt);
+void gen7_ppgtt_enable(struct intel_gt *gt);
+struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
new file mode 100644
index 000000000000..4d1de2d97d5c
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -0,0 +1,724 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/log2.h>
+
+#include "gen8_ppgtt.h"
+#include "i915_scatterlist.h"
+#include "i915_trace.h"
+#include "i915_vgpu.h"
+#include "intel_gt.h"
+#include "intel_gtt.h"
+
+static u64 gen8_pde_encode(const dma_addr_t addr,
+			   const enum i915_cache_level level)
+{
+	u64 pde = addr | _PAGE_PRESENT | _PAGE_RW;
+
+	if (level != I915_CACHE_NONE)
+		pde |= PPAT_CACHED_PDE;
+	else
+		pde |= PPAT_UNCACHED;
+
+	return pde;
+}
+
+static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
+{
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
+	struct intel_uncore *uncore = ppgtt->vm.gt->uncore;
+	enum vgt_g2v_type msg;
+	int i;
+
+	if (create)
+		atomic_inc(px_used(ppgtt->pd)); /* never remove */
+	else
+		atomic_dec(px_used(ppgtt->pd));
+
+	mutex_lock(&i915->vgpu.lock);
+
+	if (i915_vm_is_4lvl(&ppgtt->vm)) {
+		const u64 daddr = px_dma(ppgtt->pd);
+
+		intel_uncore_write(uncore,
+				   vgtif_reg(pdp[0].lo), lower_32_bits(daddr));
+		intel_uncore_write(uncore,
+				   vgtif_reg(pdp[0].hi), upper_32_bits(daddr));
+
+		msg = create ?
+			VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE :
+			VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY;
+	} else {
+		for (i = 0; i < GEN8_3LVL_PDPES; i++) {
+			const u64 daddr = i915_page_dir_dma_addr(ppgtt, i);
+
+			intel_uncore_write(uncore,
+					   vgtif_reg(pdp[i].lo),
+					   lower_32_bits(daddr));
+			intel_uncore_write(uncore,
+					   vgtif_reg(pdp[i].hi),
+					   upper_32_bits(daddr));
+		}
+
+		msg = create ?
+			VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE :
+			VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY;
+	}
+
+	/* g2v_notify atomically (via hv trap) consumes the message packet. */
+	intel_uncore_write(uncore, vgtif_reg(g2v_notify), msg);
+
+	mutex_unlock(&i915->vgpu.lock);
+}
+
+/* Index shifts into the pagetable are offset by GEN8_PTE_SHIFT [12] */
+#define GEN8_PAGE_SIZE (SZ_4K) /* page and page-directory sizes are the same */
+#define GEN8_PTE_SHIFT (ilog2(GEN8_PAGE_SIZE))
+#define GEN8_PDES (GEN8_PAGE_SIZE / sizeof(u64))
+#define gen8_pd_shift(lvl) ((lvl) * ilog2(GEN8_PDES))
+#define gen8_pd_index(i, lvl) i915_pde_index((i), gen8_pd_shift(lvl))
+#define __gen8_pte_shift(lvl) (GEN8_PTE_SHIFT + gen8_pd_shift(lvl))
+#define __gen8_pte_index(a, lvl) i915_pde_index((a), __gen8_pte_shift(lvl))
+
+#define as_pd(x) container_of((x), typeof(struct i915_page_directory), pt)
+
+static inline unsigned int
+gen8_pd_range(u64 start, u64 end, int lvl, unsigned int *idx)
+{
+	const int shift = gen8_pd_shift(lvl);
+	const u64 mask = ~0ull << gen8_pd_shift(lvl + 1);
+
+	GEM_BUG_ON(start >= end);
+	end += ~mask >> gen8_pd_shift(1);
+
+	*idx = i915_pde_index(start, shift);
+	if ((start ^ end) & mask)
+		return GEN8_PDES - *idx;
+	else
+		return i915_pde_index(end, shift) - *idx;
+}
+
+static inline bool gen8_pd_contains(u64 start, u64 end, int lvl)
+{
+	const u64 mask = ~0ull << gen8_pd_shift(lvl + 1);
+
+	GEM_BUG_ON(start >= end);
+	return (start ^ end) & mask && (start & ~mask) == 0;
+}
+
+static inline unsigned int gen8_pt_count(u64 start, u64 end)
+{
+	GEM_BUG_ON(start >= end);
+	if ((start ^ end) >> gen8_pd_shift(1))
+		return GEN8_PDES - (start & (GEN8_PDES - 1));
+	else
+		return end - start;
+}
+
+static inline unsigned int
+gen8_pd_top_count(const struct i915_address_space *vm)
+{
+	unsigned int shift = __gen8_pte_shift(vm->top);
+	return (vm->total + (1ull << shift) - 1) >> shift;
+}
+
+static inline struct i915_page_directory *
+gen8_pdp_for_page_index(struct i915_address_space * const vm, const u64 idx)
+{
+	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
+
+	if (vm->top == 2)
+		return ppgtt->pd;
+	else
+		return i915_pd_entry(ppgtt->pd, gen8_pd_index(idx, vm->top));
+}
+
+static inline struct i915_page_directory *
+gen8_pdp_for_page_address(struct i915_address_space * const vm, const u64 addr)
+{
+	return gen8_pdp_for_page_index(vm, addr >> GEN8_PTE_SHIFT);
+}
+
+static void __gen8_ppgtt_cleanup(struct i915_address_space *vm,
+				 struct i915_page_directory *pd,
+				 int count, int lvl)
+{
+	if (lvl) {
+		void **pde = pd->entry;
+
+		do {
+			if (!*pde)
+				continue;
+
+			__gen8_ppgtt_cleanup(vm, *pde, GEN8_PDES, lvl - 1);
+		} while (pde++, --count);
+	}
+
+	free_px(vm, pd);
+}
+
+static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
+{
+	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+
+	if (intel_vgpu_active(vm->i915))
+		gen8_ppgtt_notify_vgt(ppgtt, false);
+
+	__gen8_ppgtt_cleanup(vm, ppgtt->pd, gen8_pd_top_count(vm), vm->top);
+	free_scratch(vm);
+}
+
+static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
+			      struct i915_page_directory * const pd,
+			      u64 start, const u64 end, int lvl)
+{
+	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
+	unsigned int idx, len;
+
+	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
+
+	len = gen8_pd_range(start, end, lvl--, &idx);
+	DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d }\n",
+	    __func__, vm, lvl + 1, start, end,
+	    idx, len, atomic_read(px_used(pd)));
+	GEM_BUG_ON(!len || len >= atomic_read(px_used(pd)));
+
+	do {
+		struct i915_page_table *pt = pd->entry[idx];
+
+		if (atomic_fetch_inc(&pt->used) >> gen8_pd_shift(1) &&
+		    gen8_pd_contains(start, end, lvl)) {
+			DBG("%s(%p):{ lvl:%d, idx:%d, start:%llx, end:%llx } removing pd\n",
+			    __func__, vm, lvl + 1, idx, start, end);
+			clear_pd_entry(pd, idx, scratch);
+			__gen8_ppgtt_cleanup(vm, as_pd(pt), I915_PDES, lvl);
+			start += (u64)I915_PDES << gen8_pd_shift(lvl);
+			continue;
+		}
+
+		if (lvl) {
+			start = __gen8_ppgtt_clear(vm, as_pd(pt),
+						   start, end, lvl);
+		} else {
+			unsigned int count;
+			u64 *vaddr;
+
+			count = gen8_pt_count(start, end);
+			DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d } removing pte\n",
+			    __func__, vm, lvl, start, end,
+			    gen8_pd_index(start, 0), count,
+			    atomic_read(&pt->used));
+			GEM_BUG_ON(!count || count >= atomic_read(&pt->used));
+
+			vaddr = kmap_atomic_px(pt);
+			memset64(vaddr + gen8_pd_index(start, 0),
+				 vm->scratch[0].encode,
+				 count);
+			kunmap_atomic(vaddr);
+
+			atomic_sub(count, &pt->used);
+			start += count;
+		}
+
+		if (release_pd_entry(pd, idx, pt, scratch))
+			free_px(vm, pt);
+	} while (idx++, --len);
+
+	return start;
+}
+
+static void gen8_ppgtt_clear(struct i915_address_space *vm,
+			     u64 start, u64 length)
+{
+	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
+	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
+	GEM_BUG_ON(range_overflows(start, length, vm->total));
+
+	start >>= GEN8_PTE_SHIFT;
+	length >>= GEN8_PTE_SHIFT;
+	GEM_BUG_ON(length == 0);
+
+	__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
+			   start, start + length, vm->top);
+}
+
+static int __gen8_ppgtt_alloc(struct i915_address_space * const vm,
+			      struct i915_page_directory * const pd,
+			      u64 * const start, const u64 end, int lvl)
+{
+	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
+	struct i915_page_table *alloc = NULL;
+	unsigned int idx, len;
+	int ret = 0;
+
+	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
+
+	len = gen8_pd_range(*start, end, lvl--, &idx);
+	DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d }\n",
+	    __func__, vm, lvl + 1, *start, end,
+	    idx, len, atomic_read(px_used(pd)));
+	GEM_BUG_ON(!len || (idx + len - 1) >> gen8_pd_shift(1));
+
+	spin_lock(&pd->lock);
+	GEM_BUG_ON(!atomic_read(px_used(pd))); /* Must be pinned! */
+	do {
+		struct i915_page_table *pt = pd->entry[idx];
+
+		if (!pt) {
+			spin_unlock(&pd->lock);
+
+			DBG("%s(%p):{ lvl:%d, idx:%d } allocating new tree\n",
+			    __func__, vm, lvl + 1, idx);
+
+			pt = fetch_and_zero(&alloc);
+			if (lvl) {
+				if (!pt) {
+					pt = &alloc_pd(vm)->pt;
+					if (IS_ERR(pt)) {
+						ret = PTR_ERR(pt);
+						goto out;
+					}
+				}
+
+				fill_px(pt, vm->scratch[lvl].encode);
+			} else {
+				if (!pt) {
+					pt = alloc_pt(vm);
+					if (IS_ERR(pt)) {
+						ret = PTR_ERR(pt);
+						goto out;
+					}
+				}
+
+				if (intel_vgpu_active(vm->i915) ||
+				    gen8_pt_count(*start, end) < I915_PDES)
+					fill_px(pt, vm->scratch[lvl].encode);
+			}
+
+			spin_lock(&pd->lock);
+			if (likely(!pd->entry[idx]))
+				set_pd_entry(pd, idx, pt);
+			else
+				alloc = pt, pt = pd->entry[idx];
+		}
+
+		if (lvl) {
+			atomic_inc(&pt->used);
+			spin_unlock(&pd->lock);
+
+			ret = __gen8_ppgtt_alloc(vm, as_pd(pt),
+						 start, end, lvl);
+			if (unlikely(ret)) {
+				if (release_pd_entry(pd, idx, pt, scratch))
+					free_px(vm, pt);
+				goto out;
+			}
+
+			spin_lock(&pd->lock);
+			atomic_dec(&pt->used);
+			GEM_BUG_ON(!atomic_read(&pt->used));
+		} else {
+			unsigned int count = gen8_pt_count(*start, end);
+
+			DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d } inserting pte\n",
+			    __func__, vm, lvl, *start, end,
+			    gen8_pd_index(*start, 0), count,
+			    atomic_read(&pt->used));
+
+			atomic_add(count, &pt->used);
+			/* All other pdes may be simultaneously removed */
+			GEM_BUG_ON(atomic_read(&pt->used) > NALLOC * I915_PDES);
+			*start += count;
+		}
+	} while (idx++, --len);
+	spin_unlock(&pd->lock);
+out:
+	if (alloc)
+		free_px(vm, alloc);
+	return ret;
+}
+
+static int gen8_ppgtt_alloc(struct i915_address_space *vm,
+			    u64 start, u64 length)
+{
+	u64 from;
+	int err;
+
+	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
+	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
+	GEM_BUG_ON(range_overflows(start, length, vm->total));
+
+	start >>= GEN8_PTE_SHIFT;
+	length >>= GEN8_PTE_SHIFT;
+	GEM_BUG_ON(length == 0);
+	from = start;
+
+	err = __gen8_ppgtt_alloc(vm, i915_vm_to_ppgtt(vm)->pd,
+				 &start, start + length, vm->top);
+	if (unlikely(err && from != start))
+		__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
+				   from, start, vm->top);
+
+	return err;
+}
+
+static __always_inline u64
+gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
+		      struct i915_page_directory *pdp,
+		      struct sgt_dma *iter,
+		      u64 idx,
+		      enum i915_cache_level cache_level,
+		      u32 flags)
+{
+	struct i915_page_directory *pd;
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	gen8_pte_t *vaddr;
+
+	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
+	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+	do {
+		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
+		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
+
+		iter->dma += I915_GTT_PAGE_SIZE;
+		if (iter->dma >= iter->max) {
+			iter->sg = __sg_next(iter->sg);
+			if (!iter->sg) {
+				idx = 0;
+				break;
+			}
+
+			iter->dma = sg_dma_address(iter->sg);
+			iter->max = iter->dma + iter->sg->length;
+		}
+
+		if (gen8_pd_index(++idx, 0) == 0) {
+			if (gen8_pd_index(idx, 1) == 0) {
+				/* Limited by sg length for 3lvl */
+				if (gen8_pd_index(idx, 2) == 0)
+					break;
+
+				pd = pdp->entry[gen8_pd_index(idx, 2)];
+			}
+
+			kunmap_atomic(vaddr);
+			vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+		}
+	} while (1);
+	kunmap_atomic(vaddr);
+
+	return idx;
+}
+
+static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
+				   struct sgt_dma *iter,
+				   enum i915_cache_level cache_level,
+				   u32 flags)
+{
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	u64 start = vma->node.start;
+	dma_addr_t rem = iter->sg->length;
+
+	GEM_BUG_ON(!i915_vm_is_4lvl(vma->vm));
+
+	do {
+		struct i915_page_directory * const pdp =
+			gen8_pdp_for_page_address(vma->vm, start);
+		struct i915_page_directory * const pd =
+			i915_pd_entry(pdp, __gen8_pte_index(start, 2));
+		gen8_pte_t encode = pte_encode;
+		unsigned int maybe_64K = -1;
+		unsigned int page_size;
+		gen8_pte_t *vaddr;
+		u16 index;
+
+		if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_2M &&
+		    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) &&
+		    rem >= I915_GTT_PAGE_SIZE_2M &&
+		    !__gen8_pte_index(start, 0)) {
+			index = __gen8_pte_index(start, 1);
+			encode |= GEN8_PDE_PS_2M;
+			page_size = I915_GTT_PAGE_SIZE_2M;
+
+			vaddr = kmap_atomic_px(pd);
+		} else {
+			struct i915_page_table *pt =
+				i915_pt_entry(pd, __gen8_pte_index(start, 1));
+
+			index = __gen8_pte_index(start, 0);
+			page_size = I915_GTT_PAGE_SIZE;
+
+			if (!index &&
+			    vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K &&
+			    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
+			    (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
+			     rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE))
+				maybe_64K = __gen8_pte_index(start, 1);
+
+			vaddr = kmap_atomic_px(pt);
+		}
+
+		do {
+			GEM_BUG_ON(iter->sg->length < page_size);
+			vaddr[index++] = encode | iter->dma;
+
+			start += page_size;
+			iter->dma += page_size;
+			rem -= page_size;
+			if (iter->dma >= iter->max) {
+				iter->sg = __sg_next(iter->sg);
+				if (!iter->sg)
+					break;
+
+				rem = iter->sg->length;
+				iter->dma = sg_dma_address(iter->sg);
+				iter->max = iter->dma + rem;
+
+				if (maybe_64K != -1 && index < I915_PDES &&
+				    !(IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
+				      (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
+				       rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE)))
+					maybe_64K = -1;
+
+				if (unlikely(!IS_ALIGNED(iter->dma, page_size)))
+					break;
+			}
+		} while (rem >= page_size && index < I915_PDES);
+
+		kunmap_atomic(vaddr);
+
+		/*
+		 * Is it safe to mark the 2M block as 64K? -- Either we have
+		 * filled whole page-table with 64K entries, or filled part of
+		 * it and have reached the end of the sg table and we have
+		 * enough padding.
+		 */
+		if (maybe_64K != -1 &&
+		    (index == I915_PDES ||
+		     (i915_vm_has_scratch_64K(vma->vm) &&
+		      !iter->sg && IS_ALIGNED(vma->node.start +
+					      vma->node.size,
+					      I915_GTT_PAGE_SIZE_2M)))) {
+			vaddr = kmap_atomic_px(pd);
+			vaddr[maybe_64K] |= GEN8_PDE_IPS_64K;
+			kunmap_atomic(vaddr);
+			page_size = I915_GTT_PAGE_SIZE_64K;
+
+			/*
+			 * We write all 4K page entries, even when using 64K
+			 * pages. In order to verify that the HW isn't cheating
+			 * by using the 4K PTE instead of the 64K PTE, we want
+			 * to remove all the surplus entries. If the HW skipped
+			 * the 64K PTE, it will read/write into the scratch page
+			 * instead - which we detect as missing results during
+			 * selftests.
+			 */
+			if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) {
+				u16 i;
+
+				encode = vma->vm->scratch[0].encode;
+				vaddr = kmap_atomic_px(i915_pt_entry(pd, maybe_64K));
+
+				for (i = 1; i < index; i += 16)
+					memset64(vaddr + i, encode, 15);
+
+				kunmap_atomic(vaddr);
+			}
+		}
+
+		vma->page_sizes.gtt |= page_size;
+	} while (iter->sg);
+}
+
+static void gen8_ppgtt_insert(struct i915_address_space *vm,
+			      struct i915_vma *vma,
+			      enum i915_cache_level cache_level,
+			      u32 flags)
+{
+	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
+	struct sgt_dma iter = sgt_dma(vma);
+
+	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
+		gen8_ppgtt_insert_huge(vma, &iter, cache_level, flags);
+	} else  {
+		u64 idx = vma->node.start >> GEN8_PTE_SHIFT;
+
+		do {
+			struct i915_page_directory * const pdp =
+				gen8_pdp_for_page_index(vm, idx);
+
+			idx = gen8_ppgtt_insert_pte(ppgtt, pdp, &iter, idx,
+						    cache_level, flags);
+		} while (idx);
+
+		vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+	}
+}
+
+static int gen8_init_scratch(struct i915_address_space *vm)
+{
+	int ret;
+	int i;
+
+	/*
+	 * If everybody agrees to not to write into the scratch page,
+	 * we can reuse it for all vm, keeping contexts and processes separate.
+	 */
+	if (vm->has_read_only && vm->gt->vm && !i915_is_ggtt(vm->gt->vm)) {
+		struct i915_address_space *clone = vm->gt->vm;
+
+		GEM_BUG_ON(!clone->has_read_only);
+
+		vm->scratch_order = clone->scratch_order;
+		memcpy(vm->scratch, clone->scratch, sizeof(vm->scratch));
+		px_dma(&vm->scratch[0]) = 0; /* no xfer of ownership */
+		return 0;
+	}
+
+	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
+	if (ret)
+		return ret;
+
+	vm->scratch[0].encode =
+		gen8_pte_encode(px_dma(&vm->scratch[0]),
+				I915_CACHE_LLC, vm->has_read_only);
+
+	for (i = 1; i <= vm->top; i++) {
+		if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[i]))))
+			goto free_scratch;
+
+		fill_px(&vm->scratch[i], vm->scratch[i - 1].encode);
+		vm->scratch[i].encode =
+			gen8_pde_encode(px_dma(&vm->scratch[i]),
+					I915_CACHE_LLC);
+	}
+
+	return 0;
+
+free_scratch:
+	free_scratch(vm);
+	return -ENOMEM;
+}
+
+static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
+{
+	struct i915_address_space *vm = &ppgtt->vm;
+	struct i915_page_directory *pd = ppgtt->pd;
+	unsigned int idx;
+
+	GEM_BUG_ON(vm->top != 2);
+	GEM_BUG_ON(gen8_pd_top_count(vm) != GEN8_3LVL_PDPES);
+
+	for (idx = 0; idx < GEN8_3LVL_PDPES; idx++) {
+		struct i915_page_directory *pde;
+
+		pde = alloc_pd(vm);
+		if (IS_ERR(pde))
+			return PTR_ERR(pde);
+
+		fill_px(pde, vm->scratch[1].encode);
+		set_pd_entry(pd, idx, pde);
+		atomic_inc(px_used(pde)); /* keep pinned */
+	}
+	wmb();
+
+	return 0;
+}
+
+static struct i915_page_directory *
+gen8_alloc_top_pd(struct i915_address_space *vm)
+{
+	const unsigned int count = gen8_pd_top_count(vm);
+	struct i915_page_directory *pd;
+
+	GEM_BUG_ON(count > ARRAY_SIZE(pd->entry));
+
+	pd = __alloc_pd(offsetof(typeof(*pd), entry[count]));
+	if (unlikely(!pd))
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
+		kfree(pd);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	fill_page_dma(px_base(pd), vm->scratch[vm->top].encode, count);
+	atomic_inc(px_used(pd)); /* mark as pinned */
+	return pd;
+}
+
+/*
+ * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
+ * with a net effect resembling a 2-level page table in normal x86 terms. Each
+ * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
+ * space.
+ *
+ */
+struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt)
+{
+	struct i915_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
+
+	ppgtt_init(ppgtt, gt);
+	ppgtt->vm.top = i915_vm_is_4lvl(&ppgtt->vm) ? 3 : 2;
+
+	/*
+	 * From bdw, there is hw support for read-only pages in the PPGTT.
+	 *
+	 * Gen11 has HSDES#:1807136187 unresolved. Disable ro support
+	 * for now.
+	 *
+	 * Gen12 has inherited the same read-only fault issue from gen11.
+	 */
+	ppgtt->vm.has_read_only = !IS_GEN_RANGE(gt->i915, 11, 12);
+
+	/*
+	 * There are only few exceptions for gen >=6. chv and bxt.
+	 * And we are not sure about the latter so play safe for now.
+	 */
+	if (IS_CHERRYVIEW(gt->i915) || IS_BROXTON(gt->i915))
+		ppgtt->vm.pt_kmap_wc = true;
+
+	err = gen8_init_scratch(&ppgtt->vm);
+	if (err)
+		goto err_free;
+
+	ppgtt->pd = gen8_alloc_top_pd(&ppgtt->vm);
+	if (IS_ERR(ppgtt->pd)) {
+		err = PTR_ERR(ppgtt->pd);
+		goto err_free_scratch;
+	}
+
+	if (!i915_vm_is_4lvl(&ppgtt->vm)) {
+		err = gen8_preallocate_top_level_pdp(ppgtt);
+		if (err)
+			goto err_free_pd;
+	}
+
+	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
+	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
+	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
+	ppgtt->vm.clear_range = gen8_ppgtt_clear;
+
+	if (intel_vgpu_active(gt->i915))
+		gen8_ppgtt_notify_vgt(ppgtt, true);
+
+	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
+
+	return ppgtt;
+
+err_free_pd:
+	__gen8_ppgtt_cleanup(&ppgtt->vm, ppgtt->pd,
+			     gen8_pd_top_count(&ppgtt->vm), ppgtt->vm.top);
+err_free_scratch:
+	free_scratch(&ppgtt->vm);
+err_free:
+	kfree(ppgtt);
+	return ERR_PTR(err);
+}
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.h b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
new file mode 100644
index 000000000000..76a08b9c1f5c
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __GEN8_PPGTT_H__
+#define __GEN8_PPGTT_H__
+
+struct intel_gt;
+
+struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 55317081d48b..0ba524a414c6 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -28,6 +28,8 @@
 
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
 
 static void irq_enable(struct intel_engine_cs *engine)
 {
@@ -53,15 +55,17 @@ static void irq_disable(struct intel_engine_cs *engine)
 
 static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
 {
+	struct intel_engine_cs *engine =
+		container_of(b, struct intel_engine_cs, breadcrumbs);
+
 	lockdep_assert_held(&b->irq_lock);
 
 	GEM_BUG_ON(!b->irq_enabled);
 	if (!--b->irq_enabled)
-		irq_disable(container_of(b,
-					 struct intel_engine_cs,
-					 breadcrumbs));
+		irq_disable(engine);
 
 	b->irq_armed = false;
+	intel_gt_pm_put_async(engine->gt);
 }
 
 void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
@@ -127,16 +131,23 @@ __dma_fence_signal__notify(struct dma_fence *fence,
 	}
 }
 
-void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
+static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl)
 {
-	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct intel_engine_cs *engine =
+		container_of(b, struct intel_engine_cs, breadcrumbs);
+
+	intel_engine_add_retire(engine, tl);
+}
+
+static void signal_irq_work(struct irq_work *work)
+{
+	struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work);
 	const ktime_t timestamp = ktime_get();
 	struct intel_context *ce, *cn;
 	struct list_head *pos, *next;
-	unsigned long flags;
 	LIST_HEAD(signal);
 
-	spin_lock_irqsave(&b->irq_lock, flags);
+	spin_lock(&b->irq_lock);
 
 	if (b->irq_armed && list_empty(&b->signalers))
 		__intel_breadcrumbs_disarm_irq(b);
@@ -177,44 +188,41 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 		if (!list_is_first(pos, &ce->signals)) {
 			/* Advance the list to the first incomplete request */
 			__list_del_many(&ce->signals, pos);
-			if (&ce->signals == pos) /* now empty */
+			if (&ce->signals == pos) { /* now empty */
 				list_del_init(&ce->signal_link);
+				add_retire(b, ce->timeline);
+			}
 		}
 	}
 
-	spin_unlock_irqrestore(&b->irq_lock, flags);
+	spin_unlock(&b->irq_lock);
 
 	list_for_each_safe(pos, next, &signal) {
 		struct i915_request *rq =
 			list_entry(pos, typeof(*rq), signal_link);
 		struct list_head cb_list;
 
-		spin_lock_irqsave(&rq->lock, flags);
+		spin_lock(&rq->lock);
 		list_replace(&rq->fence.cb_list, &cb_list);
 		__dma_fence_signal__timestamp(&rq->fence, timestamp);
 		__dma_fence_signal__notify(&rq->fence, &cb_list);
-		spin_unlock_irqrestore(&rq->lock, flags);
+		spin_unlock(&rq->lock);
 
 		i915_request_put(rq);
 	}
 }
 
-static void signal_irq_work(struct irq_work *work)
-{
-	struct intel_engine_cs *engine =
-		container_of(work, typeof(*engine), breadcrumbs.irq_work);
-
-	intel_engine_breadcrumbs_irq(engine);
-}
-
-static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
+static bool __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 {
 	struct intel_engine_cs *engine =
 		container_of(b, struct intel_engine_cs, breadcrumbs);
 
 	lockdep_assert_held(&b->irq_lock);
 	if (b->irq_armed)
-		return;
+		return true;
+
+	if (!intel_gt_pm_get_if_awake(engine->gt))
+		return false;
 
 	/*
 	 * The breadcrumb irq will be disarmed on the interrupt after the
@@ -234,6 +242,8 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 
 	if (!b->irq_enabled++)
 		irq_enable(engine);
+
+	return true;
 }
 
 void intel_engine_init_breadcrumbs(struct intel_engine_cs *engine)
@@ -271,19 +281,20 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 
 	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
 		struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
-		struct intel_context *ce = rq->hw_context;
+		struct intel_context *ce = rq->context;
 		struct list_head *pos;
 
 		spin_lock(&b->irq_lock);
 		GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
 
-		__intel_breadcrumbs_arm_irq(b);
+		if (!__intel_breadcrumbs_arm_irq(b))
+			goto unlock;
 
 		/*
 		 * We keep the seqno in retirement order, so we can break
-		 * inside intel_engine_breadcrumbs_irq as soon as we've passed
-		 * the last completed request (or seen a request that hasn't
-		 * event started). We could iterate the timeline->requests list,
+		 * inside intel_engine_signal_breadcrumbs as soon as we've
+		 * passed the last completed request (or seen a request that
+		 * hasn't event started). We could walk the timeline->requests,
 		 * but keeping a separate signalers_list has the advantage of
 		 * hopefully being much smaller than the full list and so
 		 * provides faster iteration and detection when there are no
@@ -306,6 +317,7 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 		GEM_BUG_ON(!check_signal_order(ce, rq));
 
 		set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+unlock:
 		spin_unlock(&b->irq_lock);
 	}
 
@@ -326,7 +338,7 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq)
 	 */
 	spin_lock(&b->irq_lock);
 	if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) {
-		struct intel_context *ce = rq->hw_context;
+		struct intel_context *ce = rq->context;
 
 		list_del(&rq->signal_link);
 		if (list_empty(&ce->signals))
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 5b7ff3ccfa8e..23137b2a8689 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -31,8 +31,7 @@ void intel_context_free(struct intel_context *ce)
 }
 
 struct intel_context *
-intel_context_create(struct i915_gem_context *ctx,
-		     struct intel_engine_cs *engine)
+intel_context_create(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 
@@ -40,39 +39,82 @@ intel_context_create(struct i915_gem_context *ctx,
 	if (!ce)
 		return ERR_PTR(-ENOMEM);
 
-	intel_context_init(ce, ctx, engine);
+	intel_context_init(ce, engine);
 	return ce;
 }
 
-int __intel_context_do_pin(struct intel_context *ce)
+int intel_context_alloc_state(struct intel_context *ce)
 {
-	int err;
+	int err = 0;
 
 	if (mutex_lock_interruptible(&ce->pin_mutex))
 		return -EINTR;
 
-	if (likely(!atomic_read(&ce->pin_count))) {
-		intel_wakeref_t wakeref;
+	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
+		err = ce->ops->alloc(ce);
+		if (unlikely(err))
+			goto unlock;
 
-		if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
-			err = ce->ops->alloc(ce);
-			if (unlikely(err))
-				goto err;
+		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+	}
+
+unlock:
+	mutex_unlock(&ce->pin_mutex);
+	return err;
+}
+
+static int intel_context_active_acquire(struct intel_context *ce)
+{
+	int err;
 
-			__set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+	err = i915_active_acquire(&ce->active);
+	if (err)
+		return err;
+
+	/* Preallocate tracking nodes */
+	if (!intel_context_is_barrier(ce)) {
+		err = i915_active_acquire_preallocate_barrier(&ce->active,
+							      ce->engine);
+		if (err) {
+			i915_active_release(&ce->active);
+			return err;
 		}
+	}
+
+	return 0;
+}
 
-		err = 0;
-		with_intel_runtime_pm(ce->engine->uncore->rpm, wakeref)
-			err = ce->ops->pin(ce);
+static void intel_context_active_release(struct intel_context *ce)
+{
+	/* Nodes preallocated in intel_context_active() */
+	i915_active_acquire_barrier(&ce->active);
+	i915_active_release(&ce->active);
+}
+
+int __intel_context_do_pin(struct intel_context *ce)
+{
+	int err;
+
+	if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
+		err = intel_context_alloc_state(ce);
 		if (err)
+			return err;
+	}
+
+	if (mutex_lock_interruptible(&ce->pin_mutex))
+		return -EINTR;
+
+	if (likely(!atomic_read(&ce->pin_count))) {
+		err = intel_context_active_acquire(ce);
+		if (unlikely(err))
 			goto err;
 
-		GEM_TRACE("%s context:%llx pin ring:{head:%04x, tail:%04x}\n",
-			  ce->engine->name, ce->timeline->fence_context,
-			  ce->ring->head, ce->ring->tail);
+		err = ce->ops->pin(ce);
+		if (unlikely(err))
+			goto err_active;
 
-		i915_gem_context_get(ce->gem_context); /* for ctx->ppgtt */
+		CE_TRACE(ce, "pin ring:{head:%04x, tail:%04x}\n",
+			 ce->ring->head, ce->ring->tail);
 
 		smp_mb__before_atomic(); /* flush pin before it is visible */
 	}
@@ -83,6 +125,8 @@ int __intel_context_do_pin(struct intel_context *ce)
 	mutex_unlock(&ce->pin_mutex);
 	return 0;
 
+err_active:
+	intel_context_active_release(ce);
 err:
 	mutex_unlock(&ce->pin_mutex);
 	return err;
@@ -90,36 +134,29 @@ err:
 
 void intel_context_unpin(struct intel_context *ce)
 {
-	if (likely(atomic_add_unless(&ce->pin_count, -1, 1)))
+	if (!atomic_dec_and_test(&ce->pin_count))
 		return;
 
-	/* We may be called from inside intel_context_pin() to evict another */
-	intel_context_get(ce);
-	mutex_lock_nested(&ce->pin_mutex, SINGLE_DEPTH_NESTING);
-
-	if (likely(atomic_dec_and_test(&ce->pin_count))) {
-		GEM_TRACE("%s context:%llx retire\n",
-			  ce->engine->name, ce->timeline->fence_context);
-
-		ce->ops->unpin(ce);
-
-		i915_gem_context_put(ce->gem_context);
-		intel_context_active_release(ce);
-	}
+	CE_TRACE(ce, "unpin\n");
+	ce->ops->unpin(ce);
 
-	mutex_unlock(&ce->pin_mutex);
+	/*
+	 * Once released, we may asynchronously drop the active reference.
+	 * As that may be the only reference keeping the context alive,
+	 * take an extra now so that it is not freed before we finish
+	 * dereferencing it.
+	 */
+	intel_context_get(ce);
+	intel_context_active_release(ce);
 	intel_context_put(ce);
 }
 
 static int __context_pin_state(struct i915_vma *vma)
 {
-	u64 flags;
+	unsigned int bias = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
 	int err;
 
-	flags = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
-	flags |= PIN_HIGH | PIN_GLOBAL;
-
-	err = i915_vma_pin(vma, 0, 0, flags);
+	err = i915_ggtt_pin(vma, 0, bias | PIN_HIGH);
 	if (err)
 		return err;
 
@@ -178,9 +215,9 @@ static void __intel_context_retire(struct i915_active *active)
 {
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
 
-	GEM_TRACE("%s context:%llx retire\n",
-		  ce->engine->name, ce->timeline->fence_context);
+	CE_TRACE(ce, "retire\n");
 
+	set_bit(CONTEXT_VALID_BIT, &ce->flags);
 	if (ce->state)
 		__context_unpin_state(ce->state);
 
@@ -195,6 +232,8 @@ static int __intel_context_active(struct i915_active *active)
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
 	int err;
 
+	CE_TRACE(ce, "active\n");
+
 	intel_context_get(ce);
 
 	err = __ring_active(ce->ring);
@@ -223,60 +262,21 @@ err_put:
 	return err;
 }
 
-int intel_context_active_acquire(struct intel_context *ce)
-{
-	int err;
-
-	err = i915_active_acquire(&ce->active);
-	if (err)
-		return err;
-
-	/* Preallocate tracking nodes */
-	if (!i915_gem_context_is_kernel(ce->gem_context)) {
-		err = i915_active_acquire_preallocate_barrier(&ce->active,
-							      ce->engine);
-		if (err) {
-			i915_active_release(&ce->active);
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-void intel_context_active_release(struct intel_context *ce)
-{
-	/* Nodes preallocated in intel_context_active() */
-	i915_active_acquire_barrier(&ce->active);
-	i915_active_release(&ce->active);
-}
-
 void
 intel_context_init(struct intel_context *ce,
-		   struct i915_gem_context *ctx,
 		   struct intel_engine_cs *engine)
 {
-	struct i915_address_space *vm;
-
 	GEM_BUG_ON(!engine->cops);
+	GEM_BUG_ON(!engine->gt->vm);
 
 	kref_init(&ce->ref);
 
-	ce->gem_context = ctx;
-	rcu_read_lock();
-	vm = rcu_dereference(ctx->vm);
-	if (vm)
-		ce->vm = i915_vm_get(vm);
-	else
-		ce->vm = i915_vm_get(&engine->gt->ggtt->vm);
-	rcu_read_unlock();
-	if (ctx->timeline)
-		ce->timeline = intel_timeline_get(ctx->timeline);
-
 	ce->engine = engine;
 	ce->ops = engine->cops;
 	ce->sseu = engine->sseu;
-	ce->ring = __intel_context_ring_size(SZ_16K);
+	ce->ring = __intel_context_ring_size(SZ_4K);
+
+	ce->vm = i915_vm_get(engine->gt->vm);
 
 	INIT_LIST_HEAD(&ce->signal_link);
 	INIT_LIST_HEAD(&ce->signals);
@@ -341,30 +341,11 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 	int err;
 
 	/* Only suitable for use in remotely modifying this context */
-	GEM_BUG_ON(rq->hw_context == ce);
+	GEM_BUG_ON(rq->context == ce);
 
 	if (rcu_access_pointer(rq->timeline) != tl) { /* timeline sharing! */
-		/*
-		 * Ideally, we just want to insert our foreign fence as
-		 * a barrier into the remove context, such that this operation
-		 * occurs after all current operations in that context, and
-		 * all future operations must occur after this.
-		 *
-		 * Currently, the timeline->last_request tracking is guarded
-		 * by its mutex and so we must obtain that to atomically
-		 * insert our barrier. However, since we already hold our
-		 * timeline->mutex, we must be careful against potential
-		 * inversion if we are the kernel_context as the remote context
-		 * will itself poke at the kernel_context when it needs to
-		 * unpin. Ergo, if already locked, we drop both locks and
-		 * try again (through the magic of userspace repeating EAGAIN).
-		 */
-		if (!mutex_trylock(&tl->mutex))
-			return -EAGAIN;
-
 		/* Queue this switch after current activity by this context. */
 		err = i915_active_fence_set(&tl->last_request, rq);
-		mutex_unlock(&tl->mutex);
 		if (err)
 			return err;
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 68b3d317d959..30bd248827d8 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -7,7 +7,9 @@
 #ifndef __INTEL_CONTEXT_H__
 #define __INTEL_CONTEXT_H__
 
+#include <linux/bitops.h>
 #include <linux/lockdep.h>
+#include <linux/types.h>
 
 #include "i915_active.h"
 #include "intel_context_types.h"
@@ -15,14 +17,21 @@
 #include "intel_ring_types.h"
 #include "intel_timeline_types.h"
 
+#define CE_TRACE(ce, fmt, ...) do {					\
+	const struct intel_context *ce__ = (ce);			\
+	ENGINE_TRACE(ce__->engine, "context:%llx " fmt,			\
+		     ce__->timeline->fence_context,			\
+		     ##__VA_ARGS__);					\
+} while (0)
+
 void intel_context_init(struct intel_context *ce,
-			struct i915_gem_context *ctx,
 			struct intel_engine_cs *engine);
 void intel_context_fini(struct intel_context *ce);
 
 struct intel_context *
-intel_context_create(struct i915_gem_context *ctx,
-		     struct intel_engine_cs *engine);
+intel_context_create(struct intel_engine_cs *engine);
+
+int intel_context_alloc_state(struct intel_context *ce);
 
 void intel_context_free(struct intel_context *ce);
 
@@ -69,9 +78,14 @@ static inline void intel_context_unlock_pinned(struct intel_context *ce)
 
 int __intel_context_do_pin(struct intel_context *ce);
 
+static inline bool intel_context_pin_if_active(struct intel_context *ce)
+{
+	return atomic_inc_not_zero(&ce->pin_count);
+}
+
 static inline int intel_context_pin(struct intel_context *ce)
 {
-	if (likely(atomic_inc_not_zero(&ce->pin_count)))
+	if (likely(intel_context_pin_if_active(ce)))
 		return 0;
 
 	return __intel_context_do_pin(ce);
@@ -109,9 +123,6 @@ static inline void intel_context_exit(struct intel_context *ce)
 		ce->ops->exit(ce);
 }
 
-int intel_context_active_acquire(struct intel_context *ce);
-void intel_context_active_release(struct intel_context *ce);
-
 static inline struct intel_context *intel_context_get(struct intel_context *ce)
 {
 	kref_get(&ce->ref);
@@ -153,4 +164,64 @@ static inline struct intel_ring *__intel_context_ring_size(u64 sz)
 	return u64_to_ptr(struct intel_ring, sz);
 }
 
+static inline bool intel_context_is_barrier(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_BARRIER_BIT, &ce->flags);
+}
+
+static inline bool intel_context_use_semaphores(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
+}
+
+static inline void intel_context_set_use_semaphores(struct intel_context *ce)
+{
+	set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
+}
+
+static inline void intel_context_clear_use_semaphores(struct intel_context *ce)
+{
+	clear_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
+}
+
+static inline bool intel_context_is_banned(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_BANNED, &ce->flags);
+}
+
+static inline bool intel_context_set_banned(struct intel_context *ce)
+{
+	return test_and_set_bit(CONTEXT_BANNED, &ce->flags);
+}
+
+static inline bool
+intel_context_force_single_submission(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_FORCE_SINGLE_SUBMISSION, &ce->flags);
+}
+
+static inline void
+intel_context_set_single_submission(struct intel_context *ce)
+{
+	__set_bit(CONTEXT_FORCE_SINGLE_SUBMISSION, &ce->flags);
+}
+
+static inline bool
+intel_context_nopreempt(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_NOPREEMPT, &ce->flags);
+}
+
+static inline void
+intel_context_set_nopreempt(struct intel_context *ce)
+{
+	set_bit(CONTEXT_NOPREEMPT, &ce->flags);
+}
+
+static inline void
+intel_context_clear_nopreempt(struct intel_context *ce)
+{
+	clear_bit(CONTEXT_NOPREEMPT, &ce->flags);
+}
+
 #endif /* __INTEL_CONTEXT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 6959b05ae5f8..ca1420fb8b53 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -17,6 +17,8 @@
 #include "intel_engine_types.h"
 #include "intel_sseu.h"
 
+#define CONTEXT_REDZONE POISON_INUSE
+
 struct i915_gem_context;
 struct i915_vma;
 struct intel_context;
@@ -44,7 +46,7 @@ struct intel_context {
 #define intel_context_inflight_count(ce) ptr_unmask_bits((ce)->inflight, 2)
 
 	struct i915_address_space *vm;
-	struct i915_gem_context *gem_context;
+	struct i915_gem_context __rcu *gem_context;
 
 	struct list_head signal_link;
 	struct list_head signals;
@@ -54,7 +56,13 @@ struct intel_context {
 	struct intel_timeline *timeline;
 
 	unsigned long flags;
-#define CONTEXT_ALLOC_BIT 0
+#define CONTEXT_BARRIER_BIT		0
+#define CONTEXT_ALLOC_BIT		1
+#define CONTEXT_VALID_BIT		2
+#define CONTEXT_USE_SEMAPHORES		3
+#define CONTEXT_BANNED			4
+#define CONTEXT_FORCE_SINGLE_SUBMISSION	5
+#define CONTEXT_NOPREEMPT		6
 
 	u32 *lrc_reg_state;
 	u64 lrc_desc;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 01765a7ec18f..5df003061e44 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -29,6 +29,13 @@ struct intel_gt;
 #define CACHELINE_BYTES 64
 #define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(u32))
 
+#define ENGINE_TRACE(e, fmt, ...) do {					\
+	const struct intel_engine_cs *e__ __maybe_unused = (e);		\
+	GEM_TRACE("%s %s: " fmt,					\
+		  dev_name(e__->i915->drm.dev), e__->name,		\
+		  ##__VA_ARGS__);					\
+} while (0)
+
 /*
  * The register defines to be used with the following macros need to accept a
  * base param, e.g:
@@ -177,15 +184,15 @@ void intel_engine_stop(struct intel_engine_cs *engine);
 void intel_engine_cleanup(struct intel_engine_cs *engine);
 
 int intel_engines_init_mmio(struct intel_gt *gt);
-int intel_engines_setup(struct intel_gt *gt);
 int intel_engines_init(struct intel_gt *gt);
-void intel_engines_cleanup(struct intel_gt *gt);
+
+void intel_engines_release(struct intel_gt *gt);
+void intel_engines_free(struct intel_gt *gt);
 
 int intel_engine_init_common(struct intel_engine_cs *engine);
 void intel_engine_cleanup_common(struct intel_engine_cs *engine);
 
 int intel_ring_submission_setup(struct intel_engine_cs *engine);
-int intel_ring_submission_init(struct intel_engine_cs *engine);
 
 int intel_engine_stop_cs(struct intel_engine_cs *engine);
 void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine);
@@ -195,7 +202,7 @@ void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask);
 u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
 u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);
 
-void intel_engine_get_instdone(struct intel_engine_cs *engine,
+void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone);
 
 void intel_engine_init_execlists(struct intel_engine_cs *engine);
@@ -206,13 +213,11 @@ void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine);
 
 static inline void
-intel_engine_queue_breadcrumbs(struct intel_engine_cs *engine)
+intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine)
 {
 	irq_work_queue(&engine->breadcrumbs.irq_work);
 }
 
-void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine);
-
 void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 
@@ -270,8 +275,8 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 static inline void __intel_engine_reset(struct intel_engine_cs *engine,
 					bool stalled)
 {
-	if (engine->reset.reset)
-		engine->reset.reset(engine, stalled);
+	if (engine->reset.rewind)
+		engine->reset.rewind(engine, stalled);
 	engine->serial++; /* contexts lost */
 }
 
@@ -296,7 +301,7 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
 struct i915_request *
 intel_engine_find_active_request(struct intel_engine_cs *engine);
 
-u32 intel_engine_context_size(struct drm_i915_private *i915, u8 class);
+u32 intel_engine_context_size(struct intel_gt *gt, u8 class);
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 813bd3a610d2..f451ef376548 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -141,7 +141,7 @@ static const struct engine_info intel_engines[] = {
 
 /**
  * intel_engine_context_size() - return the size of the context for an engine
- * @dev_priv: i915 device private
+ * @gt: the gt
  * @class: engine class
  *
  * Each engine class may require a different amount of space for a context
@@ -153,17 +153,18 @@ static const struct engine_info intel_engines[] = {
  * in LRC mode, but does not include the "shared data page" used with
  * GuC submission. The caller should account for this if using the GuC.
  */
-u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
+u32 intel_engine_context_size(struct intel_gt *gt, u8 class)
 {
+	struct intel_uncore *uncore = gt->uncore;
 	u32 cxt_size;
 
 	BUILD_BUG_ON(I915_GTT_PAGE_SIZE != PAGE_SIZE);
 
 	switch (class) {
 	case RENDER_CLASS:
-		switch (INTEL_GEN(dev_priv)) {
+		switch (INTEL_GEN(gt->i915)) {
 		default:
-			MISSING_CASE(INTEL_GEN(dev_priv));
+			MISSING_CASE(INTEL_GEN(gt->i915));
 			return DEFAULT_LR_CONTEXT_RENDER_SIZE;
 		case 12:
 		case 11:
@@ -175,14 +176,14 @@ u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 		case 8:
 			return GEN8_LR_CONTEXT_RENDER_SIZE;
 		case 7:
-			if (IS_HASWELL(dev_priv))
+			if (IS_HASWELL(gt->i915))
 				return HSW_CXT_TOTAL_SIZE;
 
-			cxt_size = I915_READ(GEN7_CXT_SIZE);
+			cxt_size = intel_uncore_read(uncore, GEN7_CXT_SIZE);
 			return round_up(GEN7_CXT_TOTAL_SIZE(cxt_size) * 64,
 					PAGE_SIZE);
 		case 6:
-			cxt_size = I915_READ(CXT_SIZE);
+			cxt_size = intel_uncore_read(uncore, CXT_SIZE);
 			return round_up(GEN6_CXT_TOTAL_SIZE(cxt_size) * 64,
 					PAGE_SIZE);
 		case 5:
@@ -197,9 +198,9 @@ u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 			 * minimum allocation anyway so it should all come
 			 * out in the wash.
 			 */
-			cxt_size = I915_READ(CXT_SIZE) + 1;
+			cxt_size = intel_uncore_read(uncore, CXT_SIZE) + 1;
 			DRM_DEBUG_DRIVER("gen%d CXT_SIZE = %d bytes [0x%08x]\n",
-					 INTEL_GEN(dev_priv),
+					 INTEL_GEN(gt->i915),
 					 cxt_size * 64,
 					 cxt_size - 1);
 			return round_up(cxt_size * 64, PAGE_SIZE);
@@ -216,7 +217,7 @@ u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 	case VIDEO_DECODE_CLASS:
 	case VIDEO_ENHANCEMENT_CLASS:
 	case COPY_ENGINE_CLASS:
-		if (INTEL_GEN(dev_priv) < 8)
+		if (INTEL_GEN(gt->i915) < 8)
 			return 0;
 		return GEN8_LR_CONTEXT_OTHER_SIZE;
 	}
@@ -318,14 +319,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	engine->props.timeslice_duration_ms =
 		CONFIG_DRM_I915_TIMESLICE_DURATION;
 
-	/*
-	 * To be overridden by the backend on setup. However to facilitate
-	 * cleanup on error during setup, we always provide the destroy vfunc.
-	 */
-	engine->destroy = (typeof(engine->destroy))kfree;
-
-	engine->context_size = intel_engine_context_size(gt->i915,
-							 engine->class);
+	engine->context_size = intel_engine_context_size(gt, engine->class);
 	if (WARN_ON(engine->context_size > BIT(20)))
 		engine->context_size = 0;
 	if (engine->context_size)
@@ -334,6 +328,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
+	ewma__engine_latency_init(&engine->latency);
 	seqlock_init(&engine->stats.lock);
 
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
@@ -344,7 +339,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	gt->engine_class[info->class][info->instance] = engine;
 	gt->engine[id] = engine;
 
-	intel_engine_add_user(engine);
 	gt->i915->engine[id] = engine;
 
 	return 0;
@@ -390,21 +384,39 @@ static void intel_setup_engine_capabilities(struct intel_gt *gt)
 }
 
 /**
- * intel_engines_cleanup() - free the resources allocated for Command Streamers
+ * intel_engines_release() - free the resources allocated for Command Streamers
  * @gt: pointer to struct intel_gt
  */
-void intel_engines_cleanup(struct intel_gt *gt)
+void intel_engines_release(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	/* Decouple the backend; but keep the layout for late GPU resets */
 	for_each_engine(engine, gt, id) {
-		engine->destroy(engine);
-		gt->engine[id] = NULL;
+		if (!engine->release)
+			continue;
+
+		engine->release(engine);
+		engine->release = NULL;
+
+		memset(&engine->reset, 0, sizeof(engine->reset));
+
 		gt->i915->engine[id] = NULL;
 	}
 }
 
+void intel_engines_free(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id) {
+		kfree(engine);
+		gt->engine[id] = NULL;
+	}
+}
+
 /**
  * intel_engines_init_mmio() - allocate and prepare the Engine Command Streamers
  * @gt: pointer to struct intel_gt
@@ -455,38 +467,7 @@ int intel_engines_init_mmio(struct intel_gt *gt)
 	return 0;
 
 cleanup:
-	intel_engines_cleanup(gt);
-	return err;
-}
-
-/**
- * intel_engines_init() - init the Engine Command Streamers
- * @gt: pointer to struct intel_gt
- *
- * Return: non-zero if the initialization failed.
- */
-int intel_engines_init(struct intel_gt *gt)
-{
-	int (*init)(struct intel_engine_cs *engine);
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err;
-
-	if (HAS_EXECLISTS(gt->i915))
-		init = intel_execlists_submission_init;
-	else
-		init = intel_ring_submission_init;
-
-	for_each_engine(engine, gt, id) {
-		err = init(engine);
-		if (err)
-			goto cleanup;
-	}
-
-	return 0;
-
-cleanup:
-	intel_engines_cleanup(gt);
+	intel_engines_free(gt);
 	return err;
 }
 
@@ -601,7 +582,7 @@ err:
 	return ret;
 }
 
-static int intel_engine_setup_common(struct intel_engine_cs *engine)
+static int engine_setup_common(struct intel_engine_cs *engine)
 {
 	int err;
 
@@ -631,49 +612,6 @@ static int intel_engine_setup_common(struct intel_engine_cs *engine)
 	return 0;
 }
 
-/**
- * intel_engines_setup- setup engine state not requiring hw access
- * @gt: pointer to struct intel_gt
- *
- * Initializes engine structure members shared between legacy and execlists
- * submission modes which do not require hardware access.
- *
- * Typically done early in the submission mode specific engine setup stage.
- */
-int intel_engines_setup(struct intel_gt *gt)
-{
-	int (*setup)(struct intel_engine_cs *engine);
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err;
-
-	if (HAS_EXECLISTS(gt->i915))
-		setup = intel_execlists_submission_setup;
-	else
-		setup = intel_ring_submission_setup;
-
-	for_each_engine(engine, gt, id) {
-		err = intel_engine_setup_common(engine);
-		if (err)
-			goto cleanup;
-
-		err = setup(engine);
-		if (err)
-			goto cleanup;
-
-		/* We expect the backend to take control over its state */
-		GEM_BUG_ON(engine->destroy == (typeof(engine->destroy))kfree);
-
-		GEM_BUG_ON(!engine->cops);
-	}
-
-	return 0;
-
-cleanup:
-	intel_engines_cleanup(gt);
-	return err;
-}
-
 struct measure_breadcrumb {
 	struct i915_request rq;
 	struct intel_timeline timeline;
@@ -757,13 +695,13 @@ create_kernel_context(struct intel_engine_cs *engine)
 	struct intel_context *ce;
 	int err;
 
-	ce = intel_context_create(engine->i915->kernel_context, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return ce;
 
-	ce->ring = __intel_context_ring_size(SZ_4K);
+	__set_bit(CONTEXT_BARRIER_BIT, &ce->flags);
 
-	err = intel_context_pin(ce);
+	err = intel_context_pin(ce); /* perma-pin so it is always available */
 	if (err) {
 		intel_context_put(ce);
 		return ERR_PTR(err);
@@ -791,13 +729,19 @@ create_kernel_context(struct intel_engine_cs *engine)
  *
  * Returns zero on success or an error code on failure.
  */
-int intel_engine_init_common(struct intel_engine_cs *engine)
+static int engine_init_common(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 	int ret;
 
 	engine->set_default_submission(engine);
 
+	ret = measure_breadcrumb_dw(engine);
+	if (ret < 0)
+		return ret;
+
+	engine->emit_fini_breadcrumb_dw = ret;
+
 	/*
 	 * We may need to do things with the shrinker which
 	 * require us to immediately switch back to the default
@@ -812,18 +756,38 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 
 	engine->kernel_context = ce;
 
-	ret = measure_breadcrumb_dw(engine);
-	if (ret < 0)
-		goto err_unpin;
+	return 0;
+}
 
-	engine->emit_fini_breadcrumb_dw = ret;
+int intel_engines_init(struct intel_gt *gt)
+{
+	int (*setup)(struct intel_engine_cs *engine);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err;
 
-	return 0;
+	if (HAS_EXECLISTS(gt->i915))
+		setup = intel_execlists_submission_setup;
+	else
+		setup = intel_ring_submission_setup;
 
-err_unpin:
-	intel_context_unpin(ce);
-	intel_context_put(ce);
-	return ret;
+	for_each_engine(engine, gt, id) {
+		err = engine_setup_common(engine);
+		if (err)
+			return err;
+
+		err = setup(engine);
+		if (err)
+			return err;
+
+		err = engine_init_common(engine);
+		if (err)
+			return err;
+
+		intel_engine_add_user(engine);
+	}
+
+	return 0;
 }
 
 /**
@@ -836,6 +800,7 @@ err_unpin:
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
 	GEM_BUG_ON(!list_empty(&engine->active.requests));
+	tasklet_kill(&engine->execlists.tasklet); /* flush the callback */
 
 	cleanup_status_page(engine);
 
@@ -911,7 +876,7 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
 	if (INTEL_GEN(engine->i915) < 3)
 		return -ENODEV;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
 
@@ -920,7 +885,7 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
 					 mode, MODE_IDLE, MODE_IDLE,
 					 1000, stop_timeout(engine),
 					 NULL)) {
-		GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
+		ENGINE_TRACE(engine, "timed out on STOP_RING -> IDLE\n");
 		err = -ETIMEDOUT;
 	}
 
@@ -932,7 +897,7 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
 
 void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
 {
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	ENGINE_WRITE_FW(engine, RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
 }
@@ -949,8 +914,8 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 }
 
 static u32
-read_subslice_reg(struct intel_engine_cs *engine, int slice, int subslice,
-		  i915_reg_t reg)
+read_subslice_reg(const struct intel_engine_cs *engine,
+		  int slice, int subslice, i915_reg_t reg)
 {
 	struct drm_i915_private *i915 = engine->i915;
 	struct intel_uncore *uncore = engine->uncore;
@@ -994,7 +959,7 @@ read_subslice_reg(struct intel_engine_cs *engine, int slice, int subslice,
 }
 
 /* NB: please notice the memset */
-void intel_engine_get_instdone(struct intel_engine_cs *engine,
+void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone)
 {
 	struct drm_i915_private *i915 = engine->i915;
@@ -1478,6 +1443,10 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		drm_printf(m, "*** WEDGED ***\n");
 
 	drm_printf(m, "\tAwake? %d\n", atomic_read(&engine->wakeref.count));
+	drm_printf(m, "\tBarriers?: %s\n",
+		   yesno(!llist_empty(&engine->barrier_tasks)));
+	drm_printf(m, "\tLatency: %luus\n",
+		   ewma__engine_latency_read(&engine->latency));
 
 	rcu_read_lock();
 	rq = READ_ONCE(engine->heartbeat.systole);
@@ -1517,9 +1486,9 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 
 		print_request_ring(m, rq);
 
-		if (rq->hw_context->lrc_reg_state) {
+		if (rq->context->lrc_reg_state) {
 			drm_printf(m, "Logical Ring Context:\n");
-			hexdump(m, rq->hw_context->lrc_reg_state, PAGE_SIZE);
+			hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE);
 		}
 	}
 	spin_unlock_irqrestore(&engine->active.lock, flags);
@@ -1580,7 +1549,7 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 
 		for (port = execlists->pending; (rq = *port); port++) {
 			/* Exclude any contexts already counted in active */
-			if (!intel_context_inflight_count(rq->hw_context))
+			if (!intel_context_inflight_count(rq->context))
 				engine->stats.active++;
 		}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index 06aa14c7aa8c..6c6fd185457c 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -63,15 +63,15 @@ static void heartbeat(struct work_struct *wrk)
 	struct intel_context *ce = engine->kernel_context;
 	struct i915_request *rq;
 
-	if (!intel_engine_pm_get_if_awake(engine))
-		return;
-
 	rq = engine->heartbeat.systole;
 	if (rq && i915_request_completed(rq)) {
 		i915_request_put(rq);
 		engine->heartbeat.systole = NULL;
 	}
 
+	if (!intel_engine_pm_get_if_awake(engine))
+		return;
+
 	if (intel_gt_is_wedged(engine->gt))
 		goto out;
 
@@ -199,7 +199,7 @@ int intel_engine_pulse(struct intel_engine_cs *engine)
 		goto out_unlock;
 	}
 
-	rq->flags |= I915_REQUEST_SENTINEL;
+	__set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags);
 	idle_pulse(engine, rq);
 
 	__i915_request_commit(rq);
@@ -215,18 +215,26 @@ out_rpm:
 int intel_engine_flush_barriers(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq;
+	int err = 0;
 
 	if (llist_empty(&engine->barrier_tasks))
 		return 0;
 
+	if (!intel_engine_pm_get_if_awake(engine))
+		return 0;
+
 	rq = i915_request_create(engine->kernel_context);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_rpm;
+	}
 
 	idle_pulse(engine, rq);
 	i915_request_add(rq);
 
-	return 0;
+out_rpm:
+	intel_engine_pm_put(engine);
+	return err;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index c1dd0cd3efc7..ea90ab3e396e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -6,6 +6,7 @@
 
 #include "i915_drv.h"
 
+#include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
@@ -19,9 +20,10 @@ static int __engine_unpark(struct intel_wakeref *wf)
 {
 	struct intel_engine_cs *engine =
 		container_of(wf, typeof(*engine), wakeref);
+	struct intel_context *ce;
 	void *map;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	intel_gt_pm_get(engine->gt);
 
@@ -33,6 +35,27 @@ static int __engine_unpark(struct intel_wakeref *wf)
 	if (!IS_ERR_OR_NULL(map))
 		engine->pinned_default_state = map;
 
+	/* Discard stale context state from across idling */
+	ce = engine->kernel_context;
+	if (ce) {
+		GEM_BUG_ON(test_bit(CONTEXT_VALID_BIT, &ce->flags));
+
+		/* First poison the image to verify we never fully trust it */
+		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && ce->state) {
+			struct drm_i915_gem_object *obj = ce->state->obj;
+			int type = i915_coherent_map_type(engine->i915);
+
+			map = i915_gem_object_pin_map(obj, type);
+			if (!IS_ERR(map)) {
+				memset(map, CONTEXT_REDZONE, obj->base.size);
+				i915_gem_object_flush_map(obj);
+				i915_gem_object_unpin_map(obj);
+			}
+		}
+
+		ce->ops->reset(ce);
+	}
+
 	if (engine->unpark)
 		engine->unpark(engine);
 
@@ -73,6 +96,15 @@ static inline void __timeline_mark_unlock(struct intel_context *ce,
 
 #endif /* !IS_ENABLED(CONFIG_LOCKDEP) */
 
+static void duration(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	struct i915_request *rq = to_request(fence);
+
+	ewma__engine_latency_add(&rq->engine->latency,
+				 ktime_us_delta(rq->fence.timestamp,
+						rq->duration.emitted));
+}
+
 static void
 __queue_and_release_pm(struct i915_request *rq,
 		       struct intel_timeline *tl,
@@ -80,7 +112,7 @@ __queue_and_release_pm(struct i915_request *rq,
 {
 	struct intel_gt_timelines *timelines = &engine->gt->timelines;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * We have to serialise all potential retirement paths with our
@@ -113,14 +145,16 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	unsigned long flags;
 	bool result = true;
 
-	/* Already inside the kernel context, safe to power down. */
-	if (engine->wakeref_serial == engine->serial)
-		return true;
-
 	/* GPU is pointing to the void, as good as in the kernel context. */
 	if (intel_gt_is_wedged(engine->gt))
 		return true;
 
+	GEM_BUG_ON(!intel_context_is_barrier(ce));
+
+	/* Already inside the kernel context, safe to power down. */
+	if (engine->wakeref_serial == engine->serial)
+		return true;
+
 	/*
 	 * Note, we do this without taking the timeline->mutex. We cannot
 	 * as we may be called while retiring the kernel context and so
@@ -163,7 +197,18 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 
 	/* Install ourselves as a preemption barrier */
 	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
-	__i915_request_commit(rq);
+	if (likely(!__i915_request_commit(rq))) { /* engine should be idle! */
+		/*
+		 * Use an interrupt for precise measurement of duration,
+		 * otherwise we rely on someone else retiring all the requests
+		 * which may delay the signaling (i.e. we will likely wait
+		 * until the background request retirement running every
+		 * second or two).
+		 */
+		BUILD_BUG_ON(sizeof(rq->duration) > sizeof(rq->submitq));
+		dma_fence_add_callback(&rq->fence, &rq->duration.cb, duration);
+		rq->duration.emitted = ktime_get();
+	}
 
 	/* Expose ourselves to the world */
 	__queue_and_release_pm(rq, ce->timeline, engine);
@@ -183,7 +228,7 @@ static void call_idle_barriers(struct intel_engine_cs *engine)
 			container_of((struct list_head *)node,
 				     typeof(*cb), node);
 
-		cb->func(NULL, cb);
+		cb->func(ERR_PTR(-EAGAIN), cb);
 	}
 }
 
@@ -204,7 +249,7 @@ static int __engine_park(struct intel_wakeref *wf)
 	if (!switch_to_kernel_context(engine))
 		return -EBUSY;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	call_idle_barriers(engine); /* cleanup after wedging */
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
index 24e20344dc22..e52c2b0cb245 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
@@ -7,6 +7,7 @@
 #ifndef INTEL_ENGINE_PM_H
 #define INTEL_ENGINE_PM_H
 
+#include "i915_request.h"
 #include "intel_engine_types.h"
 #include "intel_wakeref.h"
 
@@ -41,6 +42,26 @@ static inline void intel_engine_pm_flush(struct intel_engine_cs *engine)
 	intel_wakeref_unlock_wait(&engine->wakeref);
 }
 
+static inline struct i915_request *
+intel_engine_create_kernel_request(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq;
+
+	/*
+	 * The engine->kernel_context is special as it is used inside
+	 * the engine-pm barrier (see __engine_park()), circumventing
+	 * the usual mutexes and relying on the engine-pm barrier
+	 * instead. So whenever we use the engine->kernel_context
+	 * outside of the barrier, we must manually handle the
+	 * engine wakeref to serialise with the use inside.
+	 */
+	intel_engine_pm_get(engine);
+	rq = i915_request_create(engine->kernel_context);
+	intel_engine_pm_put(engine);
+
+	return rq;
+}
+
 void intel_engine_init__pm(struct intel_engine_cs *engine);
 
 #endif /* INTEL_ENGINE_PM_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 2b446474e010..350da59e605b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -7,6 +7,7 @@
 #ifndef __INTEL_ENGINE_TYPES__
 #define __INTEL_ENGINE_TYPES__
 
+#include <linux/average.h>
 #include <linux/hashtable.h>
 #include <linux/irq_work.h>
 #include <linux/kref.h>
@@ -119,6 +120,9 @@ enum intel_engine_id {
 #define INVALID_ENGINE ((enum intel_engine_id)-1)
 };
 
+/* A simple estimator for the round-trip latency of an engine */
+DECLARE_EWMA(_engine_latency, 6, 4)
+
 struct st_preempt_hang {
 	struct completion completion;
 	unsigned int count;
@@ -316,6 +320,13 @@ struct intel_engine_cs {
 		struct intel_timeline *timeline;
 	} legacy;
 
+	/*
+	 * We track the average duration of the idle pulse on parking the
+	 * engine to keep an estimate of the how the fast the engine is
+	 * under ideal conditions.
+	 */
+	struct ewma__engine_latency latency;
+
 	/* Rather than have every client wait upon all user interrupts,
 	 * with the herd waking after every interrupt and each doing the
 	 * heavyweight seqno dance, we delegate the task (of being the
@@ -389,7 +400,10 @@ struct intel_engine_cs {
 
 	struct {
 		void (*prepare)(struct intel_engine_cs *engine);
-		void (*reset)(struct intel_engine_cs *engine, bool stalled);
+
+		void (*rewind)(struct intel_engine_cs *engine, bool stalled);
+		void (*cancel)(struct intel_engine_cs *engine);
+
 		void (*finish)(struct intel_engine_cs *engine);
 	} reset;
 
@@ -439,15 +453,7 @@ struct intel_engine_cs {
 	void		(*schedule)(struct i915_request *request,
 				    const struct i915_sched_attr *attr);
 
-	/*
-	 * Cancel all requests on the hardware, or queued for execution.
-	 * This should only cancel the ready requests that have been
-	 * submitted to the engine (via the engine->submit_request callback).
-	 * This is called when marking the device as wedged.
-	 */
-	void		(*cancel_requests)(struct intel_engine_cs *engine);
-
-	void		(*destroy)(struct intel_engine_cs *engine);
+	void		(*release)(struct intel_engine_cs *engine);
 
 	struct intel_engine_execlists execlists;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 7f7150a733f4..9e7f12bef828 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -11,6 +11,7 @@
 #include "i915_drv.h"
 #include "intel_engine.h"
 #include "intel_engine_user.h"
+#include "intel_gt.h"
 
 struct intel_engine_cs *
 intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
@@ -200,6 +201,9 @@ void intel_engines_driver_register(struct drm_i915_private *i915)
 				     uabi_node);
 		char old[sizeof(engine->name)];
 
+		if (intel_gt_has_init_error(engine->gt))
+			continue; /* ignore incomplete engines */
+
 		GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes));
 		engine->uabi_class = uabi_classes[engine->class];
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
new file mode 100644
index 000000000000..531d501be01f
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -0,0 +1,1486 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/stop_machine.h>
+
+#include <asm/set_memory.h>
+#include <asm/smp.h>
+
+#include "intel_gt.h"
+#include "i915_drv.h"
+#include "i915_scatterlist.h"
+#include "i915_vgpu.h"
+
+#include "intel_gtt.h"
+
+static int
+i915_get_ggtt_vma_pages(struct i915_vma *vma);
+
+static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
+				   unsigned long color,
+				   u64 *start,
+				   u64 *end)
+{
+	if (i915_node_color_differs(node, color))
+		*start += I915_GTT_PAGE_SIZE;
+
+	/*
+	 * Also leave a space between the unallocated reserved node after the
+	 * GTT and any objects within the GTT, i.e. we use the color adjustment
+	 * to insert a guard page to prevent prefetches crossing over the
+	 * GTT boundary.
+	 */
+	node = list_next_entry(node, node_list);
+	if (node->color != color)
+		*end -= I915_GTT_PAGE_SIZE;
+}
+
+static int ggtt_init_hw(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+
+	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
+
+	ggtt->vm.is_ggtt = true;
+
+	/* Only VLV supports read-only GGTT mappings */
+	ggtt->vm.has_read_only = IS_VALLEYVIEW(i915);
+
+	if (!HAS_LLC(i915) && !HAS_PPGTT(i915))
+		ggtt->vm.mm.color_adjust = i915_ggtt_color_adjust;
+
+	if (ggtt->mappable_end) {
+		if (!io_mapping_init_wc(&ggtt->iomap,
+					ggtt->gmadr.start,
+					ggtt->mappable_end)) {
+			ggtt->vm.cleanup(&ggtt->vm);
+			return -EIO;
+		}
+
+		ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start,
+					      ggtt->mappable_end);
+	}
+
+	i915_ggtt_init_fences(ggtt);
+
+	return 0;
+}
+
+/**
+ * i915_ggtt_init_hw - Initialize GGTT hardware
+ * @i915: i915 device
+ */
+int i915_ggtt_init_hw(struct drm_i915_private *i915)
+{
+	int ret;
+
+	stash_init(&i915->mm.wc_stash);
+
+	/*
+	 * Note that we use page colouring to enforce a guard page at the
+	 * end of the address space. This is required as the CS may prefetch
+	 * beyond the end of the batch buffer, across the page boundary,
+	 * and beyond the end of the GTT if we do not provide a guard.
+	 */
+	ret = ggtt_init_hw(&i915->ggtt);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/*
+ * Certain Gen5 chipsets require require idling the GPU before
+ * unmapping anything from the GTT when VT-d is enabled.
+ */
+static bool needs_idle_maps(struct drm_i915_private *i915)
+{
+	/*
+	 * Query intel_iommu to see if we need the workaround. Presumably that
+	 * was loaded first.
+	 */
+	return IS_GEN(i915, 5) && IS_MOBILE(i915) && intel_vtd_active();
+}
+
+static void ggtt_suspend_mappings(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+
+	/*
+	 * Don't bother messing with faults pre GEN6 as we have little
+	 * documentation supporting that it's a good idea.
+	 */
+	if (INTEL_GEN(i915) < 6)
+		return;
+
+	intel_gt_check_and_clear_faults(ggtt->vm.gt);
+
+	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
+
+	ggtt->invalidate(ggtt);
+}
+
+void i915_gem_suspend_gtt_mappings(struct drm_i915_private *i915)
+{
+	ggtt_suspend_mappings(&i915->ggtt);
+}
+
+void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
+
+	spin_lock_irq(&uncore->lock);
+	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+	intel_uncore_read_fw(uncore, GFX_FLSH_CNTL_GEN6);
+	spin_unlock_irq(&uncore->lock);
+}
+
+static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
+
+	/*
+	 * Note that as an uncached mmio write, this will flush the
+	 * WCB of the writes into the GGTT before it triggers the invalidate.
+	 */
+	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+}
+
+static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+
+	gen8_ggtt_invalidate(ggtt);
+
+	if (INTEL_GEN(i915) >= 12)
+		intel_uncore_write_fw(uncore, GEN12_GUC_TLB_INV_CR,
+				      GEN12_GUC_TLB_INV_CR_INVALIDATE);
+	else
+		intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+}
+
+static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+	intel_gtt_chipset_flush();
+}
+
+static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
+{
+	writeq(pte, addr);
+}
+
+static void gen8_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  u64 offset,
+				  enum i915_cache_level level,
+				  u32 unused)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	gen8_pte_t __iomem *pte =
+		(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
+
+	gen8_set_pte(pte, gen8_pte_encode(addr, level, 0));
+
+	ggtt->invalidate(ggtt);
+}
+
+static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
+				     struct i915_vma *vma,
+				     enum i915_cache_level level,
+				     u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	struct sgt_iter sgt_iter;
+	gen8_pte_t __iomem *gtt_entries;
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
+	dma_addr_t addr;
+
+	/*
+	 * Note that we ignore PTE_READ_ONLY here. The caller must be careful
+	 * not to allow the user to override access to a read only page.
+	 */
+
+	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
+	gtt_entries += vma->node.start / I915_GTT_PAGE_SIZE;
+	for_each_sgt_daddr(addr, sgt_iter, vma->pages)
+		gen8_set_pte(gtt_entries++, pte_encode | addr);
+
+	/*
+	 * We want to flush the TLBs only after we're certain all the PTE
+	 * updates have finished.
+	 */
+	ggtt->invalidate(ggtt);
+}
+
+static void gen6_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  u64 offset,
+				  enum i915_cache_level level,
+				  u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	gen6_pte_t __iomem *pte =
+		(gen6_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
+
+	iowrite32(vm->pte_encode(addr, level, flags), pte);
+
+	ggtt->invalidate(ggtt);
+}
+
+/*
+ * Binds an object into the global gtt with the specified cache level.
+ * The object will be accessible to the GPU via commands whose operands
+ * reference offsets within the global GTT as well as accessible by the GPU
+ * through the GMADR mapped BAR (i915->mm.gtt->gtt).
+ */
+static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
+				     struct i915_vma *vma,
+				     enum i915_cache_level level,
+				     u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	gen6_pte_t __iomem *entries = (gen6_pte_t __iomem *)ggtt->gsm;
+	unsigned int i = vma->node.start / I915_GTT_PAGE_SIZE;
+	struct sgt_iter iter;
+	dma_addr_t addr;
+
+	for_each_sgt_daddr(addr, iter, vma->pages)
+		iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]);
+
+	/*
+	 * We want to flush the TLBs only after we're certain all the PTE
+	 * updates have finished.
+	 */
+	ggtt->invalidate(ggtt);
+}
+
+static void nop_clear_range(struct i915_address_space *vm,
+			    u64 start, u64 length)
+{
+}
+
+static void gen8_ggtt_clear_range(struct i915_address_space *vm,
+				  u64 start, u64 length)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+	const gen8_pte_t scratch_pte = vm->scratch[0].encode;
+	gen8_pte_t __iomem *gtt_base =
+		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
+	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
+	int i;
+
+	if (WARN(num_entries > max_entries,
+		 "First entry = %d; Num entries = %d (max=%d)\n",
+		 first_entry, num_entries, max_entries))
+		num_entries = max_entries;
+
+	for (i = 0; i < num_entries; i++)
+		gen8_set_pte(&gtt_base[i], scratch_pte);
+}
+
+static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
+{
+	/*
+	 * Make sure the internal GAM fifo has been cleared of all GTT
+	 * writes before exiting stop_machine(). This guarantees that
+	 * any aperture accesses waiting to start in another process
+	 * cannot back up behind the GTT writes causing a hang.
+	 * The register can be any arbitrary GAM register.
+	 */
+	intel_uncore_posting_read_fw(vm->gt->uncore, GFX_FLSH_CNTL_GEN6);
+}
+
+struct insert_page {
+	struct i915_address_space *vm;
+	dma_addr_t addr;
+	u64 offset;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
+{
+	struct insert_page *arg = _arg;
+
+	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
+					  dma_addr_t addr,
+					  u64 offset,
+					  enum i915_cache_level level,
+					  u32 unused)
+{
+	struct insert_page arg = { vm, addr, offset, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
+}
+
+struct insert_entries {
+	struct i915_address_space *vm;
+	struct i915_vma *vma;
+	enum i915_cache_level level;
+	u32 flags;
+};
+
+static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
+{
+	struct insert_entries *arg = _arg;
+
+	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+					     struct i915_vma *vma,
+					     enum i915_cache_level level,
+					     u32 flags)
+{
+	struct insert_entries arg = { vm, vma, level, flags };
+
+	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
+}
+
+struct clear_range {
+	struct i915_address_space *vm;
+	u64 start;
+	u64 length;
+};
+
+static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
+{
+	struct clear_range *arg = _arg;
+
+	gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
+					  u64 start,
+					  u64 length)
+{
+	struct clear_range arg = { vm, start, length };
+
+	stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
+}
+
+static void gen6_ggtt_clear_range(struct i915_address_space *vm,
+				  u64 start, u64 length)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+	gen6_pte_t scratch_pte, __iomem *gtt_base =
+		(gen6_pte_t __iomem *)ggtt->gsm + first_entry;
+	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
+	int i;
+
+	if (WARN(num_entries > max_entries,
+		 "First entry = %d; Num entries = %d (max=%d)\n",
+		 first_entry, num_entries, max_entries))
+		num_entries = max_entries;
+
+	scratch_pte = vm->scratch[0].encode;
+	for (i = 0; i < num_entries; i++)
+		iowrite32(scratch_pte, &gtt_base[i]);
+}
+
+static void i915_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  u64 offset,
+				  enum i915_cache_level cache_level,
+				  u32 unused)
+{
+	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+
+	intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
+}
+
+static void i915_ggtt_insert_entries(struct i915_address_space *vm,
+				     struct i915_vma *vma,
+				     enum i915_cache_level cache_level,
+				     u32 unused)
+{
+	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+
+	intel_gtt_insert_sg_entries(vma->pages, vma->node.start >> PAGE_SHIFT,
+				    flags);
+}
+
+static void i915_ggtt_clear_range(struct i915_address_space *vm,
+				  u64 start, u64 length)
+{
+	intel_gtt_clear_range(start >> PAGE_SHIFT, length >> PAGE_SHIFT);
+}
+
+static int ggtt_bind_vma(struct i915_vma *vma,
+			 enum i915_cache_level cache_level,
+			 u32 flags)
+{
+	struct drm_i915_gem_object *obj = vma->obj;
+	u32 pte_flags;
+
+	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
+	pte_flags = 0;
+	if (i915_gem_object_is_readonly(obj))
+		pte_flags |= PTE_READ_ONLY;
+
+	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
+
+	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+
+	/*
+	 * Without aliasing PPGTT there's no difference between
+	 * GLOBAL/LOCAL_BIND, it's all the same ptes. Hence unconditionally
+	 * upgrade to both bound if we bind either to avoid double-binding.
+	 */
+	atomic_or(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND, &vma->flags);
+
+	return 0;
+}
+
+static void ggtt_unbind_vma(struct i915_vma *vma)
+{
+	vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
+}
+
+static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
+{
+	u64 size;
+	int ret;
+
+	if (!USES_GUC(ggtt->vm.i915))
+		return 0;
+
+	GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP);
+	size = ggtt->vm.total - GUC_GGTT_TOP;
+
+	ret = i915_gem_gtt_reserve(&ggtt->vm, &ggtt->uc_fw, size,
+				   GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE,
+				   PIN_NOEVICT);
+	if (ret)
+		DRM_DEBUG_DRIVER("Failed to reserve top of GGTT for GuC\n");
+
+	return ret;
+}
+
+static void ggtt_release_guc_top(struct i915_ggtt *ggtt)
+{
+	if (drm_mm_node_allocated(&ggtt->uc_fw))
+		drm_mm_remove_node(&ggtt->uc_fw);
+}
+
+static void cleanup_init_ggtt(struct i915_ggtt *ggtt)
+{
+	ggtt_release_guc_top(ggtt);
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		drm_mm_remove_node(&ggtt->error_capture);
+	mutex_destroy(&ggtt->error_mutex);
+}
+
+static int init_ggtt(struct i915_ggtt *ggtt)
+{
+	/*
+	 * Let GEM Manage all of the aperture.
+	 *
+	 * However, leave one page at the end still bound to the scratch page.
+	 * There are a number of places where the hardware apparently prefetches
+	 * past the end of the object, and we've seen multiple hangs with the
+	 * GPU head pointer stuck in a batchbuffer bound at the last page of the
+	 * aperture.  One page should be enough to keep any prefetching inside
+	 * of the aperture.
+	 */
+	unsigned long hole_start, hole_end;
+	struct drm_mm_node *entry;
+	int ret;
+
+	/*
+	 * GuC requires all resources that we're sharing with it to be placed in
+	 * non-WOPCM memory. If GuC is not present or not in use we still need a
+	 * small bias as ring wraparound at offset 0 sometimes hangs. No idea
+	 * why.
+	 */
+	ggtt->pin_bias = max_t(u32, I915_GTT_PAGE_SIZE,
+			       intel_wopcm_guc_size(&ggtt->vm.i915->wopcm));
+
+	ret = intel_vgt_balloon(ggtt);
+	if (ret)
+		return ret;
+
+	mutex_init(&ggtt->error_mutex);
+	if (ggtt->mappable_end) {
+		/* Reserve a mappable slot for our lockless error capture */
+		ret = drm_mm_insert_node_in_range(&ggtt->vm.mm,
+						  &ggtt->error_capture,
+						  PAGE_SIZE, 0,
+						  I915_COLOR_UNEVICTABLE,
+						  0, ggtt->mappable_end,
+						  DRM_MM_INSERT_LOW);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * The upper portion of the GuC address space has a sizeable hole
+	 * (several MB) that is inaccessible by GuC. Reserve this range within
+	 * GGTT as it can comfortably hold GuC/HuC firmware images.
+	 */
+	ret = ggtt_reserve_guc_top(ggtt);
+	if (ret)
+		goto err;
+
+	/* Clear any non-preallocated blocks */
+	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
+		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
+			      hole_start, hole_end);
+		ggtt->vm.clear_range(&ggtt->vm, hole_start,
+				     hole_end - hole_start);
+	}
+
+	/* And finally clear the reserved guard page */
+	ggtt->vm.clear_range(&ggtt->vm, ggtt->vm.total - PAGE_SIZE, PAGE_SIZE);
+
+	return 0;
+
+err:
+	cleanup_init_ggtt(ggtt);
+	return ret;
+}
+
+static int aliasing_gtt_bind_vma(struct i915_vma *vma,
+				 enum i915_cache_level cache_level,
+				 u32 flags)
+{
+	u32 pte_flags;
+	int ret;
+
+	/* Currently applicable only to VLV */
+	pte_flags = 0;
+	if (i915_gem_object_is_readonly(vma->obj))
+		pte_flags |= PTE_READ_ONLY;
+
+	if (flags & I915_VMA_LOCAL_BIND) {
+		struct i915_ppgtt *alias = i915_vm_to_ggtt(vma->vm)->alias;
+
+		if (flags & I915_VMA_ALLOC) {
+			ret = alias->vm.allocate_va_range(&alias->vm,
+							  vma->node.start,
+							  vma->size);
+			if (ret)
+				return ret;
+
+			set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
+		}
+
+		GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT,
+				     __i915_vma_flags(vma)));
+		alias->vm.insert_entries(&alias->vm, vma,
+					 cache_level, pte_flags);
+	}
+
+	if (flags & I915_VMA_GLOBAL_BIND)
+		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
+
+	return 0;
+}
+
+static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
+{
+	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) {
+		struct i915_address_space *vm = vma->vm;
+
+		vm->clear_range(vm, vma->node.start, vma->size);
+	}
+
+	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) {
+		struct i915_address_space *vm =
+			&i915_vm_to_ggtt(vma->vm)->alias->vm;
+
+		vm->clear_range(vm, vma->node.start, vma->size);
+	}
+}
+
+static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
+{
+	struct i915_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = i915_ppgtt_create(ggtt->vm.gt);
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
+
+	if (GEM_WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
+		err = -ENODEV;
+		goto err_ppgtt;
+	}
+
+	/*
+	 * Note we only pre-allocate as far as the end of the global
+	 * GTT. On 48b / 4-level page-tables, the difference is very,
+	 * very significant! We have to preallocate as GVT/vgpu does
+	 * not like the page directory disappearing.
+	 */
+	err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, ggtt->vm.total);
+	if (err)
+		goto err_ppgtt;
+
+	ggtt->alias = ppgtt;
+	ggtt->vm.bind_async_flags |= ppgtt->vm.bind_async_flags;
+
+	GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != ggtt_bind_vma);
+	ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
+
+	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
+	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
+
+	return 0;
+
+err_ppgtt:
+	i915_vm_put(&ppgtt->vm);
+	return err;
+}
+
+static void fini_aliasing_ppgtt(struct i915_ggtt *ggtt)
+{
+	struct i915_ppgtt *ppgtt;
+
+	ppgtt = fetch_and_zero(&ggtt->alias);
+	if (!ppgtt)
+		return;
+
+	i915_vm_put(&ppgtt->vm);
+
+	ggtt->vm.vma_ops.bind_vma   = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
+}
+
+int i915_init_ggtt(struct drm_i915_private *i915)
+{
+	int ret;
+
+	ret = init_ggtt(&i915->ggtt);
+	if (ret)
+		return ret;
+
+	if (INTEL_PPGTT(i915) == INTEL_PPGTT_ALIASING) {
+		ret = init_aliasing_ppgtt(&i915->ggtt);
+		if (ret)
+			cleanup_init_ggtt(&i915->ggtt);
+	}
+
+	return 0;
+}
+
+static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
+{
+	struct i915_vma *vma, *vn;
+
+	atomic_set(&ggtt->vm.open, 0);
+
+	rcu_barrier(); /* flush the RCU'ed__i915_vm_release */
+	flush_workqueue(ggtt->vm.i915->wq);
+
+	mutex_lock(&ggtt->vm.mutex);
+
+	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link)
+		WARN_ON(__i915_vma_unbind(vma));
+
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		drm_mm_remove_node(&ggtt->error_capture);
+	mutex_destroy(&ggtt->error_mutex);
+
+	ggtt_release_guc_top(ggtt);
+	intel_vgt_deballoon(ggtt);
+
+	ggtt->vm.cleanup(&ggtt->vm);
+
+	mutex_unlock(&ggtt->vm.mutex);
+	i915_address_space_fini(&ggtt->vm);
+
+	arch_phys_wc_del(ggtt->mtrr);
+
+	if (ggtt->iomap.size)
+		io_mapping_fini(&ggtt->iomap);
+}
+
+/**
+ * i915_ggtt_driver_release - Clean up GGTT hardware initialization
+ * @i915: i915 device
+ */
+void i915_ggtt_driver_release(struct drm_i915_private *i915)
+{
+	struct pagevec *pvec;
+
+	fini_aliasing_ppgtt(&i915->ggtt);
+
+	ggtt_cleanup_hw(&i915->ggtt);
+
+	pvec = &i915->mm.wc_stash.pvec;
+	if (pvec->nr) {
+		set_pages_array_wb(pvec->pages, pvec->nr);
+		__pagevec_release(pvec);
+	}
+}
+
+static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
+{
+	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
+	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
+	return snb_gmch_ctl << 20;
+}
+
+static unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
+{
+	bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
+	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
+	if (bdw_gmch_ctl)
+		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
+
+#ifdef CONFIG_X86_32
+	/* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * I915_GTT_PAGE_SIZE */
+	if (bdw_gmch_ctl > 4)
+		bdw_gmch_ctl = 4;
+#endif
+
+	return bdw_gmch_ctl << 20;
+}
+
+static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
+{
+	gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
+	gmch_ctrl &= SNB_GMCH_GGMS_MASK;
+
+	if (gmch_ctrl)
+		return 1 << (20 + gmch_ctrl);
+
+	return 0;
+}
+
+static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct pci_dev *pdev = i915->drm.pdev;
+	phys_addr_t phys_addr;
+	int ret;
+
+	/* For Modern GENs the PTEs and register space are split in the BAR */
+	phys_addr = pci_resource_start(pdev, 0) + pci_resource_len(pdev, 0) / 2;
+
+	/*
+	 * On BXT+/CNL+ writes larger than 64 bit to the GTT pagetable range
+	 * will be dropped. For WC mappings in general we have 64 byte burst
+	 * writes when the WC buffer is flushed, so we can't use it, but have to
+	 * resort to an uncached mapping. The WC issue is easily caught by the
+	 * readback check when writing GTT PTE entries.
+	 */
+	if (IS_GEN9_LP(i915) || INTEL_GEN(i915) >= 10)
+		ggtt->gsm = ioremap(phys_addr, size);
+	else
+		ggtt->gsm = ioremap_wc(phys_addr, size);
+	if (!ggtt->gsm) {
+		DRM_ERROR("Failed to map the ggtt page table\n");
+		return -ENOMEM;
+	}
+
+	ret = setup_scratch_page(&ggtt->vm, GFP_DMA32);
+	if (ret) {
+		DRM_ERROR("Scratch setup failed\n");
+		/* iounmap will also get called at remove, but meh */
+		iounmap(ggtt->gsm);
+		return ret;
+	}
+
+	ggtt->vm.scratch[0].encode =
+		ggtt->vm.pte_encode(px_dma(&ggtt->vm.scratch[0]),
+				    I915_CACHE_NONE, 0);
+
+	return 0;
+}
+
+int ggtt_set_pages(struct i915_vma *vma)
+{
+	int ret;
+
+	GEM_BUG_ON(vma->pages);
+
+	ret = i915_get_ggtt_vma_pages(vma);
+	if (ret)
+		return ret;
+
+	vma->page_sizes = vma->obj->mm.page_sizes;
+
+	return 0;
+}
+
+static void gen6_gmch_remove(struct i915_address_space *vm)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+
+	iounmap(ggtt->gsm);
+	cleanup_scratch_page(vm);
+}
+
+static struct resource pci_resource(struct pci_dev *pdev, int bar)
+{
+	return (struct resource)DEFINE_RES_MEM(pci_resource_start(pdev, bar),
+					       pci_resource_len(pdev, bar));
+}
+
+static int gen8_gmch_probe(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct pci_dev *pdev = i915->drm.pdev;
+	unsigned int size;
+	u16 snb_gmch_ctl;
+	int err;
+
+	/* TODO: We're not aware of mappable constraints on gen8 yet */
+	if (!IS_DGFX(i915)) {
+		ggtt->gmadr = pci_resource(pdev, 2);
+		ggtt->mappable_end = resource_size(&ggtt->gmadr);
+	}
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(39));
+	if (!err)
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39));
+	if (err)
+		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
+
+	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
+	if (IS_CHERRYVIEW(i915))
+		size = chv_get_total_gtt_size(snb_gmch_ctl);
+	else
+		size = gen8_get_total_gtt_size(snb_gmch_ctl);
+
+	ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
+	ggtt->vm.cleanup = gen6_gmch_remove;
+	ggtt->vm.insert_page = gen8_ggtt_insert_page;
+	ggtt->vm.clear_range = nop_clear_range;
+	if (intel_scanout_needs_vtd_wa(i915))
+		ggtt->vm.clear_range = gen8_ggtt_clear_range;
+
+	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
+
+	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
+	if (intel_ggtt_update_needs_vtd_wa(i915) ||
+	    IS_CHERRYVIEW(i915) /* fails with concurrent use/update */) {
+		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
+		if (ggtt->vm.clear_range != nop_clear_range)
+			ggtt->vm.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+	}
+
+	ggtt->invalidate = gen8_ggtt_invalidate;
+
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
+	ggtt->vm.pte_encode = gen8_pte_encode;
+
+	setup_private_pat(ggtt->vm.gt->uncore);
+
+	return ggtt_probe_common(ggtt, size);
+}
+
+static u64 snb_pte_encode(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags)
+{
+	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	switch (level) {
+	case I915_CACHE_L3_LLC:
+	case I915_CACHE_LLC:
+		pte |= GEN6_PTE_CACHE_LLC;
+		break;
+	case I915_CACHE_NONE:
+		pte |= GEN6_PTE_UNCACHED;
+		break;
+	default:
+		MISSING_CASE(level);
+	}
+
+	return pte;
+}
+
+static u64 ivb_pte_encode(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags)
+{
+	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	switch (level) {
+	case I915_CACHE_L3_LLC:
+		pte |= GEN7_PTE_CACHE_L3_LLC;
+		break;
+	case I915_CACHE_LLC:
+		pte |= GEN6_PTE_CACHE_LLC;
+		break;
+	case I915_CACHE_NONE:
+		pte |= GEN6_PTE_UNCACHED;
+		break;
+	default:
+		MISSING_CASE(level);
+	}
+
+	return pte;
+}
+
+static u64 byt_pte_encode(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags)
+{
+	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	if (!(flags & PTE_READ_ONLY))
+		pte |= BYT_PTE_WRITEABLE;
+
+	if (level != I915_CACHE_NONE)
+		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
+
+	return pte;
+}
+
+static u64 hsw_pte_encode(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags)
+{
+	gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	if (level != I915_CACHE_NONE)
+		pte |= HSW_WB_LLC_AGE3;
+
+	return pte;
+}
+
+static u64 iris_pte_encode(dma_addr_t addr,
+			   enum i915_cache_level level,
+			   u32 flags)
+{
+	gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	switch (level) {
+	case I915_CACHE_NONE:
+		break;
+	case I915_CACHE_WT:
+		pte |= HSW_WT_ELLC_LLC_AGE3;
+		break;
+	default:
+		pte |= HSW_WB_ELLC_LLC_AGE3;
+		break;
+	}
+
+	return pte;
+}
+
+static int gen6_gmch_probe(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct pci_dev *pdev = i915->drm.pdev;
+	unsigned int size;
+	u16 snb_gmch_ctl;
+	int err;
+
+	ggtt->gmadr = pci_resource(pdev, 2);
+	ggtt->mappable_end = resource_size(&ggtt->gmadr);
+
+	/*
+	 * 64/512MB is the current min/max we actually know of, but this is
+	 * just a coarse sanity check.
+	 */
+	if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) {
+		DRM_ERROR("Unknown GMADR size (%pa)\n", &ggtt->mappable_end);
+		return -ENXIO;
+	}
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(40));
+	if (!err)
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40));
+	if (err)
+		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
+	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
+
+	size = gen6_get_total_gtt_size(snb_gmch_ctl);
+	ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
+
+	ggtt->vm.clear_range = nop_clear_range;
+	if (!HAS_FULL_PPGTT(i915) || intel_scanout_needs_vtd_wa(i915))
+		ggtt->vm.clear_range = gen6_ggtt_clear_range;
+	ggtt->vm.insert_page = gen6_ggtt_insert_page;
+	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
+	ggtt->vm.cleanup = gen6_gmch_remove;
+
+	ggtt->invalidate = gen6_ggtt_invalidate;
+
+	if (HAS_EDRAM(i915))
+		ggtt->vm.pte_encode = iris_pte_encode;
+	else if (IS_HASWELL(i915))
+		ggtt->vm.pte_encode = hsw_pte_encode;
+	else if (IS_VALLEYVIEW(i915))
+		ggtt->vm.pte_encode = byt_pte_encode;
+	else if (INTEL_GEN(i915) >= 7)
+		ggtt->vm.pte_encode = ivb_pte_encode;
+	else
+		ggtt->vm.pte_encode = snb_pte_encode;
+
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
+	return ggtt_probe_common(ggtt, size);
+}
+
+static void i915_gmch_remove(struct i915_address_space *vm)
+{
+	intel_gmch_remove();
+}
+
+static int i915_gmch_probe(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+	phys_addr_t gmadr_base;
+	int ret;
+
+	ret = intel_gmch_probe(i915->bridge_dev, i915->drm.pdev, NULL);
+	if (!ret) {
+		DRM_ERROR("failed to set up gmch\n");
+		return -EIO;
+	}
+
+	intel_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end);
+
+	ggtt->gmadr =
+		(struct resource)DEFINE_RES_MEM(gmadr_base, ggtt->mappable_end);
+
+	ggtt->do_idle_maps = needs_idle_maps(i915);
+	ggtt->vm.insert_page = i915_ggtt_insert_page;
+	ggtt->vm.insert_entries = i915_ggtt_insert_entries;
+	ggtt->vm.clear_range = i915_ggtt_clear_range;
+	ggtt->vm.cleanup = i915_gmch_remove;
+
+	ggtt->invalidate = gmch_ggtt_invalidate;
+
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
+	if (unlikely(ggtt->do_idle_maps))
+		dev_notice(i915->drm.dev,
+			   "Applying Ironlake quirks for intel_iommu\n");
+
+	return 0;
+}
+
+static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	int ret;
+
+	ggtt->vm.gt = gt;
+	ggtt->vm.i915 = i915;
+	ggtt->vm.dma = &i915->drm.pdev->dev;
+
+	if (INTEL_GEN(i915) <= 5)
+		ret = i915_gmch_probe(ggtt);
+	else if (INTEL_GEN(i915) < 8)
+		ret = gen6_gmch_probe(ggtt);
+	else
+		ret = gen8_gmch_probe(ggtt);
+	if (ret)
+		return ret;
+
+	if ((ggtt->vm.total - 1) >> 32) {
+		DRM_ERROR("We never expected a Global GTT with more than 32bits"
+			  " of address space! Found %lldM!\n",
+			  ggtt->vm.total >> 20);
+		ggtt->vm.total = 1ULL << 32;
+		ggtt->mappable_end =
+			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
+	}
+
+	if (ggtt->mappable_end > ggtt->vm.total) {
+		DRM_ERROR("mappable aperture extends past end of GGTT,"
+			  " aperture=%pa, total=%llx\n",
+			  &ggtt->mappable_end, ggtt->vm.total);
+		ggtt->mappable_end = ggtt->vm.total;
+	}
+
+	/* GMADR is the PCI mmio aperture into the global GTT. */
+	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20);
+	DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20);
+	DRM_DEBUG_DRIVER("DSM size = %lluM\n",
+			 (u64)resource_size(&intel_graphics_stolen_res) >> 20);
+
+	return 0;
+}
+
+/**
+ * i915_ggtt_probe_hw - Probe GGTT hardware location
+ * @i915: i915 device
+ */
+int i915_ggtt_probe_hw(struct drm_i915_private *i915)
+{
+	int ret;
+
+	ret = ggtt_probe_hw(&i915->ggtt, &i915->gt);
+	if (ret)
+		return ret;
+
+	if (intel_vtd_active())
+		dev_info(i915->drm.dev, "VT-d active for gfx access\n");
+
+	return 0;
+}
+
+int i915_ggtt_enable_hw(struct drm_i915_private *i915)
+{
+	if (INTEL_GEN(i915) < 6 && !intel_enable_gtt())
+		return -EIO;
+
+	return 0;
+}
+
+void i915_ggtt_enable_guc(struct i915_ggtt *ggtt)
+{
+	GEM_BUG_ON(ggtt->invalidate != gen8_ggtt_invalidate);
+
+	ggtt->invalidate = guc_ggtt_invalidate;
+
+	ggtt->invalidate(ggtt);
+}
+
+void i915_ggtt_disable_guc(struct i915_ggtt *ggtt)
+{
+	/* XXX Temporary pardon for error unload */
+	if (ggtt->invalidate == gen8_ggtt_invalidate)
+		return;
+
+	/* We should only be called after i915_ggtt_enable_guc() */
+	GEM_BUG_ON(ggtt->invalidate != guc_ggtt_invalidate);
+
+	ggtt->invalidate = gen8_ggtt_invalidate;
+
+	ggtt->invalidate(ggtt);
+}
+
+static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
+{
+	struct i915_vma *vma;
+	bool flush = false;
+	int open;
+
+	intel_gt_check_and_clear_faults(ggtt->vm.gt);
+
+	mutex_lock(&ggtt->vm.mutex);
+
+	/* First fill our portion of the GTT with scratch pages */
+	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
+
+	/* Skip rewriting PTE on VMA unbind. */
+	open = atomic_xchg(&ggtt->vm.open, 0);
+
+	/* clflush objects bound into the GGTT and rebind them. */
+	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
+			continue;
+
+		clear_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
+		WARN_ON(i915_vma_bind(vma,
+				      obj ? obj->cache_level : 0,
+				      PIN_GLOBAL, NULL));
+		if (obj) { /* only used during resume => exclusive access */
+			flush |= fetch_and_zero(&obj->write_domain);
+			obj->read_domains |= I915_GEM_DOMAIN_GTT;
+		}
+	}
+
+	atomic_set(&ggtt->vm.open, open);
+	ggtt->invalidate(ggtt);
+
+	mutex_unlock(&ggtt->vm.mutex);
+
+	if (flush)
+		wbinvd_on_all_cpus();
+}
+
+void i915_gem_restore_gtt_mappings(struct drm_i915_private *i915)
+{
+	struct i915_ggtt *ggtt = &i915->ggtt;
+
+	ggtt_restore_mappings(ggtt);
+
+	if (INTEL_GEN(i915) >= 8)
+		setup_private_pat(ggtt->vm.gt->uncore);
+}
+
+static struct scatterlist *
+rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset,
+	     unsigned int width, unsigned int height,
+	     unsigned int stride,
+	     struct sg_table *st, struct scatterlist *sg)
+{
+	unsigned int column, row;
+	unsigned int src_idx;
+
+	for (column = 0; column < width; column++) {
+		src_idx = stride * (height - 1) + column + offset;
+		for (row = 0; row < height; row++) {
+			st->nents++;
+			/*
+			 * We don't need the pages, but need to initialize
+			 * the entries so the sg list can be happily traversed.
+			 * The only thing we need are DMA addresses.
+			 */
+			sg_set_page(sg, NULL, I915_GTT_PAGE_SIZE, 0);
+			sg_dma_address(sg) =
+				i915_gem_object_get_dma_address(obj, src_idx);
+			sg_dma_len(sg) = I915_GTT_PAGE_SIZE;
+			sg = sg_next(sg);
+			src_idx -= stride;
+		}
+	}
+
+	return sg;
+}
+
+static noinline struct sg_table *
+intel_rotate_pages(struct intel_rotation_info *rot_info,
+		   struct drm_i915_gem_object *obj)
+{
+	unsigned int size = intel_rotation_info_size(rot_info);
+	struct sg_table *st;
+	struct scatterlist *sg;
+	int ret = -ENOMEM;
+	int i;
+
+	/* Allocate target SG list. */
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto err_st_alloc;
+
+	ret = sg_alloc_table(st, size, GFP_KERNEL);
+	if (ret)
+		goto err_sg_alloc;
+
+	st->nents = 0;
+	sg = st->sgl;
+
+	for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) {
+		sg = rotate_pages(obj, rot_info->plane[i].offset,
+				  rot_info->plane[i].width, rot_info->plane[i].height,
+				  rot_info->plane[i].stride, st, sg);
+	}
+
+	return st;
+
+err_sg_alloc:
+	kfree(st);
+err_st_alloc:
+
+	DRM_DEBUG_DRIVER("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
+			 obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
+
+	return ERR_PTR(ret);
+}
+
+static struct scatterlist *
+remap_pages(struct drm_i915_gem_object *obj, unsigned int offset,
+	    unsigned int width, unsigned int height,
+	    unsigned int stride,
+	    struct sg_table *st, struct scatterlist *sg)
+{
+	unsigned int row;
+
+	for (row = 0; row < height; row++) {
+		unsigned int left = width * I915_GTT_PAGE_SIZE;
+
+		while (left) {
+			dma_addr_t addr;
+			unsigned int length;
+
+			/*
+			 * We don't need the pages, but need to initialize
+			 * the entries so the sg list can be happily traversed.
+			 * The only thing we need are DMA addresses.
+			 */
+
+			addr = i915_gem_object_get_dma_address_len(obj, offset, &length);
+
+			length = min(left, length);
+
+			st->nents++;
+
+			sg_set_page(sg, NULL, length, 0);
+			sg_dma_address(sg) = addr;
+			sg_dma_len(sg) = length;
+			sg = sg_next(sg);
+
+			offset += length / I915_GTT_PAGE_SIZE;
+			left -= length;
+		}
+
+		offset += stride - width;
+	}
+
+	return sg;
+}
+
+static noinline struct sg_table *
+intel_remap_pages(struct intel_remapped_info *rem_info,
+		  struct drm_i915_gem_object *obj)
+{
+	unsigned int size = intel_remapped_info_size(rem_info);
+	struct sg_table *st;
+	struct scatterlist *sg;
+	int ret = -ENOMEM;
+	int i;
+
+	/* Allocate target SG list. */
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto err_st_alloc;
+
+	ret = sg_alloc_table(st, size, GFP_KERNEL);
+	if (ret)
+		goto err_sg_alloc;
+
+	st->nents = 0;
+	sg = st->sgl;
+
+	for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) {
+		sg = remap_pages(obj, rem_info->plane[i].offset,
+				 rem_info->plane[i].width, rem_info->plane[i].height,
+				 rem_info->plane[i].stride, st, sg);
+	}
+
+	i915_sg_trim(st);
+
+	return st;
+
+err_sg_alloc:
+	kfree(st);
+err_st_alloc:
+
+	DRM_DEBUG_DRIVER("Failed to create remapped mapping for object size %zu! (%ux%u tiles, %u pages)\n",
+			 obj->base.size, rem_info->plane[0].width, rem_info->plane[0].height, size);
+
+	return ERR_PTR(ret);
+}
+
+static noinline struct sg_table *
+intel_partial_pages(const struct i915_ggtt_view *view,
+		    struct drm_i915_gem_object *obj)
+{
+	struct sg_table *st;
+	struct scatterlist *sg, *iter;
+	unsigned int count = view->partial.size;
+	unsigned int offset;
+	int ret = -ENOMEM;
+
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto err_st_alloc;
+
+	ret = sg_alloc_table(st, count, GFP_KERNEL);
+	if (ret)
+		goto err_sg_alloc;
+
+	iter = i915_gem_object_get_sg(obj, view->partial.offset, &offset);
+	GEM_BUG_ON(!iter);
+
+	sg = st->sgl;
+	st->nents = 0;
+	do {
+		unsigned int len;
+
+		len = min(iter->length - (offset << PAGE_SHIFT),
+			  count << PAGE_SHIFT);
+		sg_set_page(sg, NULL, len, 0);
+		sg_dma_address(sg) =
+			sg_dma_address(iter) + (offset << PAGE_SHIFT);
+		sg_dma_len(sg) = len;
+
+		st->nents++;
+		count -= len >> PAGE_SHIFT;
+		if (count == 0) {
+			sg_mark_end(sg);
+			i915_sg_trim(st); /* Drop any unused tail entries. */
+
+			return st;
+		}
+
+		sg = __sg_next(sg);
+		iter = __sg_next(iter);
+		offset = 0;
+	} while (1);
+
+err_sg_alloc:
+	kfree(st);
+err_st_alloc:
+	return ERR_PTR(ret);
+}
+
+static int
+i915_get_ggtt_vma_pages(struct i915_vma *vma)
+{
+	int ret;
+
+	/*
+	 * The vma->pages are only valid within the lifespan of the borrowed
+	 * obj->mm.pages. When the obj->mm.pages sg_table is regenerated, so
+	 * must be the vma->pages. A simple rule is that vma->pages must only
+	 * be accessed when the obj->mm.pages are pinned.
+	 */
+	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(vma->obj));
+
+	switch (vma->ggtt_view.type) {
+	default:
+		GEM_BUG_ON(vma->ggtt_view.type);
+		/* fall through */
+	case I915_GGTT_VIEW_NORMAL:
+		vma->pages = vma->obj->mm.pages;
+		return 0;
+
+	case I915_GGTT_VIEW_ROTATED:
+		vma->pages =
+			intel_rotate_pages(&vma->ggtt_view.rotated, vma->obj);
+		break;
+
+	case I915_GGTT_VIEW_REMAPPED:
+		vma->pages =
+			intel_remap_pages(&vma->ggtt_view.remapped, vma->obj);
+		break;
+
+	case I915_GGTT_VIEW_PARTIAL:
+		vma->pages = intel_partial_pages(&vma->ggtt_view, vma->obj);
+		break;
+	}
+
+	ret = 0;
+	if (IS_ERR(vma->pages)) {
+		ret = PTR_ERR(vma->pages);
+		vma->pages = NULL;
+		DRM_ERROR("Failed to get pages for VMA view type %u (%d)!\n",
+			  vma->ggtt_view.type, ret);
+	}
+	return ret;
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 4294f146f13c..51b8718513bc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -7,6 +7,8 @@
 #ifndef _INTEL_GPU_COMMANDS_H_
 #define _INTEL_GPU_COMMANDS_H_
 
+#include <linux/bitops.h>
+
 /*
  * Target address alignments required for GPU access e.g.
  * MI_STORE_DWORD_IMM.
@@ -319,4 +321,31 @@
 #define COLOR_BLT     ((0x2<<29)|(0x40<<22))
 #define SRC_COPY_BLT  ((0x2<<29)|(0x43<<22))
 
+/*
+ * Used to convert any address to canonical form.
+ * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS,
+ * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the
+ * addresses to be in a canonical form:
+ * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct
+ * canonical form [63:48] == [47]."
+ */
+#define GEN8_HIGH_ADDRESS_BIT 47
+static inline u64 gen8_canonical_addr(u64 address)
+{
+	return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT);
+}
+
+static inline u64 gen8_noncanonical_addr(u64 address)
+{
+	return address & GENMASK_ULL(GEN8_HIGH_ADDRESS_BIT, 0);
+}
+
+static inline u32 *__gen6_emit_bb_start(u32 *cs, u32 addr, unsigned int flags)
+{
+	*cs++ = MI_BATCH_BUFFER_START | flags;
+	*cs++ = addr;
+
+	return cs;
+}
+
 #endif /* _INTEL_GPU_COMMANDS_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 4c26daf7ee46..da2b6e2ae692 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -3,12 +3,15 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include "debugfs_gt.h"
 #include "i915_drv.h"
+#include "intel_context.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 #include "intel_mocs.h"
 #include "intel_rc6.h"
+#include "intel_renderstate.h"
 #include "intel_rps.h"
 #include "intel_uncore.h"
 #include "intel_pm.h"
@@ -25,6 +28,7 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
+	intel_gt_init_timelines(gt);
 	intel_gt_pm_init_early(gt);
 
 	intel_rps_init_early(&gt->rps);
@@ -34,8 +38,6 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt)
 {
 	gt->ggtt = ggtt;
-
-	intel_gt_sanitize(gt, false);
 }
 
 static void init_unused_ring(struct intel_gt *gt, u32 base)
@@ -73,11 +75,6 @@ int intel_gt_init_hw(struct intel_gt *gt)
 	struct intel_uncore *uncore = gt->uncore;
 	int ret;
 
-	BUG_ON(!i915->kernel_context);
-	ret = intel_gt_terminally_wedged(gt);
-	if (ret)
-		return ret;
-
 	gt->last_init_time = ktime_get();
 
 	/* Double layer security blanket, see i915_gem_init() */
@@ -303,7 +300,7 @@ void intel_gt_flush_ggtt_writes(struct intel_gt *gt)
 
 	intel_gt_chipset_flush(gt);
 
-	with_intel_runtime_pm(uncore->rpm, wakeref) {
+	with_intel_runtime_pm_if_in_use(uncore->rpm, wakeref) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&uncore->lock, flags);
@@ -323,6 +320,8 @@ void intel_gt_chipset_flush(struct intel_gt *gt)
 void intel_gt_driver_register(struct intel_gt *gt)
 {
 	intel_rps_driver_register(&gt->rps);
+
+	debugfs_gt_register(gt);
 }
 
 static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
@@ -364,22 +363,272 @@ static void intel_gt_fini_scratch(struct intel_gt *gt)
 	i915_vma_unpin_and_release(&gt->scratch, 0);
 }
 
+static struct i915_address_space *kernel_vm(struct intel_gt *gt)
+{
+	if (INTEL_PPGTT(gt->i915) > INTEL_PPGTT_ALIASING)
+		return &i915_ppgtt_create(gt)->vm;
+	else
+		return i915_vm_get(&gt->ggtt->vm);
+}
+
+static int __intel_context_flush_retire(struct intel_context *ce)
+{
+	struct intel_timeline *tl;
+
+	tl = intel_context_timeline_lock(ce);
+	if (IS_ERR(tl))
+		return PTR_ERR(tl);
+
+	intel_context_timeline_unlock(tl);
+	return 0;
+}
+
+static int __engines_record_defaults(struct intel_gt *gt)
+{
+	struct i915_request *requests[I915_NUM_ENGINES] = {};
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/*
+	 * As we reset the gpu during very early sanitisation, the current
+	 * register state on the GPU should reflect its defaults values.
+	 * We load a context onto the hw (with restore-inhibit), then switch
+	 * over to a second context to save that default register state. We
+	 * can then prime every new context with that state so they all start
+	 * from the same default HW values.
+	 */
+
+	for_each_engine(engine, gt, id) {
+		struct intel_renderstate so;
+		struct intel_context *ce;
+		struct i915_request *rq;
+
+		/* We must be able to switch to something! */
+		GEM_BUG_ON(!engine->kernel_context);
+
+		err = intel_renderstate_init(&so, engine);
+		if (err)
+			goto out;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			goto out;
+		}
+
+		rq = intel_context_create_request(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			intel_context_put(ce);
+			goto out;
+		}
+
+		err = intel_engine_emit_ctx_wa(rq);
+		if (err)
+			goto err_rq;
+
+		err = intel_renderstate_emit(&so, rq);
+		if (err)
+			goto err_rq;
+
+err_rq:
+		requests[id] = i915_request_get(rq);
+		i915_request_add(rq);
+		intel_renderstate_fini(&so);
+		if (err)
+			goto out;
+	}
+
+	/* Flush the default context image to memory, and enable powersaving. */
+	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+		err = -EIO;
+		goto out;
+	}
+
+	for (id = 0; id < ARRAY_SIZE(requests); id++) {
+		struct i915_request *rq;
+		struct i915_vma *state;
+		void *vaddr;
+
+		rq = requests[id];
+		if (!rq)
+			continue;
+
+		GEM_BUG_ON(!test_bit(CONTEXT_ALLOC_BIT, &rq->context->flags));
+		state = rq->context->state;
+		if (!state)
+			continue;
+
+		/* Serialise with retirement on another CPU */
+		GEM_BUG_ON(!i915_request_completed(rq));
+		err = __intel_context_flush_retire(rq->context);
+		if (err)
+			goto out;
+
+		/* We want to be able to unbind the state from the GGTT */
+		GEM_BUG_ON(intel_context_is_pinned(rq->context));
+
+		/*
+		 * As we will hold a reference to the logical state, it will
+		 * not be torn down with the context, and importantly the
+		 * object will hold onto its vma (making it possible for a
+		 * stray GTT write to corrupt our defaults). Unmap the vma
+		 * from the GTT to prevent such accidents and reclaim the
+		 * space.
+		 */
+		err = i915_vma_unbind(state);
+		if (err)
+			goto out;
+
+		i915_gem_object_lock(state->obj);
+		err = i915_gem_object_set_to_cpu_domain(state->obj, false);
+		i915_gem_object_unlock(state->obj);
+		if (err)
+			goto out;
+
+		i915_gem_object_set_cache_coherency(state->obj, I915_CACHE_LLC);
+
+		/* Check we can acquire the image of the context state */
+		vaddr = i915_gem_object_pin_map(state->obj, I915_MAP_FORCE_WB);
+		if (IS_ERR(vaddr)) {
+			err = PTR_ERR(vaddr);
+			goto out;
+		}
+
+		rq->engine->default_state = i915_gem_object_get(state->obj);
+		i915_gem_object_unpin_map(state->obj);
+	}
+
+out:
+	/*
+	 * If we have to abandon now, we expect the engines to be idle
+	 * and ready to be torn-down. The quickest way we can accomplish
+	 * this is by declaring ourselves wedged.
+	 */
+	if (err)
+		intel_gt_set_wedged(gt);
+
+	for (id = 0; id < ARRAY_SIZE(requests); id++) {
+		struct intel_context *ce;
+		struct i915_request *rq;
+
+		rq = requests[id];
+		if (!rq)
+			continue;
+
+		ce = rq->context;
+		i915_request_put(rq);
+		intel_context_put(ce);
+	}
+	return err;
+}
+
+static int __engines_verify_workarounds(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		return 0;
+
+	for_each_engine(engine, gt, id) {
+		if (intel_engine_verify_workarounds(engine, "load"))
+			err = -EIO;
+	}
+
+	return err;
+}
+
+static void __intel_gt_disable(struct intel_gt *gt)
+{
+	intel_gt_set_wedged_on_init(gt);
+
+	intel_gt_suspend_prepare(gt);
+	intel_gt_suspend_late(gt);
+
+	GEM_BUG_ON(intel_gt_pm_is_awake(gt));
+}
+
 int intel_gt_init(struct intel_gt *gt)
 {
 	int err;
 
-	err = intel_gt_init_scratch(gt, IS_GEN(gt->i915, 2) ? SZ_256K : SZ_4K);
+	err = i915_inject_probe_error(gt->i915, -ENODEV);
 	if (err)
 		return err;
 
+	/*
+	 * This is just a security blanket to placate dragons.
+	 * On some systems, we very sporadically observe that the first TLBs
+	 * used by the CS may be stale, despite us poking the TLB reset. If
+	 * we hold the forcewake during initialisation these problems
+	 * just magically go away.
+	 */
+	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
+
+	err = intel_gt_init_scratch(gt, IS_GEN(gt->i915, 2) ? SZ_256K : SZ_4K);
+	if (err)
+		goto out_fw;
+
 	intel_gt_pm_init(gt);
 
-	return 0;
+	gt->vm = kernel_vm(gt);
+	if (!gt->vm) {
+		err = -ENOMEM;
+		goto err_pm;
+	}
+
+	err = intel_engines_init(gt);
+	if (err)
+		goto err_engines;
+
+	intel_uc_init(&gt->uc);
+
+	err = intel_gt_resume(gt);
+	if (err)
+		goto err_uc_init;
+
+	err = __engines_record_defaults(gt);
+	if (err)
+		goto err_gt;
+
+	err = __engines_verify_workarounds(gt);
+	if (err)
+		goto err_gt;
+
+	err = i915_inject_probe_error(gt->i915, -EIO);
+	if (err)
+		goto err_gt;
+
+	goto out_fw;
+err_gt:
+	__intel_gt_disable(gt);
+	intel_uc_fini_hw(&gt->uc);
+err_uc_init:
+	intel_uc_fini(&gt->uc);
+err_engines:
+	intel_engines_release(gt);
+	i915_vm_put(fetch_and_zero(&gt->vm));
+err_pm:
+	intel_gt_pm_fini(gt);
+	intel_gt_fini_scratch(gt);
+out_fw:
+	if (err)
+		intel_gt_set_wedged_on_init(gt);
+	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
+	return err;
 }
 
 void intel_gt_driver_remove(struct intel_gt *gt)
 {
-	GEM_BUG_ON(gt->awake);
+	__intel_gt_disable(gt);
+
+	intel_uc_fini_hw(&gt->uc);
+	intel_uc_fini(&gt->uc);
+
+	intel_engines_release(gt);
 }
 
 void intel_gt_driver_unregister(struct intel_gt *gt)
@@ -389,6 +638,12 @@ void intel_gt_driver_unregister(struct intel_gt *gt)
 
 void intel_gt_driver_release(struct intel_gt *gt)
 {
+	struct i915_address_space *vm;
+
+	vm = fetch_and_zero(&gt->vm);
+	if (vm) /* FIXME being called twice on error paths :( */
+		i915_vm_put(vm);
+
 	intel_gt_pm_fini(gt);
 	intel_gt_fini_scratch(gt);
 }
@@ -396,5 +651,8 @@ void intel_gt_driver_release(struct intel_gt *gt)
 void intel_gt_driver_late_release(struct intel_gt *gt)
 {
 	intel_uc_driver_late_release(&gt->uc);
+	intel_gt_fini_requests(gt);
 	intel_gt_fini_reset(gt);
+	intel_gt_fini_timelines(gt);
+	intel_engines_free(gt);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 5436f8c30708..1dac441cb8f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -12,6 +12,12 @@
 
 struct drm_i915_private;
 
+#define GT_TRACE(gt, fmt, ...) do {					\
+	const struct intel_gt *gt__ __maybe_unused = (gt);		\
+	GEM_TRACE("%s  " fmt, dev_name(gt__->i915->drm.dev),		\
+		  ##__VA_ARGS__);					\
+} while (0)
+
 static inline struct intel_gt *uc_to_gt(struct intel_uc *uc)
 {
 	return container_of(uc, struct intel_gt, uc);
@@ -52,9 +58,14 @@ static inline u32 intel_gt_scratch_offset(const struct intel_gt *gt,
 	return i915_ggtt_offset(gt->scratch) + field;
 }
 
-static inline bool intel_gt_is_wedged(struct intel_gt *gt)
+static inline bool intel_gt_is_wedged(const struct intel_gt *gt)
 {
 	return __intel_reset_failed(&gt->reset);
 }
 
+static inline bool intel_gt_has_init_error(const struct intel_gt *gt)
+{
+	return test_bit(I915_WEDGED_ON_INIT, &gt->reset.flags);
+}
+
 #endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index 973ee7eded64..f796bdf1ed30 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -28,7 +28,7 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 		tasklet = true;
 
 	if (iir & GT_RENDER_USER_INTERRUPT) {
-		intel_engine_breadcrumbs_irq(engine);
+		intel_engine_signal_breadcrumbs(engine);
 		tasklet |= intel_engine_needs_breadcrumb_tasklet(engine);
 	}
 
@@ -245,9 +245,9 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 void gen5_gt_irq_handler(struct intel_gt *gt, u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[RENDER_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]);
 	if (gt_iir & ILK_BSD_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]);
 }
 
 static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir)
@@ -271,11 +271,11 @@ static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir)
 void gen6_gt_irq_handler(struct intel_gt *gt, u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[RENDER_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]);
 	if (gt_iir & GT_BSD_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]);
 	if (gt_iir & GT_BLT_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[COPY_ENGINE_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[COPY_ENGINE_CLASS][0]);
 
 	if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
 		      GT_BSD_CS_ERROR_INTERRUPT |
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 7e64b7d7d330..d1c2f034296a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -43,7 +43,7 @@ static int __gt_unpark(struct intel_wakeref *wf)
 	struct intel_gt *gt = container_of(wf, typeof(*gt), wakeref);
 	struct drm_i915_private *i915 = gt->i915;
 
-	GEM_TRACE("\n");
+	GT_TRACE(gt, "\n");
 
 	i915_globals_unpark();
 
@@ -61,9 +61,7 @@ static int __gt_unpark(struct intel_wakeref *wf)
 	gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 	GEM_BUG_ON(!gt->awake);
 
-	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
-		intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
-
+	intel_rc6_unpark(&gt->rc6);
 	intel_rps_unpark(&gt->rps);
 	i915_pmu_gt_unparked(i915);
 
@@ -78,22 +76,18 @@ static int __gt_park(struct intel_wakeref *wf)
 	intel_wakeref_t wakeref = fetch_and_zero(&gt->awake);
 	struct drm_i915_private *i915 = gt->i915;
 
-	GEM_TRACE("\n");
+	GT_TRACE(gt, "\n");
 
 	intel_gt_park_requests(gt);
 
 	i915_vma_parked(gt);
 	i915_pmu_gt_parked(i915);
 	intel_rps_park(&gt->rps);
+	intel_rc6_park(&gt->rc6);
 
 	/* Everything switched off, flush any residual interrupt just in case */
 	intel_synchronize_irq(i915);
 
-	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) {
-		intel_rc6_ctx_wa_check(&i915->gt.rc6);
-		intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
-	}
-
 	/* Defer dropping the display power well for 100ms, it's slow! */
 	GEM_BUG_ON(!wakeref);
 	intel_display_power_put_async(i915, POWER_DOMAIN_GT_IRQ, wakeref);
@@ -132,23 +126,13 @@ static bool reset_engines(struct intel_gt *gt)
 	return __intel_gt_reset(gt, ALL_ENGINES) == 0;
 }
 
-/**
- * intel_gt_sanitize: called after the GPU has lost power
- * @gt: the i915 GT container
- * @force: ignore a failed reset and sanitize engine state anyway
- *
- * Anytime we reset the GPU, either with an explicit GPU reset or through a
- * PCI power cycle, the GPU loses state and we must reset our state tracking
- * to match. Note that calling intel_gt_sanitize() if the GPU has not
- * been reset results in much confusion!
- */
-void intel_gt_sanitize(struct intel_gt *gt, bool force)
+static void gt_sanitize(struct intel_gt *gt, bool force)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	intel_wakeref_t wakeref;
 
-	GEM_TRACE("force:%s\n", yesno(force));
+	GT_TRACE(gt, "force:%s", yesno(force));
 
 	/* Use a raw wakeref to avoid calling intel_display_power_get early */
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
@@ -193,9 +177,13 @@ int intel_gt_resume(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	int err = 0;
+	int err;
 
-	GEM_TRACE("\n");
+	err = intel_gt_has_init_error(gt);
+	if (err)
+		return err;
+
+	GT_TRACE(gt, "\n");
 
 	/*
 	 * After resume, we may need to poke into the pinned kernel
@@ -207,21 +195,26 @@ int intel_gt_resume(struct intel_gt *gt)
 
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	intel_rc6_sanitize(&gt->rc6);
+	gt_sanitize(gt, true);
+	if (intel_gt_is_wedged(gt)) {
+		err = -EIO;
+		goto out_fw;
+	}
+
+	/* Only when the HW is re-initialised, can we replay the requests */
+	err = intel_gt_init_hw(gt);
+	if (err) {
+		dev_err(gt->i915->drm.dev,
+			"Failed to initialize GPU, declaring it wedged!\n");
+		goto err_wedged;
+	}
 
 	intel_rps_enable(&gt->rps);
 	intel_llc_enable(&gt->llc);
 
 	for_each_engine(engine, gt, id) {
-		struct intel_context *ce;
-
 		intel_engine_pm_get(engine);
 
-		ce = engine->kernel_context;
-		if (ce) {
-			GEM_BUG_ON(!intel_context_is_pinned(ce));
-			ce->ops->reset(ce);
-		}
-
 		engine->serial++; /* kernel context lost */
 		err = engine->resume(engine);
 
@@ -230,7 +223,7 @@ int intel_gt_resume(struct intel_gt *gt)
 			dev_err(gt->i915->drm.dev,
 				"Failed to restart %s (%d)\n",
 				engine->name, err);
-			break;
+			goto err_wedged;
 		}
 	}
 
@@ -240,10 +233,14 @@ int intel_gt_resume(struct intel_gt *gt)
 
 	user_forcewake(gt, false);
 
+out_fw:
 	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 	intel_gt_pm_put(gt);
-
 	return err;
+
+err_wedged:
+	intel_gt_set_wedged(gt);
+	goto out_fw;
 }
 
 static void wait_for_suspend(struct intel_gt *gt)
@@ -257,6 +254,7 @@ static void wait_for_suspend(struct intel_gt *gt)
 		 * the gpu quiet.
 		 */
 		intel_gt_set_wedged(gt);
+		intel_gt_retire_requests(gt);
 	}
 
 	intel_gt_pm_wait_for_idle(gt);
@@ -286,6 +284,11 @@ void intel_gt_suspend_late(struct intel_gt *gt)
 	/* We expect to be idle already; but also want to be independent */
 	wait_for_suspend(gt);
 
+	if (is_mock_gt(gt))
+		return;
+
+	GEM_BUG_ON(gt->awake);
+
 	/*
 	 * On disabling the device, we want to turn off HW access to memory
 	 * that we no longer own.
@@ -305,22 +308,21 @@ void intel_gt_suspend_late(struct intel_gt *gt)
 		intel_llc_disable(&gt->llc);
 	}
 
-	intel_gt_sanitize(gt, false);
+	gt_sanitize(gt, false);
 
-	GEM_TRACE("\n");
+	GT_TRACE(gt, "\n");
 }
 
 void intel_gt_runtime_suspend(struct intel_gt *gt)
 {
 	intel_uc_runtime_suspend(&gt->uc);
 
-	GEM_TRACE("\n");
+	GT_TRACE(gt, "\n");
 }
 
 int intel_gt_runtime_resume(struct intel_gt *gt)
 {
-	GEM_TRACE("\n");
-
+	GT_TRACE(gt, "\n");
 	intel_gt_init_swizzling(gt);
 
 	return intel_uc_runtime_resume(&gt->uc);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index 990efc27a4e4..60f0e2fbe55c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -22,6 +22,11 @@ static inline void intel_gt_pm_get(struct intel_gt *gt)
 	intel_wakeref_get(&gt->wakeref);
 }
 
+static inline void __intel_gt_pm_get(struct intel_gt *gt)
+{
+	__intel_wakeref_get(&gt->wakeref);
+}
+
 static inline bool intel_gt_pm_get_if_awake(struct intel_gt *gt)
 {
 	return intel_wakeref_get_if_active(&gt->wakeref);
@@ -46,8 +51,6 @@ void intel_gt_pm_init_early(struct intel_gt *gt);
 void intel_gt_pm_init(struct intel_gt *gt);
 void intel_gt_pm_fini(struct intel_gt *gt);
 
-void intel_gt_sanitize(struct intel_gt *gt, bool force);
-
 void intel_gt_suspend_prepare(struct intel_gt *gt);
 void intel_gt_suspend_late(struct intel_gt *gt);
 int intel_gt_resume(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 3dc13ecf41bf..7ef1d37970f6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -8,27 +8,40 @@
 
 #include "i915_drv.h" /* for_each_engine() */
 #include "i915_request.h"
+#include "intel_engine_heartbeat.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 #include "intel_timeline.h"
 
-static void retire_requests(struct intel_timeline *tl)
+static bool retire_requests(struct intel_timeline *tl)
 {
 	struct i915_request *rq, *rn;
 
 	list_for_each_entry_safe(rq, rn, &tl->requests, link)
 		if (!i915_request_retire(rq))
-			break;
+			return false;
+
+	/* And check nothing new was submitted */
+	return !i915_active_fence_isset(&tl->last_request);
 }
 
-static void flush_submission(struct intel_gt *gt)
+static bool flush_submission(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	bool active = false;
+
+	if (!intel_gt_pm_is_awake(gt))
+		return false;
 
-	for_each_engine(engine, gt, id)
+	for_each_engine(engine, gt, id) {
 		intel_engine_flush_submission(engine);
+		active |= flush_work(&engine->retire_work);
+		active |= flush_work(&engine->wakeref.work);
+	}
+
+	return active;
 }
 
 static void engine_retire(struct work_struct *work)
@@ -62,19 +75,16 @@ static void engine_retire(struct work_struct *work)
 static bool add_retire(struct intel_engine_cs *engine,
 		       struct intel_timeline *tl)
 {
+#define STUB ((struct intel_timeline *)1)
 	struct intel_timeline *first;
 
 	/*
 	 * We open-code a llist here to include the additional tag [BIT(0)]
 	 * so that we know when the timeline is already on a
 	 * retirement queue: either this engine or another.
-	 *
-	 * However, we rely on that a timeline can only be active on a single
-	 * engine at any one time and that add_retire() is called before the
-	 * engine releases the timeline and transferred to another to retire.
 	 */
 
-	if (READ_ONCE(tl->retire)) /* already queued */
+	if (cmpxchg(&tl->retire, NULL, STUB)) /* already queued */
 		return false;
 
 	intel_timeline_get(tl);
@@ -109,7 +119,6 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl, *tn;
 	unsigned long active_count = 0;
-	unsigned long flags;
 	bool interruptible;
 	LIST_HEAD(free);
 
@@ -118,8 +127,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 		timeout = -timeout, interruptible = false;
 
 	flush_submission(gt); /* kick the ksoftirqd tasklets */
-
-	spin_lock_irqsave(&timelines->lock, flags);
+	spin_lock(&timelines->lock);
 	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
 		if (!mutex_trylock(&tl->mutex)) {
 			active_count++; /* report busy to caller, try again? */
@@ -129,7 +137,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 		intel_timeline_get(tl);
 		GEM_BUG_ON(!atomic_read(&tl->active_count));
 		atomic_inc(&tl->active_count); /* pin the list element */
-		spin_unlock_irqrestore(&timelines->lock, flags);
+		spin_unlock(&timelines->lock);
 
 		if (timeout > 0) {
 			struct dma_fence *fence;
@@ -143,16 +151,15 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 			}
 		}
 
-		retire_requests(tl);
+		if (!retire_requests(tl) || flush_submission(gt))
+			active_count++;
 
-		spin_lock_irqsave(&timelines->lock, flags);
+		spin_lock(&timelines->lock);
 
 		/* Resume iteration after dropping lock */
 		list_safe_reset_next(tl, tn, link);
 		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
-		else
-			active_count += !!rcu_access_pointer(tl->last_request.fence);
 
 		mutex_unlock(&tl->mutex);
 
@@ -162,7 +169,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 			list_add(&tl->link, &free);
 		}
 	}
-	spin_unlock_irqrestore(&timelines->lock, flags);
+	spin_unlock(&timelines->lock);
 
 	list_for_each_entry_safe(tl, tn, &free, link)
 		__intel_timeline_free(&tl->kref);
@@ -190,9 +197,9 @@ static void retire_work_handler(struct work_struct *work)
 	struct intel_gt *gt =
 		container_of(work, typeof(*gt), requests.retire_work.work);
 
-	intel_gt_retire_requests(gt);
 	schedule_delayed_work(&gt->requests.retire_work,
 			      round_jiffies_up_relative(HZ));
+	intel_gt_retire_requests(gt);
 }
 
 void intel_gt_init_requests(struct intel_gt *gt)
@@ -210,3 +217,9 @@ void intel_gt_unpark_requests(struct intel_gt *gt)
 	schedule_delayed_work(&gt->requests.retire_work,
 			      round_jiffies_up_relative(HZ));
 }
+
+void intel_gt_fini_requests(struct intel_gt *gt)
+{
+	/* Wait until the work is marked as finished before unloading! */
+	cancel_delayed_work_sync(&gt->requests.retire_work);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
index d626fb115386..dbac53baf1cb 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
@@ -27,5 +27,6 @@ int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
 void intel_gt_init_requests(struct intel_gt *gt);
 void intel_gt_park_requests(struct intel_gt *gt);
 void intel_gt_unpark_requests(struct intel_gt *gt);
+void intel_gt_fini_requests(struct intel_gt *gt);
 
 #endif /* INTEL_GT_REQUESTS_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index d4e14dbd172e..96890dd12b5f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -90,6 +90,13 @@ struct intel_gt {
 	struct intel_engine_cs *engine[I915_NUM_ENGINES];
 	struct intel_engine_cs *engine_class[MAX_ENGINE_CLASS + 1]
 					    [MAX_ENGINE_INSTANCE + 1];
+
+	/*
+	 * Default address space (either GGTT or ppGTT depending on arch).
+	 *
+	 * Reserved for exclusive use by the kernel.
+	 */
+	struct i915_address_space *vm;
 };
 
 enum intel_gt_scratch_field {
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
new file mode 100644
index 000000000000..16acdc5d6734
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -0,0 +1,598 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/slab.h> /* fault-inject.h is not standalone! */
+
+#include <linux/fault-inject.h>
+
+#include "i915_trace.h"
+#include "intel_gt.h"
+#include "intel_gtt.h"
+
+void stash_init(struct pagestash *stash)
+{
+	pagevec_init(&stash->pvec);
+	spin_lock_init(&stash->lock);
+}
+
+static struct page *stash_pop_page(struct pagestash *stash)
+{
+	struct page *page = NULL;
+
+	spin_lock(&stash->lock);
+	if (likely(stash->pvec.nr))
+		page = stash->pvec.pages[--stash->pvec.nr];
+	spin_unlock(&stash->lock);
+
+	return page;
+}
+
+static void stash_push_pagevec(struct pagestash *stash, struct pagevec *pvec)
+{
+	unsigned int nr;
+
+	spin_lock_nested(&stash->lock, SINGLE_DEPTH_NESTING);
+
+	nr = min_t(typeof(nr), pvec->nr, pagevec_space(&stash->pvec));
+	memcpy(stash->pvec.pages + stash->pvec.nr,
+	       pvec->pages + pvec->nr - nr,
+	       sizeof(pvec->pages[0]) * nr);
+	stash->pvec.nr += nr;
+
+	spin_unlock(&stash->lock);
+
+	pvec->nr -= nr;
+}
+
+static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
+{
+	struct pagevec stack;
+	struct page *page;
+
+	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
+		i915_gem_shrink_all(vm->i915);
+
+	page = stash_pop_page(&vm->free_pages);
+	if (page)
+		return page;
+
+	if (!vm->pt_kmap_wc)
+		return alloc_page(gfp);
+
+	/* Look in our global stash of WC pages... */
+	page = stash_pop_page(&vm->i915->mm.wc_stash);
+	if (page)
+		return page;
+
+	/*
+	 * Otherwise batch allocate pages to amortize cost of set_pages_wc.
+	 *
+	 * We have to be careful as page allocation may trigger the shrinker
+	 * (via direct reclaim) which will fill up the WC stash underneath us.
+	 * So we add our WB pages into a temporary pvec on the stack and merge
+	 * them into the WC stash after all the allocations are complete.
+	 */
+	pagevec_init(&stack);
+	do {
+		struct page *page;
+
+		page = alloc_page(gfp);
+		if (unlikely(!page))
+			break;
+
+		stack.pages[stack.nr++] = page;
+	} while (pagevec_space(&stack));
+
+	if (stack.nr && !set_pages_array_wc(stack.pages, stack.nr)) {
+		page = stack.pages[--stack.nr];
+
+		/* Merge spare WC pages to the global stash */
+		if (stack.nr)
+			stash_push_pagevec(&vm->i915->mm.wc_stash, &stack);
+
+		/* Push any surplus WC pages onto the local VM stash */
+		if (stack.nr)
+			stash_push_pagevec(&vm->free_pages, &stack);
+	}
+
+	/* Return unwanted leftovers */
+	if (unlikely(stack.nr)) {
+		WARN_ON_ONCE(set_pages_array_wb(stack.pages, stack.nr));
+		__pagevec_release(&stack);
+	}
+
+	return page;
+}
+
+static void vm_free_pages_release(struct i915_address_space *vm,
+				  bool immediate)
+{
+	struct pagevec *pvec = &vm->free_pages.pvec;
+	struct pagevec stack;
+
+	lockdep_assert_held(&vm->free_pages.lock);
+	GEM_BUG_ON(!pagevec_count(pvec));
+
+	if (vm->pt_kmap_wc) {
+		/*
+		 * When we use WC, first fill up the global stash and then
+		 * only if full immediately free the overflow.
+		 */
+		stash_push_pagevec(&vm->i915->mm.wc_stash, pvec);
+
+		/*
+		 * As we have made some room in the VM's free_pages,
+		 * we can wait for it to fill again. Unless we are
+		 * inside i915_address_space_fini() and must
+		 * immediately release the pages!
+		 */
+		if (pvec->nr <= (immediate ? 0 : PAGEVEC_SIZE - 1))
+			return;
+
+		/*
+		 * We have to drop the lock to allow ourselves to sleep,
+		 * so take a copy of the pvec and clear the stash for
+		 * others to use it as we sleep.
+		 */
+		stack = *pvec;
+		pagevec_reinit(pvec);
+		spin_unlock(&vm->free_pages.lock);
+
+		pvec = &stack;
+		set_pages_array_wb(pvec->pages, pvec->nr);
+
+		spin_lock(&vm->free_pages.lock);
+	}
+
+	__pagevec_release(pvec);
+}
+
+static void vm_free_page(struct i915_address_space *vm, struct page *page)
+{
+	/*
+	 * On !llc, we need to change the pages back to WB. We only do so
+	 * in bulk, so we rarely need to change the page attributes here,
+	 * but doing so requires a stop_machine() from deep inside arch/x86/mm.
+	 * To make detection of the possible sleep more likely, use an
+	 * unconditional might_sleep() for everybody.
+	 */
+	might_sleep();
+	spin_lock(&vm->free_pages.lock);
+	while (!pagevec_space(&vm->free_pages.pvec))
+		vm_free_pages_release(vm, false);
+	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec) >= PAGEVEC_SIZE);
+	pagevec_add(&vm->free_pages.pvec, page);
+	spin_unlock(&vm->free_pages.lock);
+}
+
+void __i915_vm_close(struct i915_address_space *vm)
+{
+	struct i915_vma *vma, *vn;
+
+	mutex_lock(&vm->mutex);
+	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		/* Keep the obj (and hence the vma) alive as _we_ destroy it */
+		if (!kref_get_unless_zero(&obj->base.refcount))
+			continue;
+
+		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
+		WARN_ON(__i915_vma_unbind(vma));
+		__i915_vma_put(vma);
+
+		i915_gem_object_put(obj);
+	}
+	GEM_BUG_ON(!list_empty(&vm->bound_list));
+	mutex_unlock(&vm->mutex);
+}
+
+void i915_address_space_fini(struct i915_address_space *vm)
+{
+	spin_lock(&vm->free_pages.lock);
+	if (pagevec_count(&vm->free_pages.pvec))
+		vm_free_pages_release(vm, true);
+	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec));
+	spin_unlock(&vm->free_pages.lock);
+
+	drm_mm_takedown(&vm->mm);
+
+	mutex_destroy(&vm->mutex);
+}
+
+static void __i915_vm_release(struct work_struct *work)
+{
+	struct i915_address_space *vm =
+		container_of(work, struct i915_address_space, rcu.work);
+
+	vm->cleanup(vm);
+	i915_address_space_fini(vm);
+
+	kfree(vm);
+}
+
+void i915_vm_release(struct kref *kref)
+{
+	struct i915_address_space *vm =
+		container_of(kref, struct i915_address_space, ref);
+
+	GEM_BUG_ON(i915_is_ggtt(vm));
+	trace_i915_ppgtt_release(vm);
+
+	queue_rcu_work(vm->i915->wq, &vm->rcu);
+}
+
+void i915_address_space_init(struct i915_address_space *vm, int subclass)
+{
+	kref_init(&vm->ref);
+	INIT_RCU_WORK(&vm->rcu, __i915_vm_release);
+	atomic_set(&vm->open, 1);
+
+	/*
+	 * The vm->mutex must be reclaim safe (for use in the shrinker).
+	 * Do a dummy acquire now under fs_reclaim so that any allocation
+	 * attempt holding the lock is immediately reported by lockdep.
+	 */
+	mutex_init(&vm->mutex);
+	lockdep_set_subclass(&vm->mutex, subclass);
+	i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex);
+
+	GEM_BUG_ON(!vm->total);
+	drm_mm_init(&vm->mm, 0, vm->total);
+	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
+
+	stash_init(&vm->free_pages);
+
+	INIT_LIST_HEAD(&vm->bound_list);
+}
+
+void clear_pages(struct i915_vma *vma)
+{
+	GEM_BUG_ON(!vma->pages);
+
+	if (vma->pages != vma->obj->mm.pages) {
+		sg_free_table(vma->pages);
+		kfree(vma->pages);
+	}
+	vma->pages = NULL;
+
+	memset(&vma->page_sizes, 0, sizeof(vma->page_sizes));
+}
+
+static int __setup_page_dma(struct i915_address_space *vm,
+			    struct i915_page_dma *p,
+			    gfp_t gfp)
+{
+	p->page = vm_alloc_page(vm, gfp | I915_GFP_ALLOW_FAIL);
+	if (unlikely(!p->page))
+		return -ENOMEM;
+
+	p->daddr = dma_map_page_attrs(vm->dma,
+				      p->page, 0, PAGE_SIZE,
+				      PCI_DMA_BIDIRECTIONAL,
+				      DMA_ATTR_SKIP_CPU_SYNC |
+				      DMA_ATTR_NO_WARN);
+	if (unlikely(dma_mapping_error(vm->dma, p->daddr))) {
+		vm_free_page(vm, p->page);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p)
+{
+	return __setup_page_dma(vm, p, __GFP_HIGHMEM);
+}
+
+void cleanup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p)
+{
+	dma_unmap_page(vm->dma, p->daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	vm_free_page(vm, p->page);
+}
+
+void
+fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count)
+{
+	kunmap_atomic(memset64(kmap_atomic(p->page), val, count));
+}
+
+int setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
+{
+	unsigned long size;
+
+	/*
+	 * In order to utilize 64K pages for an object with a size < 2M, we will
+	 * need to support a 64K scratch page, given that every 16th entry for a
+	 * page-table operating in 64K mode must point to a properly aligned 64K
+	 * region, including any PTEs which happen to point to scratch.
+	 *
+	 * This is only relevant for the 48b PPGTT where we support
+	 * huge-gtt-pages, see also i915_vma_insert(). However, as we share the
+	 * scratch (read-only) between all vm, we create one 64k scratch page
+	 * for all.
+	 */
+	size = I915_GTT_PAGE_SIZE_4K;
+	if (i915_vm_is_4lvl(vm) &&
+	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) {
+		size = I915_GTT_PAGE_SIZE_64K;
+		gfp |= __GFP_NOWARN;
+	}
+	gfp |= __GFP_ZERO | __GFP_RETRY_MAYFAIL;
+
+	do {
+		unsigned int order = get_order(size);
+		struct page *page;
+		dma_addr_t addr;
+
+		page = alloc_pages(gfp, order);
+		if (unlikely(!page))
+			goto skip;
+
+		addr = dma_map_page_attrs(vm->dma,
+					  page, 0, size,
+					  PCI_DMA_BIDIRECTIONAL,
+					  DMA_ATTR_SKIP_CPU_SYNC |
+					  DMA_ATTR_NO_WARN);
+		if (unlikely(dma_mapping_error(vm->dma, addr)))
+			goto free_page;
+
+		if (unlikely(!IS_ALIGNED(addr, size)))
+			goto unmap_page;
+
+		vm->scratch[0].base.page = page;
+		vm->scratch[0].base.daddr = addr;
+		vm->scratch_order = order;
+		return 0;
+
+unmap_page:
+		dma_unmap_page(vm->dma, addr, size, PCI_DMA_BIDIRECTIONAL);
+free_page:
+		__free_pages(page, order);
+skip:
+		if (size == I915_GTT_PAGE_SIZE_4K)
+			return -ENOMEM;
+
+		size = I915_GTT_PAGE_SIZE_4K;
+		gfp &= ~__GFP_NOWARN;
+	} while (1);
+}
+
+void cleanup_scratch_page(struct i915_address_space *vm)
+{
+	struct i915_page_dma *p = px_base(&vm->scratch[0]);
+	unsigned int order = vm->scratch_order;
+
+	dma_unmap_page(vm->dma, p->daddr, BIT(order) << PAGE_SHIFT,
+		       PCI_DMA_BIDIRECTIONAL);
+	__free_pages(p->page, order);
+}
+
+void free_scratch(struct i915_address_space *vm)
+{
+	int i;
+
+	if (!px_dma(&vm->scratch[0])) /* set to 0 on clones */
+		return;
+
+	for (i = 1; i <= vm->top; i++) {
+		if (!px_dma(&vm->scratch[i]))
+			break;
+		cleanup_page_dma(vm, px_base(&vm->scratch[i]));
+	}
+
+	cleanup_scratch_page(vm);
+}
+
+void gtt_write_workarounds(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+
+	/*
+	 * This function is for gtt related workarounds. This function is
+	 * called on driver load and after a GPU reset, so you can place
+	 * workarounds here even if they get overwritten by GPU reset.
+	 */
+	/* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt,kbl,glk,cfl,cnl,icl */
+	if (IS_BROADWELL(i915))
+		intel_uncore_write(uncore,
+				   GEN8_L3_LRA_1_GPGPU,
+				   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW);
+	else if (IS_CHERRYVIEW(i915))
+		intel_uncore_write(uncore,
+				   GEN8_L3_LRA_1_GPGPU,
+				   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV);
+	else if (IS_GEN9_LP(i915))
+		intel_uncore_write(uncore,
+				   GEN8_L3_LRA_1_GPGPU,
+				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
+	else if (INTEL_GEN(i915) >= 9 && INTEL_GEN(i915) <= 11)
+		intel_uncore_write(uncore,
+				   GEN8_L3_LRA_1_GPGPU,
+				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
+
+	/*
+	 * To support 64K PTEs we need to first enable the use of the
+	 * Intermediate-Page-Size(IPS) bit of the PDE field via some magical
+	 * mmio, otherwise the page-walker will simply ignore the IPS bit. This
+	 * shouldn't be needed after GEN10.
+	 *
+	 * 64K pages were first introduced from BDW+, although technically they
+	 * only *work* from gen9+. For pre-BDW we instead have the option for
+	 * 32K pages, but we don't currently have any support for it in our
+	 * driver.
+	 */
+	if (HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_64K) &&
+	    INTEL_GEN(i915) <= 10)
+		intel_uncore_rmw(uncore,
+				 GEN8_GAMW_ECO_DEV_RW_IA,
+				 0,
+				 GAMW_ECO_ENABLE_64K_IPS_FIELD);
+
+	if (IS_GEN_RANGE(i915, 8, 11)) {
+		bool can_use_gtt_cache = true;
+
+		/*
+		 * According to the BSpec if we use 2M/1G pages then we also
+		 * need to disable the GTT cache. At least on BDW we can see
+		 * visual corruption when using 2M pages, and not disabling the
+		 * GTT cache.
+		 */
+		if (HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_2M))
+			can_use_gtt_cache = false;
+
+		/* WaGttCachingOffByDefault */
+		intel_uncore_write(uncore,
+				   HSW_GTT_CACHE_EN,
+				   can_use_gtt_cache ? GTT_CACHE_EN_ALL : 0);
+		WARN_ON_ONCE(can_use_gtt_cache &&
+			     intel_uncore_read(uncore,
+					       HSW_GTT_CACHE_EN) == 0);
+	}
+}
+
+u64 gen8_pte_encode(dma_addr_t addr,
+		    enum i915_cache_level level,
+		    u32 flags)
+{
+	gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
+
+	if (unlikely(flags & PTE_READ_ONLY))
+		pte &= ~_PAGE_RW;
+
+	switch (level) {
+	case I915_CACHE_NONE:
+		pte |= PPAT_UNCACHED;
+		break;
+	case I915_CACHE_WT:
+		pte |= PPAT_DISPLAY_ELLC;
+		break;
+	default:
+		pte |= PPAT_CACHED;
+		break;
+	}
+
+	return pte;
+}
+
+static void tgl_setup_private_ppat(struct intel_uncore *uncore)
+{
+	/* TGL doesn't support LLC or AGE settings */
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(0), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(1), GEN8_PPAT_WC);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(2), GEN8_PPAT_WT);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(3), GEN8_PPAT_UC);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(4), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(5), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(6), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB);
+}
+
+static void cnl_setup_private_ppat(struct intel_uncore *uncore)
+{
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(0),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(1),
+			   GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(2),
+			   GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(3),
+			   GEN8_PPAT_UC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(4),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(5),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(6),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(7),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+}
+
+/*
+ * The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
+ * bits. When using advanced contexts each context stores its own PAT, but
+ * writing this data shouldn't be harmful even in those cases.
+ */
+static void bdw_setup_private_ppat(struct intel_uncore *uncore)
+{
+	u64 pat;
+
+	pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC) |	/* for normal objects, no eLLC */
+	      GEN8_PPAT(1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC) |	/* for something pointing to ptes? */
+	      GEN8_PPAT(2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC) |	/* for scanout with eLLC */
+	      GEN8_PPAT(3, GEN8_PPAT_UC) |			/* Uncached objects, mostly for scanout */
+	      GEN8_PPAT(4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)) |
+	      GEN8_PPAT(5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)) |
+	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
+	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
+}
+
+static void chv_setup_private_ppat(struct intel_uncore *uncore)
+{
+	u64 pat;
+
+	/*
+	 * Map WB on BDW to snooped on CHV.
+	 *
+	 * Only the snoop bit has meaning for CHV, the rest is
+	 * ignored.
+	 *
+	 * The hardware will never snoop for certain types of accesses:
+	 * - CPU GTT (GMADR->GGTT->no snoop->memory)
+	 * - PPGTT page tables
+	 * - some other special cycles
+	 *
+	 * As with BDW, we also need to consider the following for GT accesses:
+	 * "For GGTT, there is NO pat_sel[2:0] from the entry,
+	 * so RTL will always use the value corresponding to
+	 * pat_sel = 000".
+	 * Which means we must set the snoop bit in PAT entry 0
+	 * in order to keep the global status page working.
+	 */
+
+	pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(1, 0) |
+	      GEN8_PPAT(2, 0) |
+	      GEN8_PPAT(3, 0) |
+	      GEN8_PPAT(4, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(5, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(7, CHV_PPAT_SNOOP);
+
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
+}
+
+void setup_private_pat(struct intel_uncore *uncore)
+{
+	struct drm_i915_private *i915 = uncore->i915;
+
+	GEM_BUG_ON(INTEL_GEN(i915) < 8);
+
+	if (INTEL_GEN(i915) >= 12)
+		tgl_setup_private_ppat(uncore);
+	else if (INTEL_GEN(i915) >= 10)
+		cnl_setup_private_ppat(uncore);
+	else if (IS_CHERRYVIEW(i915) || IS_GEN9_LP(i915))
+		chv_setup_private_ppat(uncore);
+	else
+		bdw_setup_private_ppat(uncore);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/mock_gtt.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
new file mode 100644
index 000000000000..7da7681c20b1
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -0,0 +1,587 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ *
+ * Please try to maintain the following order within this file unless it makes
+ * sense to do otherwise. From top to bottom:
+ * 1. typedefs
+ * 2. #defines, and macros
+ * 3. structure definitions
+ * 4. function prototypes
+ *
+ * Within each section, please try to order by generation in ascending order,
+ * from top to bottom (ie. gen6 on the top, gen8 on the bottom).
+ */
+
+#ifndef __INTEL_GTT_H__
+#define __INTEL_GTT_H__
+
+#include <linux/io-mapping.h>
+#include <linux/kref.h>
+#include <linux/mm.h>
+#include <linux/pagevec.h>
+#include <linux/scatterlist.h>
+#include <linux/workqueue.h>
+
+#include <drm/drm_mm.h>
+
+#include "gt/intel_reset.h"
+#include "i915_gem_fence_reg.h"
+#include "i915_selftest.h"
+#include "i915_vma_types.h"
+
+#define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
+
+#if IS_ENABLED(CONFIG_DRM_I915_TRACE_GTT)
+#define DBG(...) trace_printk(__VA_ARGS__)
+#else
+#define DBG(...)
+#endif
+
+#define NALLOC 3 /* 1 normal, 1 for concurrent threads, 1 for preallocation */
+
+#define I915_GTT_PAGE_SIZE_4K	BIT_ULL(12)
+#define I915_GTT_PAGE_SIZE_64K	BIT_ULL(16)
+#define I915_GTT_PAGE_SIZE_2M	BIT_ULL(21)
+
+#define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K
+#define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M
+
+#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE
+
+#define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE
+
+#define I915_FENCE_REG_NONE -1
+#define I915_MAX_NUM_FENCES 32
+/* 32 fences + sign bit for FENCE_REG_NONE */
+#define I915_MAX_NUM_FENCE_BITS 6
+
+typedef u32 gen6_pte_t;
+typedef u64 gen8_pte_t;
+
+#define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)
+
+#define I915_PTES(pte_len)		((unsigned int)(PAGE_SIZE / (pte_len)))
+#define I915_PTE_MASK(pte_len)		(I915_PTES(pte_len) - 1)
+#define I915_PDES			512
+#define I915_PDE_MASK			(I915_PDES - 1)
+
+/* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
+#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
+#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+#define GEN6_PTE_CACHE_LLC		(2 << 1)
+#define GEN6_PTE_UNCACHED		(1 << 1)
+#define GEN6_PTE_VALID			REG_BIT(0)
+
+#define GEN6_PTES			I915_PTES(sizeof(gen6_pte_t))
+#define GEN6_PD_SIZE		        (I915_PDES * PAGE_SIZE)
+#define GEN6_PD_ALIGN			(PAGE_SIZE * 16)
+#define GEN6_PDE_SHIFT			22
+#define GEN6_PDE_VALID			REG_BIT(0)
+#define NUM_PTE(pde_shift)     (1 << (pde_shift - PAGE_SHIFT))
+
+#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
+
+#define BYT_PTE_SNOOPED_BY_CPU_CACHES	REG_BIT(2)
+#define BYT_PTE_WRITEABLE		REG_BIT(1)
+
+/*
+ * Cacheability Control is a 4-bit value. The low three bits are stored in bits
+ * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
+ */
+#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
+					 (((bits) & 0x8) << (11 - 3)))
+#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
+#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
+#define HSW_WB_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x8)
+#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
+#define HSW_WT_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x7)
+#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
+#define HSW_PTE_UNCACHED		(0)
+#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
+#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
+
+/*
+ * GEN8 32b style address is defined as a 3 level page table:
+ * 31:30 | 29:21 | 20:12 |  11:0
+ * PDPE  |  PDE  |  PTE  | offset
+ * The difference as compared to normal x86 3 level page table is the PDPEs are
+ * programmed via register.
+ *
+ * GEN8 48b style address is defined as a 4 level page table:
+ * 47:39 | 38:30 | 29:21 | 20:12 |  11:0
+ * PML4E | PDPE  |  PDE  |  PTE  | offset
+ */
+#define GEN8_3LVL_PDPES			4
+
+#define PPAT_UNCACHED			(_PAGE_PWT | _PAGE_PCD)
+#define PPAT_CACHED_PDE			0 /* WB LLC */
+#define PPAT_CACHED			_PAGE_PAT /* WB LLCeLLC */
+#define PPAT_DISPLAY_ELLC		_PAGE_PCD /* WT eLLC */
+
+#define CHV_PPAT_SNOOP			REG_BIT(6)
+#define GEN8_PPAT_AGE(x)		((x)<<4)
+#define GEN8_PPAT_LLCeLLC		(3<<2)
+#define GEN8_PPAT_LLCELLC		(2<<2)
+#define GEN8_PPAT_LLC			(1<<2)
+#define GEN8_PPAT_WB			(3<<0)
+#define GEN8_PPAT_WT			(2<<0)
+#define GEN8_PPAT_WC			(1<<0)
+#define GEN8_PPAT_UC			(0<<0)
+#define GEN8_PPAT_ELLC_OVERRIDE		(0<<2)
+#define GEN8_PPAT(i, x)			((u64)(x) << ((i) * 8))
+
+#define GEN8_PDE_IPS_64K BIT(11)
+#define GEN8_PDE_PS_2M   BIT(7)
+
+#define for_each_sgt_daddr(__dp, __iter, __sgt) \
+	__for_each_sgt_daddr(__dp, __iter, __sgt, I915_GTT_PAGE_SIZE)
+
+struct i915_page_dma {
+	struct page *page;
+	union {
+		dma_addr_t daddr;
+
+		/*
+		 * For gen6/gen7 only. This is the offset in the GGTT
+		 * where the page directory entries for PPGTT begin
+		 */
+		u32 ggtt_offset;
+	};
+};
+
+struct i915_page_scratch {
+	struct i915_page_dma base;
+	u64 encode;
+};
+
+struct i915_page_table {
+	struct i915_page_dma base;
+	atomic_t used;
+};
+
+struct i915_page_directory {
+	struct i915_page_table pt;
+	spinlock_t lock;
+	void *entry[512];
+};
+
+#define __px_choose_expr(x, type, expr, other) \
+	__builtin_choose_expr( \
+	__builtin_types_compatible_p(typeof(x), type) || \
+	__builtin_types_compatible_p(typeof(x), const type), \
+	({ type __x = (type)(x); expr; }), \
+	other)
+
+#define px_base(px) \
+	__px_choose_expr(px, struct i915_page_dma *, __x, \
+	__px_choose_expr(px, struct i915_page_scratch *, &__x->base, \
+	__px_choose_expr(px, struct i915_page_table *, &__x->base, \
+	__px_choose_expr(px, struct i915_page_directory *, &__x->pt.base, \
+	(void)0))))
+#define px_dma(px) (px_base(px)->daddr)
+
+#define px_pt(px) \
+	__px_choose_expr(px, struct i915_page_table *, __x, \
+	__px_choose_expr(px, struct i915_page_directory *, &__x->pt, \
+	(void)0))
+#define px_used(px) (&px_pt(px)->used)
+
+enum i915_cache_level;
+
+struct drm_i915_file_private;
+struct drm_i915_gem_object;
+struct i915_vma;
+struct intel_gt;
+
+struct i915_vma_ops {
+	/* Map an object into an address space with the given cache flags. */
+	int (*bind_vma)(struct i915_vma *vma,
+			enum i915_cache_level cache_level,
+			u32 flags);
+	/*
+	 * Unmap an object from an address space. This usually consists of
+	 * setting the valid PTE entries to a reserved scratch page.
+	 */
+	void (*unbind_vma)(struct i915_vma *vma);
+
+	int (*set_pages)(struct i915_vma *vma);
+	void (*clear_pages)(struct i915_vma *vma);
+};
+
+struct pagestash {
+	spinlock_t lock;
+	struct pagevec pvec;
+};
+
+void stash_init(struct pagestash *stash);
+
+struct i915_address_space {
+	struct kref ref;
+	struct rcu_work rcu;
+
+	struct drm_mm mm;
+	struct intel_gt *gt;
+	struct drm_i915_private *i915;
+	struct device *dma;
+	/*
+	 * Every address space belongs to a struct file - except for the global
+	 * GTT that is owned by the driver (and so @file is set to NULL). In
+	 * principle, no information should leak from one context to another
+	 * (or between files/processes etc) unless explicitly shared by the
+	 * owner. Tracking the owner is important in order to free up per-file
+	 * objects along with the file, to aide resource tracking, and to
+	 * assign blame.
+	 */
+	struct drm_i915_file_private *file;
+	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
+	u64 reserved;		/* size addr space reserved */
+
+	unsigned int bind_async_flags;
+
+	/*
+	 * Each active user context has its own address space (in full-ppgtt).
+	 * Since the vm may be shared between multiple contexts, we count how
+	 * many contexts keep us "open". Once open hits zero, we are closed
+	 * and do not allow any new attachments, and proceed to shutdown our
+	 * vma and page directories.
+	 */
+	atomic_t open;
+
+	struct mutex mutex; /* protects vma and our lists */
+#define VM_CLASS_GGTT 0
+#define VM_CLASS_PPGTT 1
+
+	struct i915_page_scratch scratch[4];
+	unsigned int scratch_order;
+	unsigned int top;
+
+	/**
+	 * List of vma currently bound.
+	 */
+	struct list_head bound_list;
+
+	struct pagestash free_pages;
+
+	/* Global GTT */
+	bool is_ggtt:1;
+
+	/* Some systems require uncached updates of the page directories */
+	bool pt_kmap_wc:1;
+
+	/* Some systems support read-only mappings for GGTT and/or PPGTT */
+	bool has_read_only:1;
+
+	u64 (*pte_encode)(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags); /* Create a valid PTE */
+#define PTE_READ_ONLY	BIT(0)
+
+	int (*allocate_va_range)(struct i915_address_space *vm,
+				 u64 start, u64 length);
+	void (*clear_range)(struct i915_address_space *vm,
+			    u64 start, u64 length);
+	void (*insert_page)(struct i915_address_space *vm,
+			    dma_addr_t addr,
+			    u64 offset,
+			    enum i915_cache_level cache_level,
+			    u32 flags);
+	void (*insert_entries)(struct i915_address_space *vm,
+			       struct i915_vma *vma,
+			       enum i915_cache_level cache_level,
+			       u32 flags);
+	void (*cleanup)(struct i915_address_space *vm);
+
+	struct i915_vma_ops vma_ops;
+
+	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
+	I915_SELFTEST_DECLARE(bool scrub_64K);
+};
+
+/*
+ * The Graphics Translation Table is the way in which GEN hardware translates a
+ * Graphics Virtual Address into a Physical Address. In addition to the normal
+ * collateral associated with any va->pa translations GEN hardware also has a
+ * portion of the GTT which can be mapped by the CPU and remain both coherent
+ * and correct (in cases like swizzling). That region is referred to as GMADR in
+ * the spec.
+ */
+struct i915_ggtt {
+	struct i915_address_space vm;
+
+	struct io_mapping iomap;	/* Mapping to our CPU mappable region */
+	struct resource gmadr;          /* GMADR resource */
+	resource_size_t mappable_end;	/* End offset that we can CPU map */
+
+	/** "Graphics Stolen Memory" holds the global PTEs */
+	void __iomem *gsm;
+	void (*invalidate)(struct i915_ggtt *ggtt);
+
+	/** PPGTT used for aliasing the PPGTT with the GTT */
+	struct i915_ppgtt *alias;
+
+	bool do_idle_maps;
+
+	int mtrr;
+
+	/** Bit 6 swizzling required for X tiling */
+	u32 bit_6_swizzle_x;
+	/** Bit 6 swizzling required for Y tiling */
+	u32 bit_6_swizzle_y;
+
+	u32 pin_bias;
+
+	unsigned int num_fences;
+	struct i915_fence_reg fence_regs[I915_MAX_NUM_FENCES];
+	struct list_head fence_list;
+
+	/**
+	 * List of all objects in gtt_space, currently mmaped by userspace.
+	 * All objects within this list must also be on bound_list.
+	 */
+	struct list_head userfault_list;
+
+	/* Manual runtime pm autosuspend delay for user GGTT mmaps */
+	struct intel_wakeref_auto userfault_wakeref;
+
+	struct mutex error_mutex;
+	struct drm_mm_node error_capture;
+	struct drm_mm_node uc_fw;
+};
+
+struct i915_ppgtt {
+	struct i915_address_space vm;
+
+	struct i915_page_directory *pd;
+};
+
+#define i915_is_ggtt(vm) ((vm)->is_ggtt)
+
+static inline bool
+i915_vm_is_4lvl(const struct i915_address_space *vm)
+{
+	return (vm->total - 1) >> 32;
+}
+
+static inline bool
+i915_vm_has_scratch_64K(struct i915_address_space *vm)
+{
+	return vm->scratch_order == get_order(I915_GTT_PAGE_SIZE_64K);
+}
+
+static inline bool
+i915_vm_has_cache_coloring(struct i915_address_space *vm)
+{
+	return i915_is_ggtt(vm) && vm->mm.color_adjust;
+}
+
+static inline struct i915_ggtt *
+i915_vm_to_ggtt(struct i915_address_space *vm)
+{
+	BUILD_BUG_ON(offsetof(struct i915_ggtt, vm));
+	GEM_BUG_ON(!i915_is_ggtt(vm));
+	return container_of(vm, struct i915_ggtt, vm);
+}
+
+static inline struct i915_ppgtt *
+i915_vm_to_ppgtt(struct i915_address_space *vm)
+{
+	BUILD_BUG_ON(offsetof(struct i915_ppgtt, vm));
+	GEM_BUG_ON(i915_is_ggtt(vm));
+	return container_of(vm, struct i915_ppgtt, vm);
+}
+
+static inline struct i915_address_space *
+i915_vm_get(struct i915_address_space *vm)
+{
+	kref_get(&vm->ref);
+	return vm;
+}
+
+void i915_vm_release(struct kref *kref);
+
+static inline void i915_vm_put(struct i915_address_space *vm)
+{
+	kref_put(&vm->ref, i915_vm_release);
+}
+
+static inline struct i915_address_space *
+i915_vm_open(struct i915_address_space *vm)
+{
+	GEM_BUG_ON(!atomic_read(&vm->open));
+	atomic_inc(&vm->open);
+	return i915_vm_get(vm);
+}
+
+static inline bool
+i915_vm_tryopen(struct i915_address_space *vm)
+{
+	if (atomic_add_unless(&vm->open, 1, 0))
+		return i915_vm_get(vm);
+
+	return false;
+}
+
+void __i915_vm_close(struct i915_address_space *vm);
+
+static inline void
+i915_vm_close(struct i915_address_space *vm)
+{
+	GEM_BUG_ON(!atomic_read(&vm->open));
+	if (atomic_dec_and_test(&vm->open))
+		__i915_vm_close(vm);
+
+	i915_vm_put(vm);
+}
+
+void i915_address_space_init(struct i915_address_space *vm, int subclass);
+void i915_address_space_fini(struct i915_address_space *vm);
+
+static inline u32 i915_pte_index(u64 address, unsigned int pde_shift)
+{
+	const u32 mask = NUM_PTE(pde_shift) - 1;
+
+	return (address >> PAGE_SHIFT) & mask;
+}
+
+/*
+ * Helper to counts the number of PTEs within the given length. This count
+ * does not cross a page table boundary, so the max value would be
+ * GEN6_PTES for GEN6, and GEN8_PTES for GEN8.
+ */
+static inline u32 i915_pte_count(u64 addr, u64 length, unsigned int pde_shift)
+{
+	const u64 mask = ~((1ULL << pde_shift) - 1);
+	u64 end;
+
+	GEM_BUG_ON(length == 0);
+	GEM_BUG_ON(offset_in_page(addr | length));
+
+	end = addr + length;
+
+	if ((addr & mask) != (end & mask))
+		return NUM_PTE(pde_shift) - i915_pte_index(addr, pde_shift);
+
+	return i915_pte_index(end, pde_shift) - i915_pte_index(addr, pde_shift);
+}
+
+static inline u32 i915_pde_index(u64 addr, u32 shift)
+{
+	return (addr >> shift) & I915_PDE_MASK;
+}
+
+static inline struct i915_page_table *
+i915_pt_entry(const struct i915_page_directory * const pd,
+	      const unsigned short n)
+{
+	return pd->entry[n];
+}
+
+static inline struct i915_page_directory *
+i915_pd_entry(const struct i915_page_directory * const pdp,
+	      const unsigned short n)
+{
+	return pdp->entry[n];
+}
+
+static inline dma_addr_t
+i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n)
+{
+	struct i915_page_dma *pt = ppgtt->pd->entry[n];
+
+	return px_dma(pt ?: px_base(&ppgtt->vm.scratch[ppgtt->vm.top]));
+}
+
+void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt);
+
+int i915_ggtt_probe_hw(struct drm_i915_private *i915);
+int i915_ggtt_init_hw(struct drm_i915_private *i915);
+int i915_ggtt_enable_hw(struct drm_i915_private *i915);
+void i915_ggtt_enable_guc(struct i915_ggtt *ggtt);
+void i915_ggtt_disable_guc(struct i915_ggtt *ggtt);
+int i915_init_ggtt(struct drm_i915_private *i915);
+void i915_ggtt_driver_release(struct drm_i915_private *i915);
+
+static inline bool i915_ggtt_has_aperture(const struct i915_ggtt *ggtt)
+{
+	return ggtt->mappable_end > 0;
+}
+
+int i915_ppgtt_init_hw(struct intel_gt *gt);
+
+struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt);
+
+void i915_gem_suspend_gtt_mappings(struct drm_i915_private *i915);
+void i915_gem_restore_gtt_mappings(struct drm_i915_private *i915);
+
+u64 gen8_pte_encode(dma_addr_t addr,
+		    enum i915_cache_level level,
+		    u32 flags);
+
+int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p);
+void cleanup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p);
+
+#define kmap_atomic_px(px) kmap_atomic(px_base(px)->page)
+
+void
+fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count);
+
+#define fill_px(px, v) fill_page_dma(px_base(px), (v), PAGE_SIZE / sizeof(u64))
+#define fill32_px(px, v) do {						\
+	u64 v__ = lower_32_bits(v);					\
+	fill_px((px), v__ << 32 | v__);					\
+} while (0)
+
+int setup_scratch_page(struct i915_address_space *vm, gfp_t gfp);
+void cleanup_scratch_page(struct i915_address_space *vm);
+void free_scratch(struct i915_address_space *vm);
+
+struct i915_page_table *alloc_pt(struct i915_address_space *vm);
+struct i915_page_directory *alloc_pd(struct i915_address_space *vm);
+struct i915_page_directory *__alloc_pd(size_t sz);
+
+void free_pd(struct i915_address_space *vm, struct i915_page_dma *pd);
+
+#define free_px(vm, px) free_pd(vm, px_base(px))
+
+void
+__set_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short idx,
+	       struct i915_page_dma * const to,
+	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level));
+
+#define set_pd_entry(pd, idx, to) \
+	__set_pd_entry((pd), (idx), px_base(to), gen8_pde_encode)
+
+void
+clear_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short idx,
+	       const struct i915_page_scratch * const scratch);
+
+bool
+release_pd_entry(struct i915_page_directory * const pd,
+		 const unsigned short idx,
+		 struct i915_page_table * const pt,
+		 const struct i915_page_scratch * const scratch);
+void gen6_ggtt_invalidate(struct i915_ggtt *ggtt);
+
+int ggtt_set_pages(struct i915_vma *vma);
+int ppgtt_set_pages(struct i915_vma *vma);
+void clear_pages(struct i915_vma *vma);
+
+void gtt_write_workarounds(struct intel_gt *gt);
+
+void setup_private_pat(struct intel_uncore *uncore);
+
+static inline struct sgt_dma {
+	struct scatterlist *sg;
+	dma_addr_t dma, max;
+} sgt_dma(struct i915_vma *vma) {
+	struct scatterlist *sg = vma->pages->sgl;
+	dma_addr_t addr = sg_dma_address(sg);
+
+	return (struct sgt_dma){ sg, addr, addr + sg->length };
+}
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d925a1035c9d..0cf0f6fae675 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -133,12 +133,11 @@
  */
 #include <linux/interrupt.h>
 
-#include "gem/i915_gem_context.h"
-
 #include "i915_drv.h"
 #include "i915_perf.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
+#include "intel_context.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
@@ -489,17 +488,23 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	return desc;
 }
 
-static u32 *set_offsets(u32 *regs,
+static inline unsigned int dword_in_page(void *addr)
+{
+	return offset_in_page(addr) / sizeof(u32);
+}
+
+static void set_offsets(u32 *regs,
 			const u8 *data,
-			const struct intel_engine_cs *engine)
+			const struct intel_engine_cs *engine,
+			bool clear)
 #define NOP(x) (BIT(7) | (x))
-#define LRI(count, flags) ((flags) << 6 | (count))
+#define LRI(count, flags) ((flags) << 6 | (count) | BUILD_BUG_ON_ZERO(count >= BIT(6)))
 #define POSTED BIT(0)
 #define REG(x) (((x) >> 2) | BUILD_BUG_ON_ZERO(x >= 0x200))
 #define REG16(x) \
 	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
 	(((x) >> 2) & 0x7f)
-#define END() 0
+#define END(x) 0, (x)
 {
 	const u32 base = engine->mmio_base;
 
@@ -507,7 +512,10 @@ static u32 *set_offsets(u32 *regs,
 		u8 count, flags;
 
 		if (*data & BIT(7)) { /* skip */
-			regs += *data++ & ~BIT(7);
+			count = *data++ & ~BIT(7);
+			if (clear)
+				memset32(regs, MI_NOOP, count);
+			regs += count;
 			continue;
 		}
 
@@ -533,12 +541,25 @@ static u32 *set_offsets(u32 *regs,
 				offset |= v & ~BIT(7);
 			} while (v & BIT(7));
 
-			*regs = base + (offset << 2);
+			regs[0] = base + (offset << 2);
+			if (clear)
+				regs[1] = 0;
 			regs += 2;
 		} while (--count);
 	}
 
-	return regs;
+	if (clear) {
+		u8 count = *++data;
+
+		/* Clear past the tail for HW access */
+		GEM_BUG_ON(dword_in_page(regs) > count);
+		memset32(regs, MI_NOOP, count - dword_in_page(regs));
+
+		/* Close the batch; used mainly by live_lrc_layout() */
+		*regs = MI_BATCH_BUFFER_END;
+		if (INTEL_GEN(engine->i915) >= 10)
+			*regs |= BIT(0);
+	}
 }
 
 static const u8 gen8_xcs_offsets[] = {
@@ -573,7 +594,7 @@ static const u8 gen8_xcs_offsets[] = {
 	REG16(0x200),
 	REG(0x028),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen9_xcs_offsets[] = {
@@ -657,7 +678,7 @@ static const u8 gen9_xcs_offsets[] = {
 	REG16(0x67c),
 	REG(0x068),
 
-	END(),
+	END(176)
 };
 
 static const u8 gen12_xcs_offsets[] = {
@@ -689,7 +710,7 @@ static const u8 gen12_xcs_offsets[] = {
 	REG16(0x274),
 	REG16(0x270),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen8_rcs_offsets[] = {
@@ -726,7 +747,91 @@ static const u8 gen8_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
+};
+
+static const u8 gen9_rcs_offsets[] = {
+	NOP(1),
+	LRI(14, POSTED),
+	REG16(0x244),
+	REG(0x34),
+	REG(0x30),
+	REG(0x38),
+	REG(0x3c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x11c),
+	REG(0x114),
+	REG(0x118),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+
+	NOP(3),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	NOP(13),
+	LRI(1, 0),
+	REG(0xc8),
+
+	NOP(13),
+	LRI(44, POSTED),
+	REG(0x28),
+	REG(0x9c),
+	REG(0xc0),
+	REG(0x178),
+	REG(0x17c),
+	REG16(0x358),
+	REG(0x170),
+	REG(0x150),
+	REG(0x154),
+	REG(0x158),
+	REG16(0x41c),
+	REG16(0x600),
+	REG16(0x604),
+	REG16(0x608),
+	REG16(0x60c),
+	REG16(0x610),
+	REG16(0x614),
+	REG16(0x618),
+	REG16(0x61c),
+	REG16(0x620),
+	REG16(0x624),
+	REG16(0x628),
+	REG16(0x62c),
+	REG16(0x630),
+	REG16(0x634),
+	REG16(0x638),
+	REG16(0x63c),
+	REG16(0x640),
+	REG16(0x644),
+	REG16(0x648),
+	REG16(0x64c),
+	REG16(0x650),
+	REG16(0x654),
+	REG16(0x658),
+	REG16(0x65c),
+	REG16(0x660),
+	REG16(0x664),
+	REG16(0x668),
+	REG16(0x66c),
+	REG16(0x670),
+	REG16(0x674),
+	REG16(0x678),
+	REG16(0x67c),
+	REG(0x68),
+
+	END(176)
 };
 
 static const u8 gen11_rcs_offsets[] = {
@@ -767,7 +872,7 @@ static const u8 gen11_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen12_rcs_offsets[] = {
@@ -808,7 +913,7 @@ static const u8 gen12_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
 };
 
 #undef END
@@ -833,6 +938,8 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 			return gen12_rcs_offsets;
 		else if (INTEL_GEN(engine->i915) >= 11)
 			return gen11_rcs_offsets;
+		else if (INTEL_GEN(engine->i915) >= 9)
+			return gen9_rcs_offsets;
 		else
 			return gen8_rcs_offsets;
 	} else {
@@ -880,7 +987,7 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 			list_move(&rq->sched.link, pl);
 			active = rq;
 		} else {
-			struct intel_engine_cs *owner = rq->hw_context->engine;
+			struct intel_engine_cs *owner = rq->context->engine;
 
 			/*
 			 * Decouple the virtual breadcrumb before moving it
@@ -983,6 +1090,58 @@ static void intel_engine_context_out(struct intel_engine_cs *engine)
 	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
+static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0x60;
+	else if (INTEL_GEN(engine->i915) >= 9)
+		return 0x54;
+	else if (engine->class == RENDER_CLASS)
+		return 0x58;
+	else
+		return -1;
+}
+
+static void
+execlists_check_context(const struct intel_context *ce,
+			const struct intel_engine_cs *engine)
+{
+	const struct intel_ring *ring = ce->ring;
+	u32 *regs = ce->lrc_reg_state;
+	bool valid = true;
+	int x;
+
+	if (regs[CTX_RING_START] != i915_ggtt_offset(ring->vma)) {
+		pr_err("%s: context submitted with incorrect RING_START [%08x], expected %08x\n",
+		       engine->name,
+		       regs[CTX_RING_START],
+		       i915_ggtt_offset(ring->vma));
+		regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
+		valid = false;
+	}
+
+	if ((regs[CTX_RING_CTL] & ~(RING_WAIT | RING_WAIT_SEMAPHORE)) !=
+	    (RING_CTL_SIZE(ring->size) | RING_VALID)) {
+		pr_err("%s: context submitted with incorrect RING_CTL [%08x], expected %08x\n",
+		       engine->name,
+		       regs[CTX_RING_CTL],
+		       (u32)(RING_CTL_SIZE(ring->size) | RING_VALID));
+		regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
+		valid = false;
+	}
+
+	x = lrc_ring_mi_mode(engine);
+	if (x != -1 && regs[x + 1] & (regs[x + 1] >> 16) & STOP_RING) {
+		pr_err("%s: context submitted with STOP_RING [%08x] in RING_MI_MODE\n",
+		       engine->name, regs[x + 1]);
+		regs[x + 1] &= ~STOP_RING;
+		regs[x + 1] |= STOP_RING << 16;
+		valid = false;
+	}
+
+	WARN_ONCE(!valid, "Invalid lrc state found before submission\n");
+}
+
 static void restore_default_state(struct intel_context *ce,
 				  struct intel_engine_cs *engine)
 {
@@ -999,7 +1158,7 @@ static void restore_default_state(struct intel_context *ce,
 static void reset_active(struct i915_request *rq,
 			 struct intel_engine_cs *engine)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	u32 head;
 
 	/*
@@ -1017,8 +1176,8 @@ static void reset_active(struct i915_request *rq,
 	 * remain correctly ordered. And we defer to __i915_request_submit()
 	 * so that all asynchronous waits are correctly handled.
 	 */
-	GEM_TRACE("%s(%s): { rq=%llx:%lld }\n",
-		  __func__, engine->name, rq->fence.context, rq->fence.seqno);
+	ENGINE_TRACE(engine, "{ rq=%llx:%lld }\n",
+		     rq->fence.context, rq->fence.seqno);
 
 	/* On resubmission of the active request, payload will be scrubbed */
 	if (i915_request_completed(rq))
@@ -1040,13 +1199,16 @@ static inline struct intel_engine_cs *
 __execlists_schedule_in(struct i915_request *rq)
 {
 	struct intel_engine_cs * const engine = rq->engine;
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 
 	intel_context_get(ce);
 
-	if (unlikely(i915_gem_context_is_banned(ce->gem_context)))
+	if (unlikely(intel_context_is_banned(ce)))
 		reset_active(rq, engine);
 
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		execlists_check_context(ce, engine);
+
 	if (ce->tag) {
 		/* Use a fixed tag for OA and friends */
 		ce->lrc_desc |= (u64)ce->tag << 32;
@@ -1054,12 +1216,12 @@ __execlists_schedule_in(struct i915_request *rq)
 		/* We don't need a strict matching tag, just different values */
 		ce->lrc_desc &= ~GENMASK_ULL(47, 37);
 		ce->lrc_desc |=
-			(u64)(engine->context_tag++ % NUM_CONTEXT_TAG) <<
+			(u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
 			GEN11_SW_CTX_ID_SHIFT;
 		BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID);
 	}
 
-	intel_gt_pm_get(engine->gt);
+	__intel_gt_pm_get(engine->gt);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
 
@@ -1069,7 +1231,7 @@ __execlists_schedule_in(struct i915_request *rq)
 static inline struct i915_request *
 execlists_schedule_in(struct i915_request *rq, int idx)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *old;
 
 	GEM_BUG_ON(!intel_engine_pm_is_awake(rq->engine));
@@ -1100,7 +1262,7 @@ static inline void
 __execlists_schedule_out(struct i915_request *rq,
 			 struct intel_engine_cs * const engine)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 
 	/*
 	 * NB process_csb() is not under the engine->active.lock and hence
@@ -1138,7 +1300,7 @@ __execlists_schedule_out(struct i915_request *rq,
 static inline void
 execlists_schedule_out(struct i915_request *rq)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *cur, *old;
 
 	trace_i915_request_out(rq);
@@ -1155,7 +1317,7 @@ execlists_schedule_out(struct i915_request *rq)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
-	struct intel_context *ce = rq->hw_context;
+	struct intel_context *ce = rq->context;
 	u64 desc = ce->lrc_desc;
 	u32 tail;
 
@@ -1186,17 +1348,8 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * may not be visible to the HW prior to the completion of the UC
 	 * register write and that we may begin execution from the context
 	 * before its image is complete leading to invalid PD chasing.
-	 *
-	 * Furthermore, Braswell, at least, wants a full mb to be sure that
-	 * the writes are coherent in memory (visible to the GPU) prior to
-	 * execution, and not just visible to other CPUs (as is the result of
-	 * wmb).
 	 */
-	mb();
-
-	/* Wa_1607138340:tgl */
-	if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0))
-		desc |= CTX_DESC_FORCE_RESTORE;
+	wmb();
 
 	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
 	return desc;
@@ -1224,15 +1377,14 @@ trace_ports(const struct intel_engine_execlists *execlists,
 	if (!ports[0])
 		return;
 
-	GEM_TRACE("%s: %s { %llx:%lld%s, %llx:%lld }\n",
-		  engine->name, msg,
-		  ports[0]->fence.context,
-		  ports[0]->fence.seqno,
-		  i915_request_completed(ports[0]) ? "!" :
-		  i915_request_started(ports[0]) ? "*" :
-		  "",
-		  ports[1] ? ports[1]->fence.context : 0,
-		  ports[1] ? ports[1]->fence.seqno : 0);
+	ENGINE_TRACE(engine, "%s { %llx:%lld%s, %llx:%lld }\n", msg,
+		     ports[0]->fence.context,
+		     ports[0]->fence.seqno,
+		     i915_request_completed(ports[0]) ? "!" :
+		     i915_request_started(ports[0]) ? "*" :
+		     "",
+		     ports[1] ? ports[1]->fence.context : 0,
+		     ports[1] ? ports[1]->fence.seqno : 0);
 }
 
 static __maybe_unused bool
@@ -1256,33 +1408,56 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 	}
 
 	for (port = execlists->pending; (rq = *port); port++) {
-		if (ce == rq->hw_context) {
-			GEM_TRACE_ERR("Duplicate context in pending[%zd]\n",
+		unsigned long flags;
+		bool ok = true;
+
+		GEM_BUG_ON(!kref_read(&rq->fence.refcount));
+		GEM_BUG_ON(!i915_request_is_active(rq));
+
+		if (ce == rq->context) {
+			GEM_TRACE_ERR("Dup context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			return false;
 		}
+		ce = rq->context;
 
-		ce = rq->hw_context;
-		if (i915_request_completed(rq))
+		/* Hold tightly onto the lock to prevent concurrent retires! */
+		if (!spin_trylock_irqsave(&rq->lock, flags))
 			continue;
 
-		if (i915_active_is_idle(&ce->active)) {
-			GEM_TRACE_ERR("Inactive context in pending[%zd]\n",
+		if (i915_request_completed(rq))
+			goto unlock;
+
+		if (i915_active_is_idle(&ce->active) &&
+		    !intel_context_is_barrier(ce)) {
+			GEM_TRACE_ERR("Inactive context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
 
 		if (!i915_vma_is_pinned(ce->state)) {
-			GEM_TRACE_ERR("Unpinned context in pending[%zd]\n",
+			GEM_TRACE_ERR("Unpinned context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
 
 		if (!i915_vma_is_pinned(ce->ring->vma)) {
-			GEM_TRACE_ERR("Unpinned ringbuffer in pending[%zd]\n",
+			GEM_TRACE_ERR("Unpinned ring:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
+
+unlock:
+		spin_unlock_irqrestore(&rq->lock, flags);
+		if (!ok)
+			return false;
 	}
 
 	return ce;
@@ -1327,7 +1502,7 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 static bool ctx_single_port_submission(const struct intel_context *ce)
 {
 	return (IS_ENABLED(CONFIG_DRM_I915_GVT) &&
-		i915_gem_context_force_single_submission(ce->gem_context));
+		intel_context_force_single_submission(ce));
 }
 
 static bool can_merge_ctx(const struct intel_context *prev,
@@ -1359,11 +1534,11 @@ static bool can_merge_rq(const struct i915_request *prev,
 	if (i915_request_completed(next))
 		return true;
 
-	if (unlikely((prev->flags ^ next->flags) &
-		     (I915_REQUEST_NOPREEMPT | I915_REQUEST_SENTINEL)))
+	if (unlikely((prev->fence.flags ^ next->fence.flags) &
+		     (I915_FENCE_FLAG_NOPREEMPT | I915_FENCE_FLAG_SENTINEL)))
 		return false;
 
-	if (!can_merge_ctx(prev->hw_context, next->hw_context))
+	if (!can_merge_ctx(prev->context, next->context))
 		return false;
 
 	return true;
@@ -1372,7 +1547,7 @@ static bool can_merge_rq(const struct i915_request *prev,
 static void virtual_update_register_offsets(u32 *regs,
 					    struct intel_engine_cs *engine)
 {
-	set_offsets(regs, reg_offsets(engine), engine);
+	set_offsets(regs, reg_offsets(engine), engine, false);
 }
 
 static bool virtual_matches(const struct virtual_engine *ve,
@@ -1411,7 +1586,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 	if (!list_empty(&ve->context.signal_link)) {
 		list_move_tail(&ve->context.signal_link,
 			       &engine->breadcrumbs.signalers);
-		intel_engine_queue_breadcrumbs(engine);
+		intel_engine_signal_breadcrumbs(engine);
 	}
 	spin_unlock(&old->breadcrumbs.irq_lock);
 }
@@ -1519,7 +1694,7 @@ active_timeslice(const struct intel_engine_cs *engine)
 {
 	const struct i915_request *rq = *engine->execlists.active;
 
-	if (i915_request_completed(rq))
+	if (!rq || i915_request_completed(rq))
 		return 0;
 
 	if (engine->execlists.switch_priority_hint < effective_prio(rq))
@@ -1550,7 +1725,7 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine)
 		return 0;
 
 	/* Force a fast reset for terminated contexts (ignoring sysfs!) */
-	if (unlikely(i915_gem_context_is_banned(rq->gem_context)))
+	if (unlikely(intel_context_is_banned(rq->context)))
 		return 1;
 
 	return READ_ONCE(engine->props.preempt_timeout_ms);
@@ -1565,6 +1740,11 @@ static void set_preempt_timeout(struct intel_engine_cs *engine)
 		     active_preempt_timeout(engine));
 }
 
+static inline void clear_ports(struct i915_request **ports, int count)
+{
+	memset_p((void **)ports, NULL, count);
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1627,12 +1807,12 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	last = last_active(execlists);
 	if (last) {
 		if (need_preempt(engine, last, rb)) {
-			GEM_TRACE("%s: preempting last=%llx:%lld, prio=%d, hint=%d\n",
-				  engine->name,
-				  last->fence.context,
-				  last->fence.seqno,
-				  last->sched.attr.priority,
-				  execlists->queue_priority_hint);
+			ENGINE_TRACE(engine,
+				     "preempting last=%llx:%lld, prio=%d, hint=%d\n",
+				     last->fence.context,
+				     last->fence.seqno,
+				     last->sched.attr.priority,
+				     execlists->queue_priority_hint);
 			record_preemption(execlists);
 
 			/*
@@ -1658,16 +1838,16 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * tendency to ignore us rewinding the TAIL to the
 			 * end of an earlier request.
 			 */
-			last->hw_context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+			last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
 			   timer_expired(&engine->execlists.timer)) {
-			GEM_TRACE("%s: expired last=%llx:%lld, prio=%d, hint=%d\n",
-				  engine->name,
-				  last->fence.context,
-				  last->fence.seqno,
-				  last->sched.attr.priority,
-				  execlists->queue_priority_hint);
+			ENGINE_TRACE(engine,
+				     "expired last=%llx:%lld, prio=%d, hint=%d\n",
+				     last->fence.context,
+				     last->fence.seqno,
+				     last->sched.attr.priority,
+				     execlists->queue_priority_hint);
 
 			ring_set_paused(engine, 1);
 			defer_active(engine);
@@ -1730,7 +1910,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 		GEM_BUG_ON(rq != ve->request);
 		GEM_BUG_ON(rq->engine != &ve->base);
-		GEM_BUG_ON(rq->hw_context != &ve->context);
+		GEM_BUG_ON(rq->context != &ve->context);
 
 		if (rq_prio(rq) >= queue_prio(execlists)) {
 			if (!virtual_matches(ve, rq, engine)) {
@@ -1744,14 +1924,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				return; /* leave this for another */
 			}
 
-			GEM_TRACE("%s: virtual rq=%llx:%lld%s, new engine? %s\n",
-				  engine->name,
-				  rq->fence.context,
-				  rq->fence.seqno,
-				  i915_request_completed(rq) ? "!" :
-				  i915_request_started(rq) ? "*" :
-				  "",
-				  yesno(engine != ve->siblings[0]));
+			ENGINE_TRACE(engine,
+				     "virtual rq=%llx:%lld%s, new engine? %s\n",
+				     rq->fence.context,
+				     rq->fence.seqno,
+				     i915_request_completed(rq) ? "!" :
+				     i915_request_started(rq) ? "*" :
+				     "",
+				     yesno(engine != ve->siblings[0]));
 
 			ve->request = NULL;
 			ve->base.execlists.queue_priority_hint = INT_MIN;
@@ -1849,7 +2029,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * same LRCA, i.e. we must submit 2 different
 				 * contexts if we submit 2 ELSP.
 				 */
-				if (last->hw_context == rq->hw_context)
+				if (last->context == rq->context)
 					goto done;
 
 				if (i915_request_has_sentinel(last))
@@ -1862,8 +2042,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * the same context (even though a different
 				 * request) to the second port.
 				 */
-				if (ctx_single_port_submission(last->hw_context) ||
-				    ctx_single_port_submission(rq->hw_context))
+				if (ctx_single_port_submission(last->context) ||
+				    ctx_single_port_submission(rq->context))
 					goto done;
 
 				merge = false;
@@ -1877,8 +2057,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				}
 
 				GEM_BUG_ON(last &&
-					   !can_merge_ctx(last->hw_context,
-							  rq->hw_context));
+					   !can_merge_ctx(last->context,
+							  rq->context));
 
 				submit = true;
 				last = rq;
@@ -1907,9 +2087,6 @@ done:
 	 * interrupt for secondary ports).
 	 */
 	execlists->queue_priority_hint = queue_prio(execlists);
-	GEM_TRACE("%s: queue_priority_hint:%d, submit:%s\n",
-		  engine->name, execlists->queue_priority_hint,
-		  yesno(submit));
 
 	if (submit) {
 		*port = execlists_schedule_in(last, port - execlists->pending);
@@ -1928,10 +2105,9 @@ done:
 
 			goto skip_submit;
 		}
+		clear_ports(port + 1, last_port - port);
 
-		memset(port + 1, 0, (last_port - port) * sizeof(*port));
 		execlists_submit_ports(engine);
-
 		set_preempt_timeout(engine);
 	} else {
 skip_submit:
@@ -1946,13 +2122,14 @@ cancel_port_requests(struct intel_engine_execlists * const execlists)
 
 	for (port = execlists->pending; *port; port++)
 		execlists_schedule_out(*port);
-	memset(execlists->pending, 0, sizeof(execlists->pending));
+	clear_ports(execlists->pending, ARRAY_SIZE(execlists->pending));
 
 	/* Mark the end of active before we overwrite *active */
 	for (port = xchg(&execlists->active, execlists->pending); *port; port++)
 		execlists_schedule_out(*port);
-	WRITE_ONCE(execlists->active,
-		   memset(execlists->inflight, 0, sizeof(execlists->inflight)));
+	clear_ports(execlists->inflight, ARRAY_SIZE(execlists->inflight));
+
+	WRITE_ONCE(execlists->active, execlists->inflight);
 }
 
 static inline void
@@ -2058,7 +2235,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	 */
 	head = execlists->csb_head;
 	tail = READ_ONCE(*execlists->csb_write);
-	GEM_TRACE("%s cs-irq head=%d, tail=%d\n", engine->name, head, tail);
+	ENGINE_TRACE(engine, "cs-irq head=%d, tail=%d\n", head, tail);
 	if (unlikely(head == tail))
 		return;
 
@@ -2096,9 +2273,8 @@ static void process_csb(struct intel_engine_cs *engine)
 		 * status notifier.
 		 */
 
-		GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x\n",
-			  engine->name, head,
-			  buf[2 * head + 0], buf[2 * head + 1]);
+		ENGINE_TRACE(engine, "csb[%d]: status=0x%08x:0x%08x\n",
+			     head, buf[2 * head + 0], buf[2 * head + 1]);
 
 		if (INTEL_GEN(engine->i915) >= 12)
 			promote = gen12_csb_parse(execlists, buf + 2 * head);
@@ -2109,7 +2285,6 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			/* Point active to the new ELSP; prevent overwriting */
 			WRITE_ONCE(execlists->active, execlists->pending);
-			set_timeslice(engine);
 
 			if (!inject_preempt_hang(execlists))
 				ring_set_paused(engine, 0);
@@ -2150,6 +2325,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	} while (head != tail);
 
 	execlists->csb_head = head;
+	set_timeslice(engine);
 
 	/*
 	 * Gen11 has proven to fail wrt global observation point between
@@ -2189,10 +2365,9 @@ static noinline void preempt_reset(struct intel_engine_cs *engine)
 	/* Mark this tasklet as disabled to avoid waiting for it to complete */
 	tasklet_disable_nosync(&engine->execlists.tasklet);
 
-	GEM_TRACE("%s: preempt timeout %lu+%ums\n",
-		  engine->name,
-		  READ_ONCE(engine->props.preempt_timeout_ms),
-		  jiffies_to_msecs(jiffies - engine->execlists.preempt.expires));
+	ENGINE_TRACE(engine, "preempt timeout %lu+%ums\n",
+		     READ_ONCE(engine->props.preempt_timeout_ms),
+		     jiffies_to_msecs(jiffies - engine->execlists.preempt.expires));
 	intel_engine_reset(engine, "preemption time out");
 
 	tasklet_enable(&engine->execlists.tasklet);
@@ -2333,7 +2508,7 @@ set_redzone(void *vaddr, const struct intel_engine_cs *engine)
 
 	vaddr += engine->context_size;
 
-	memset(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE);
+	memset(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE);
 }
 
 static void
@@ -2344,7 +2519,7 @@ check_redzone(const void *vaddr, const struct intel_engine_cs *engine)
 
 	vaddr += engine->context_size;
 
-	if (memchr_inv(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE))
+	if (memchr_inv(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE))
 		dev_err_once(engine->i915->drm.dev,
 			     "%s context redzone overwritten!\n",
 			     engine->name);
@@ -2369,7 +2544,7 @@ __execlists_update_reg_state(const struct intel_context *ce,
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
 
-	regs[CTX_RING_BUFFER_START] = i915_ggtt_offset(ring->vma);
+	regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
 	regs[CTX_RING_HEAD] = ring->head;
 	regs[CTX_RING_TAIL] = ring->tail;
 
@@ -2387,33 +2562,21 @@ __execlists_context_pin(struct intel_context *ce,
 			struct intel_engine_cs *engine)
 {
 	void *vaddr;
-	int ret;
 
 	GEM_BUG_ON(!ce->state);
-
-	ret = intel_context_active_acquire(ce);
-	if (ret)
-		goto err;
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	vaddr = i915_gem_object_pin_map(ce->state->obj,
 					i915_coherent_map_type(engine->i915) |
 					I915_MAP_OVERRIDE);
-	if (IS_ERR(vaddr)) {
-		ret = PTR_ERR(vaddr);
-		goto unpin_active;
-	}
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
 
-	ce->lrc_desc = lrc_descriptor(ce, engine);
+	ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	__execlists_update_reg_state(ce, engine);
 
 	return 0;
-
-unpin_active:
-	intel_context_active_release(ce);
-err:
-	return ret;
 }
 
 static int execlists_context_pin(struct intel_context *ce)
@@ -2428,6 +2591,9 @@ static int execlists_context_alloc(struct intel_context *ce)
 
 static void execlists_context_reset(struct intel_context *ce)
 {
+	CE_TRACE(ce, "reset\n");
+	GEM_BUG_ON(!intel_context_is_pinned(ce));
+
 	/*
 	 * Because we emit WA_TAIL_DWORDS there may be a disparity
 	 * between our bookkeeping in ce->ring->head and ce->ring->tail and
@@ -2444,8 +2610,14 @@ static void execlists_context_reset(struct intel_context *ce)
 	 * So to avoid that we reset the context images upon resume. For
 	 * simplicity, we just zero everything out.
 	 */
-	intel_ring_reset(ce->ring, 0);
+	intel_ring_reset(ce->ring, ce->ring->emit);
+
+	/* Scrub away the garbage */
+	execlists_init_reg_state(ce->lrc_reg_state,
+				 ce, ce->engine, ce->ring, true);
 	__execlists_update_reg_state(ce, ce->engine);
+
+	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 }
 
 static const struct intel_context_ops execlists_context_ops = {
@@ -2497,7 +2669,7 @@ static int execlists_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!intel_context_is_pinned(request->hw_context));
+	GEM_BUG_ON(!intel_context_is_pinned(request->context));
 
 	/*
 	 * Flush enough space to reduce the likelihood of waiting after
@@ -2867,6 +3039,8 @@ static void enable_execlists(struct intel_engine_cs *engine)
 			RING_HWS_PGA,
 			i915_ggtt_offset(engine->status_page.vma));
 	ENGINE_POSTING_READ(engine, RING_HWS_PGA);
+
+	engine->context_tag = 0;
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)
@@ -2906,8 +3080,8 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	unsigned long flags;
 
-	GEM_TRACE("%s: depth<-%d\n", engine->name,
-		  atomic_read(&execlists->tasklet.count));
+	ENGINE_TRACE(engine, "depth<-%d\n",
+		     atomic_read(&execlists->tasklet.count));
 
 	/*
 	 * Prevent request submission to the hardware until we have
@@ -2960,26 +3134,20 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 	WRITE_ONCE(*execlists->csb_write, reset_value);
 	wmb(); /* Make sure this is visible to HW (paranoia?) */
 
+	/*
+	 * Sometimes Icelake forgets to reset its pointers on a GPU reset.
+	 * Bludgeon them with a mmio update to be sure.
+	 */
+	ENGINE_WRITE(engine, RING_CONTEXT_STATUS_PTR,
+		     reset_value << 8 | reset_value);
+	ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR);
+
 	invalidate_csb_entries(&execlists->csb_status[0],
 			       &execlists->csb_status[reset_value]);
 }
 
-static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
-{
-	if (INTEL_GEN(engine->i915) >= 12)
-		return 0x60;
-	else if (INTEL_GEN(engine->i915) >= 9)
-		return 0x54;
-	else if (engine->class == RENDER_CLASS)
-		return 0x58;
-	else
-		return -1;
-}
-
-static void __execlists_reset_reg_state(const struct intel_context *ce,
-					const struct intel_engine_cs *engine)
+static void __reset_stop_ring(u32 *regs, const struct intel_engine_cs *engine)
 {
-	u32 *regs = ce->lrc_reg_state;
 	int x;
 
 	x = lrc_ring_mi_mode(engine);
@@ -2989,6 +3157,14 @@ static void __execlists_reset_reg_state(const struct intel_context *ce,
 	}
 }
 
+static void __execlists_reset_reg_state(const struct intel_context *ce,
+					const struct intel_engine_cs *engine)
+{
+	u32 *regs = ce->lrc_reg_state;
+
+	__reset_stop_ring(regs, engine);
+}
+
 static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -3016,7 +3192,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	/* We still have requests in-flight; the engine should be active */
 	GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
 
-	ce = rq->hw_context;
+	ce = rq->context;
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	if (i915_request_completed(rq)) {
@@ -3073,8 +3249,8 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	restore_default_state(ce, engine);
 
 out_replay:
-	GEM_TRACE("%s replay {head:%04x, tail:%04x}\n",
-		  engine->name, ce->ring->head, ce->ring->tail);
+	ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n",
+		     ce->ring->head, ce->ring->tail);
 	intel_ring_update_space(ce->ring);
 	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine);
@@ -3086,11 +3262,11 @@ unwind:
 	__unwind_incomplete_requests(engine);
 }
 
-static void execlists_reset(struct intel_engine_cs *engine, bool stalled)
+static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	spin_lock_irqsave(&engine->active.lock, flags);
 
@@ -3104,14 +3280,14 @@ static void nop_submission_tasklet(unsigned long data)
 	/* The driver is wedged; don't process any more events. */
 }
 
-static void execlists_cancel_requests(struct intel_engine_cs *engine)
+static void execlists_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq, *rn;
 	struct rb_node *rb;
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * Before we call engine->cancel_requests(), we should have exclusive
@@ -3198,13 +3374,13 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	if (__tasklet_enable(&execlists->tasklet))
 		/* And kick in case we missed a new request submission. */
 		tasklet_hi_schedule(&execlists->tasklet);
-	GEM_TRACE("%s: depth->%d\n", engine->name,
-		  atomic_read(&execlists->tasklet.count));
+	ENGINE_TRACE(engine, "depth->%d\n",
+		     atomic_read(&execlists->tasklet.count));
 }
 
-static int gen8_emit_bb_start(struct i915_request *rq,
-			      u64 offset, u32 len,
-			      const unsigned int flags)
+static int gen8_emit_bb_start_noarb(struct i915_request *rq,
+				    u64 offset, u32 len,
+				    const unsigned int flags)
 {
 	u32 *cs;
 
@@ -3238,7 +3414,7 @@ static int gen8_emit_bb_start(struct i915_request *rq,
 	return 0;
 }
 
-static int gen9_emit_bb_start(struct i915_request *rq,
+static int gen8_emit_bb_start(struct i915_request *rq,
 			      u64 offset, u32 len,
 			      const unsigned int flags)
 {
@@ -3693,12 +3869,12 @@ static void execlists_park(struct intel_engine_cs *engine)
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = execlists_submit_request;
-	engine->cancel_requests = execlists_cancel_requests;
 	engine->schedule = i915_schedule;
 	engine->execlists.tasklet.func = execlists_submission_tasklet;
 
 	engine->reset.prepare = execlists_reset_prepare;
-	engine->reset.reset = execlists_reset;
+	engine->reset.rewind = execlists_reset_rewind;
+	engine->reset.cancel = execlists_reset_cancel;
 	engine->reset.finish = execlists_reset_finish;
 
 	engine->park = execlists_park;
@@ -3713,13 +3889,27 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 
 	if (INTEL_GEN(engine->i915) >= 12)
 		engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
+
+	if (intel_engine_has_preemption(engine))
+		engine->emit_bb_start = gen8_emit_bb_start;
+	else
+		engine->emit_bb_start = gen8_emit_bb_start_noarb;
 }
 
-static void execlists_destroy(struct intel_engine_cs *engine)
+static void execlists_shutdown(struct intel_engine_cs *engine)
 {
+	/* Synchronise with residual timers and any softirq they raise */
+	del_timer_sync(&engine->execlists.timer);
+	del_timer_sync(&engine->execlists.preempt);
+	tasklet_kill(&engine->execlists.tasklet);
+}
+
+static void execlists_release(struct intel_engine_cs *engine)
+{
+	execlists_shutdown(engine);
+
 	intel_engine_cleanup_common(engine);
 	lrc_destroy_wa_ctx(engine);
-	kfree(engine);
 }
 
 static void
@@ -3727,13 +3917,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 {
 	/* Default vfuncs which can be overriden by each engine. */
 
-	engine->destroy = execlists_destroy;
 	engine->resume = execlists_resume;
 
-	engine->reset.prepare = execlists_reset_prepare;
-	engine->reset.reset = execlists_reset;
-	engine->reset.finish = execlists_reset_finish;
-
 	engine->cops = &execlists_context_ops;
 	engine->request_alloc = execlists_request_alloc;
 
@@ -3756,10 +3941,6 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 		 * until a more refined solution exists.
 		 */
 	}
-	if (IS_GEN(engine->i915, 8))
-		engine->emit_bb_start = gen8_emit_bb_start;
-	else
-		engine->emit_bb_start = gen9_emit_bb_start;
 }
 
 static inline void
@@ -3803,6 +3984,11 @@ static void rcs_submission_override(struct intel_engine_cs *engine)
 
 int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 {
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_uncore *uncore = engine->uncore;
+	u32 base = engine->mmio_base;
+
 	tasklet_init(&engine->execlists.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
 	timer_setup(&engine->execlists.timer, execlists_timeslice, 0);
@@ -3814,21 +4000,6 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	if (engine->class == RENDER_CLASS)
 		rcs_submission_override(engine);
 
-	return 0;
-}
-
-int intel_execlists_submission_init(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct drm_i915_private *i915 = engine->i915;
-	struct intel_uncore *uncore = engine->uncore;
-	u32 base = engine->mmio_base;
-	int ret;
-
-	ret = intel_engine_init_common(engine);
-	if (ret)
-		return ret;
-
 	if (intel_init_workaround_bb(engine))
 		/*
 		 * We continue even if we fail to initialize WA batch
@@ -3860,6 +4031,9 @@ int intel_execlists_submission_init(struct intel_engine_cs *engine)
 
 	reset_csb_pointers(engine);
 
+	/* Finally, take ownership and responsibility for cleanup! */
+	engine->release = execlists_release;
+
 	return 0;
 }
 
@@ -3899,18 +4073,21 @@ static u32 intel_lr_indirect_ctx_offset(const struct intel_engine_cs *engine)
 
 static void init_common_reg_state(u32 * const regs,
 				  const struct intel_engine_cs *engine,
-				  const struct intel_ring *ring)
+				  const struct intel_ring *ring,
+				  bool inhibit)
 {
-	regs[CTX_CONTEXT_CONTROL] =
-		_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
-		_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
+	u32 ctl;
+
+	ctl = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
+	ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
+	if (inhibit)
+		ctl |= CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT;
 	if (INTEL_GEN(engine->i915) < 11)
-		regs[CTX_CONTEXT_CONTROL] |=
-			_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
-					    CTX_CTRL_RS_CTX_ENABLE);
+		ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
+					   CTX_CTRL_RS_CTX_ENABLE);
+	regs[CTX_CONTEXT_CONTROL] = ctl;
 
-	regs[CTX_RING_BUFFER_CONTROL] = RING_CTL_SIZE(ring->size) | RING_VALID;
-	regs[CTX_BB_STATE] = RING_BB_PPGTT;
+	regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
 }
 
 static void init_wa_bb_reg_state(u32 * const regs,
@@ -3966,7 +4143,7 @@ static void execlists_init_reg_state(u32 *regs,
 				     const struct intel_context *ce,
 				     const struct intel_engine_cs *engine,
 				     const struct intel_ring *ring,
-				     bool close)
+				     bool inhibit)
 {
 	/*
 	 * A context is actually a big batch buffer with several
@@ -3978,21 +4155,17 @@ static void execlists_init_reg_state(u32 *regs,
 	 *
 	 * Must keep consistent with virtual_update_register_offsets().
 	 */
-	u32 *bbe = set_offsets(regs, reg_offsets(engine), engine);
-
-	if (close) { /* Close the batch; used mainly by live_lrc_layout() */
-		*bbe = MI_BATCH_BUFFER_END;
-		if (INTEL_GEN(engine->i915) >= 10)
-			*bbe |= BIT(0);
-	}
+	set_offsets(regs, reg_offsets(engine), engine, inhibit);
 
-	init_common_reg_state(regs, engine, ring);
+	init_common_reg_state(regs, engine, ring, inhibit);
 	init_ppgtt_reg_state(regs, vm_alias(ce->vm));
 
 	init_wa_bb_reg_state(regs, engine,
 			     INTEL_GEN(engine->i915) >= 12 ?
 			     GEN12_CTX_BB_PER_CTX_PTR :
 			     CTX_BB_PER_CTX_PTR);
+
+	__reset_stop_ring(regs, engine);
 }
 
 static int
@@ -4003,7 +4176,6 @@ populate_lr_context(struct intel_context *ce,
 {
 	bool inhibit = true;
 	void *vaddr;
-	u32 *regs;
 	int ret;
 
 	vaddr = i915_gem_object_pin_map(ctx_obj, I915_MAP_WB);
@@ -4027,16 +4199,14 @@ populate_lr_context(struct intel_context *ce,
 
 		memcpy(vaddr, defaults, engine->context_size);
 		i915_gem_object_unpin_map(engine->default_state);
+		__set_bit(CONTEXT_VALID_BIT, &ce->flags);
 		inhibit = false;
 	}
 
 	/* The second page of the context object contains some fields which must
 	 * be set up prior to the first execution. */
-	regs = vaddr + LRC_STATE_PN * PAGE_SIZE;
-	execlists_init_reg_state(regs, ce, engine, ring, inhibit);
-	if (inhibit)
-		regs[CTX_CONTEXT_CONTROL] |=
-			_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
+	execlists_init_reg_state(vaddr + LRC_STATE_PN * PAGE_SIZE,
+				 ce, engine, ring, inhibit);
 
 	ret = 0;
 err_unpin_ctx:
@@ -4174,6 +4344,13 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve)
 						ve->siblings[0]);
 }
 
+static int virtual_context_alloc(struct intel_context *ce)
+{
+	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
+
+	return __execlists_context_alloc(ce, ve->siblings[0]);
+}
+
 static int virtual_context_pin(struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
@@ -4211,6 +4388,8 @@ static void virtual_context_exit(struct intel_context *ce)
 }
 
 static const struct intel_context_ops virtual_context_ops = {
+	.alloc = virtual_context_alloc,
+
 	.pin = virtual_context_pin,
 	.unpin = execlists_context_unpin,
 
@@ -4237,10 +4416,9 @@ static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve)
 		mask = ve->siblings[0]->mask;
 	}
 
-	GEM_TRACE("%s: rq=%llx:%lld, mask=%x, prio=%d\n",
-		  ve->base.name,
-		  rq->fence.context, rq->fence.seqno,
-		  mask, ve->base.execlists.queue_priority_hint);
+	ENGINE_TRACE(&ve->base, "rq=%llx:%lld, mask=%x, prio=%d\n",
+		     rq->fence.context, rq->fence.seqno,
+		     mask, ve->base.execlists.queue_priority_hint);
 
 	return mask;
 }
@@ -4331,10 +4509,9 @@ static void virtual_submit_request(struct i915_request *rq)
 	struct i915_request *old;
 	unsigned long flags;
 
-	GEM_TRACE("%s: rq=%llx:%lld\n",
-		  ve->base.name,
-		  rq->fence.context,
-		  rq->fence.seqno);
+	ENGINE_TRACE(&ve->base, "rq=%llx:%lld\n",
+		     rq->fence.context,
+		     rq->fence.seqno);
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
@@ -4402,8 +4579,7 @@ virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
 }
 
 struct intel_context *
-intel_execlists_create_virtual(struct i915_gem_context *ctx,
-			       struct intel_engine_cs **siblings,
+intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 			       unsigned int count)
 {
 	struct virtual_engine *ve;
@@ -4414,13 +4590,13 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 		return ERR_PTR(-EINVAL);
 
 	if (count == 1)
-		return intel_context_create(ctx, siblings[0]);
+		return intel_context_create(siblings[0]);
 
 	ve = kzalloc(struct_size(ve, siblings, count), GFP_KERNEL);
 	if (!ve)
 		return ERR_PTR(-ENOMEM);
 
-	ve->base.i915 = ctx->i915;
+	ve->base.i915 = siblings[0]->i915;
 	ve->base.gt = siblings[0]->gt;
 	ve->base.uncore = siblings[0]->uncore;
 	ve->base.id = -1;
@@ -4449,7 +4625,6 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 	intel_engine_init_breadcrumbs(&ve->base);
-
 	intel_engine_init_execlists(&ve->base);
 
 	ve->base.cops = &virtual_context_ops;
@@ -4465,7 +4640,7 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 		     virtual_submission_tasklet,
 		     (unsigned long)ve);
 
-	intel_context_init(&ve->context, ctx, &ve->base);
+	intel_context_init(&ve->context, &ve->base);
 
 	for (n = 0; n < count; n++) {
 		struct intel_engine_cs *sibling = siblings[n];
@@ -4532,12 +4707,6 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 
 	ve->base.flags |= I915_ENGINE_IS_VIRTUAL;
 
-	err = __execlists_context_alloc(&ve->context, siblings[0]);
-	if (err)
-		goto err_put;
-
-	__set_bit(CONTEXT_ALLOC_BIT, &ve->context.flags);
-
 	return &ve->context;
 
 err_put:
@@ -4546,14 +4715,12 @@ err_put:
 }
 
 struct intel_context *
-intel_execlists_clone_virtual(struct i915_gem_context *ctx,
-			      struct intel_engine_cs *src)
+intel_execlists_clone_virtual(struct intel_engine_cs *src)
 {
 	struct virtual_engine *se = to_virtual_engine(src);
 	struct intel_context *dst;
 
-	dst = intel_execlists_create_virtual(ctx,
-					     se->siblings,
+	dst = intel_execlists_create_virtual(se->siblings,
 					     se->num_siblings);
 	if (IS_ERR(dst))
 		return dst;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 04511d8ebdc1..dfbc214e14f5 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -83,7 +83,6 @@ enum {
 void intel_logical_ring_cleanup(struct intel_engine_cs *engine);
 
 int intel_execlists_submission_setup(struct intel_engine_cs *engine);
-int intel_execlists_submission_init(struct intel_engine_cs *engine);
 
 /* Logical Ring Contexts */
 /* At the start of the context image is its per-process HWS page */
@@ -111,13 +110,11 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 				   unsigned int max);
 
 struct intel_context *
-intel_execlists_create_virtual(struct i915_gem_context *ctx,
-			       struct intel_engine_cs **siblings,
+intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 			       unsigned int count);
 
 struct intel_context *
-intel_execlists_clone_virtual(struct i915_gem_context *ctx,
-			      struct intel_engine_cs *src);
+intel_execlists_clone_virtual(struct intel_engine_cs *src);
 
 int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine,
 				     const struct intel_engine_cs *master,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index 06ab0276e10e..08a3be65f700 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -13,8 +13,8 @@
 #define CTX_CONTEXT_CONTROL		(0x02 + 1)
 #define CTX_RING_HEAD			(0x04 + 1)
 #define CTX_RING_TAIL			(0x06 + 1)
-#define CTX_RING_BUFFER_START		(0x08 + 1)
-#define CTX_RING_BUFFER_CONTROL		(0x0a + 1)
+#define CTX_RING_START			(0x08 + 1)
+#define CTX_RING_CTL			(0x0a + 1)
 #define CTX_BB_STATE			(0x10 + 1)
 #define CTX_BB_PER_CTX_PTR		(0x18 + 1)
 #define CTX_PDP3_UDW			(0x24 + 1)
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 2b977991b785..eeef90b55c64 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -127,7 +127,7 @@ struct drm_i915_mocs_table {
 		   LE_0_PAGETABLE | LE_TC_2_LLC_ELLC | LE_LRUM(3), \
 		   L3_3_WB)
 
-static const struct drm_i915_mocs_entry skylake_mocs_table[] = {
+static const struct drm_i915_mocs_entry skl_mocs_table[] = {
 	GEN9_MOCS_ENTRIES,
 	MOCS_ENTRY(I915_MOCS_CACHED,
 		   LE_3_WB | LE_TC_2_LLC_ELLC | LE_LRUM(3),
@@ -233,7 +233,7 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
 		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), \
 		   L3_1_UC)
 
-static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = {
+static const struct drm_i915_mocs_entry tgl_mocs_table[] = {
 	/* Base - Error (Reserved for Non-Use) */
 	MOCS_ENTRY(0, 0x0, 0x0),
 	/* Base - Reserved */
@@ -267,7 +267,7 @@ static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = {
 		   L3_3_WB),
 };
 
-static const struct drm_i915_mocs_entry icelake_mocs_table[] = {
+static const struct drm_i915_mocs_entry icl_mocs_table[] = {
 	/* Base - Uncached (Deprecated) */
 	MOCS_ENTRY(I915_MOCS_UNCACHED,
 		   LE_1_UC | LE_TC_1_LLC,
@@ -283,65 +283,42 @@ static const struct drm_i915_mocs_entry icelake_mocs_table[] = {
 static bool get_mocs_settings(const struct drm_i915_private *i915,
 			      struct drm_i915_mocs_table *table)
 {
-	bool result = false;
-
 	if (INTEL_GEN(i915) >= 12) {
-		table->size  = ARRAY_SIZE(tigerlake_mocs_table);
-		table->table = tigerlake_mocs_table;
+		table->size  = ARRAY_SIZE(tgl_mocs_table);
+		table->table = tgl_mocs_table;
 		table->n_entries = GEN11_NUM_MOCS_ENTRIES;
-		result = true;
 	} else if (IS_GEN(i915, 11)) {
-		table->size  = ARRAY_SIZE(icelake_mocs_table);
-		table->table = icelake_mocs_table;
+		table->size  = ARRAY_SIZE(icl_mocs_table);
+		table->table = icl_mocs_table;
 		table->n_entries = GEN11_NUM_MOCS_ENTRIES;
-		result = true;
 	} else if (IS_GEN9_BC(i915) || IS_CANNONLAKE(i915)) {
-		table->size  = ARRAY_SIZE(skylake_mocs_table);
+		table->size  = ARRAY_SIZE(skl_mocs_table);
 		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
-		table->table = skylake_mocs_table;
-		result = true;
+		table->table = skl_mocs_table;
 	} else if (IS_GEN9_LP(i915)) {
 		table->size  = ARRAY_SIZE(broxton_mocs_table);
 		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
 		table->table = broxton_mocs_table;
-		result = true;
 	} else {
 		WARN_ONCE(INTEL_GEN(i915) >= 9,
 			  "Platform that should have a MOCS table does not.\n");
+		return false;
 	}
 
+	if (GEM_DEBUG_WARN_ON(table->size > table->n_entries))
+		return false;
+
 	/* WaDisableSkipCaching:skl,bxt,kbl,glk */
 	if (IS_GEN(i915, 9)) {
 		int i;
 
 		for (i = 0; i < table->size; i++)
-			if (WARN_ON(table->table[i].l3cc_value &
-				    (L3_ESC(1) | L3_SCC(0x7))))
+			if (GEM_DEBUG_WARN_ON(table->table[i].l3cc_value &
+					      (L3_ESC(1) | L3_SCC(0x7))))
 				return false;
 	}
 
-	return result;
-}
-
-static i915_reg_t mocs_register(const struct intel_engine_cs *engine, int index)
-{
-	switch (engine->id) {
-	case RCS0:
-		return GEN9_GFX_MOCS(index);
-	case VCS0:
-		return GEN9_MFX0_MOCS(index);
-	case BCS0:
-		return GEN9_BLT_MOCS(index);
-	case VECS0:
-		return GEN9_VEBOX_MOCS(index);
-	case VCS1:
-		return GEN9_MFX1_MOCS(index);
-	case VCS2:
-		return GEN11_MFX2_MOCS(index);
-	default:
-		MISSING_CASE(engine->id);
-		return INVALID_MMIO_REG;
-	}
+	return true;
 }
 
 /*
@@ -351,29 +328,47 @@ static i915_reg_t mocs_register(const struct intel_engine_cs *engine, int index)
 static u32 get_entry_control(const struct drm_i915_mocs_table *table,
 			     unsigned int index)
 {
-	if (table->table[index].used)
+	if (index < table->size && table->table[index].used)
 		return table->table[index].control_value;
 
 	return table->table[I915_MOCS_PTE].control_value;
 }
 
-static void init_mocs_table(struct intel_engine_cs *engine,
-			    const struct drm_i915_mocs_table *table)
+#define for_each_mocs(mocs, t, i) \
+	for (i = 0; \
+	     i < (t)->n_entries ? (mocs = get_entry_control((t), i)), 1 : 0;\
+	     i++)
+
+static void __init_mocs_table(struct intel_uncore *uncore,
+			      const struct drm_i915_mocs_table *table,
+			      u32 addr)
 {
-	struct intel_uncore *uncore = engine->uncore;
-	u32 unused_value = table->table[I915_MOCS_PTE].control_value;
 	unsigned int i;
+	u32 mocs;
+
+	for_each_mocs(mocs, table, i)
+		intel_uncore_write_fw(uncore, _MMIO(addr + i * 4), mocs);
+}
 
-	for (i = 0; i < table->size; i++)
-		intel_uncore_write_fw(uncore,
-				      mocs_register(engine, i),
-				      get_entry_control(table, i));
+static u32 mocs_offset(const struct intel_engine_cs *engine)
+{
+	static const u32 offset[] = {
+		[RCS0]  =  __GEN9_RCS0_MOCS0,
+		[VCS0]  =  __GEN9_VCS0_MOCS0,
+		[VCS1]  =  __GEN9_VCS1_MOCS0,
+		[VECS0] =  __GEN9_VECS0_MOCS0,
+		[BCS0]  =  __GEN9_BCS0_MOCS0,
+		[VCS2]  = __GEN11_VCS2_MOCS0,
+	};
+
+	GEM_BUG_ON(engine->id >= ARRAY_SIZE(offset));
+	return offset[engine->id];
+}
 
-	/* All remaining entries are unused */
-	for (; i < table->n_entries; i++)
-		intel_uncore_write_fw(uncore,
-				      mocs_register(engine, i),
-				      unused_value);
+static void init_mocs_table(struct intel_engine_cs *engine,
+			    const struct drm_i915_mocs_table *table)
+{
+	__init_mocs_table(engine->uncore, table, mocs_offset(engine));
 }
 
 /*
@@ -383,51 +378,34 @@ static void init_mocs_table(struct intel_engine_cs *engine,
 static u16 get_entry_l3cc(const struct drm_i915_mocs_table *table,
 			  unsigned int index)
 {
-	if (table->table[index].used)
+	if (index < table->size && table->table[index].used)
 		return table->table[index].l3cc_value;
 
 	return table->table[I915_MOCS_PTE].l3cc_value;
 }
 
-static inline u32 l3cc_combine(const struct drm_i915_mocs_table *table,
-			       u16 low,
-			       u16 high)
+static inline u32 l3cc_combine(u16 low, u16 high)
 {
 	return low | (u32)high << 16;
 }
 
+#define for_each_l3cc(l3cc, t, i) \
+	for (i = 0; \
+	     i < ((t)->n_entries + 1) / 2 ? \
+	     (l3cc = l3cc_combine(get_entry_l3cc((t), 2 * i), \
+				  get_entry_l3cc((t), 2 * i + 1))), 1 : \
+	     0; \
+	     i++)
+
 static void init_l3cc_table(struct intel_engine_cs *engine,
 			    const struct drm_i915_mocs_table *table)
 {
 	struct intel_uncore *uncore = engine->uncore;
-	u16 unused_value = table->table[I915_MOCS_PTE].l3cc_value;
 	unsigned int i;
+	u32 l3cc;
 
-	for (i = 0; i < table->size / 2; i++) {
-		u16 low = get_entry_l3cc(table, 2 * i);
-		u16 high = get_entry_l3cc(table, 2 * i + 1);
-
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(table, low, high));
-	}
-
-	/* Odd table size - 1 left over */
-	if (table->size & 1) {
-		u16 low = get_entry_l3cc(table, 2 * i);
-
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(table, low, unused_value));
-		i++;
-	}
-
-	/* All remaining entries are also unused */
-	for (; i < table->n_entries / 2; i++)
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(table, unused_value,
-						unused_value));
+	for_each_l3cc(l3cc, table, i)
+		intel_uncore_write_fw(uncore, GEN9_LNCFCMOCS(i), l3cc);
 }
 
 void intel_mocs_init_engine(struct intel_engine_cs *engine)
@@ -448,11 +426,14 @@ void intel_mocs_init_engine(struct intel_engine_cs *engine)
 		init_l3cc_table(engine, &table);
 }
 
-static void intel_mocs_init_global(struct intel_gt *gt)
+static u32 global_mocs_offset(void)
+{
+	return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0));
+}
+
+static void init_global_mocs(struct intel_gt *gt)
 {
-	struct intel_uncore *uncore = gt->uncore;
 	struct drm_i915_mocs_table table;
-	unsigned int index;
 
 	/*
 	 * LLC and eDRAM control values are not applicable to dgfx
@@ -460,32 +441,18 @@ static void intel_mocs_init_global(struct intel_gt *gt)
 	if (IS_DGFX(gt->i915))
 		return;
 
-	GEM_BUG_ON(!HAS_GLOBAL_MOCS_REGISTERS(gt->i915));
-
 	if (!get_mocs_settings(gt->i915, &table))
 		return;
 
-	if (GEM_DEBUG_WARN_ON(table.size > table.n_entries))
-		return;
-
-	for (index = 0; index < table.size; index++)
-		intel_uncore_write(uncore,
-				   GEN12_GLOBAL_MOCS(index),
-				   table.table[index].control_value);
-
-	/*
-	 * Ok, now set the unused entries to the invalid entry (index 0). These
-	 * entries are officially undefined and no contract for the contents and
-	 * settings is given for these entries.
-	 */
-	for (; index < table.n_entries; index++)
-		intel_uncore_write(uncore,
-				   GEN12_GLOBAL_MOCS(index),
-				   table.table[0].control_value);
+	__init_mocs_table(gt->uncore, &table, global_mocs_offset());
 }
 
 void intel_mocs_init(struct intel_gt *gt)
 {
 	if (HAS_GLOBAL_MOCS_REGISTERS(gt->i915))
-		intel_mocs_init_global(gt);
+		init_global_mocs(gt);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_mocs.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
new file mode 100644
index 000000000000..f86f7e68ce5e
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/slab.h>
+
+#include "i915_trace.h"
+#include "intel_gtt.h"
+#include "gen6_ppgtt.h"
+#include "gen8_ppgtt.h"
+
+struct i915_page_table *alloc_pt(struct i915_address_space *vm)
+{
+	struct i915_page_table *pt;
+
+	pt = kmalloc(sizeof(*pt), I915_GFP_ALLOW_FAIL);
+	if (unlikely(!pt))
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(setup_page_dma(vm, &pt->base))) {
+		kfree(pt);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	atomic_set(&pt->used, 0);
+	return pt;
+}
+
+struct i915_page_directory *__alloc_pd(size_t sz)
+{
+	struct i915_page_directory *pd;
+
+	pd = kzalloc(sz, I915_GFP_ALLOW_FAIL);
+	if (unlikely(!pd))
+		return NULL;
+
+	spin_lock_init(&pd->lock);
+	return pd;
+}
+
+struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
+{
+	struct i915_page_directory *pd;
+
+	pd = __alloc_pd(sizeof(*pd));
+	if (unlikely(!pd))
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
+		kfree(pd);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return pd;
+}
+
+void free_pd(struct i915_address_space *vm, struct i915_page_dma *pd)
+{
+	cleanup_page_dma(vm, pd);
+	kfree(pd);
+}
+
+static inline void
+write_dma_entry(struct i915_page_dma * const pdma,
+		const unsigned short idx,
+		const u64 encoded_entry)
+{
+	u64 * const vaddr = kmap_atomic(pdma->page);
+
+	vaddr[idx] = encoded_entry;
+	kunmap_atomic(vaddr);
+}
+
+void
+__set_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short idx,
+	       struct i915_page_dma * const to,
+	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level))
+{
+	/* Each thread pre-pins the pd, and we may have a thread per pde. */
+	GEM_BUG_ON(atomic_read(px_used(pd)) > NALLOC * ARRAY_SIZE(pd->entry));
+
+	atomic_inc(px_used(pd));
+	pd->entry[idx] = to;
+	write_dma_entry(px_base(pd), idx, encode(to->daddr, I915_CACHE_LLC));
+}
+
+void
+clear_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short idx,
+	       const struct i915_page_scratch * const scratch)
+{
+	GEM_BUG_ON(atomic_read(px_used(pd)) == 0);
+
+	write_dma_entry(px_base(pd), idx, scratch->encode);
+	pd->entry[idx] = NULL;
+	atomic_dec(px_used(pd));
+}
+
+bool
+release_pd_entry(struct i915_page_directory * const pd,
+		 const unsigned short idx,
+		 struct i915_page_table * const pt,
+		 const struct i915_page_scratch * const scratch)
+{
+	bool free = false;
+
+	if (atomic_add_unless(&pt->used, -1, 1))
+		return false;
+
+	spin_lock(&pd->lock);
+	if (atomic_dec_and_test(&pt->used)) {
+		clear_pd_entry(pd, idx, scratch);
+		free = true;
+	}
+	spin_unlock(&pd->lock);
+
+	return free;
+}
+
+int i915_ppgtt_init_hw(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+
+	gtt_write_workarounds(gt);
+
+	if (IS_GEN(i915, 6))
+		gen6_ppgtt_enable(gt);
+	else if (IS_GEN(i915, 7))
+		gen7_ppgtt_enable(gt);
+
+	return 0;
+}
+
+static struct i915_ppgtt *
+__ppgtt_create(struct intel_gt *gt)
+{
+	if (INTEL_GEN(gt->i915) < 8)
+		return gen6_ppgtt_create(gt);
+	else
+		return gen8_ppgtt_create(gt);
+}
+
+struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt)
+{
+	struct i915_ppgtt *ppgtt;
+
+	ppgtt = __ppgtt_create(gt);
+	if (IS_ERR(ppgtt))
+		return ppgtt;
+
+	trace_i915_ppgtt_create(&ppgtt->vm);
+
+	return ppgtt;
+}
+
+static int ppgtt_bind_vma(struct i915_vma *vma,
+			  enum i915_cache_level cache_level,
+			  u32 flags)
+{
+	u32 pte_flags;
+	int err;
+
+	if (flags & I915_VMA_ALLOC) {
+		err = vma->vm->allocate_va_range(vma->vm,
+						 vma->node.start, vma->size);
+		if (err)
+			return err;
+
+		set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
+	}
+
+	/* Applicable to VLV, and gen8+ */
+	pte_flags = 0;
+	if (i915_gem_object_is_readonly(vma->obj))
+		pte_flags |= PTE_READ_ONLY;
+
+	GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)));
+	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
+	wmb();
+
+	return 0;
+}
+
+static void ppgtt_unbind_vma(struct i915_vma *vma)
+{
+	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)))
+		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
+}
+
+int ppgtt_set_pages(struct i915_vma *vma)
+{
+	GEM_BUG_ON(vma->pages);
+
+	vma->pages = vma->obj->mm.pages;
+
+	vma->page_sizes = vma->obj->mm.page_sizes;
+
+	return 0;
+}
+
+void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+
+	ppgtt->vm.gt = gt;
+	ppgtt->vm.i915 = i915;
+	ppgtt->vm.dma = &i915->drm.pdev->dev;
+	ppgtt->vm.total = BIT_ULL(INTEL_INFO(i915)->ppgtt_size);
+
+	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
+
+	ppgtt->vm.vma_ops.bind_vma    = ppgtt_bind_vma;
+	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
+	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->vm.vma_ops.clear_pages = clear_pages;
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 700104b90163..9e303c29d6e3 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -88,21 +88,18 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 	 * do not want the enable hysteresis to less than the wakeup latency.
 	 *
 	 * igt/gem_exec_nop/sequential provides a rough estimate for the
-	 * service latency, and puts it around 10us for Broadwell (and other
-	 * big core) and around 40us for Broxton (and other low power cores).
-	 * [Note that for legacy ringbuffer submission, this is less than 1us!]
-	 * However, the wakeup latency on Broxton is closer to 100us. To be
-	 * conservative, we have to factor in a context switch on top (due
-	 * to ksoftirqd).
+	 * service latency, and puts it under 10us for Icelake, similar to
+	 * Broadwell+, To be conservative, we want to factor in a context
+	 * switch on top (due to ksoftirqd).
 	 */
-	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
-	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
+	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 60);
+	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 60);
 
 	/* 3a: Enable RC6 */
-	set(uncore, GEN6_RC_CONTROL,
-	    GEN6_RC_CTL_HW_ENABLE |
-	    GEN6_RC_CTL_RC6_ENABLE |
-	    GEN6_RC_CTL_EI_MODE(1));
+	rc6->ctl_enable =
+		GEN6_RC_CTL_HW_ENABLE |
+		GEN6_RC_CTL_RC6_ENABLE |
+		GEN6_RC_CTL_EI_MODE(1);
 
 	set(uncore, GEN9_PG_ENABLE,
 	    GEN9_RENDER_PG_ENABLE |
@@ -173,10 +170,10 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 	else
 		rc6_mode = GEN6_RC_CTL_EI_MODE(1);
 
-	set(uncore, GEN6_RC_CONTROL,
-	    GEN6_RC_CTL_HW_ENABLE |
-	    GEN6_RC_CTL_RC6_ENABLE |
-	    rc6_mode);
+	rc6->ctl_enable =
+		GEN6_RC_CTL_HW_ENABLE |
+		GEN6_RC_CTL_RC6_ENABLE |
+		rc6_mode;
 
 	/*
 	 * WaRsDisableCoarsePowerGating:skl,cnl
@@ -203,10 +200,10 @@ static void gen8_rc6_enable(struct intel_rc6 *rc6)
 	set(uncore, GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
 
 	/* 3: Enable RC6 */
-	set(uncore, GEN6_RC_CONTROL,
+	rc6->ctl_enable =
 	    GEN6_RC_CTL_HW_ENABLE |
 	    GEN7_RC_CTL_TO_MODE |
-	    GEN6_RC_CTL_RC6_ENABLE);
+	    GEN6_RC_CTL_RC6_ENABLE;
 }
 
 static void gen6_rc6_enable(struct intel_rc6 *rc6)
@@ -242,10 +239,10 @@ static void gen6_rc6_enable(struct intel_rc6 *rc6)
 		rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
 	if (HAS_RC6pp(i915))
 		rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
-	set(uncore, GEN6_RC_CONTROL,
+	rc6->ctl_enable =
 	    rc6_mask |
 	    GEN6_RC_CTL_EI_MODE(1) |
-	    GEN6_RC_CTL_HW_ENABLE);
+	    GEN6_RC_CTL_HW_ENABLE;
 
 	rc6vids = 0;
 	ret = sandybridge_pcode_read(i915, GEN6_PCODE_READ_RC6VIDS,
@@ -363,7 +360,7 @@ static void chv_rc6_enable(struct intel_rc6 *rc6)
 			       VLV_RENDER_RC6_COUNT_EN));
 
 	/* 3: Enable RC6 */
-	set(uncore, GEN6_RC_CONTROL, GEN7_RC_CTL_TO_MODE);
+	rc6->ctl_enable = GEN7_RC_CTL_TO_MODE;
 }
 
 static void vlv_rc6_enable(struct intel_rc6 *rc6)
@@ -389,8 +386,8 @@ static void vlv_rc6_enable(struct intel_rc6 *rc6)
 			       VLV_MEDIA_RC6_COUNT_EN |
 			       VLV_RENDER_RC6_COUNT_EN));
 
-	set(uncore, GEN6_RC_CONTROL,
-	    GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL);
+	rc6->ctl_enable =
+	    GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL;
 }
 
 static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6)
@@ -491,64 +488,19 @@ static void rpm_put(struct intel_rc6 *rc6)
 	rc6->wakeref = false;
 }
 
-static bool intel_rc6_ctx_corrupted(struct intel_rc6 *rc6)
-{
-	return !intel_uncore_read(rc6_to_uncore(rc6), GEN8_RC6_CTX_INFO);
-}
-
-static void intel_rc6_ctx_wa_init(struct intel_rc6 *rc6)
+static bool pctx_corrupted(struct intel_rc6 *rc6)
 {
 	struct drm_i915_private *i915 = rc6_to_i915(rc6);
 
 	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
-		return;
-
-	if (intel_rc6_ctx_corrupted(rc6)) {
-		DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
-		rc6->ctx_corrupted = true;
-	}
-}
-
-/**
- * intel_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
- * @rc6: rc6 state
- *
- * Perform any steps needed to re-init the RC6 CTX WA after system resume.
- */
-void intel_rc6_ctx_wa_resume(struct intel_rc6 *rc6)
-{
-	if (rc6->ctx_corrupted && !intel_rc6_ctx_corrupted(rc6)) {
-		DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
-		rc6->ctx_corrupted = false;
-	}
-}
-
-/**
- * intel_rc6_ctx_wa_check - check for a new RC6 CTX corruption
- * @rc6: rc6 state
- *
- * Check if an RC6 CTX corruption has happened since the last check and if so
- * disable RC6 and runtime power management.
-*/
-void intel_rc6_ctx_wa_check(struct intel_rc6 *rc6)
-{
-	struct drm_i915_private *i915 = rc6_to_i915(rc6);
-
-	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
-		return;
-
-	if (rc6->ctx_corrupted)
-		return;
-
-	if (!intel_rc6_ctx_corrupted(rc6))
-		return;
-
-	DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
+		return false;
 
-	intel_rc6_disable(rc6);
-	rc6->ctx_corrupted = true;
+	if (intel_uncore_read(rc6_to_uncore(rc6), GEN8_RC6_CTX_INFO))
+		return false;
 
-	return;
+	dev_notice(i915->drm.dev,
+		   "RC6 context corruption, disabling runtime power management\n");
+	return true;
 }
 
 static void __intel_rc6_disable(struct intel_rc6 *rc6)
@@ -575,8 +527,6 @@ void intel_rc6_init(struct intel_rc6 *rc6)
 	if (!rc6_supported(rc6))
 		return;
 
-	intel_rc6_ctx_wa_init(rc6);
-
 	if (IS_CHERRYVIEW(i915))
 		err = chv_rc6_init(rc6);
 	else if (IS_VALLEYVIEW(i915))
@@ -611,9 +561,6 @@ void intel_rc6_enable(struct intel_rc6 *rc6)
 
 	GEM_BUG_ON(rc6->enabled);
 
-	if (rc6->ctx_corrupted)
-		return;
-
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	if (IS_CHERRYVIEW(i915))
@@ -629,13 +576,51 @@ void intel_rc6_enable(struct intel_rc6 *rc6)
 	else if (INTEL_GEN(i915) >= 6)
 		gen6_rc6_enable(rc6);
 
+	rc6->manual = rc6->ctl_enable & GEN6_RC_CTL_RC6_ENABLE;
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		rc6->ctl_enable = 0;
+
 	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
 
+	if (unlikely(pctx_corrupted(rc6)))
+		return;
+
 	/* rc6 is ready, runtime-pm is go! */
 	rpm_put(rc6);
 	rc6->enabled = true;
 }
 
+void intel_rc6_unpark(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+
+	if (!rc6->enabled)
+		return;
+
+	/* Restore HW timers for automatic RC6 entry while busy */
+	set(uncore, GEN6_RC_CONTROL, rc6->ctl_enable);
+}
+
+void intel_rc6_park(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+
+	if (!rc6->enabled)
+		return;
+
+	if (unlikely(pctx_corrupted(rc6))) {
+		intel_rc6_disable(rc6);
+		return;
+	}
+
+	if (!rc6->manual)
+		return;
+
+	/* Turn off the HW timers and go directly to rc6 */
+	set(uncore, GEN6_RC_CONTROL, GEN6_RC_CTL_RC6_ENABLE);
+	set(uncore, GEN6_RC_STATE, 0x4 << RC_SW_TARGET_STATE_SHIFT);
+}
+
 void intel_rc6_disable(struct intel_rc6 *rc6)
 {
 	if (!rc6->enabled)
@@ -785,3 +770,7 @@ u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg)
 {
 	return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, reg), 1000);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_rc6.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.h b/drivers/gpu/drm/i915/gt/intel_rc6.h
index 1370f6834a4c..9f0f23fca8af 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.h
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.h
@@ -15,6 +15,9 @@ struct intel_rc6;
 void intel_rc6_init(struct intel_rc6 *rc6);
 void intel_rc6_fini(struct intel_rc6 *rc6);
 
+void intel_rc6_unpark(struct intel_rc6 *rc6);
+void intel_rc6_park(struct intel_rc6 *rc6);
+
 void intel_rc6_sanitize(struct intel_rc6 *rc6);
 void intel_rc6_enable(struct intel_rc6 *rc6);
 void intel_rc6_disable(struct intel_rc6 *rc6);
@@ -22,7 +25,4 @@ void intel_rc6_disable(struct intel_rc6 *rc6);
 u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, i915_reg_t reg);
 u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg);
 
-void intel_rc6_ctx_wa_check(struct intel_rc6 *rc6);
-void intel_rc6_ctx_wa_resume(struct intel_rc6 *rc6);
-
 #endif /* INTEL_RC6_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6_types.h b/drivers/gpu/drm/i915/gt/intel_rc6_types.h
index 89ad5697a8d4..bfbb623f7a4f 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_rc6_types.h
@@ -18,12 +18,14 @@ struct intel_rc6 {
 	u64 prev_hw_residency[4];
 	u64 cur_residency[4];
 
+	u32 ctl_enable;
+
 	struct drm_i915_gem_object *pctx;
 
 	bool supported : 1;
 	bool enabled : 1;
+	bool manual : 1;
 	bool wakeref : 1;
-	bool ctx_corrupted : 1;
 };
 
 #endif /* INTEL_RC6_TYPES_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index c4edc35e7d89..5954ecc3207f 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -29,16 +29,6 @@
 #include "intel_renderstate.h"
 #include "intel_ring.h"
 
-struct intel_renderstate {
-	const struct intel_renderstate_rodata *rodata;
-	struct drm_i915_gem_object *obj;
-	struct i915_vma *vma;
-	u32 batch_offset;
-	u32 batch_size;
-	u32 aux_offset;
-	u32 aux_size;
-};
-
 static const struct intel_renderstate_rodata *
 render_state_get_rodata(const struct intel_engine_cs *engine)
 {
@@ -84,11 +74,11 @@ static int render_state_setup(struct intel_renderstate *so,
 	u32 *d;
 	int ret;
 
-	ret = i915_gem_object_prepare_write(so->obj, &needs_clflush);
+	ret = i915_gem_object_prepare_write(so->vma->obj, &needs_clflush);
 	if (ret)
 		return ret;
 
-	d = kmap_atomic(i915_gem_object_get_dirty_page(so->obj, 0));
+	d = kmap_atomic(i915_gem_object_get_dirty_page(so->vma->obj, 0));
 
 	while (i < rodata->batch_items) {
 		u32 s = rodata->batch[i];
@@ -166,7 +156,7 @@ static int render_state_setup(struct intel_renderstate *so,
 
 	ret = 0;
 out:
-	i915_gem_object_finish_access(so->obj);
+	i915_gem_object_finish_access(so->vma->obj);
 	return ret;
 
 err:
@@ -177,61 +167,84 @@ err:
 
 #undef OUT_BATCH
 
-int intel_renderstate_emit(struct i915_request *rq)
+int intel_renderstate_init(struct intel_renderstate *so,
+			   struct intel_engine_cs *engine)
 {
-	struct intel_engine_cs *engine = rq->engine;
-	struct intel_renderstate so = {}; /* keep the compiler happy */
+	struct drm_i915_gem_object *obj;
 	int err;
 
-	so.rodata = render_state_get_rodata(engine);
-	if (!so.rodata)
+	memset(so, 0, sizeof(*so));
+
+	so->rodata = render_state_get_rodata(engine);
+	if (!so->rodata)
 		return 0;
 
-	if (so.rodata->batch_items * 4 > PAGE_SIZE)
+	if (so->rodata->batch_items * 4 > PAGE_SIZE)
 		return -EINVAL;
 
-	so.obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
-	if (IS_ERR(so.obj))
-		return PTR_ERR(so.obj);
+	obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
-	so.vma = i915_vma_instance(so.obj, &engine->gt->ggtt->vm, NULL);
-	if (IS_ERR(so.vma)) {
-		err = PTR_ERR(so.vma);
+	so->vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
+	if (IS_ERR(so->vma)) {
+		err = PTR_ERR(so->vma);
 		goto err_obj;
 	}
 
-	err = i915_vma_pin(so.vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
+	err = i915_vma_pin(so->vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
 		goto err_vma;
 
-	err = render_state_setup(&so, rq->i915);
+	err = render_state_setup(so, engine->i915);
 	if (err)
 		goto err_unpin;
 
+	return 0;
+
+err_unpin:
+	i915_vma_unpin(so->vma);
+err_vma:
+	i915_vma_close(so->vma);
+err_obj:
+	i915_gem_object_put(obj);
+	so->vma = NULL;
+	return err;
+}
+
+int intel_renderstate_emit(struct intel_renderstate *so,
+			   struct i915_request *rq)
+{
+	struct intel_engine_cs *engine = rq->engine;
+	int err;
+
+	if (!so->vma)
+		return 0;
+
 	err = engine->emit_bb_start(rq,
-				    so.batch_offset, so.batch_size,
+				    so->batch_offset, so->batch_size,
 				    I915_DISPATCH_SECURE);
 	if (err)
-		goto err_unpin;
+		return err;
 
-	if (so.aux_size > 8) {
+	if (so->aux_size > 8) {
 		err = engine->emit_bb_start(rq,
-					    so.aux_offset, so.aux_size,
+					    so->aux_offset, so->aux_size,
 					    I915_DISPATCH_SECURE);
 		if (err)
-			goto err_unpin;
+			return err;
 	}
 
-	i915_vma_lock(so.vma);
-	err = i915_request_await_object(rq, so.vma->obj, false);
+	i915_vma_lock(so->vma);
+	err = i915_request_await_object(rq, so->vma->obj, false);
 	if (err == 0)
-		err = i915_vma_move_to_active(so.vma, rq, 0);
-	i915_vma_unlock(so.vma);
-err_unpin:
-	i915_vma_unpin(so.vma);
-err_vma:
-	i915_vma_close(so.vma);
-err_obj:
-	i915_gem_object_put(so.obj);
+		err = i915_vma_move_to_active(so->vma, rq, 0);
+	i915_vma_unlock(so->vma);
+
 	return err;
 }
+
+void intel_renderstate_fini(struct intel_renderstate *so)
+{
+	i915_vma_unpin_and_release(&so->vma, 0);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.h b/drivers/gpu/drm/i915/gt/intel_renderstate.h
index 8d5079145054..5700be69a05a 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.h
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.h
@@ -27,6 +27,8 @@
 #include <linux/types.h>
 
 struct i915_request;
+struct intel_engine_cs;
+struct i915_vma;
 
 struct intel_renderstate_rodata {
 	const u32 *reloc;
@@ -46,6 +48,19 @@ extern const struct intel_renderstate_rodata gen7_null_state;
 extern const struct intel_renderstate_rodata gen8_null_state;
 extern const struct intel_renderstate_rodata gen9_null_state;
 
-int intel_renderstate_emit(struct i915_request *rq);
+struct intel_renderstate {
+	const struct intel_renderstate_rodata *rodata;
+	struct i915_vma *vma;
+	u32 batch_offset;
+	u32 batch_size;
+	u32 aux_offset;
+	u32 aux_size;
+};
+
+int intel_renderstate_init(struct intel_renderstate *so,
+			   struct intel_engine_cs *engine);
+int intel_renderstate_emit(struct intel_renderstate *so,
+			   struct i915_request *rq);
+void intel_renderstate_fini(struct intel_renderstate *so);
 
 #endif /* _INTEL_RENDERSTATE_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index c97423a76642..beee0cf89bce 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -21,6 +21,7 @@
 #include "intel_reset.h"
 
 #include "uc/intel_guc.h"
+#include "uc/intel_guc_submission.h"
 
 #define RESET_MAX_RETRIES 3
 
@@ -40,27 +41,29 @@ static void rmw_clear_fw(struct intel_uncore *uncore, i915_reg_t reg, u32 clr)
 static void engine_skip_context(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
-	struct i915_gem_context *hung_ctx = rq->gem_context;
+	struct intel_context *hung_ctx = rq->context;
 
 	if (!i915_request_is_active(rq))
 		return;
 
 	lockdep_assert_held(&engine->active.lock);
 	list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
-		if (rq->gem_context == hung_ctx)
+		if (rq->context == hung_ctx)
 			i915_request_skip(rq, -EIO);
 }
 
-static void client_mark_guilty(struct drm_i915_file_private *file_priv,
-			       const struct i915_gem_context *ctx)
+static void client_mark_guilty(struct i915_gem_context *ctx, bool banned)
 {
-	unsigned int score;
+	struct drm_i915_file_private *file_priv = ctx->file_priv;
 	unsigned long prev_hang;
+	unsigned int score;
+
+	if (IS_ERR_OR_NULL(file_priv))
+		return;
 
-	if (i915_gem_context_is_banned(ctx))
+	score = 0;
+	if (banned)
 		score = I915_CLIENT_SCORE_CONTEXT_BAN;
-	else
-		score = 0;
 
 	prev_hang = xchg(&file_priv->hang_timestamp, jiffies);
 	if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES))
@@ -75,17 +78,38 @@ static void client_mark_guilty(struct drm_i915_file_private *file_priv,
 	}
 }
 
-static bool context_mark_guilty(struct i915_gem_context *ctx)
+static bool mark_guilty(struct i915_request *rq)
 {
+	struct i915_gem_context *ctx;
 	unsigned long prev_hang;
 	bool banned;
 	int i;
 
+	rcu_read_lock();
+	ctx = rcu_dereference(rq->context->gem_context);
+	if (ctx && !kref_get_unless_zero(&ctx->ref))
+		ctx = NULL;
+	rcu_read_unlock();
+	if (!ctx)
+		return false;
+
+	if (i915_gem_context_is_closed(ctx)) {
+		intel_context_set_banned(rq->context);
+		banned = true;
+		goto out;
+	}
+
 	atomic_inc(&ctx->guilty_count);
 
 	/* Cool contexts are too cool to be banned! (Used for reset testing.) */
-	if (!i915_gem_context_is_bannable(ctx))
-		return false;
+	if (!i915_gem_context_is_bannable(ctx)) {
+		banned = false;
+		goto out;
+	}
+
+	dev_notice(ctx->i915->drm.dev,
+		   "%s context reset due to GPU hang\n",
+		   ctx->name);
 
 	/* Record the timestamp for the last N hangs */
 	prev_hang = ctx->hang_timestamp[0];
@@ -100,38 +124,43 @@ static bool context_mark_guilty(struct i915_gem_context *ctx)
 	if (banned) {
 		DRM_DEBUG_DRIVER("context %s: guilty %d, banned\n",
 				 ctx->name, atomic_read(&ctx->guilty_count));
-		i915_gem_context_set_banned(ctx);
+		intel_context_set_banned(rq->context);
 	}
 
-	if (!IS_ERR_OR_NULL(ctx->file_priv))
-		client_mark_guilty(ctx->file_priv, ctx);
+	client_mark_guilty(ctx, banned);
 
+out:
+	i915_gem_context_put(ctx);
 	return banned;
 }
 
-static void context_mark_innocent(struct i915_gem_context *ctx)
+static void mark_innocent(struct i915_request *rq)
 {
-	atomic_inc(&ctx->active_count);
+	struct i915_gem_context *ctx;
+
+	rcu_read_lock();
+	ctx = rcu_dereference(rq->context->gem_context);
+	if (ctx)
+		atomic_inc(&ctx->active_count);
+	rcu_read_unlock();
 }
 
 void __i915_request_reset(struct i915_request *rq, bool guilty)
 {
-	GEM_TRACE("%s rq=%llx:%lld, guilty? %s\n",
-		  rq->engine->name,
-		  rq->fence.context,
-		  rq->fence.seqno,
-		  yesno(guilty));
+	RQ_TRACE(rq, "guilty? %s\n", yesno(guilty));
 
 	GEM_BUG_ON(i915_request_completed(rq));
 
+	rcu_read_lock(); /* protect the GEM context */
 	if (guilty) {
 		i915_request_skip(rq, -EIO);
-		if (context_mark_guilty(rq->gem_context))
+		if (mark_guilty(rq))
 			engine_skip_context(rq);
 	} else {
 		dma_fence_set_error(&rq->fence, -EAGAIN);
-		context_mark_innocent(rq->gem_context);
+		mark_innocent(rq);
 	}
+	rcu_read_unlock();
 }
 
 static bool i915_in_reset(struct pci_dev *pdev)
@@ -218,9 +247,8 @@ out:
 	return ret;
 }
 
-static int ironlake_do_reset(struct intel_gt *gt,
-			     intel_engine_mask_t engine_mask,
-			     unsigned int retry)
+static int ilk_do_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask,
+			unsigned int retry)
 {
 	struct intel_uncore *uncore = gt->uncore;
 	int ret;
@@ -564,7 +592,7 @@ static reset_func intel_get_gpu_reset(const struct intel_gt *gt)
 	else if (INTEL_GEN(i915) >= 6)
 		return gen6_reset_engines;
 	else if (INTEL_GEN(i915) >= 5)
-		return ironlake_do_reset;
+		return ilk_do_reset;
 	else if (IS_G4X(i915))
 		return g4x_do_reset;
 	else if (IS_G33(i915) || IS_PINEVIEW(i915))
@@ -592,7 +620,7 @@ int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 	 */
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	for (retry = 0; ret == -ETIMEDOUT && retry < retries; retry++) {
-		GEM_TRACE("engine_mask=%x\n", engine_mask);
+		GT_TRACE(gt, "engine_mask=%x\n", engine_mask);
 		preempt_disable();
 		ret = reset(gt, engine_mask, retry);
 		preempt_enable();
@@ -647,7 +675,8 @@ static void reset_prepare_engine(struct intel_engine_cs *engine)
 	 * GPU state upon resume, i.e. fail to restart after a reset.
 	 */
 	intel_uncore_forcewake_get(engine->uncore, FORCEWAKE_ALL);
-	engine->reset.prepare(engine);
+	if (engine->reset.prepare)
+		engine->reset.prepare(engine);
 }
 
 static void revoke_mmaps(struct intel_gt *gt)
@@ -667,8 +696,13 @@ static void revoke_mmaps(struct intel_gt *gt)
 			continue;
 
 		GEM_BUG_ON(vma->fence != &gt->ggtt->fence_regs[i]);
-		node = &vma->obj->base.vma_node;
+
+		if (!vma->mmo)
+			continue;
+
+		node = &vma->mmo->vma_node;
 		vma_offset = vma->ggtt_view.partial.offset << PAGE_SHIFT;
+
 		unmap_mapping_range(gt->i915->drm.anon_inode->i_mapping,
 				    drm_vma_node_offset_addr(node) + vma_offset,
 				    vma->size,
@@ -722,10 +756,11 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 
 static void reset_finish_engine(struct intel_engine_cs *engine)
 {
-	engine->reset.finish(engine);
+	if (engine->reset.finish)
+		engine->reset.finish(engine);
 	intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL);
 
-	intel_engine_breadcrumbs_irq(engine);
+	intel_engine_signal_breadcrumbs(engine);
 }
 
 static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake)
@@ -745,8 +780,7 @@ static void nop_submit_request(struct i915_request *request)
 	struct intel_engine_cs *engine = request->engine;
 	unsigned long flags;
 
-	GEM_TRACE("%s fence %llx:%lld -> -EIO\n",
-		  engine->name, request->fence.context, request->fence.seqno);
+	RQ_TRACE(request, "-EIO\n");
 	dma_fence_set_error(&request->fence, -EIO);
 
 	spin_lock_irqsave(&engine->active.lock, flags);
@@ -754,7 +788,7 @@ static void nop_submit_request(struct i915_request *request)
 	i915_request_mark_complete(request);
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 
-	intel_engine_queue_breadcrumbs(engine);
+	intel_engine_signal_breadcrumbs(engine);
 }
 
 static void __intel_gt_set_wedged(struct intel_gt *gt)
@@ -773,7 +807,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 	}
 
-	GEM_TRACE("start\n");
+	GT_TRACE(gt, "start\n");
 
 	/*
 	 * First, stop submission to hw, but do not yet complete requests by
@@ -799,11 +833,12 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 
 	/* Mark all executing requests as skipped */
 	for_each_engine(engine, gt, id)
-		engine->cancel_requests(engine);
+		if (engine->reset.cancel)
+			engine->reset.cancel(engine);
 
 	reset_finish(gt, awake);
 
-	GEM_TRACE("end\n");
+	GT_TRACE(gt, "end\n");
 }
 
 void intel_gt_set_wedged(struct intel_gt *gt)
@@ -820,7 +855,6 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl;
-	unsigned long flags;
 	bool ok;
 
 	if (!test_bit(I915_WEDGED, &gt->reset.flags))
@@ -830,7 +864,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	if (test_bit(I915_WEDGED_ON_INIT, &gt->reset.flags))
 		return false;
 
-	GEM_TRACE("start\n");
+	GT_TRACE(gt, "start\n");
 
 	/*
 	 * Before unwedging, make sure that all pending operations
@@ -842,7 +876,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	 *
 	 * No more can be submitted until we reset the wedged bit.
 	 */
-	spin_lock_irqsave(&timelines->lock, flags);
+	spin_lock(&timelines->lock);
 	list_for_each_entry(tl, &timelines->active_list, link) {
 		struct dma_fence *fence;
 
@@ -850,7 +884,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		if (!fence)
 			continue;
 
-		spin_unlock_irqrestore(&timelines->lock, flags);
+		spin_unlock(&timelines->lock);
 
 		/*
 		 * All internal dependencies (i915_requests) will have
@@ -863,10 +897,10 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		dma_fence_put(fence);
 
 		/* Restart iteration after droping lock */
-		spin_lock_irqsave(&timelines->lock, flags);
+		spin_lock(&timelines->lock);
 		tl = list_entry(&timelines->active_list, typeof(*tl), link);
 	}
-	spin_unlock_irqrestore(&timelines->lock, flags);
+	spin_unlock(&timelines->lock);
 
 	/* We must reset pending GPU events before restoring our submission */
 	ok = !HAS_EXECLISTS(gt->i915); /* XXX better agnosticism desired */
@@ -892,7 +926,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	 */
 	intel_engines_reset_default_submission(gt);
 
-	GEM_TRACE("end\n");
+	GT_TRACE(gt, "end\n");
 
 	smp_mb__before_atomic(); /* complete takeover before enabling execbuf */
 	clear_bit(I915_WEDGED, &gt->reset.flags);
@@ -967,7 +1001,7 @@ void intel_gt_reset(struct intel_gt *gt,
 	intel_engine_mask_t awake;
 	int ret;
 
-	GEM_TRACE("flags=%lx\n", gt->reset.flags);
+	GT_TRACE(gt, "flags=%lx\n", gt->reset.flags);
 
 	might_sleep();
 	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &gt->reset.flags));
@@ -1070,9 +1104,10 @@ static inline int intel_gt_reset_engine(struct intel_engine_cs *engine)
 int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 {
 	struct intel_gt *gt = engine->gt;
+	bool uses_guc = intel_engine_in_guc_submission_mode(engine);
 	int ret;
 
-	GEM_TRACE("%s flags=%lx\n", engine->name, gt->reset.flags);
+	ENGINE_TRACE(engine, "flags=%lx\n", gt->reset.flags);
 	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &gt->reset.flags));
 
 	if (!intel_engine_pm_get_if_awake(engine))
@@ -1085,14 +1120,14 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 			   "Resetting %s for %s\n", engine->name, msg);
 	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
 
-	if (!engine->gt->uc.guc.execbuf_client)
+	if (!uses_guc)
 		ret = intel_gt_reset_engine(engine);
 	else
 		ret = intel_guc_reset_engine(&engine->gt->uc.guc, engine);
 	if (ret) {
 		/* If we fail here, we expect to fallback to a global reset */
 		DRM_DEBUG_DRIVER("%sFailed to reset %s, ret=%d\n",
-				 engine->gt->uc.guc.execbuf_client ? "GuC " : "",
+				 uses_guc ? "GuC " : "",
 				 engine->name, ret);
 		goto out;
 	}
@@ -1195,7 +1230,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	engine_mask &= INTEL_INFO(gt->i915)->engine_mask;
 
 	if (flags & I915_ERROR_CAPTURE) {
-		i915_capture_error_state(gt->i915, engine_mask, msg);
+		i915_capture_error_state(gt->i915);
 		intel_gt_clear_error_registers(gt, engine_mask);
 	}
 
@@ -1288,10 +1323,10 @@ int intel_gt_terminally_wedged(struct intel_gt *gt)
 	if (!intel_gt_is_wedged(gt))
 		return 0;
 
-	/* Reset still in progress? Maybe we will recover? */
-	if (!test_bit(I915_RESET_BACKOFF, &gt->reset.flags))
+	if (intel_gt_has_init_error(gt))
 		return -EIO;
 
+	/* Reset still in progress? Maybe we will recover? */
 	if (wait_event_interruptible(gt->reset.queue,
 				     !test_bit(I915_RESET_BACKOFF,
 					       &gt->reset.flags)))
@@ -1313,6 +1348,9 @@ void intel_gt_init_reset(struct intel_gt *gt)
 	init_waitqueue_head(&gt->reset.queue);
 	mutex_init(&gt->reset.mutex);
 	init_srcu_struct(&gt->reset.backoff_srcu);
+
+	/* no GPU until we are ready! */
+	__set_bit(I915_WEDGED, &gt->reset.flags);
 }
 
 void intel_gt_fini_reset(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 93026217c121..bc44fe8e5ffa 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -33,6 +33,7 @@
 
 #include "gem/i915_gem_context.h"
 
+#include "gen6_ppgtt.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "intel_context.h"
@@ -362,6 +363,12 @@ gen7_render_ring_flush(struct i915_request *rq, u32 mode)
 	 */
 	flags |= PIPE_CONTROL_CS_STALL;
 
+	/*
+	 * CS_STALL suggests at least a post-sync write.
+	 */
+	flags |= PIPE_CONTROL_QW_WRITE;
+	flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
 	/* Just flush everything.  Experiments have shown that reducing the
 	 * number of bits based on the write domains has little performance
 	 * impact.
@@ -380,13 +387,6 @@ gen7_render_ring_flush(struct i915_request *rq, u32 mode)
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_MEDIA_STATE_CLEAR;
-		/*
-		 * TLB invalidate requires a post-sync write.
-		 */
-		flags |= PIPE_CONTROL_QW_WRITE;
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
-
-		flags |= PIPE_CONTROL_STALL_AT_SCOREBOARD;
 
 		/* Workaround: we must issue a pipe_control with CS-stall bit
 		 * set before a pipe_control command that has the state cache
@@ -454,7 +454,8 @@ static u32 *gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 	GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma);
 	GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
 
-	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
+	*cs++ = MI_FLUSH_DW | MI_INVALIDATE_TLB |
+		MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
 	*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
 	*cs++ = rq->fence.seqno;
 
@@ -496,14 +497,13 @@ static void set_hwstam(struct intel_engine_cs *engine, u32 mask)
 
 static void set_hws_pga(struct intel_engine_cs *engine, phys_addr_t phys)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
 	u32 addr;
 
 	addr = lower_32_bits(phys);
-	if (INTEL_GEN(dev_priv) >= 4)
+	if (INTEL_GEN(engine->i915) >= 4)
 		addr |= (phys >> 28) & 0xf0;
 
-	I915_WRITE(HWS_PGA, addr);
+	intel_uncore_write(engine->uncore, HWS_PGA, addr);
 }
 
 static struct page *status_page(struct intel_engine_cs *engine)
@@ -522,14 +522,13 @@ static void ring_setup_phys_status_page(struct intel_engine_cs *engine)
 
 static void set_hwsp(struct intel_engine_cs *engine, u32 offset)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
 	i915_reg_t hwsp;
 
 	/*
 	 * The ring status page addresses are no longer next to the rest of
 	 * the ring registers as of gen7.
 	 */
-	if (IS_GEN(dev_priv, 7)) {
+	if (IS_GEN(engine->i915, 7)) {
 		switch (engine->id) {
 		/*
 		 * No more rings exist on Gen7. Default case is only to shut up
@@ -551,14 +550,14 @@ static void set_hwsp(struct intel_engine_cs *engine, u32 offset)
 			hwsp = VEBOX_HWS_PGA_GEN7;
 			break;
 		}
-	} else if (IS_GEN(dev_priv, 6)) {
+	} else if (IS_GEN(engine->i915, 6)) {
 		hwsp = RING_HWS_PGA_GEN6(engine->mmio_base);
 	} else {
 		hwsp = RING_HWS_PGA(engine->mmio_base);
 	}
 
-	I915_WRITE(hwsp, offset);
-	POSTING_READ(hwsp);
+	intel_uncore_write(engine->uncore, hwsp, offset);
+	intel_uncore_posting_read(engine->uncore, hwsp);
 }
 
 static void flush_cs_tlb(struct intel_engine_cs *engine)
@@ -633,8 +632,8 @@ static int xcs_resume(struct intel_engine_cs *engine)
 	struct intel_ring *ring = engine->legacy.ring;
 	int ret = 0;
 
-	GEM_TRACE("%s: ring:{HEAD:%04x, TAIL:%04x}\n",
-		  engine->name, ring->head, ring->tail);
+	ENGINE_TRACE(engine, "ring:{HEAD:%04x, TAIL:%04x}\n",
+		     ring->head, ring->tail);
 
 	intel_uncore_forcewake_get(engine->uncore, FORCEWAKE_ALL);
 
@@ -721,7 +720,7 @@ static int xcs_resume(struct intel_engine_cs *engine)
 	}
 
 	/* Papering over lost _interrupts_ immediately following the restart */
-	intel_engine_queue_breadcrumbs(engine);
+	intel_engine_signal_breadcrumbs(engine);
 out:
 	intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL);
 
@@ -747,10 +746,10 @@ static void reset_prepare(struct intel_engine_cs *engine)
 	 *
 	 * FIXME: Wa for more modern gens needs to be validated
 	 */
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	if (intel_engine_stop_cs(engine))
-		GEM_TRACE("%s: timed out on STOP_RING\n", engine->name);
+		ENGINE_TRACE(engine, "timed out on STOP_RING\n");
 
 	intel_uncore_write_fw(uncore,
 			      RING_HEAD(base),
@@ -766,12 +765,11 @@ static void reset_prepare(struct intel_engine_cs *engine)
 
 	/* Check acts as a post */
 	if (intel_uncore_read_fw(uncore, RING_HEAD(base)))
-		GEM_TRACE("%s: ring head [%x] not parked\n",
-			  engine->name,
-			  intel_uncore_read_fw(uncore, RING_HEAD(base)));
+		ENGINE_TRACE(engine, "ring head [%x] not parked\n",
+			     intel_uncore_read_fw(uncore, RING_HEAD(base)));
 }
 
-static void reset_ring(struct intel_engine_cs *engine, bool stalled)
+static void reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	struct i915_request *pos, *rq;
 	unsigned long flags;
@@ -842,7 +840,8 @@ static void reset_finish(struct intel_engine_cs *engine)
 
 static int rcs_resume(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_uncore *uncore = engine->uncore;
 
 	/*
 	 * Disable CONSTANT_BUFFER before it is loaded from the context
@@ -854,13 +853,14 @@ static int rcs_resume(struct intel_engine_cs *engine)
 	 * they are already accustomed to from before contexts were
 	 * enabled.
 	 */
-	if (IS_GEN(dev_priv, 4))
-		I915_WRITE(ECOSKPD,
+	if (IS_GEN(i915, 4))
+		intel_uncore_write(uncore, ECOSKPD,
 			   _MASKED_BIT_ENABLE(ECO_CONSTANT_BUFFER_SR_DISABLE));
 
 	/* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */
-	if (IS_GEN_RANGE(dev_priv, 4, 6))
-		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH));
+	if (IS_GEN_RANGE(i915, 4, 6))
+		intel_uncore_write(uncore, MI_MODE,
+				   _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH));
 
 	/* We need to disable the AsyncFlip performance optimisations in order
 	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
@@ -868,38 +868,40 @@ static int rcs_resume(struct intel_engine_cs *engine)
 	 *
 	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
 	 */
-	if (IS_GEN_RANGE(dev_priv, 6, 7))
-		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
+	if (IS_GEN_RANGE(i915, 6, 7))
+		intel_uncore_write(uncore, MI_MODE,
+				   _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
 
 	/* Required for the hardware to program scanline values for waiting */
 	/* WaEnableFlushTlbInvalidationMode:snb */
-	if (IS_GEN(dev_priv, 6))
-		I915_WRITE(GFX_MODE,
+	if (IS_GEN(i915, 6))
+		intel_uncore_write(uncore, GFX_MODE,
 			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT));
 
 	/* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */
-	if (IS_GEN(dev_priv, 7))
-		I915_WRITE(GFX_MODE_GEN7,
+	if (IS_GEN(i915, 7))
+		intel_uncore_write(uncore, GFX_MODE_GEN7,
 			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT) |
 			   _MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
 
-	if (IS_GEN(dev_priv, 6)) {
+	if (IS_GEN(i915, 6)) {
 		/* From the Sandybridge PRM, volume 1 part 3, page 24:
 		 * "If this bit is set, STCunit will have LRA as replacement
 		 *  policy. [...] This bit must be reset.  LRA replacement
 		 *  policy is not supported."
 		 */
-		I915_WRITE(CACHE_MODE_0,
+		intel_uncore_write(uncore, CACHE_MODE_0,
 			   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
 	}
 
-	if (IS_GEN_RANGE(dev_priv, 6, 7))
-		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
+	if (IS_GEN_RANGE(i915, 6, 7))
+		intel_uncore_write(uncore, INSTPM,
+				   _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	return xcs_resume(engine);
 }
 
-static void cancel_requests(struct intel_engine_cs *engine)
+static void reset_cancel(struct intel_engine_cs *engine)
 {
 	struct i915_request *request;
 	unsigned long flags;
@@ -1318,6 +1320,8 @@ static int ring_context_alloc(struct intel_context *ce)
 			return PTR_ERR(vma);
 
 		ce->state = vma;
+		if (engine->default_state)
+			__set_bit(CONTEXT_VALID_BIT, &ce->flags);
 	}
 
 	return 0;
@@ -1325,26 +1329,12 @@ static int ring_context_alloc(struct intel_context *ce)
 
 static int ring_context_pin(struct intel_context *ce)
 {
-	int err;
-
-	err = intel_context_active_acquire(ce);
-	if (err)
-		return err;
-
-	err = __context_pin_ppgtt(ce);
-	if (err)
-		goto err_active;
-
-	return 0;
-
-err_active:
-	intel_context_active_release(ce);
-	return err;
+	return __context_pin_ppgtt(ce);
 }
 
 static void ring_context_reset(struct intel_context *ce)
 {
-	intel_ring_reset(ce->ring, 0);
+	intel_ring_reset(ce->ring, ce->ring->emit);
 }
 
 static const struct intel_context_ops ring_context_ops = {
@@ -1360,46 +1350,38 @@ static const struct intel_context_ops ring_context_ops = {
 	.destroy = ring_context_destroy,
 };
 
-static int load_pd_dir(struct i915_request *rq, const struct i915_ppgtt *ppgtt)
+static int load_pd_dir(struct i915_request *rq,
+		       const struct i915_ppgtt *ppgtt,
+		       u32 valid)
 {
 	const struct intel_engine_cs * const engine = rq->engine;
 	u32 *cs;
 
-	cs = intel_ring_begin(rq, 6);
+	cs = intel_ring_begin(rq, 12);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
 	*cs++ = MI_LOAD_REGISTER_IMM(1);
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine->mmio_base));
-	*cs++ = PP_DIR_DCLV_2G;
+	*cs++ = valid;
 
 	*cs++ = MI_LOAD_REGISTER_IMM(1);
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base));
 	*cs++ = px_base(ppgtt->pd)->ggtt_offset << 10;
 
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
-static int flush_pd_dir(struct i915_request *rq)
-{
-	const struct intel_engine_cs * const engine = rq->engine;
-	u32 *cs;
-
-	cs = intel_ring_begin(rq, 4);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	/* Stall until the page table load is complete */
+	/* Stall until the page table load is complete? */
 	*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base));
-	*cs++ = intel_gt_scratch_offset(rq->engine->gt,
+	*cs++ = intel_gt_scratch_offset(engine->gt,
 					INTEL_GT_SCRATCH_FIELD_DEFAULT);
-	*cs++ = MI_NOOP;
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_INSTPM(engine->mmio_base));
+	*cs++ = _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE);
 
 	intel_ring_advance(rq, cs);
-	return 0;
+
+	return rq->engine->emit_flush(rq, EMIT_FLUSH);
 }
 
 static inline int mi_set_context(struct i915_request *rq, u32 flags)
@@ -1477,7 +1459,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 
 	*cs++ = MI_NOOP;
 	*cs++ = MI_SET_CONTEXT;
-	*cs++ = i915_ggtt_offset(rq->hw_context->state) | flags;
+	*cs++ = i915_ggtt_offset(rq->context->state) | flags;
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -1547,10 +1529,10 @@ static int remap_l3_slice(struct i915_request *rq, int slice)
 
 static int remap_l3(struct i915_request *rq)
 {
-	struct i915_gem_context *ctx = rq->gem_context;
+	struct i915_gem_context *ctx = i915_request_gem_context(rq);
 	int i, err;
 
-	if (!ctx->remap_slice)
+	if (!ctx || !ctx->remap_slice)
 		return 0;
 
 	for (i = 0; i < MAX_L3_SLICES; i++) {
@@ -1566,19 +1548,42 @@ static int remap_l3(struct i915_request *rq)
 	return 0;
 }
 
+static int switch_mm(struct i915_request *rq, struct i915_address_space *vm)
+{
+	int ret;
+
+	if (!vm)
+		return 0;
+
+	ret = rq->engine->emit_flush(rq, EMIT_FLUSH);
+	if (ret)
+		return ret;
+
+	/*
+	 * Not only do we need a full barrier (post-sync write) after
+	 * invalidating the TLBs, but we need to wait a little bit
+	 * longer. Whether this is merely delaying us, or the
+	 * subsequent flush is a key part of serialising with the
+	 * post-sync op, this extra pass appears vital before a
+	 * mm switch!
+	 */
+	ret = load_pd_dir(rq, i915_vm_to_ppgtt(vm), PP_DIR_DCLV_2G);
+	if (ret)
+		return ret;
+
+	return rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+}
+
 static int switch_context(struct i915_request *rq)
 {
-	struct intel_context *ce = rq->hw_context;
-	struct i915_address_space *vm = vm_alias(ce);
+	struct intel_context *ce = rq->context;
 	int ret;
 
 	GEM_BUG_ON(HAS_EXECLISTS(rq->i915));
 
-	if (vm) {
-		ret = load_pd_dir(rq, i915_vm_to_ppgtt(vm));
-		if (ret)
-			return ret;
-	}
+	ret = switch_mm(rq, vm_alias(ce));
+	if (ret)
+		return ret;
 
 	if (ce->state) {
 		u32 flags;
@@ -1590,7 +1595,7 @@ static int switch_context(struct i915_request *rq)
 		BUILD_BUG_ON(HSW_MI_RS_RESTORE_STATE_EN != MI_RESTORE_EXT_STATE_EN);
 
 		flags = MI_SAVE_EXT_STATE_EN | MI_MM_SPACE_GTT;
-		if (!i915_gem_context_is_kernel(rq->gem_context))
+		if (test_bit(CONTEXT_VALID_BIT, &ce->flags))
 			flags |= MI_RESTORE_EXT_STATE_EN;
 		else
 			flags |= MI_RESTORE_INHIBIT;
@@ -1600,34 +1605,6 @@ static int switch_context(struct i915_request *rq)
 			return ret;
 	}
 
-	if (vm) {
-		struct intel_engine_cs *engine = rq->engine;
-
-		ret = engine->emit_flush(rq, EMIT_INVALIDATE);
-		if (ret)
-			return ret;
-
-		ret = flush_pd_dir(rq);
-		if (ret)
-			return ret;
-
-		/*
-		 * Not only do we need a full barrier (post-sync write) after
-		 * invalidating the TLBs, but we need to wait a little bit
-		 * longer. Whether this is merely delaying us, or the
-		 * subsequent flush is a key part of serialising with the
-		 * post-sync op, this extra pass appears vital before a
-		 * mm switch!
-		 */
-		ret = engine->emit_flush(rq, EMIT_INVALIDATE);
-		if (ret)
-			return ret;
-
-		ret = engine->emit_flush(rq, EMIT_FLUSH);
-		if (ret)
-			return ret;
-	}
-
 	ret = remap_l3(rq);
 	if (ret)
 		return ret;
@@ -1639,7 +1616,7 @@ static int ring_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!intel_context_is_pinned(request->hw_context));
+	GEM_BUG_ON(!intel_context_is_pinned(request->context));
 	GEM_BUG_ON(i915_request_timeline(request)->has_initial_breadcrumb);
 
 	/*
@@ -1795,7 +1772,6 @@ static int gen6_ring_flush(struct i915_request *rq, u32 mode)
 static void i9xx_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = i9xx_submit_request;
-	engine->cancel_requests = cancel_requests;
 
 	engine->park = NULL;
 	engine->unpark = NULL;
@@ -1807,7 +1783,7 @@ static void gen6_bsd_set_default_submission(struct intel_engine_cs *engine)
 	engine->submit_request = gen6_bsd_submit_request;
 }
 
-static void ring_destroy(struct intel_engine_cs *engine)
+static void ring_release(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 
@@ -1821,8 +1797,6 @@ static void ring_destroy(struct intel_engine_cs *engine)
 
 	intel_timeline_unpin(engine->legacy.timeline);
 	intel_timeline_put(engine->legacy.timeline);
-
-	kfree(engine);
 }
 
 static void setup_irq(struct intel_engine_cs *engine)
@@ -1853,11 +1827,10 @@ static void setup_common(struct intel_engine_cs *engine)
 
 	setup_irq(engine);
 
-	engine->destroy = ring_destroy;
-
 	engine->resume = xcs_resume;
 	engine->reset.prepare = reset_prepare;
-	engine->reset.reset = reset_ring;
+	engine->reset.rewind = reset_rewind;
+	engine->reset.cancel = reset_cancel;
 	engine->reset.finish = reset_finish;
 
 	engine->cops = &ring_context_ops;
@@ -1968,6 +1941,10 @@ static void setup_vecs(struct intel_engine_cs *engine)
 
 int intel_ring_submission_setup(struct intel_engine_cs *engine)
 {
+	struct intel_timeline *timeline;
+	struct intel_ring *ring;
+	int err;
+
 	setup_common(engine);
 
 	switch (engine->class) {
@@ -1988,15 +1965,6 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine)
 		return -ENODEV;
 	}
 
-	return 0;
-}
-
-int intel_ring_submission_init(struct intel_engine_cs *engine)
-{
-	struct intel_timeline *timeline;
-	struct intel_ring *ring;
-	int err;
-
 	timeline = intel_timeline_create(engine->gt, engine->status_page.vma);
 	if (IS_ERR(timeline)) {
 		err = PTR_ERR(timeline);
@@ -2022,16 +1990,13 @@ int intel_ring_submission_init(struct intel_engine_cs *engine)
 	engine->legacy.ring = ring;
 	engine->legacy.timeline = timeline;
 
-	err = intel_engine_init_common(engine);
-	if (err)
-		goto err_ring_unpin;
-
 	GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma);
 
+	/* Finally, take ownership and responsibility for cleanup! */
+	engine->release = ring_release;
+
 	return 0;
 
-err_ring_unpin:
-	intel_ring_unpin(ring);
 err_ring:
 	intel_ring_put(ring);
 err_timeline_unpin:
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 20d6ee148afc..d2a3d935d186 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -37,6 +37,11 @@ static u32 rps_pm_sanitize_mask(struct intel_rps *rps, u32 mask)
 	return mask & ~rps->pm_intrmsk_mbz;
 }
 
+static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val)
+{
+	intel_uncore_write_fw(uncore, reg, val);
+}
+
 static u32 rps_pm_mask(struct intel_rps *rps, u8 val)
 {
 	u32 mask = 0;
@@ -78,8 +83,7 @@ static void rps_enable_interrupts(struct intel_rps *rps)
 	gen6_gt_pm_enable_irq(gt, rps->pm_events);
 	spin_unlock_irq(&gt->irq_lock);
 
-	intel_uncore_write(gt->uncore, GEN6_PMINTRMSK,
-			   rps_pm_mask(rps, rps->cur_freq));
+	set(gt->uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, rps->cur_freq));
 }
 
 static void gen6_rps_reset_interrupts(struct intel_rps *rps)
@@ -113,8 +117,7 @@ static void rps_disable_interrupts(struct intel_rps *rps)
 
 	rps->pm_events = 0;
 
-	intel_uncore_write(gt->uncore, GEN6_PMINTRMSK,
-			   rps_pm_sanitize_mask(rps, ~0u));
+	set(gt->uncore, GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u));
 
 	spin_lock_irq(&gt->irq_lock);
 	gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS);
@@ -573,25 +576,21 @@ static void rps_set_power(struct intel_rps *rps, int new_power)
 	if (IS_VALLEYVIEW(i915))
 		goto skip_hw_write;
 
-	intel_uncore_write(uncore, GEN6_RP_UP_EI,
-			   GT_INTERVAL_FROM_US(i915, ei_up));
-	intel_uncore_write(uncore, GEN6_RP_UP_THRESHOLD,
-			   GT_INTERVAL_FROM_US(i915,
-					       ei_up * threshold_up / 100));
-
-	intel_uncore_write(uncore, GEN6_RP_DOWN_EI,
-			   GT_INTERVAL_FROM_US(i915, ei_down));
-	intel_uncore_write(uncore, GEN6_RP_DOWN_THRESHOLD,
-			   GT_INTERVAL_FROM_US(i915,
-					       ei_down * threshold_down / 100));
-
-	intel_uncore_write(uncore, GEN6_RP_CONTROL,
-			   (INTEL_GEN(i915) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
-			   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-			   GEN6_RP_MEDIA_IS_GFX |
-			   GEN6_RP_ENABLE |
-			   GEN6_RP_UP_BUSY_AVG |
-			   GEN6_RP_DOWN_IDLE_AVG);
+	set(uncore, GEN6_RP_UP_EI, GT_INTERVAL_FROM_US(i915, ei_up));
+	set(uncore, GEN6_RP_UP_THRESHOLD,
+	    GT_INTERVAL_FROM_US(i915, ei_up * threshold_up / 100));
+
+	set(uncore, GEN6_RP_DOWN_EI, GT_INTERVAL_FROM_US(i915, ei_down));
+	set(uncore, GEN6_RP_DOWN_THRESHOLD,
+	    GT_INTERVAL_FROM_US(i915, ei_down * threshold_down / 100));
+
+	set(uncore, GEN6_RP_CONTROL,
+	    (INTEL_GEN(i915) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
+	    GEN6_RP_MEDIA_HW_NORMAL_MODE |
+	    GEN6_RP_MEDIA_IS_GFX |
+	    GEN6_RP_ENABLE |
+	    GEN6_RP_UP_BUSY_AVG |
+	    GEN6_RP_DOWN_IDLE_AVG);
 
 skip_hw_write:
 	rps->power.mode = new_power;
@@ -666,7 +665,7 @@ static int gen6_rps_set(struct intel_rps *rps, u8 val)
 		swreq = (GEN6_FREQUENCY(val) |
 			 GEN6_OFFSET(0) |
 			 GEN6_AGGRESSIVE_TURBO);
-	intel_uncore_write(uncore, GEN6_RPNSWREQ, swreq);
+	set(uncore, GEN6_RPNSWREQ, swreq);
 
 	return 0;
 }
@@ -683,7 +682,7 @@ static int vlv_rps_set(struct intel_rps *rps, u8 val)
 	return err;
 }
 
-static int rps_set(struct intel_rps *rps, u8 val)
+static int rps_set(struct intel_rps *rps, u8 val, bool update)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	int err;
@@ -701,7 +700,8 @@ static int rps_set(struct intel_rps *rps, u8 val)
 	if (err)
 		return err;
 
-	gen6_rps_set_thresholds(rps, val);
+	if (update)
+		gen6_rps_set_thresholds(rps, val);
 	rps->last_freq = val;
 
 	return 0;
@@ -761,7 +761,7 @@ void intel_rps_park(struct intel_rps *rps)
 	 * power than the render powerwell.
 	 */
 	intel_uncore_forcewake_get(rps_to_uncore(rps), FORCEWAKE_MEDIA);
-	rps_set(rps, rps->idle_freq);
+	rps_set(rps, rps->idle_freq, false);
 	intel_uncore_forcewake_put(rps_to_uncore(rps), FORCEWAKE_MEDIA);
 }
 
@@ -777,7 +777,7 @@ void intel_rps_boost(struct i915_request *rq)
 	spin_lock_irqsave(&rq->lock, flags);
 	if (!i915_request_has_waitboost(rq) &&
 	    !dma_fence_is_signaled_locked(&rq->fence)) {
-		rq->flags |= I915_REQUEST_WAITBOOST;
+		set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags);
 
 		if (!atomic_fetch_inc(&rps->num_waiters) &&
 		    READ_ONCE(rps->cur_freq) < rps->boost_freq)
@@ -790,14 +790,16 @@ void intel_rps_boost(struct i915_request *rq)
 
 int intel_rps_set(struct intel_rps *rps, u8 val)
 {
-	int err = 0;
+	int err;
 
 	lockdep_assert_held(&rps->lock);
 	GEM_BUG_ON(val > rps->max_freq);
 	GEM_BUG_ON(val < rps->min_freq);
 
 	if (rps->active) {
-		err = rps_set(rps, val);
+		err = rps_set(rps, val, true);
+		if (err)
+			return err;
 
 		/*
 		 * Make sure we continue to get interrupts
@@ -806,18 +808,15 @@ int intel_rps_set(struct intel_rps *rps, u8 val)
 		if (INTEL_GEN(rps_to_i915(rps)) >= 6) {
 			struct intel_uncore *uncore = rps_to_uncore(rps);
 
-			intel_uncore_write(uncore, GEN6_RP_INTERRUPT_LIMITS,
-					   rps_limits(rps, val));
+			set(uncore,
+			    GEN6_RP_INTERRUPT_LIMITS, rps_limits(rps, val));
 
-			intel_uncore_write(uncore, GEN6_PMINTRMSK,
-					   rps_pm_mask(rps, val));
+			set(uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, val));
 		}
 	}
 
-	if (err == 0)
-		rps->cur_freq = val;
-
-	return err;
+	rps->cur_freq = val;
+	return 0;
 }
 
 static void gen6_rps_init(struct intel_rps *rps)
@@ -878,7 +877,7 @@ static bool rps_reset(struct intel_rps *rps)
 	rps->power.mode = -1;
 	rps->last_freq = -1;
 
-	if (rps_set(rps, rps->min_freq)) {
+	if (rps_set(rps, rps->min_freq, true)) {
 		DRM_ERROR("Failed to reset RPS to initial values\n");
 		return false;
 	}
@@ -1201,7 +1200,7 @@ void intel_rps_enable(struct intel_rps *rps)
 
 static void gen6_rps_disable(struct intel_rps *rps)
 {
-	intel_uncore_write(rps_to_uncore(rps), GEN6_RP_CONTROL, 0);
+	set(rps_to_uncore(rps), GEN6_RP_CONTROL, 0);
 }
 
 void intel_rps_disable(struct intel_rps *rps)
@@ -1566,7 +1565,7 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
 		return;
 
 	if (pm_iir & PM_VEBOX_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine[VECS0]);
+		intel_engine_signal_breadcrumbs(gt->engine[VECS0]);
 
 	if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
 		DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
@@ -1663,23 +1662,53 @@ void intel_rps_init(struct intel_rps *rps)
 	if (INTEL_GEN(i915) <= 7)
 		rps->pm_intrmsk_mbz |= GEN6_PM_RP_UP_EI_EXPIRED;
 
-	if (INTEL_GEN(i915) >= 8)
+	if (INTEL_GEN(i915) >= 8 && INTEL_GEN(i915) < 11)
 		rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
 }
 
-u32 intel_get_cagf(struct intel_rps *rps, u32 rpstat)
+u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	u32 cagf;
 
-	if (INTEL_GEN(i915) >= 9)
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
+		cagf = (rpstat >> 8) & 0xff;
+	else if (INTEL_GEN(i915) >= 9)
 		cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
 	else if (IS_HASWELL(i915) || IS_BROADWELL(i915))
 		cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
 	else
 		cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
 
-	return  cagf;
+	return cagf;
+}
+
+static u32 read_cagf(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 freq;
+
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		vlv_punit_get(i915);
+		freq = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
+		vlv_punit_put(i915);
+	} else {
+		freq = intel_uncore_read(rps_to_gt(rps)->uncore, GEN6_RPSTAT1);
+	}
+
+	return intel_rps_get_cagf(rps, freq);
+}
+
+u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
+{
+	struct intel_runtime_pm *rpm = rps_to_gt(rps)->uncore->rpm;
+	intel_wakeref_t wakeref;
+	u32 freq = 0;
+
+	with_intel_runtime_pm_if_in_use(rpm, wakeref)
+		freq = intel_gpu_freq(rps, read_cagf(rps));
+
+	return freq;
 }
 
 /* External interface for intel_ips.ko */
@@ -1715,6 +1744,7 @@ void intel_rps_driver_register(struct intel_rps *rps)
 	 * set up, to avoid intel-ips sneaking in and reading bogus values.
 	 */
 	if (IS_GEN(gt->i915, 5)) {
+		GEM_BUG_ON(ips_mchdev);
 		rcu_assign_pointer(ips_mchdev, gt->i915);
 		ips_ping_for_i915_load();
 	}
@@ -1722,7 +1752,8 @@ void intel_rps_driver_register(struct intel_rps *rps)
 
 void intel_rps_driver_unregister(struct intel_rps *rps)
 {
-	rcu_assign_pointer(ips_mchdev, NULL);
+	if (rcu_access_pointer(ips_mchdev) == rps_to_i915(rps))
+		rcu_assign_pointer(ips_mchdev, NULL);
 }
 
 static struct drm_i915_private *mchdev_get(void)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
index 9518c66c9792..dfa98194f3b2 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -29,7 +29,8 @@ void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive);
 
 int intel_gpu_freq(struct intel_rps *rps, int val);
 int intel_freq_opcode(struct intel_rps *rps, int val);
-u32 intel_get_cagf(struct intel_rps *rps, u32 rpstat1);
+u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat1);
+u32 intel_rps_read_actual_frequency(struct intel_rps *rps);
 
 void gen5_rps_irq_handler(struct intel_rps *rps);
 void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 649798c184fb..87716529cd2f 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -15,6 +15,9 @@
 #define ptr_set_bit(ptr, bit) ((typeof(ptr))((unsigned long)(ptr) | BIT(bit)))
 #define ptr_test_bit(ptr, bit) ((unsigned long)(ptr) & BIT(bit))
 
+#define CACHELINE_BITS 6
+#define CACHELINE_FREE CACHELINE_BITS
+
 struct intel_timeline_hwsp {
 	struct intel_gt *gt;
 	struct intel_gt_timelines *gt_timelines;
@@ -23,14 +26,6 @@ struct intel_timeline_hwsp {
 	u64 free_bitmap;
 };
 
-struct intel_timeline_cacheline {
-	struct i915_active active;
-	struct intel_timeline_hwsp *hwsp;
-	void *vaddr;
-#define CACHELINE_BITS 6
-#define CACHELINE_FREE CACHELINE_BITS
-};
-
 static struct i915_vma *__hwsp_alloc(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
@@ -133,7 +128,7 @@ static void __idle_cacheline_free(struct intel_timeline_cacheline *cl)
 	__idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS));
 
 	i915_active_fini(&cl->active);
-	kfree(cl);
+	kfree_rcu(cl, rcu);
 }
 
 __i915_active_call
@@ -254,7 +249,7 @@ int intel_timeline_init(struct intel_timeline *timeline,
 
 	mutex_init(&timeline->mutex);
 
-	INIT_ACTIVE_FENCE(&timeline->last_request, &timeline->mutex);
+	INIT_ACTIVE_FENCE(&timeline->last_request);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
@@ -262,7 +257,7 @@ int intel_timeline_init(struct intel_timeline *timeline,
 	return 0;
 }
 
-static void timelines_init(struct intel_gt *gt)
+void intel_gt_init_timelines(struct intel_gt *gt)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 
@@ -273,11 +268,6 @@ static void timelines_init(struct intel_gt *gt)
 	INIT_LIST_HEAD(&timelines->hwsp_free_list);
 }
 
-void intel_timelines_init(struct drm_i915_private *i915)
-{
-	timelines_init(&i915->gt);
-}
-
 void intel_timeline_fini(struct intel_timeline *timeline)
 {
 	GEM_BUG_ON(atomic_read(&timeline->pin_count));
@@ -338,7 +328,6 @@ int intel_timeline_pin(struct intel_timeline *tl)
 void intel_timeline_enter(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
-	unsigned long flags;
 
 	/*
 	 * Pretend we are serialised by the timeline->mutex.
@@ -359,21 +348,19 @@ void intel_timeline_enter(struct intel_timeline *tl)
 	 * use atomic to manipulate tl->active_count.
 	 */
 	lockdep_assert_held(&tl->mutex);
-	GEM_BUG_ON(!atomic_read(&tl->pin_count));
 
 	if (atomic_add_unless(&tl->active_count, 1, 0))
 		return;
 
-	spin_lock_irqsave(&timelines->lock, flags);
+	spin_lock(&timelines->lock);
 	if (!atomic_fetch_inc(&tl->active_count))
 		list_add_tail(&tl->link, &timelines->active_list);
-	spin_unlock_irqrestore(&timelines->lock, flags);
+	spin_unlock(&timelines->lock);
 }
 
 void intel_timeline_exit(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
-	unsigned long flags;
 
 	/* See intel_timeline_enter() */
 	lockdep_assert_held(&tl->mutex);
@@ -382,10 +369,10 @@ void intel_timeline_exit(struct intel_timeline *tl)
 	if (atomic_add_unless(&tl->active_count, -1, 1))
 		return;
 
-	spin_lock_irqsave(&timelines->lock, flags);
+	spin_lock(&timelines->lock);
 	if (atomic_dec_and_test(&tl->active_count))
 		list_del(&tl->link);
-	spin_unlock_irqrestore(&timelines->lock, flags);
+	spin_unlock(&timelines->lock);
 
 	/*
 	 * Since this timeline is idle, all bariers upon which we were waiting
@@ -521,46 +508,35 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 			     struct i915_request *to,
 			     u32 *hwsp)
 {
-	struct intel_timeline *tl;
+	struct intel_timeline_cacheline *cl;
 	int err;
 
+	GEM_BUG_ON(!rcu_access_pointer(from->hwsp_cacheline));
+
 	rcu_read_lock();
-	tl = rcu_dereference(from->timeline);
-	if (i915_request_completed(from) || !kref_get_unless_zero(&tl->kref))
-		tl = NULL;
+	cl = rcu_dereference(from->hwsp_cacheline);
+	if (unlikely(!i915_active_acquire_if_busy(&cl->active)))
+		goto unlock; /* seqno wrapped and completed! */
+	if (unlikely(i915_request_completed(from)))
+		goto release;
 	rcu_read_unlock();
-	if (!tl) /* already completed */
-		return 1;
-
-	GEM_BUG_ON(rcu_access_pointer(to->timeline) == tl);
-
-	err = -EBUSY;
-	if (mutex_trylock(&tl->mutex)) {
-		struct intel_timeline_cacheline *cl = from->hwsp_cacheline;
 
-		if (i915_request_completed(from)) {
-			err = 1;
-			goto unlock;
-		}
+	err = cacheline_ref(cl, to);
+	if (err)
+		goto out;
 
-		err = cacheline_ref(cl, to);
-		if (err)
-			goto unlock;
+	*hwsp = i915_ggtt_offset(cl->hwsp->vma) +
+		ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES;
 
-		if (likely(cl == tl->hwsp_cacheline)) {
-			*hwsp = tl->hwsp_offset;
-		} else { /* across a seqno wrap, recover the original offset */
-			*hwsp = i915_ggtt_offset(cl->hwsp->vma) +
-				ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) *
-				CACHELINE_BYTES;
-		}
+out:
+	i915_active_release(&cl->active);
+	return err;
 
+release:
+	i915_active_release(&cl->active);
 unlock:
-		mutex_unlock(&tl->mutex);
-	}
-	intel_timeline_put(tl);
-
-	return err;
+	rcu_read_unlock();
+	return 1;
 }
 
 void intel_timeline_unpin(struct intel_timeline *tl)
@@ -583,7 +559,7 @@ void __intel_timeline_free(struct kref *kref)
 	kfree_rcu(timeline, rcu);
 }
 
-static void timelines_fini(struct intel_gt *gt)
+void intel_gt_fini_timelines(struct intel_gt *gt)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 
@@ -591,11 +567,6 @@ static void timelines_fini(struct intel_gt *gt)
 	GEM_BUG_ON(!list_empty(&timelines->hwsp_free_list));
 }
 
-void intel_timelines_fini(struct drm_i915_private *i915)
-{
-	timelines_fini(&i915->gt);
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "gt/selftests/mock_timeline.c"
 #include "gt/selftest_timeline.c"
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index f583af1ba18d..f5b7eade3809 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -88,7 +88,7 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 			     struct i915_request *until,
 			     u32 *hwsp_offset);
 
-void intel_timelines_init(struct drm_i915_private *i915);
-void intel_timelines_fini(struct drm_i915_private *i915);
+void intel_gt_init_timelines(struct intel_gt *gt);
+void intel_gt_fini_timelines(struct intel_gt *gt);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index aaf15cbe1ce1..02181c5020db 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -10,14 +10,15 @@
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/mutex.h>
+#include <linux/rcupdate.h>
 #include <linux/types.h>
 
 #include "i915_active_types.h"
 
-struct drm_i915_private;
 struct i915_vma;
-struct intel_timeline_cacheline;
 struct i915_syncmap;
+struct intel_gt;
+struct intel_timeline_hwsp;
 
 struct intel_timeline {
 	u64 fence_context;
@@ -87,4 +88,13 @@ struct intel_timeline {
 	struct rcu_head rcu;
 };
 
+struct intel_timeline_cacheline {
+	struct i915_active active;
+
+	struct intel_timeline_hwsp *hwsp;
+	void *vaddr;
+
+	struct rcu_head rcu;
+};
+
 #endif /* __I915_TIMELINE_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index e4bccc14602f..4e292d4bf7b9 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -6,6 +6,7 @@
 
 #include "i915_drv.h"
 #include "intel_context.h"
+#include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_ring.h"
 #include "intel_workarounds.h"
@@ -146,21 +147,27 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
 	}
 }
 
-static void
-wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
-		   u32 val)
+static void wa_add(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
+		   u32 val, u32 read_mask)
 {
 	struct i915_wa wa = {
 		.reg  = reg,
 		.mask = mask,
 		.val  = val,
-		.read = mask,
+		.read = read_mask,
 	};
 
 	_wa_add(wal, &wa);
 }
 
 static void
+wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
+		   u32 val)
+{
+	wa_add(wal, reg, mask, val, mask);
+}
+
+static void
 wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 {
 	wa_write_masked_or(wal, reg, val, _MASKED_BIT_ENABLE(val));
@@ -247,7 +254,7 @@ static void bdw_ctx_workarounds_init(struct intel_engine_cs *engine,
 
 	/* WaDisableDopClockGating:bdw
 	 *
-	 * Also see the related UCGTCL1 write in broadwell_init_clock_gating()
+	 * Also see the related UCGTCL1 write in bdw_init_clock_gating()
 	 * to disable EUTC clock gating.
 	 */
 	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
@@ -568,9 +575,24 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
+	u32 val;
+
 	/* Wa_1409142259:tgl */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
+
+	/* Wa_1604555607:tgl */
+	val = intel_uncore_read(engine->uncore, FF_MODE2);
+	val &= ~FF_MODE2_TDS_TIMER_MASK;
+	val |= FF_MODE2_TDS_TIMER_128;
+	/*
+	 * FIXME: FF_MODE2 register is not readable till TGL B0. We can
+	 * enable verification of WA from the later steppings, which enables
+	 * the read of FF_MODE2.
+	 */
+	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val,
+	       IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 :
+			    FF_MODE2_TDS_TIMER_MASK);
 }
 
 static void
@@ -1315,6 +1337,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     GEN6_RC_SLEEP_PSMI_CONTROL,
 			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
 			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
+
+		/*
+		 * Wa_1606679103:tgl
+		 * (see also Wa_1606682166:icl)
+		 */
+		wa_write_or(wal,
+			    GEN7_SARCHKMD,
+			    GEN7_DISABLE_SAMPLER_PREFETCH);
 	}
 
 	if (IS_GEN(i915, 11)) {
@@ -1574,7 +1604,9 @@ static int engine_wa_list_verify(struct intel_context *ce,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
+	intel_engine_pm_get(ce->engine);
 	rq = intel_context_create_request(ce);
+	intel_engine_pm_put(ce->engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_vma;
@@ -1584,16 +1616,17 @@ static int engine_wa_list_verify(struct intel_context *ce,
 	if (err)
 		goto err_vma;
 
+	i915_request_get(rq);
 	i915_request_add(rq);
 	if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 		err = -ETIME;
-		goto err_vma;
+		goto err_rq;
 	}
 
 	results = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
 	if (IS_ERR(results)) {
 		err = PTR_ERR(results);
-		goto err_vma;
+		goto err_rq;
 	}
 
 	err = 0;
@@ -1607,6 +1640,8 @@ static int engine_wa_list_verify(struct intel_context *ce,
 
 	i915_gem_object_unpin_map(vma->obj);
 
+err_rq:
+	i915_request_put(rq);
 err_vma:
 	i915_vma_unpin(vma);
 	i915_vma_put(vma);
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 83f549d203a0..a560b7eee2cd 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -77,7 +77,7 @@ static void advance(struct i915_request *request)
 	i915_request_mark_complete(request);
 	GEM_BUG_ON(!i915_request_completed(request));
 
-	intel_engine_queue_breadcrumbs(request->engine);
+	intel_engine_signal_breadcrumbs(request->engine);
 }
 
 static void hw_delay_complete(struct timer_list *t)
@@ -149,7 +149,11 @@ static int mock_context_alloc(struct intel_context *ce)
 
 static int mock_context_pin(struct intel_context *ce)
 {
-	return intel_context_active_acquire(ce);
+	return 0;
+}
+
+static void mock_context_reset(struct intel_context *ce)
+{
 }
 
 static const struct intel_context_ops mock_context_ops = {
@@ -161,6 +165,7 @@ static const struct intel_context_ops mock_context_ops = {
 	.enter = intel_context_enter_engine,
 	.exit = intel_context_exit_engine,
 
+	.reset = mock_context_reset,
 	.destroy = mock_context_destroy,
 };
 
@@ -207,16 +212,12 @@ static void mock_reset_prepare(struct intel_engine_cs *engine)
 {
 }
 
-static void mock_reset(struct intel_engine_cs *engine, bool stalled)
+static void mock_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	GEM_BUG_ON(stalled);
 }
 
-static void mock_reset_finish(struct intel_engine_cs *engine)
-{
-}
-
-static void mock_cancel_requests(struct intel_engine_cs *engine)
+static void mock_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct i915_request *request;
 	unsigned long flags;
@@ -234,6 +235,24 @@ static void mock_cancel_requests(struct intel_engine_cs *engine)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
+static void mock_reset_finish(struct intel_engine_cs *engine)
+{
+}
+
+static void mock_engine_release(struct intel_engine_cs *engine)
+{
+	struct mock_engine *mock =
+		container_of(engine, typeof(*mock), base);
+
+	GEM_BUG_ON(timer_pending(&mock->hw_delay));
+
+	intel_context_unpin(engine->kernel_context);
+	intel_context_put(engine->kernel_context);
+
+	intel_engine_fini_retire(engine);
+	intel_engine_fini_breadcrumbs(engine);
+}
+
 struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 				    const char *name,
 				    int id)
@@ -265,9 +284,11 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.submit_request = mock_submit_request;
 
 	engine->base.reset.prepare = mock_reset_prepare;
-	engine->base.reset.reset = mock_reset;
+	engine->base.reset.rewind = mock_reset_rewind;
+	engine->base.reset.cancel = mock_reset_cancel;
 	engine->base.reset.finish = mock_reset_finish;
-	engine->base.cancel_requests = mock_cancel_requests;
+
+	engine->base.release = mock_engine_release;
 
 	i915->gt.engine[id] = &engine->base;
 	i915->gt.engine_class[0][id] = &engine->base;
@@ -290,6 +311,7 @@ int mock_engine_init(struct intel_engine_cs *engine)
 	intel_engine_init_breadcrumbs(engine);
 	intel_engine_init_execlists(engine);
 	intel_engine_init__pm(engine);
+	intel_engine_init_retire(engine);
 	intel_engine_pool_init(&engine->pool);
 
 	ce = create_kernel_context(engine);
@@ -321,18 +343,3 @@ void mock_engine_flush(struct intel_engine_cs *engine)
 void mock_engine_reset(struct intel_engine_cs *engine)
 {
 }
-
-void mock_engine_free(struct intel_engine_cs *engine)
-{
-	struct mock_engine *mock =
-		container_of(engine, typeof(*mock), base);
-
-	GEM_BUG_ON(timer_pending(&mock->hw_delay));
-
-	intel_context_unpin(engine->kernel_context);
-	intel_context_put(engine->kernel_context);
-
-	intel_engine_fini_breadcrumbs(engine);
-
-	kfree(engine);
-}
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index bc720defc6b8..e874dfaa5316 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -5,6 +5,7 @@
  */
 
 #include "i915_selftest.h"
+#include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 
@@ -47,35 +48,36 @@ static int context_sync(struct intel_context *ce)
 
 	mutex_lock(&tl->mutex);
 	do {
-		struct dma_fence *fence;
+		struct i915_request *rq;
 		long timeout;
 
-		fence = i915_active_fence_get(&tl->last_request);
-		if (!fence)
+		if (list_empty(&tl->requests))
 			break;
 
-		timeout = dma_fence_wait_timeout(fence, false, HZ / 10);
+		rq = list_last_entry(&tl->requests, typeof(*rq), link);
+		i915_request_get(rq);
+
+		timeout = i915_request_wait(rq, 0, HZ / 10);
 		if (timeout < 0)
 			err = timeout;
 		else
-			i915_request_retire_upto(to_request(fence));
+			i915_request_retire_upto(rq);
 
-		dma_fence_put(fence);
+		i915_request_put(rq);
 	} while (!err);
 	mutex_unlock(&tl->mutex);
 
 	return err;
 }
 
-static int __live_context_size(struct intel_engine_cs *engine,
-			       struct i915_gem_context *fixme)
+static int __live_context_size(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 	struct i915_request *rq;
 	void *vaddr;
 	int err;
 
-	ce = intel_context_create(fixme, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
@@ -118,7 +120,7 @@ static int __live_context_size(struct intel_engine_cs *engine,
 		goto err_unpin;
 
 	/* Force the context switch */
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_unpin;
@@ -143,7 +145,6 @@ static int live_context_size(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	enum intel_engine_id id;
 	int err = 0;
 
@@ -152,10 +153,6 @@ static int live_context_size(void *arg)
 	 * HW tries to write past the end of one.
 	 */
 
-	fixme = kernel_context(gt->i915);
-	if (IS_ERR(fixme))
-		return PTR_ERR(fixme);
-
 	for_each_engine(engine, gt, id) {
 		struct {
 			struct drm_i915_gem_object *state;
@@ -180,7 +177,7 @@ static int live_context_size(void *arg)
 		/* Overlaps with the execlists redzone */
 		engine->context_size += I915_GTT_PAGE_SIZE;
 
-		err = __live_context_size(engine, fixme);
+		err = __live_context_size(engine);
 
 		engine->context_size -= I915_GTT_PAGE_SIZE;
 
@@ -193,13 +190,12 @@ static int live_context_size(void *arg)
 			break;
 	}
 
-	kernel_context_close(fixme);
 	return err;
 }
 
-static int __live_active_context(struct intel_engine_cs *engine,
-				 struct i915_gem_context *fixme)
+static int __live_active_context(struct intel_engine_cs *engine)
 {
+	unsigned long saved_heartbeat;
 	struct intel_context *ce;
 	int pass;
 	int err;
@@ -223,40 +219,55 @@ static int __live_active_context(struct intel_engine_cs *engine,
 		return -EINVAL;
 	}
 
-	ce = intel_context_create(fixme, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
+	saved_heartbeat = engine->props.heartbeat_interval_ms;
+	engine->props.heartbeat_interval_ms = 0;
+
 	for (pass = 0; pass <= 2; pass++) {
 		struct i915_request *rq;
 
+		intel_engine_pm_get(engine);
+
 		rq = intel_context_create_request(ce);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
-			goto err;
+			goto out_engine;
 		}
 
 		err = request_sync(rq);
 		if (err)
-			goto err;
+			goto out_engine;
 
 		/* Context will be kept active until after an idle-barrier. */
 		if (i915_active_is_idle(&ce->active)) {
 			pr_err("context is not active; expected idle-barrier (%s pass %d)\n",
 			       engine->name, pass);
 			err = -EINVAL;
-			goto err;
+			goto out_engine;
 		}
 
 		if (!intel_engine_pm_is_awake(engine)) {
 			pr_err("%s is asleep before idle-barrier\n",
 			       engine->name);
 			err = -EINVAL;
-			goto err;
+			goto out_engine;
 		}
+
+out_engine:
+		intel_engine_pm_put(engine);
+		if (err)
+			goto err;
 	}
 
 	/* Now make sure our idle-barriers are flushed */
+	err = intel_engine_flush_barriers(engine);
+	if (err)
+		goto err;
+
+	/* Wait for the barrier and in the process wait for engine to park */
 	err = context_sync(engine->kernel_context);
 	if (err)
 		goto err;
@@ -266,12 +277,15 @@ static int __live_active_context(struct intel_engine_cs *engine,
 		err = -EINVAL;
 	}
 
+	intel_engine_pm_flush(engine);
+
 	if (intel_engine_pm_is_awake(engine)) {
 		struct drm_printer p = drm_debug_printer(__func__);
 
 		intel_engine_dump(engine, &p,
-				  "%s is still awake after idle-barriers\n",
-				  engine->name);
+				  "%s is still awake:%d after idle-barriers\n",
+				  engine->name,
+				  atomic_read(&engine->wakeref.count));
 		GEM_TRACE_DUMP();
 
 		err = -EINVAL;
@@ -279,6 +293,7 @@ static int __live_active_context(struct intel_engine_cs *engine,
 	}
 
 err:
+	engine->props.heartbeat_interval_ms = saved_heartbeat;
 	intel_context_put(ce);
 	return err;
 }
@@ -287,23 +302,11 @@ static int live_active_context(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	enum intel_engine_id id;
-	struct drm_file *file;
 	int err = 0;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	fixme = live_context(gt->i915, file);
-	if (IS_ERR(fixme)) {
-		err = PTR_ERR(fixme);
-		goto out_file;
-	}
-
 	for_each_engine(engine, gt, id) {
-		err = __live_active_context(engine, fixme);
+		err = __live_active_context(engine);
 		if (err)
 			break;
 
@@ -312,8 +315,6 @@ static int live_active_context(void *arg)
 			break;
 	}
 
-out_file:
-	mock_file_free(gt->i915, file);
 	return err;
 }
 
@@ -345,10 +346,10 @@ unpin:
 	return err;
 }
 
-static int __live_remote_context(struct intel_engine_cs *engine,
-				 struct i915_gem_context *fixme)
+static int __live_remote_context(struct intel_engine_cs *engine)
 {
 	struct intel_context *local, *remote;
+	unsigned long saved_heartbeat;
 	int pass;
 	int err;
 
@@ -360,16 +361,26 @@ static int __live_remote_context(struct intel_engine_cs *engine,
 	 * clobber the idle-barrier.
 	 */
 
-	remote = intel_context_create(fixme, engine);
+	if (intel_engine_pm_is_awake(engine)) {
+		pr_err("%s is awake before starting %s!\n",
+		       engine->name, __func__);
+		return -EINVAL;
+	}
+
+	remote = intel_context_create(engine);
 	if (IS_ERR(remote))
 		return PTR_ERR(remote);
 
-	local = intel_context_create(fixme, engine);
+	local = intel_context_create(engine);
 	if (IS_ERR(local)) {
 		err = PTR_ERR(local);
 		goto err_remote;
 	}
 
+	saved_heartbeat = engine->props.heartbeat_interval_ms;
+	engine->props.heartbeat_interval_ms = 0;
+	intel_engine_pm_get(engine);
+
 	for (pass = 0; pass <= 2; pass++) {
 		err = __remote_sync(local, remote);
 		if (err)
@@ -387,6 +398,9 @@ static int __live_remote_context(struct intel_engine_cs *engine,
 		}
 	}
 
+	intel_engine_pm_put(engine);
+	engine->props.heartbeat_interval_ms = saved_heartbeat;
+
 	intel_context_put(local);
 err_remote:
 	intel_context_put(remote);
@@ -397,23 +411,11 @@ static int live_remote_context(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	enum intel_engine_id id;
-	struct drm_file *file;
 	int err = 0;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	fixme = live_context(gt->i915, file);
-	if (IS_ERR(fixme)) {
-		err = PTR_ERR(fixme);
-		goto out_file;
-	}
-
 	for_each_engine(engine, gt, id) {
-		err = __live_remote_context(engine, fixme);
+		err = __live_remote_context(engine);
 		if (err)
 			break;
 
@@ -422,8 +424,6 @@ static int live_remote_context(void *arg)
 			break;
 	}
 
-out_file:
-	mock_file_free(gt->i915, file);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
index 3880f07c29b8..f88e445a1cae 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
@@ -4,7 +4,365 @@
  * Copyright © 2018 Intel Corporation
  */
 
-#include "../i915_selftest.h"
+#include <linux/sort.h>
+
+#include "intel_gt_pm.h"
+#include "intel_rps.h"
+
+#include "i915_selftest.h"
+#include "selftests/igt_flush_test.h"
+
+#define COUNT 5
+
+static int cmp_u32(const void *A, const void *B)
+{
+	const u32 *a = A, *b = B;
+
+	return *a - *b;
+}
+
+static void perf_begin(struct intel_gt *gt)
+{
+	intel_gt_pm_get(gt);
+
+	/* Boost gpufreq to max [waitboost] and keep it fixed */
+	atomic_inc(&gt->rps.num_waiters);
+	schedule_work(&gt->rps.work);
+	flush_work(&gt->rps.work);
+}
+
+static int perf_end(struct intel_gt *gt)
+{
+	atomic_dec(&gt->rps.num_waiters);
+	intel_gt_pm_put(gt);
+
+	return igt_flush_test(gt->i915);
+}
+
+static int write_timestamp(struct i915_request *rq, int slot)
+{
+	u32 cmd;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	cmd = MI_STORE_REGISTER_MEM | MI_USE_GGTT;
+	if (INTEL_GEN(rq->i915) >= 8)
+		cmd++;
+	*cs++ = cmd;
+	*cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(rq->engine->mmio_base));
+	*cs++ = i915_request_timeline(rq)->hwsp_offset + slot * sizeof(u32);
+	*cs++ = 0;
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static struct i915_vma *create_empty_batch(struct intel_context *ce)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	u32 *cs;
+	int err;
+
+	obj = i915_gem_object_create_internal(ce->engine->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	cs = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_put;
+	}
+
+	cs[0] = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(obj);
+
+	vma = i915_vma_instance(obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_unpin;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto err_unpin;
+
+	i915_gem_object_unpin_map(obj);
+	return vma;
+
+err_unpin:
+	i915_gem_object_unpin_map(obj);
+err_put:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
+}
+
+static u32 trifilter(u32 *a)
+{
+	u64 sum;
+
+	sort(a, COUNT, sizeof(*a), cmp_u32, NULL);
+
+	sum = mul_u32_u32(a[2], 2);
+	sum += a[1];
+	sum += a[3];
+
+	return sum >> 2;
+}
+
+static int perf_mi_bb_start(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	if (INTEL_GEN(gt->i915) < 7) /* for per-engine CS_TIMESTAMP */
+		return 0;
+
+	perf_begin(gt);
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce = engine->kernel_context;
+		struct i915_vma *batch;
+		u32 cycles[COUNT];
+		int i;
+
+		intel_engine_pm_get(engine);
+
+		batch = create_empty_batch(ce);
+		if (IS_ERR(batch)) {
+			err = PTR_ERR(batch);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		err = i915_vma_sync(batch);
+		if (err) {
+			intel_engine_pm_put(engine);
+			i915_vma_put(batch);
+			break;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(cycles); i++) {
+			struct i915_request *rq;
+
+			rq = i915_request_create(ce);
+			if (IS_ERR(rq)) {
+				err = PTR_ERR(rq);
+				break;
+			}
+
+			err = write_timestamp(rq, 2);
+			if (err)
+				goto out;
+
+			err = rq->engine->emit_bb_start(rq,
+							batch->node.start, 8,
+							0);
+			if (err)
+				goto out;
+
+			err = write_timestamp(rq, 3);
+			if (err)
+				goto out;
+
+out:
+			i915_request_get(rq);
+			i915_request_add(rq);
+
+			if (i915_request_wait(rq, 0, HZ / 5) < 0)
+				err = -EIO;
+			i915_request_put(rq);
+			if (err)
+				break;
+
+			cycles[i] = rq->hwsp_seqno[3] - rq->hwsp_seqno[2];
+		}
+		i915_vma_put(batch);
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
+
+		pr_info("%s: MI_BB_START cycles: %u\n",
+			engine->name, trifilter(cycles));
+	}
+	if (perf_end(gt))
+		err = -EIO;
+
+	return err;
+}
+
+static struct i915_vma *create_nop_batch(struct intel_context *ce)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	u32 *cs;
+	int err;
+
+	obj = i915_gem_object_create_internal(ce->engine->i915, SZ_64K);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	cs = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_put;
+	}
+
+	memset(cs, 0, SZ_64K);
+	cs[SZ_64K / sizeof(*cs) - 1] = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(obj);
+
+	vma = i915_vma_instance(obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_unpin;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto err_unpin;
+
+	i915_gem_object_unpin_map(obj);
+	return vma;
+
+err_unpin:
+	i915_gem_object_unpin_map(obj);
+err_put:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
+}
+
+static int perf_mi_noop(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	if (INTEL_GEN(gt->i915) < 7) /* for per-engine CS_TIMESTAMP */
+		return 0;
+
+	perf_begin(gt);
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce = engine->kernel_context;
+		struct i915_vma *base, *nop;
+		u32 cycles[COUNT];
+		int i;
+
+		intel_engine_pm_get(engine);
+
+		base = create_empty_batch(ce);
+		if (IS_ERR(base)) {
+			err = PTR_ERR(base);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		err = i915_vma_sync(base);
+		if (err) {
+			i915_vma_put(base);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		nop = create_nop_batch(ce);
+		if (IS_ERR(nop)) {
+			err = PTR_ERR(nop);
+			i915_vma_put(base);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		err = i915_vma_sync(nop);
+		if (err) {
+			i915_vma_put(nop);
+			i915_vma_put(base);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(cycles); i++) {
+			struct i915_request *rq;
+
+			rq = i915_request_create(ce);
+			if (IS_ERR(rq)) {
+				err = PTR_ERR(rq);
+				break;
+			}
+
+			err = write_timestamp(rq, 2);
+			if (err)
+				goto out;
+
+			err = rq->engine->emit_bb_start(rq,
+							base->node.start, 8,
+							0);
+			if (err)
+				goto out;
+
+			err = write_timestamp(rq, 3);
+			if (err)
+				goto out;
+
+			err = rq->engine->emit_bb_start(rq,
+							nop->node.start,
+							nop->node.size,
+							0);
+			if (err)
+				goto out;
+
+			err = write_timestamp(rq, 4);
+			if (err)
+				goto out;
+
+out:
+			i915_request_get(rq);
+			i915_request_add(rq);
+
+			if (i915_request_wait(rq, 0, HZ / 5) < 0)
+				err = -EIO;
+			i915_request_put(rq);
+			if (err)
+				break;
+
+			cycles[i] =
+				(rq->hwsp_seqno[4] - rq->hwsp_seqno[3]) -
+				(rq->hwsp_seqno[3] - rq->hwsp_seqno[2]);
+		}
+		i915_vma_put(nop);
+		i915_vma_put(base);
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
+
+		pr_info("%s: 16K MI_NOOP cycles: %u\n",
+			engine->name, trifilter(cycles));
+	}
+	if (perf_end(gt))
+		err = -EIO;
+
+	return err;
+}
+
+int intel_engine_cs_perf_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(perf_mi_bb_start),
+		SUBTEST(perf_mi_noop),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
 
 static int intel_mmio_bases_check(void *arg)
 {
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index e864406bd2d9..43d4d589749f 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -11,6 +11,28 @@
 #include "intel_gt_requests.h"
 #include "i915_selftest.h"
 
+static int timeline_sync(struct intel_timeline *tl)
+{
+	struct dma_fence *fence;
+	long timeout;
+
+	fence = i915_active_fence_get(&tl->last_request);
+	if (!fence)
+		return 0;
+
+	timeout = dma_fence_wait_timeout(fence, true, HZ / 2);
+	dma_fence_put(fence);
+	if (timeout < 0)
+		return timeout;
+
+	return 0;
+}
+
+static int engine_sync_barrier(struct intel_engine_cs *engine)
+{
+	return timeline_sync(engine->kernel_context->timeline);
+}
+
 struct pulse {
 	struct i915_active active;
 	struct kref kref;
@@ -53,9 +75,7 @@ static struct pulse *pulse_create(void)
 
 static void pulse_unlock_wait(struct pulse *p)
 {
-	mutex_lock(&p->active.mutex);
-	mutex_unlock(&p->active.mutex);
-	flush_work(&p->active.work);
+	i915_active_unlock_wait(&p->active);
 }
 
 static int __live_idle_pulse(struct intel_engine_cs *engine,
@@ -92,7 +112,12 @@ static int __live_idle_pulse(struct intel_engine_cs *engine,
 
 	GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));
 
-	if (intel_gt_retire_requests_timeout(engine->gt, HZ / 5)) {
+	if (engine_sync_barrier(engine)) {
+		struct drm_printer m = drm_err_printer("pulse");
+
+		pr_err("%s: no heartbeat pulse?\n", engine->name);
+		intel_engine_dump(engine, &m, "%s", engine->name);
+
 		err = -ETIME;
 		goto out;
 	}
@@ -175,8 +200,7 @@ static int __live_heartbeat_fast(struct intel_engine_cs *engine)
 	int err;
 	int i;
 
-	ce = intel_context_create(engine->kernel_context->gem_context,
-				  engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index d1752f15702a..09ff8e4f88af 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -6,6 +6,7 @@
  */
 
 #include "selftest_llc.h"
+#include "selftest_rc6.h"
 
 static int live_gt_resume(void *arg)
 {
@@ -50,6 +51,7 @@ static int live_gt_resume(void *arg)
 int intel_gt_pm_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(live_rc6_manual),
 		SUBTEST(live_gt_resume),
 	};
 
@@ -58,3 +60,20 @@ int intel_gt_pm_live_selftests(struct drm_i915_private *i915)
 
 	return intel_gt_live_subtests(tests, &i915->gt);
 }
+
+int intel_gt_pm_late_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		/*
+		 * These tests may leave the system in an undesirable state.
+		 * They are intended to be run last in CI and the system
+		 * rebooted afterwards.
+		 */
+		SUBTEST(live_rc6_ctx_wa),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 85e9ccf5c304..3e5e6c86e843 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -25,7 +25,9 @@
 #include <linux/kthread.h>
 
 #include "gem/i915_gem_context.h"
-#include "gt/intel_gt.h"
+
+#include "intel_gt.h"
+#include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
 
 #include "i915_selftest.h"
@@ -308,6 +310,24 @@ static bool wait_until_running(struct hang *h, struct i915_request *rq)
 			  1000));
 }
 
+static void engine_heartbeat_disable(struct intel_engine_cs *engine,
+				     unsigned long *saved)
+{
+	*saved = engine->props.heartbeat_interval_ms;
+	engine->props.heartbeat_interval_ms = 0;
+
+	intel_engine_pm_get(engine);
+	intel_engine_park_heartbeat(engine);
+}
+
+static void engine_heartbeat_enable(struct intel_engine_cs *engine,
+				    unsigned long saved)
+{
+	intel_engine_pm_put(engine);
+
+	engine->props.heartbeat_interval_ms = saved;
+}
+
 static int igt_hang_sanitycheck(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -377,36 +397,30 @@ static int igt_reset_nop(void *arg)
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	unsigned int reset_count, count;
 	enum intel_engine_id id;
-	struct drm_file *file;
 	IGT_TIMEOUT(end_time);
 	int err = 0;
 
 	/* Check that we can reset during non-user portions of requests */
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	ctx = live_context(gt->i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out;
-	}
-
-	i915_gem_context_clear_bannable(ctx);
 	reset_count = i915_reset_count(global);
 	count = 0;
 	do {
 		for_each_engine(engine, gt, id) {
+			struct intel_context *ce;
 			int i;
 
+			ce = intel_context_create(engine);
+			if (IS_ERR(ce)) {
+				err = PTR_ERR(ce);
+				break;
+			}
+
 			for (i = 0; i < 16; i++) {
 				struct i915_request *rq;
 
-				rq = igt_request_alloc(ctx, engine);
+				rq = intel_context_create_request(ce);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
 					break;
@@ -414,6 +428,8 @@ static int igt_reset_nop(void *arg)
 
 				i915_request_add(rq);
 			}
+
+			intel_context_put(ce);
 		}
 
 		igt_global_reset_lock(gt);
@@ -437,10 +453,7 @@ static int igt_reset_nop(void *arg)
 	} while (time_before(jiffies, end_time));
 	pr_info("%s: %d resets\n", __func__, count);
 
-	err = igt_flush_test(gt->i915);
-out:
-	mock_file_free(gt->i915, file);
-	if (intel_gt_is_wedged(gt))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 	return err;
 }
@@ -450,36 +463,29 @@ static int igt_reset_nop_engine(void *arg)
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
-	struct drm_file *file;
-	int err = 0;
 
 	/* Check that we can engine-reset during non-user portions */
 
 	if (!intel_has_reset_engine(gt))
 		return 0;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	ctx = live_context(gt->i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out;
-	}
-
-	i915_gem_context_clear_bannable(ctx);
 	for_each_engine(engine, gt, id) {
-		unsigned int reset_count, reset_engine_count;
-		unsigned int count;
+		unsigned int reset_count, reset_engine_count, count;
+		struct intel_context *ce;
+		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
+		int err;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce))
+			return PTR_ERR(ce);
 
 		reset_count = i915_reset_count(global);
 		reset_engine_count = i915_reset_engine_count(global, engine);
 		count = 0;
 
+		engine_heartbeat_disable(engine, &heartbeat);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			int i;
@@ -494,7 +500,7 @@ static int igt_reset_nop_engine(void *arg)
 			for (i = 0; i < 16; i++) {
 				struct i915_request *rq;
 
-				rq = igt_request_alloc(ctx, engine);
+				rq = intel_context_create_request(ce);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
 					break;
@@ -523,22 +529,18 @@ static int igt_reset_nop_engine(void *arg)
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
+		engine_heartbeat_enable(engine, heartbeat);
 
-		if (err)
-			break;
+		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
 
-		err = igt_flush_test(gt->i915);
+		intel_context_put(ce);
+		if (igt_flush_test(gt->i915))
+			err = -EIO;
 		if (err)
-			break;
+			return err;
 	}
 
-	err = igt_flush_test(gt->i915);
-out:
-	mock_file_free(gt->i915, file);
-	if (intel_gt_is_wedged(gt))
-		err = -EIO;
-	return err;
+	return 0;
 }
 
 static int __igt_reset_engine(struct intel_gt *gt, bool active)
@@ -562,6 +564,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 
 	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count;
+		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 
 		if (active && !intel_engine_can_store_dword(engine))
@@ -577,7 +580,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 		reset_count = i915_reset_count(global);
 		reset_engine_count = i915_reset_engine_count(global, engine);
 
-		intel_engine_pm_get(engine);
+		engine_heartbeat_disable(engine, &heartbeat);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			if (active) {
@@ -629,7 +632,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		intel_engine_pm_put(engine);
+		engine_heartbeat_enable(engine, heartbeat);
 
 		if (err)
 			break;
@@ -699,43 +702,43 @@ static int active_engine(void *data)
 	struct active_engine *arg = data;
 	struct intel_engine_cs *engine = arg->engine;
 	struct i915_request *rq[8] = {};
-	struct i915_gem_context *ctx[ARRAY_SIZE(rq)];
-	struct drm_file *file;
-	unsigned long count = 0;
+	struct intel_context *ce[ARRAY_SIZE(rq)];
+	unsigned long count;
 	int err = 0;
 
-	file = mock_file(engine->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	for (count = 0; count < ARRAY_SIZE(ctx); count++) {
-		ctx[count] = live_context(engine->i915, file);
-		if (IS_ERR(ctx[count])) {
-			err = PTR_ERR(ctx[count]);
+	for (count = 0; count < ARRAY_SIZE(ce); count++) {
+		ce[count] = intel_context_create(engine);
+		if (IS_ERR(ce[count])) {
+			err = PTR_ERR(ce[count]);
 			while (--count)
-				i915_gem_context_put(ctx[count]);
-			goto err_file;
+				intel_context_put(ce[count]);
+			return err;
 		}
 	}
 
+	count = 0;
 	while (!kthread_should_stop()) {
 		unsigned int idx = count++ & (ARRAY_SIZE(rq) - 1);
 		struct i915_request *old = rq[idx];
 		struct i915_request *new;
 
-		new = igt_request_alloc(ctx[idx], engine);
+		new = intel_context_create_request(ce[idx]);
 		if (IS_ERR(new)) {
 			err = PTR_ERR(new);
 			break;
 		}
 
-		if (arg->flags & TEST_PRIORITY)
-			ctx[idx]->sched.priority =
-				i915_prandom_u32_max_state(512, &prng);
-
 		rq[idx] = i915_request_get(new);
 		i915_request_add(new);
 
+		if (engine->schedule && arg->flags & TEST_PRIORITY) {
+			struct i915_sched_attr attr = {
+				.priority =
+					i915_prandom_u32_max_state(512, &prng),
+			};
+			engine->schedule(rq[idx], &attr);
+		}
+
 		err = active_request_put(old);
 		if (err)
 			break;
@@ -749,10 +752,10 @@ static int active_engine(void *data)
 		/* Keep the first error */
 		if (!err)
 			err = err__;
+
+		intel_context_put(ce[count]);
 	}
 
-err_file:
-	mock_file_free(engine->i915, file);
 	return err;
 }
 
@@ -786,6 +789,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 		struct active_engine threads[I915_NUM_ENGINES] = {};
 		unsigned long device = i915_reset_count(global);
 		unsigned long count = 0, reported;
+		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 
 		if (flags & TEST_ACTIVE &&
@@ -828,7 +832,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 
 		yield(); /* start all threads before we begin */
 
-		intel_engine_pm_get(engine);
+		engine_heartbeat_disable(engine, &heartbeat);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			struct i915_request *rq = NULL;
@@ -902,7 +906,8 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		intel_engine_pm_put(engine);
+		engine_heartbeat_enable(engine, heartbeat);
+
 		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
 			engine->name, test_name, count);
 
@@ -1300,32 +1305,21 @@ static int igt_reset_evict_ggtt(void *arg)
 static int igt_reset_evict_ppgtt(void *arg)
 {
 	struct intel_gt *gt = arg;
-	struct i915_gem_context *ctx;
-	struct i915_address_space *vm;
-	struct drm_file *file;
+	struct i915_ppgtt *ppgtt;
 	int err;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+	/* aliasing == global gtt locking, covered above */
+	if (INTEL_PPGTT(gt->i915) < INTEL_PPGTT_FULL)
+		return 0;
 
-	ctx = live_context(gt->i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out;
-	}
+	ppgtt = i915_ppgtt_create(gt);
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
 
-	err = 0;
-	vm = i915_gem_context_get_vm_rcu(ctx);
-	if (!i915_is_ggtt(vm)) {
-		/* aliasing == global gtt locking, covered above */
-		err = __igt_reset_evict_vma(gt, vm,
-					    evict_vma, EXEC_OBJECT_WRITE);
-	}
-	i915_vm_put(vm);
+	err = __igt_reset_evict_vma(gt, &ppgtt->vm,
+				    evict_vma, EXEC_OBJECT_WRITE);
+	i915_vm_put(&ppgtt->vm);
 
-out:
-	mock_file_free(gt->i915, file);
 	return err;
 }
 
@@ -1504,7 +1498,7 @@ static int igt_handle_error(void *arg)
 	struct intel_engine_cs *engine = gt->engine[RCS0];
 	struct hang h;
 	struct i915_request *rq;
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 	int err;
 
 	/* Check that we can issue a global GPU and engine reset */
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index eb71ac2f992c..15cda024e3e4 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -50,14 +50,31 @@ static struct i915_vma *create_scratch(struct intel_gt *gt)
 	return vma;
 }
 
+static void engine_heartbeat_disable(struct intel_engine_cs *engine,
+				     unsigned long *saved)
+{
+	*saved = engine->props.heartbeat_interval_ms;
+	engine->props.heartbeat_interval_ms = 0;
+
+	intel_engine_pm_get(engine);
+	intel_engine_park_heartbeat(engine);
+}
+
+static void engine_heartbeat_enable(struct intel_engine_cs *engine,
+				    unsigned long saved)
+{
+	intel_engine_pm_put(engine);
+
+	engine->props.heartbeat_interval_ms = saved;
+}
+
 static int live_sanitycheck(void *arg)
 {
 	struct intel_gt *gt = arg;
-	struct i915_gem_engines_iter it;
-	struct i915_gem_context *ctx;
-	struct intel_context *ce;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	struct igt_spinner spin;
-	int err = -ENOMEM;
+	int err = 0;
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(gt->i915))
 		return 0;
@@ -65,17 +82,20 @@ static int live_sanitycheck(void *arg)
 	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
-		goto err_spin;
-
-	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
 		struct i915_request *rq;
 
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
 		rq = igt_spinner_create_request(&spin, ce, MI_NOOP);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
-			goto err_ctx;
+			goto out_ctx;
 		}
 
 		i915_request_add(rq);
@@ -84,21 +104,21 @@ static int live_sanitycheck(void *arg)
 			GEM_TRACE_DUMP();
 			intel_gt_set_wedged(gt);
 			err = -EIO;
-			goto err_ctx;
+			goto out_ctx;
 		}
 
 		igt_spinner_end(&spin);
 		if (igt_flush_test(gt->i915)) {
 			err = -EIO;
-			goto err_ctx;
+			goto out_ctx;
 		}
+
+out_ctx:
+		intel_context_put(ce);
+		if (err)
+			break;
 	}
 
-	err = 0;
-err_ctx:
-	i915_gem_context_unlock_engines(ctx);
-	kernel_context_close(ctx);
-err_spin:
 	igt_spinner_fini(&spin);
 	return err;
 }
@@ -106,7 +126,6 @@ err_spin:
 static int live_unlite_restore(struct intel_gt *gt, int prio)
 {
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
 	struct igt_spinner spin;
 	int err = -ENOMEM;
@@ -119,15 +138,12 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 	if (igt_spinner_init(&spin, gt))
 		return err;
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
-		goto err_spin;
-
 	err = 0;
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce[2] = {};
 		struct i915_request *rq[2];
 		struct igt_live_test t;
+		unsigned long saved;
 		int n;
 
 		if (prio && !intel_engine_has_preemption(engine))
@@ -140,11 +156,12 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 			err = -EIO;
 			break;
 		}
+		engine_heartbeat_disable(engine, &saved);
 
 		for (n = 0; n < ARRAY_SIZE(ce); n++) {
 			struct intel_context *tmp;
 
-			tmp = intel_context_create(ctx, engine);
+			tmp = intel_context_create(engine);
 			if (IS_ERR(tmp)) {
 				err = PTR_ERR(tmp);
 				goto err_ce;
@@ -247,14 +264,13 @@ err_ce:
 			intel_context_put(ce[n]);
 		}
 
+		engine_heartbeat_enable(engine, saved);
 		if (igt_live_test_end(&t))
 			err = -EIO;
 		if (err)
 			break;
 	}
 
-	kernel_context_close(ctx);
-err_spin:
 	igt_spinner_fini(&spin);
 	return err;
 }
@@ -309,17 +325,17 @@ emit_semaphore_chain(struct i915_request *rq, struct i915_vma *vma, int idx)
 static struct i915_request *
 semaphore_queue(struct intel_engine_cs *engine, struct i915_vma *vma, int idx)
 {
-	struct i915_gem_context *ctx;
+	struct intel_context *ce;
 	struct i915_request *rq;
 	int err;
 
-	ctx = kernel_context(engine->i915);
-	if (!ctx)
-		return ERR_PTR(-ENOMEM);
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return ERR_CAST(ce);
 
-	rq = igt_request_alloc(ctx, engine);
+	rq = intel_context_create_request(ce);
 	if (IS_ERR(rq))
-		goto out_ctx;
+		goto out_ce;
 
 	err = 0;
 	if (rq->engine->emit_init_breadcrumb)
@@ -332,8 +348,8 @@ semaphore_queue(struct intel_engine_cs *engine, struct i915_vma *vma, int idx)
 	if (err)
 		rq = ERR_PTR(err);
 
-out_ctx:
-	kernel_context_close(ctx);
+out_ce:
+	intel_context_put(ce);
 	return rq;
 }
 
@@ -348,7 +364,7 @@ release_queue(struct intel_engine_cs *engine,
 	struct i915_request *rq;
 	u32 *cs;
 
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -468,12 +484,16 @@ static int live_timeslice_preempt(void *arg)
 		enum intel_engine_id id;
 
 		for_each_engine(engine, gt, id) {
+			unsigned long saved;
+
 			if (!intel_engine_has_preemption(engine))
 				continue;
 
 			memset(vaddr, 0, PAGE_SIZE);
 
+			engine_heartbeat_disable(engine, &saved);
 			err = slice_semaphore_queue(engine, vma, count);
+			engine_heartbeat_enable(engine, saved);
 			if (err)
 				goto err_pin;
 
@@ -497,7 +517,7 @@ static struct i915_request *nop_request(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq;
 
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq))
 		return rq;
 
@@ -507,13 +527,19 @@ static struct i915_request *nop_request(struct intel_engine_cs *engine)
 	return rq;
 }
 
-static void wait_for_submit(struct intel_engine_cs *engine,
-			    struct i915_request *rq)
+static int wait_for_submit(struct intel_engine_cs *engine,
+			   struct i915_request *rq,
+			   unsigned long timeout)
 {
+	timeout += jiffies;
 	do {
 		cond_resched();
 		intel_engine_flush_submission(engine);
-	} while (!i915_request_is_active(rq));
+		if (i915_request_is_active(rq))
+			return 0;
+	} while (time_before(jiffies, timeout));
+
+	return -ETIME;
 }
 
 static long timeslice_threshold(const struct intel_engine_cs *engine)
@@ -566,40 +592,49 @@ static int live_timeslice_queue(void *arg)
 			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
 		};
 		struct i915_request *rq, *nop;
+		unsigned long saved;
 
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
+		engine_heartbeat_disable(engine, &saved);
 		memset(vaddr, 0, PAGE_SIZE);
 
 		/* ELSP[0]: semaphore wait */
 		rq = semaphore_queue(engine, vma, 0);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
-			goto err_pin;
+			goto err_heartbeat;
 		}
 		engine->schedule(rq, &attr);
-		wait_for_submit(engine, rq);
+		err = wait_for_submit(engine, rq, HZ / 2);
+		if (err) {
+			pr_err("%s: Timed out trying to submit semaphores\n",
+			       engine->name);
+			goto err_rq;
+		}
 
 		/* ELSP[1]: nop request */
 		nop = nop_request(engine);
 		if (IS_ERR(nop)) {
 			err = PTR_ERR(nop);
-			i915_request_put(rq);
-			goto err_pin;
+			goto err_rq;
 		}
-		wait_for_submit(engine, nop);
+		err = wait_for_submit(engine, nop, HZ / 2);
 		i915_request_put(nop);
+		if (err) {
+			pr_err("%s: Timed out trying to submit nop\n",
+			       engine->name);
+			goto err_rq;
+		}
 
 		GEM_BUG_ON(i915_request_completed(rq));
 		GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
 
 		/* Queue: semaphore signal, matching priority as semaphore */
 		err = release_queue(engine, vma, 1, effective_prio(rq));
-		if (err) {
-			i915_request_put(rq);
-			goto err_pin;
-		}
+		if (err)
+			goto err_rq;
 
 		intel_engine_flush_submission(engine);
 		if (!READ_ONCE(engine->execlists.timer.expires) &&
@@ -630,12 +665,14 @@ static int live_timeslice_queue(void *arg)
 			memset(vaddr, 0xff, PAGE_SIZE);
 			err = -EIO;
 		}
+err_rq:
 		i915_request_put(rq);
+err_heartbeat:
+		engine_heartbeat_enable(engine, saved);
 		if (err)
 			break;
 	}
 
-err_pin:
 	i915_vma_unpin(vma);
 err_map:
 	i915_gem_object_unpin_map(obj);
@@ -748,15 +785,19 @@ static int live_busywait_preempt(void *arg)
 		*cs++ = 0;
 
 		intel_ring_advance(lo, cs);
+
+		i915_request_get(lo);
 		i915_request_add(lo);
 
 		if (wait_for(READ_ONCE(*map), 10)) {
+			i915_request_put(lo);
 			err = -ETIMEDOUT;
 			goto err_vma;
 		}
 
 		/* Low priority request should be busywaiting now */
 		if (i915_request_wait(lo, 0, 1) != -ETIME) {
+			i915_request_put(lo);
 			pr_err("%s: Busywaiting request did not!\n",
 			       engine->name);
 			err = -EIO;
@@ -766,6 +807,7 @@ static int live_busywait_preempt(void *arg)
 		hi = igt_request_alloc(ctx_hi, engine);
 		if (IS_ERR(hi)) {
 			err = PTR_ERR(hi);
+			i915_request_put(lo);
 			goto err_vma;
 		}
 
@@ -773,6 +815,7 @@ static int live_busywait_preempt(void *arg)
 		if (IS_ERR(cs)) {
 			err = PTR_ERR(cs);
 			i915_request_add(hi);
+			i915_request_put(lo);
 			goto err_vma;
 		}
 
@@ -793,11 +836,13 @@ static int live_busywait_preempt(void *arg)
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 			GEM_TRACE_DUMP();
 
+			i915_request_put(lo);
 			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_vma;
 		}
 		GEM_BUG_ON(READ_ONCE(*map));
+		i915_request_put(lo);
 
 		if (igt_live_test_end(&t)) {
 			err = -EIO;
@@ -1108,7 +1153,7 @@ static int live_nopreempt(void *arg)
 		}
 
 		/* Low priority client, but unpreemptable! */
-		rq_a->flags |= I915_REQUEST_NOPREEMPT;
+		__set_bit(I915_FENCE_FLAG_NOPREEMPT, &rq_a->fence.flags);
 
 		i915_request_add(rq_a);
 		if (!igt_wait_for_spinner(&a.spin, rq_a)) {
@@ -1187,13 +1232,13 @@ static int __cancel_active0(struct live_preempt_cancel *arg)
 				__func__, arg->engine->name))
 		return -EIO;
 
-	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
 	rq = spinner_create_request(&arg->a.spin,
 				    arg->a.ctx, arg->engine,
 				    MI_ARB_CHECK);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
+	clear_bit(CONTEXT_BANNED, &rq->context->flags);
 	i915_request_get(rq);
 	i915_request_add(rq);
 	if (!igt_wait_for_spinner(&arg->a.spin, rq)) {
@@ -1201,7 +1246,7 @@ static int __cancel_active0(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	i915_gem_context_set_banned(arg->a.ctx);
+	intel_context_set_banned(rq->context);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -1236,13 +1281,13 @@ static int __cancel_active1(struct live_preempt_cancel *arg)
 				__func__, arg->engine->name))
 		return -EIO;
 
-	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
 	rq[0] = spinner_create_request(&arg->a.spin,
 				       arg->a.ctx, arg->engine,
 				       MI_NOOP); /* no preemption */
 	if (IS_ERR(rq[0]))
 		return PTR_ERR(rq[0]);
 
+	clear_bit(CONTEXT_BANNED, &rq[0]->context->flags);
 	i915_request_get(rq[0]);
 	i915_request_add(rq[0]);
 	if (!igt_wait_for_spinner(&arg->a.spin, rq[0])) {
@@ -1250,7 +1295,6 @@ static int __cancel_active1(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	clear_bit(CONTEXT_BANNED, &arg->b.ctx->flags);
 	rq[1] = spinner_create_request(&arg->b.spin,
 				       arg->b.ctx, arg->engine,
 				       MI_ARB_CHECK);
@@ -1259,13 +1303,14 @@ static int __cancel_active1(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
+	clear_bit(CONTEXT_BANNED, &rq[1]->context->flags);
 	i915_request_get(rq[1]);
 	err = i915_request_await_dma_fence(rq[1], &rq[0]->fence);
 	i915_request_add(rq[1]);
 	if (err)
 		goto out;
 
-	i915_gem_context_set_banned(arg->b.ctx);
+	intel_context_set_banned(rq[1]->context);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -1308,13 +1353,13 @@ static int __cancel_queued(struct live_preempt_cancel *arg)
 				__func__, arg->engine->name))
 		return -EIO;
 
-	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
 	rq[0] = spinner_create_request(&arg->a.spin,
 				       arg->a.ctx, arg->engine,
 				       MI_ARB_CHECK);
 	if (IS_ERR(rq[0]))
 		return PTR_ERR(rq[0]);
 
+	clear_bit(CONTEXT_BANNED, &rq[0]->context->flags);
 	i915_request_get(rq[0]);
 	i915_request_add(rq[0]);
 	if (!igt_wait_for_spinner(&arg->a.spin, rq[0])) {
@@ -1322,13 +1367,13 @@ static int __cancel_queued(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	clear_bit(CONTEXT_BANNED, &arg->b.ctx->flags);
 	rq[1] = igt_request_alloc(arg->b.ctx, arg->engine);
 	if (IS_ERR(rq[1])) {
 		err = PTR_ERR(rq[1]);
 		goto out;
 	}
 
+	clear_bit(CONTEXT_BANNED, &rq[1]->context->flags);
 	i915_request_get(rq[1]);
 	err = i915_request_await_dma_fence(rq[1], &rq[0]->fence);
 	i915_request_add(rq[1]);
@@ -1349,7 +1394,7 @@ static int __cancel_queued(struct live_preempt_cancel *arg)
 	if (err)
 		goto out;
 
-	i915_gem_context_set_banned(arg->a.ctx);
+	intel_context_set_banned(rq[2]->context);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -1396,13 +1441,13 @@ static int __cancel_hostile(struct live_preempt_cancel *arg)
 		return 0;
 
 	GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
-	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
 	rq = spinner_create_request(&arg->a.spin,
 				    arg->a.ctx, arg->engine,
 				    MI_NOOP); /* preemption disabled */
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
+	clear_bit(CONTEXT_BANNED, &rq->context->flags);
 	i915_request_get(rq);
 	i915_request_add(rq);
 	if (!igt_wait_for_spinner(&arg->a.spin, rq)) {
@@ -1410,7 +1455,7 @@ static int __cancel_hostile(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	i915_gem_context_set_banned(arg->a.ctx);
+	intel_context_set_banned(rq->context);
 	err = intel_engine_pulse(arg->engine); /* force reset */
 	if (err)
 		goto out;
@@ -1665,6 +1710,7 @@ static int live_suppress_wait_preempt(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct preempt_client client[4];
+	struct i915_request *rq[ARRAY_SIZE(client)] = {};
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	int err = -ENOMEM;
@@ -1698,7 +1744,6 @@ static int live_suppress_wait_preempt(void *arg)
 			continue;
 
 		for (depth = 0; depth < ARRAY_SIZE(client); depth++) {
-			struct i915_request *rq[ARRAY_SIZE(client)];
 			struct i915_request *dummy;
 
 			engine->execlists.preempt_hang.count = 0;
@@ -1708,18 +1753,22 @@ static int live_suppress_wait_preempt(void *arg)
 				goto err_client_3;
 
 			for (i = 0; i < ARRAY_SIZE(client); i++) {
-				rq[i] = spinner_create_request(&client[i].spin,
-							       client[i].ctx, engine,
-							       MI_NOOP);
-				if (IS_ERR(rq[i])) {
-					err = PTR_ERR(rq[i]);
+				struct i915_request *this;
+
+				this = spinner_create_request(&client[i].spin,
+							      client[i].ctx, engine,
+							      MI_NOOP);
+				if (IS_ERR(this)) {
+					err = PTR_ERR(this);
 					goto err_wedged;
 				}
 
 				/* Disable NEWCLIENT promotion */
-				__i915_active_fence_set(&i915_request_timeline(rq[i])->last_request,
+				__i915_active_fence_set(&i915_request_timeline(this)->last_request,
 							&dummy->fence);
-				i915_request_add(rq[i]);
+
+				rq[i] = i915_request_get(this);
+				i915_request_add(this);
 			}
 
 			dummy_request_free(dummy);
@@ -1740,8 +1789,11 @@ static int live_suppress_wait_preempt(void *arg)
 				goto err_wedged;
 			}
 
-			for (i = 0; i < ARRAY_SIZE(client); i++)
+			for (i = 0; i < ARRAY_SIZE(client); i++) {
 				igt_spinner_end(&client[i].spin);
+				i915_request_put(rq[i]);
+				rq[i] = NULL;
+			}
 
 			if (igt_flush_test(gt->i915))
 				goto err_wedged;
@@ -1769,8 +1821,10 @@ err_client_0:
 	return err;
 
 err_wedged:
-	for (i = 0; i < ARRAY_SIZE(client); i++)
+	for (i = 0; i < ARRAY_SIZE(client); i++) {
 		igt_spinner_end(&client[i].spin);
+		i915_request_put(rq[i]);
+	}
 	intel_gt_set_wedged(gt);
 	err = -EIO;
 	goto err_client_3;
@@ -1815,6 +1869,8 @@ static int live_chain_preempt(void *arg)
 					    MI_ARB_CHECK);
 		if (IS_ERR(rq))
 			goto err_wedged;
+
+		i915_request_get(rq);
 		i915_request_add(rq);
 
 		ring_size = rq->wa_tail - rq->head;
@@ -1827,8 +1883,10 @@ static int live_chain_preempt(void *arg)
 		igt_spinner_end(&lo.spin);
 		if (i915_request_wait(rq, 0, HZ / 2) < 0) {
 			pr_err("Timed out waiting to flush %s\n", engine->name);
+			i915_request_put(rq);
 			goto err_wedged;
 		}
+		i915_request_put(rq);
 
 		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
 			err = -EIO;
@@ -1862,6 +1920,8 @@ static int live_chain_preempt(void *arg)
 			rq = igt_request_alloc(hi.ctx, engine);
 			if (IS_ERR(rq))
 				goto err_wedged;
+
+			i915_request_get(rq);
 			i915_request_add(rq);
 			engine->schedule(rq, &attr);
 
@@ -1874,14 +1934,19 @@ static int live_chain_preempt(void *arg)
 				       count);
 				intel_engine_dump(engine, &p,
 						  "%s\n", engine->name);
+				i915_request_put(rq);
 				goto err_wedged;
 			}
 			igt_spinner_end(&lo.spin);
+			i915_request_put(rq);
 
 			rq = igt_request_alloc(lo.ctx, engine);
 			if (IS_ERR(rq))
 				goto err_wedged;
+
+			i915_request_get(rq);
 			i915_request_add(rq);
+
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				struct drm_printer p =
 					drm_info_printer(gt->i915->drm.dev);
@@ -1890,8 +1955,11 @@ static int live_chain_preempt(void *arg)
 				       count);
 				intel_engine_dump(engine, &p,
 						  "%s\n", engine->name);
+
+				i915_request_put(rq);
 				goto err_wedged;
 			}
+			i915_request_put(rq);
 		}
 
 		if (igt_live_test_end(&t)) {
@@ -1915,6 +1983,201 @@ err_wedged:
 	goto err_client_lo;
 }
 
+static int create_gang(struct intel_engine_cs *engine,
+		       struct i915_request **prev)
+{
+	struct drm_i915_gem_object *obj;
+	struct intel_context *ce;
+	struct i915_request *rq;
+	struct i915_vma *vma;
+	u32 *cs;
+	int err;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	obj = i915_gem_object_create_internal(engine->i915, 4096);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto err_ce;
+	}
+
+	vma = i915_vma_instance(obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto err_obj;
+
+	cs = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(cs))
+		goto err_obj;
+
+	/* Semaphore target: spin until zero */
+	*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
+
+	*cs++ = MI_SEMAPHORE_WAIT |
+		MI_SEMAPHORE_POLL |
+		MI_SEMAPHORE_SAD_EQ_SDD;
+	*cs++ = 0;
+	*cs++ = lower_32_bits(vma->node.start);
+	*cs++ = upper_32_bits(vma->node.start);
+
+	if (*prev) {
+		u64 offset = (*prev)->batch->node.start;
+
+		/* Terminate the spinner in the next lower priority batch. */
+		*cs++ = MI_STORE_DWORD_IMM_GEN4;
+		*cs++ = lower_32_bits(offset);
+		*cs++ = upper_32_bits(offset);
+		*cs++ = 0;
+	}
+
+	*cs++ = MI_BATCH_BUFFER_END;
+	i915_gem_object_flush_map(obj);
+	i915_gem_object_unpin_map(obj);
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		goto err_obj;
+
+	rq->batch = vma;
+	i915_request_get(rq);
+
+	i915_vma_lock(vma);
+	err = i915_request_await_object(rq, vma->obj, false);
+	if (!err)
+		err = i915_vma_move_to_active(vma, rq, 0);
+	if (!err)
+		err = rq->engine->emit_bb_start(rq,
+						vma->node.start,
+						PAGE_SIZE, 0);
+	i915_vma_unlock(vma);
+	i915_request_add(rq);
+	if (err)
+		goto err_rq;
+
+	i915_gem_object_put(obj);
+	intel_context_put(ce);
+
+	rq->client_link.next = &(*prev)->client_link;
+	*prev = rq;
+	return 0;
+
+err_rq:
+	i915_request_put(rq);
+err_obj:
+	i915_gem_object_put(obj);
+err_ce:
+	intel_context_put(ce);
+	return err;
+}
+
+static int live_preempt_gang(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
+		return 0;
+
+	/*
+	 * Build as long a chain of preempters as we can, with each
+	 * request higher priority than the last. Once we are ready, we release
+	 * the last batch which then precolates down the chain, each releasing
+	 * the next oldest in turn. The intent is to simply push as hard as we
+	 * can with the number of preemptions, trying to exceed narrow HW
+	 * limits. At a minimum, we insist that we can sort all the user
+	 * high priority levels into execution order.
+	 */
+
+	for_each_engine(engine, gt, id) {
+		struct i915_request *rq = NULL;
+		struct igt_live_test t;
+		IGT_TIMEOUT(end_time);
+		int prio = 0;
+		int err = 0;
+		u32 *cs;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name))
+			return -EIO;
+
+		do {
+			struct i915_sched_attr attr = {
+				.priority = I915_USER_PRIORITY(prio++),
+			};
+
+			err = create_gang(engine, &rq);
+			if (err)
+				break;
+
+			/* Submit each spinner at increasing priority */
+			engine->schedule(rq, &attr);
+
+			if (prio <= I915_PRIORITY_MAX)
+				continue;
+
+			if (prio > (INT_MAX >> I915_USER_PRIORITY_SHIFT))
+				break;
+
+			if (__igt_timeout(end_time, NULL))
+				break;
+		} while (1);
+		pr_debug("%s: Preempt chain of %d requests\n",
+			 engine->name, prio);
+
+		/*
+		 * Such that the last spinner is the highest priority and
+		 * should execute first. When that spinner completes,
+		 * it will terminate the next lowest spinner until there
+		 * are no more spinners and the gang is complete.
+		 */
+		cs = i915_gem_object_pin_map(rq->batch->obj, I915_MAP_WC);
+		if (!IS_ERR(cs)) {
+			*cs = 0;
+			i915_gem_object_unpin_map(rq->batch->obj);
+		} else {
+			err = PTR_ERR(cs);
+			intel_gt_set_wedged(gt);
+		}
+
+		while (rq) { /* wait for each rq from highest to lowest prio */
+			struct i915_request *n =
+				list_next_entry(rq, client_link);
+
+			if (err == 0 && i915_request_wait(rq, 0, HZ / 5) < 0) {
+				struct drm_printer p =
+					drm_info_printer(engine->i915->drm.dev);
+
+				pr_err("Failed to flush chain of %d requests, at %d\n",
+				       prio, rq_prio(rq) >> I915_USER_PRIORITY_SHIFT);
+				intel_engine_dump(engine, &p,
+						  "%s\n", engine->name);
+
+				err = -ETIME;
+			}
+
+			i915_request_put(rq);
+			rq = n;
+		}
+
+		if (igt_live_test_end(&t))
+			err = -EIO;
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int live_preempt_hang(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -2391,28 +2654,18 @@ static int nop_virtual_engine(struct intel_gt *gt,
 #define CHAIN BIT(0)
 {
 	IGT_TIMEOUT(end_time);
-	struct i915_request *request[16];
-	struct i915_gem_context *ctx[16];
+	struct i915_request *request[16] = {};
 	struct intel_context *ve[16];
 	unsigned long n, prime, nc;
 	struct igt_live_test t;
 	ktime_t times[2] = {};
 	int err;
 
-	GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ctx));
+	GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve));
 
 	for (n = 0; n < nctx; n++) {
-		ctx[n] = kernel_context(gt->i915);
-		if (!ctx[n]) {
-			err = -ENOMEM;
-			nctx = n;
-			goto out;
-		}
-
-		ve[n] = intel_execlists_create_virtual(ctx[n],
-						       siblings, nsibling);
+		ve[n] = intel_execlists_create_virtual(siblings, nsibling);
 		if (IS_ERR(ve[n])) {
-			kernel_context_close(ctx[n]);
 			err = PTR_ERR(ve[n]);
 			nctx = n;
 			goto out;
@@ -2421,7 +2674,6 @@ static int nop_virtual_engine(struct intel_gt *gt,
 		err = intel_context_pin(ve[n]);
 		if (err) {
 			intel_context_put(ve[n]);
-			kernel_context_close(ctx[n]);
 			nctx = n;
 			goto out;
 		}
@@ -2437,27 +2689,35 @@ static int nop_virtual_engine(struct intel_gt *gt,
 		if (flags & CHAIN) {
 			for (nc = 0; nc < nctx; nc++) {
 				for (n = 0; n < prime; n++) {
-					request[nc] =
-						i915_request_create(ve[nc]);
-					if (IS_ERR(request[nc])) {
-						err = PTR_ERR(request[nc]);
+					struct i915_request *rq;
+
+					rq = i915_request_create(ve[nc]);
+					if (IS_ERR(rq)) {
+						err = PTR_ERR(rq);
 						goto out;
 					}
 
-					i915_request_add(request[nc]);
+					if (request[nc])
+						i915_request_put(request[nc]);
+					request[nc] = i915_request_get(rq);
+					i915_request_add(rq);
 				}
 			}
 		} else {
 			for (n = 0; n < prime; n++) {
 				for (nc = 0; nc < nctx; nc++) {
-					request[nc] =
-						i915_request_create(ve[nc]);
-					if (IS_ERR(request[nc])) {
-						err = PTR_ERR(request[nc]);
+					struct i915_request *rq;
+
+					rq = i915_request_create(ve[nc]);
+					if (IS_ERR(rq)) {
+						err = PTR_ERR(rq);
 						goto out;
 					}
 
-					i915_request_add(request[nc]);
+					if (request[nc])
+						i915_request_put(request[nc]);
+					request[nc] = i915_request_get(rq);
+					i915_request_add(rq);
 				}
 			}
 		}
@@ -2483,6 +2743,11 @@ static int nop_virtual_engine(struct intel_gt *gt,
 		if (prime == 1)
 			times[0] = times[1];
 
+		for (nc = 0; nc < nctx; nc++) {
+			i915_request_put(request[nc]);
+			request[nc] = NULL;
+		}
+
 		if (__igt_timeout(end_time, NULL))
 			break;
 	}
@@ -2500,9 +2765,9 @@ out:
 		err = -EIO;
 
 	for (nc = 0; nc < nctx; nc++) {
+		i915_request_put(request[nc]);
 		intel_context_unpin(ve[nc]);
 		intel_context_put(ve[nc]);
-		kernel_context_close(ctx[nc]);
 	}
 	return err;
 }
@@ -2561,7 +2826,6 @@ static int mask_virtual_engine(struct intel_gt *gt,
 			       unsigned int nsibling)
 {
 	struct i915_request *request[MAX_ENGINE_INSTANCE + 1];
-	struct i915_gem_context *ctx;
 	struct intel_context *ve;
 	struct igt_live_test t;
 	unsigned int n;
@@ -2572,11 +2836,7 @@ static int mask_virtual_engine(struct intel_gt *gt,
 	 * restrict it to our desired engine within the virtual engine.
 	 */
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
-		return -ENOMEM;
-
-	ve = intel_execlists_create_virtual(ctx, siblings, nsibling);
+	ve = intel_execlists_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_close;
@@ -2644,7 +2904,6 @@ out_unpin:
 out_put:
 	intel_context_put(ve);
 out_close:
-	kernel_context_close(ctx);
 	return err;
 }
 
@@ -2684,7 +2943,6 @@ static int preserved_virtual_engine(struct intel_gt *gt,
 				    unsigned int nsibling)
 {
 	struct i915_request *last = NULL;
-	struct i915_gem_context *ctx;
 	struct intel_context *ve;
 	struct i915_vma *scratch;
 	struct igt_live_test t;
@@ -2692,17 +2950,11 @@ static int preserved_virtual_engine(struct intel_gt *gt,
 	int err = 0;
 	u32 *cs;
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
-		return -ENOMEM;
-
 	scratch = create_scratch(siblings[0]->gt);
-	if (IS_ERR(scratch)) {
-		err = PTR_ERR(scratch);
-		goto out_close;
-	}
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
 
-	ve = intel_execlists_create_virtual(ctx, siblings, nsibling);
+	ve = intel_execlists_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_scratch;
@@ -2785,8 +3037,6 @@ out_put:
 	intel_context_put(ve);
 out_scratch:
 	i915_vma_unpin_and_release(&scratch, 0);
-out_close:
-	kernel_context_close(ctx);
 	return err;
 }
 
@@ -2838,16 +3088,54 @@ static int bond_virtual_engine(struct intel_gt *gt,
 #define BOND_SCHEDULE BIT(0)
 {
 	struct intel_engine_cs *master;
-	struct i915_gem_context *ctx;
 	struct i915_request *rq[16];
 	enum intel_engine_id id;
+	struct igt_spinner spin;
 	unsigned long n;
 	int err;
 
+	/*
+	 * A set of bonded requests is intended to be run concurrently
+	 * across a number of engines. We use one request per-engine
+	 * and a magic fence to schedule each of the bonded requests
+	 * at the same time. A consequence of our current scheduler is that
+	 * we only move requests to the HW ready queue when the request
+	 * becomes ready, that is when all of its prerequisite fences have
+	 * been signaled. As one of those fences is the master submit fence,
+	 * there is a delay on all secondary fences as the HW may be
+	 * currently busy. Equally, as all the requests are independent,
+	 * they may have other fences that delay individual request
+	 * submission to HW. Ergo, we do not guarantee that all requests are
+	 * immediately submitted to HW at the same time, just that if the
+	 * rules are abided by, they are ready at the same time as the
+	 * first is submitted. Userspace can embed semaphores in its batch
+	 * to ensure parallel execution of its phases as it requires.
+	 * Though naturally it gets requested that perhaps the scheduler should
+	 * take care of parallel execution, even across preemption events on
+	 * different HW. (The proper answer is of course "lalalala".)
+	 *
+	 * With the submit-fence, we have identified three possible phases
+	 * of synchronisation depending on the master fence: queued (not
+	 * ready), executing, and signaled. The first two are quite simple
+	 * and checked below. However, the signaled master fence handling is
+	 * contentious. Currently we do not distinguish between a signaled
+	 * fence and an expired fence, as once signaled it does not convey
+	 * any information about the previous execution. It may even be freed
+	 * and hence checking later it may not exist at all. Ergo we currently
+	 * do not apply the bonding constraint for an already signaled fence,
+	 * as our expectation is that it should not constrain the secondaries
+	 * and is outside of the scope of the bonded request API (i.e. all
+	 * userspace requests are meant to be running in parallel). As
+	 * it imposes no constraint, and is effectively a no-op, we do not
+	 * check below as normal execution flows are checked extensively above.
+	 *
+	 * XXX Is the degenerate handling of signaled submit fences the
+	 * expected behaviour for userpace?
+	 */
+
 	GEM_BUG_ON(nsibling >= ARRAY_SIZE(rq) - 1);
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
+	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
 	err = 0;
@@ -2860,7 +3148,9 @@ static int bond_virtual_engine(struct intel_gt *gt,
 
 		memset_p((void *)rq, ERR_PTR(-EINVAL), ARRAY_SIZE(rq));
 
-		rq[0] = igt_request_alloc(ctx, master);
+		rq[0] = igt_spinner_create_request(&spin,
+						   master->kernel_context,
+						   MI_NOOP);
 		if (IS_ERR(rq[0])) {
 			err = PTR_ERR(rq[0]);
 			goto out;
@@ -2873,16 +3163,21 @@ static int bond_virtual_engine(struct intel_gt *gt,
 							       &fence,
 							       GFP_KERNEL);
 		}
+
 		i915_request_add(rq[0]);
 		if (err < 0)
 			goto out;
 
+		if (!(flags & BOND_SCHEDULE) &&
+		    !igt_wait_for_spinner(&spin, rq[0])) {
+			err = -EIO;
+			goto out;
+		}
+
 		for (n = 0; n < nsibling; n++) {
 			struct intel_context *ve;
 
-			ve = intel_execlists_create_virtual(ctx,
-							    siblings,
-							    nsibling);
+			ve = intel_execlists_create_virtual(siblings, nsibling);
 			if (IS_ERR(ve)) {
 				err = PTR_ERR(ve);
 				onstack_fence_fini(&fence);
@@ -2924,6 +3219,8 @@ static int bond_virtual_engine(struct intel_gt *gt,
 			}
 		}
 		onstack_fence_fini(&fence);
+		intel_engine_flush_submission(master);
+		igt_spinner_end(&spin);
 
 		if (i915_request_wait(rq[0], 0, HZ / 10) < 0) {
 			pr_err("Master request did not execute (on %s)!\n",
@@ -2960,7 +3257,7 @@ out:
 	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
-	kernel_context_close(ctx);
+	igt_spinner_fini(&spin);
 	return err;
 }
 
@@ -3028,6 +3325,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_suppress_self_preempt),
 		SUBTEST(live_suppress_wait_preempt),
 		SUBTEST(live_chain_preempt),
+		SUBTEST(live_preempt_gang),
 		SUBTEST(live_preempt_hang),
 		SUBTEST(live_preempt_timeout),
 		SUBTEST(live_preempt_smoke),
@@ -3080,7 +3378,7 @@ static int live_lrc_layout(void *arg)
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	u32 *mem;
+	u32 *lrc;
 	int err;
 
 	/*
@@ -3088,13 +3386,13 @@ static int live_lrc_layout(void *arg)
 	 * match the layout saved by HW.
 	 */
 
-	mem = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!mem)
+	lrc = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!lrc)
 		return -ENOMEM;
 
 	err = 0;
 	for_each_engine(engine, gt, id) {
-		u32 *hw, *lrc;
+		u32 *hw;
 		int dw;
 
 		if (!engine->default_state)
@@ -3108,8 +3406,7 @@ static int live_lrc_layout(void *arg)
 		}
 		hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
 
-		lrc = memset(mem, 0, PAGE_SIZE);
-		execlists_init_reg_state(lrc,
+		execlists_init_reg_state(memset(lrc, POISON_INUSE, PAGE_SIZE),
 					 engine->kernel_context,
 					 engine,
 					 engine->kernel_context->ring,
@@ -3124,6 +3421,13 @@ static int live_lrc_layout(void *arg)
 				continue;
 			}
 
+			if (lrc[dw] == 0) {
+				pr_debug("%s: skipped instruction %x at dword %d\n",
+					 engine->name, lri, dw);
+				dw++;
+				continue;
+			}
+
 			if ((lri & GENMASK(31, 23)) != MI_INSTR(0x22, 0)) {
 				pr_err("%s: Expected LRI command at dword %d, found %08x\n",
 				       engine->name, dw, lri);
@@ -3172,7 +3476,7 @@ static int live_lrc_layout(void *arg)
 			break;
 	}
 
-	kfree(mem);
+	kfree(lrc);
 	return err;
 }
 
@@ -3207,12 +3511,12 @@ static int live_lrc_fixed(void *arg)
 		} tbl[] = {
 			{
 				i915_mmio_reg_offset(RING_START(engine->mmio_base)),
-				CTX_RING_BUFFER_START - 1,
+				CTX_RING_START - 1,
 				"RING_START"
 			},
 			{
 				i915_mmio_reg_offset(RING_CTL(engine->mmio_base)),
-				CTX_RING_BUFFER_CONTROL - 1,
+				CTX_RING_CTL - 1,
 				"RING_CTL"
 			},
 			{
@@ -3231,7 +3535,7 @@ static int live_lrc_fixed(void *arg)
 				"RING_MI_MODE"
 			},
 			{
-				engine->mmio_base + 0x110,
+				i915_mmio_reg_offset(RING_BBSTATE(engine->mmio_base)),
 				CTX_BB_STATE - 1,
 				"BB_STATE"
 			},
@@ -3270,8 +3574,7 @@ static int live_lrc_fixed(void *arg)
 	return err;
 }
 
-static int __live_lrc_state(struct i915_gem_context *fixme,
-			    struct intel_engine_cs *engine,
+static int __live_lrc_state(struct intel_engine_cs *engine,
 			    struct i915_vma *scratch)
 {
 	struct intel_context *ce;
@@ -3286,7 +3589,7 @@ static int __live_lrc_state(struct i915_gem_context *fixme,
 	int err;
 	int n;
 
-	ce = intel_context_create(fixme, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
@@ -3360,7 +3663,6 @@ static int live_lrc_state(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	struct i915_vma *scratch;
 	enum intel_engine_id id;
 	int err = 0;
@@ -3370,18 +3672,12 @@ static int live_lrc_state(void *arg)
 	 * intel_context.
 	 */
 
-	fixme = kernel_context(gt->i915);
-	if (!fixme)
-		return -ENOMEM;
-
 	scratch = create_scratch(gt);
-	if (IS_ERR(scratch)) {
-		err = PTR_ERR(scratch);
-		goto out_close;
-	}
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
 
 	for_each_engine(engine, gt, id) {
-		err = __live_lrc_state(fixme, engine, scratch);
+		err = __live_lrc_state(engine, scratch);
 		if (err)
 			break;
 	}
@@ -3390,8 +3686,6 @@ static int live_lrc_state(void *arg)
 		err = -EIO;
 
 	i915_vma_unpin_and_release(&scratch, 0);
-out_close:
-	kernel_context_close(fixme);
 	return err;
 }
 
@@ -3401,7 +3695,7 @@ static int gpr_make_dirty(struct intel_engine_cs *engine)
 	u32 *cs;
 	int n;
 
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -3424,8 +3718,7 @@ static int gpr_make_dirty(struct intel_engine_cs *engine)
 	return 0;
 }
 
-static int __live_gpr_clear(struct i915_gem_context *fixme,
-			    struct intel_engine_cs *engine,
+static int __live_gpr_clear(struct intel_engine_cs *engine,
 			    struct i915_vma *scratch)
 {
 	struct intel_context *ce;
@@ -3441,7 +3734,7 @@ static int __live_gpr_clear(struct i915_gem_context *fixme,
 	if (err)
 		return err;
 
-	ce = intel_context_create(fixme, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
@@ -3503,7 +3796,6 @@ static int live_gpr_clear(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	struct i915_vma *scratch;
 	enum intel_engine_id id;
 	int err = 0;
@@ -3513,18 +3805,12 @@ static int live_gpr_clear(void *arg)
 	 * to avoid leaking any information from previous contexts.
 	 */
 
-	fixme = kernel_context(gt->i915);
-	if (!fixme)
-		return -ENOMEM;
-
 	scratch = create_scratch(gt);
-	if (IS_ERR(scratch)) {
-		err = PTR_ERR(scratch);
-		goto out_close;
-	}
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
 
 	for_each_engine(engine, gt, id) {
-		err = __live_gpr_clear(fixme, engine, scratch);
+		err = __live_gpr_clear(engine, scratch);
 		if (err)
 			break;
 	}
@@ -3533,8 +3819,6 @@ static int live_gpr_clear(void *arg)
 		err = -EIO;
 
 	i915_vma_unpin_and_release(&scratch, 0);
-out_close:
-	kernel_context_close(fixme);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c
new file mode 100644
index 000000000000..de1f83100fb6
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c
@@ -0,0 +1,419 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "gt/intel_engine_pm.h"
+#include "i915_selftest.h"
+
+#include "gem/selftests/mock_context.h"
+#include "selftests/igt_reset.h"
+#include "selftests/igt_spinner.h"
+
+struct live_mocs {
+	struct drm_i915_mocs_table table;
+	struct i915_vma *scratch;
+	void *vaddr;
+};
+
+static int request_add_sync(struct i915_request *rq, int err)
+{
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (i915_request_wait(rq, 0, HZ / 5) < 0)
+		err = -ETIME;
+	i915_request_put(rq);
+
+	return err;
+}
+
+static int request_add_spin(struct i915_request *rq, struct igt_spinner *spin)
+{
+	int err = 0;
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (spin && !igt_wait_for_spinner(spin, rq))
+		err = -ETIME;
+	i915_request_put(rq);
+
+	return err;
+}
+
+static struct i915_vma *create_scratch(struct intel_gt *gt)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int err;
+
+	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	i915_gem_object_set_cache_coherency(obj, I915_CACHING_CACHED);
+
+	vma = i915_vma_instance(obj, &gt->ggtt->vm, NULL);
+	if (IS_ERR(vma)) {
+		i915_gem_object_put(obj);
+		return vma;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL);
+	if (err) {
+		i915_gem_object_put(obj);
+		return ERR_PTR(err);
+	}
+
+	return vma;
+}
+
+static int live_mocs_init(struct live_mocs *arg, struct intel_gt *gt)
+{
+	int err;
+
+	if (!get_mocs_settings(gt->i915, &arg->table))
+		return -EINVAL;
+
+	arg->scratch = create_scratch(gt);
+	if (IS_ERR(arg->scratch))
+		return PTR_ERR(arg->scratch);
+
+	arg->vaddr = i915_gem_object_pin_map(arg->scratch->obj, I915_MAP_WB);
+	if (IS_ERR(arg->vaddr)) {
+		err = PTR_ERR(arg->vaddr);
+		goto err_scratch;
+	}
+
+	return 0;
+
+err_scratch:
+	i915_vma_unpin_and_release(&arg->scratch, 0);
+	return err;
+}
+
+static void live_mocs_fini(struct live_mocs *arg)
+{
+	i915_vma_unpin_and_release(&arg->scratch, I915_VMA_RELEASE_MAP);
+}
+
+static int read_regs(struct i915_request *rq,
+		     u32 addr, unsigned int count,
+		     uint32_t *offset)
+{
+	unsigned int i;
+	u32 *cs;
+
+	GEM_BUG_ON(!IS_ALIGNED(*offset, sizeof(u32)));
+
+	cs = intel_ring_begin(rq, 4 * count);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	for (i = 0; i < count; i++) {
+		*cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
+		*cs++ = addr;
+		*cs++ = *offset;
+		*cs++ = 0;
+
+		addr += sizeof(u32);
+		*offset += sizeof(u32);
+	}
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int read_mocs_table(struct i915_request *rq,
+			   const struct drm_i915_mocs_table *table,
+			   uint32_t *offset)
+{
+	u32 addr;
+
+	if (HAS_GLOBAL_MOCS_REGISTERS(rq->i915))
+		addr = global_mocs_offset();
+	else
+		addr = mocs_offset(rq->engine);
+
+	return read_regs(rq, addr, table->n_entries, offset);
+}
+
+static int read_l3cc_table(struct i915_request *rq,
+			   const struct drm_i915_mocs_table *table,
+			   uint32_t *offset)
+{
+	u32 addr = i915_mmio_reg_offset(GEN9_LNCFCMOCS(0));
+
+	return read_regs(rq, addr, (table->n_entries + 1) / 2, offset);
+}
+
+static int check_mocs_table(struct intel_engine_cs *engine,
+			    const struct drm_i915_mocs_table *table,
+			    uint32_t **vaddr)
+{
+	unsigned int i;
+	u32 expect;
+
+	for_each_mocs(expect, table, i) {
+		if (**vaddr != expect) {
+			pr_err("%s: Invalid MOCS[%d] entry, found %08x, expected %08x\n",
+			       engine->name, i, **vaddr, expect);
+			return -EINVAL;
+		}
+		++*vaddr;
+	}
+
+	return 0;
+}
+
+static bool mcr_range(struct drm_i915_private *i915, u32 offset)
+{
+	/*
+	 * Registers in this range are affected by the MCR selector
+	 * which only controls CPU initiated MMIO. Routing does not
+	 * work for CS access so we cannot verify them on this path.
+	 */
+	return INTEL_GEN(i915) >= 8 && offset >= 0xb000 && offset <= 0xb4ff;
+}
+
+static int check_l3cc_table(struct intel_engine_cs *engine,
+			    const struct drm_i915_mocs_table *table,
+			    uint32_t **vaddr)
+{
+	/* Can we read the MCR range 0xb00 directly? See intel_workarounds! */
+	u32 reg = i915_mmio_reg_offset(GEN9_LNCFCMOCS(0));
+	unsigned int i;
+	u32 expect;
+
+	for_each_l3cc(expect, table, i) {
+		if (!mcr_range(engine->i915, reg) && **vaddr != expect) {
+			pr_err("%s: Invalid L3CC[%d] entry, found %08x, expected %08x\n",
+			       engine->name, i, **vaddr, expect);
+			return -EINVAL;
+		}
+		++*vaddr;
+		reg += 4;
+	}
+
+	return 0;
+}
+
+static int check_mocs_engine(struct live_mocs *arg,
+			     struct intel_context *ce)
+{
+	struct i915_vma *vma = arg->scratch;
+	struct i915_request *rq;
+	u32 offset;
+	u32 *vaddr;
+	int err;
+
+	memset32(arg->vaddr, STACK_MAGIC, PAGE_SIZE / sizeof(u32));
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_vma_lock(vma);
+	err = i915_request_await_object(rq, vma->obj, true);
+	if (!err)
+		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	i915_vma_unlock(vma);
+
+	/* Read the mocs tables back using SRM */
+	offset = i915_ggtt_offset(vma);
+	if (!err)
+		err = read_mocs_table(rq, &arg->table, &offset);
+	if (!err && ce->engine->class == RENDER_CLASS)
+		err = read_l3cc_table(rq, &arg->table, &offset);
+	offset -= i915_ggtt_offset(vma);
+	GEM_BUG_ON(offset > PAGE_SIZE);
+
+	err = request_add_sync(rq, err);
+	if (err)
+		return err;
+
+	/* Compare the results against the expected tables */
+	vaddr = arg->vaddr;
+	if (!err)
+		err = check_mocs_table(ce->engine, &arg->table, &vaddr);
+	if (!err && ce->engine->class == RENDER_CLASS)
+		err = check_l3cc_table(ce->engine, &arg->table, &vaddr);
+	if (err)
+		return err;
+
+	GEM_BUG_ON(arg->vaddr + offset != vaddr);
+	return 0;
+}
+
+static int live_mocs_kernel(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct live_mocs mocs;
+	int err;
+
+	/* Basic check the system is configured with the expected mocs table */
+
+	err = live_mocs_init(&mocs, gt);
+	if (err)
+		return err;
+
+	for_each_engine(engine, gt, id) {
+		intel_engine_pm_get(engine);
+		err = check_mocs_engine(&mocs, engine->kernel_context);
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
+	}
+
+	live_mocs_fini(&mocs);
+	return err;
+}
+
+static int live_mocs_clean(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct live_mocs mocs;
+	int err;
+
+	/* Every new context should see the same mocs table */
+
+	err = live_mocs_init(&mocs, gt);
+	if (err)
+		return err;
+
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
+		err = check_mocs_engine(&mocs, ce);
+		intel_context_put(ce);
+		if (err)
+			break;
+	}
+
+	live_mocs_fini(&mocs);
+	return err;
+}
+
+static int active_engine_reset(struct intel_context *ce,
+			       const char *reason)
+{
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	int err;
+
+	err = igt_spinner_init(&spin, ce->engine->gt);
+	if (err)
+		return err;
+
+	rq = igt_spinner_create_request(&spin, ce, MI_NOOP);
+	if (IS_ERR(rq)) {
+		igt_spinner_fini(&spin);
+		return PTR_ERR(rq);
+	}
+
+	err = request_add_spin(rq, &spin);
+	if (err == 0)
+		err = intel_engine_reset(ce->engine, reason);
+
+	igt_spinner_end(&spin);
+	igt_spinner_fini(&spin);
+
+	return err;
+}
+
+static int __live_mocs_reset(struct live_mocs *mocs,
+			     struct intel_context *ce)
+{
+	int err;
+
+	err = intel_engine_reset(ce->engine, "mocs");
+	if (err)
+		return err;
+
+	err = check_mocs_engine(mocs, ce);
+	if (err)
+		return err;
+
+	err = active_engine_reset(ce, "mocs");
+	if (err)
+		return err;
+
+	err = check_mocs_engine(mocs, ce);
+	if (err)
+		return err;
+
+	intel_gt_reset(ce->engine->gt, ce->engine->mask, "mocs");
+
+	err = check_mocs_engine(mocs, ce);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int live_mocs_reset(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct live_mocs mocs;
+	int err = 0;
+
+	/* Check the mocs setup is retained over per-engine and global resets */
+
+	if (!intel_has_reset_engine(gt))
+		return 0;
+
+	err = live_mocs_init(&mocs, gt);
+	if (err)
+		return err;
+
+	igt_global_reset_lock(gt);
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
+		intel_engine_pm_get(engine);
+		err = __live_mocs_reset(&mocs, ce);
+		intel_engine_pm_put(engine);
+
+		intel_context_put(ce);
+		if (err)
+			break;
+	}
+	igt_global_reset_unlock(gt);
+
+	live_mocs_fini(&mocs);
+	return err;
+}
+
+int intel_mocs_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_mocs_kernel),
+		SUBTEST(live_mocs_clean),
+		SUBTEST(live_mocs_reset),
+	};
+	struct drm_i915_mocs_table table;
+
+	if (!get_mocs_settings(i915, &table))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
new file mode 100644
index 000000000000..8cc55a0e9e06
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
@@ -0,0 +1,203 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "intel_context.h"
+#include "intel_engine_pm.h"
+#include "intel_gt_requests.h"
+#include "intel_ring.h"
+#include "selftest_rc6.h"
+
+#include "selftests/i915_random.h"
+
+int live_rc6_manual(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_rc6 *rc6 = &gt->rc6;
+	intel_wakeref_t wakeref;
+	u64 res[2];
+	int err = 0;
+
+	/*
+	 * Our claim is that we can "encourage" the GPU to enter rc6 at will.
+	 * Let's try it!
+	 */
+
+	if (!rc6->enabled)
+		return 0;
+
+	/* bsw/byt use a PCU and decouple RC6 from our manual control */
+	if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915))
+		return 0;
+
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+
+	/* Force RC6 off for starters */
+	__intel_rc6_disable(rc6);
+	msleep(1); /* wakeup is not immediate, takes about 100us on icl */
+
+	res[0] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6);
+	msleep(250);
+	res[1] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6);
+	if ((res[1] - res[0]) >> 10) {
+		pr_err("RC6 residency increased by %lldus while disabled for 250ms!\n",
+		       (res[1] - res[0]) >> 10);
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
+	/* Manually enter RC6 */
+	intel_rc6_park(rc6);
+
+	res[0] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6);
+	msleep(100);
+	res[1] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6);
+
+	if (res[1] == res[0]) {
+		pr_err("Did not enter RC6! RC6_STATE=%08x, RC6_CONTROL=%08x\n",
+		       intel_uncore_read_fw(gt->uncore, GEN6_RC_STATE),
+		       intel_uncore_read_fw(gt->uncore, GEN6_RC_CONTROL));
+		err = -EINVAL;
+	}
+
+	/* Restore what should have been the original state! */
+	intel_rc6_unpark(rc6);
+
+out_unlock:
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+	return err;
+}
+
+static const u32 *__live_rc6_ctx(struct intel_context *ce)
+{
+	struct i915_request *rq;
+	const u32 *result;
+	u32 cmd;
+	u32 *cs;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return ERR_CAST(rq);
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs)) {
+		i915_request_add(rq);
+		return cs;
+	}
+
+	cmd = MI_STORE_REGISTER_MEM | MI_USE_GGTT;
+	if (INTEL_GEN(rq->i915) >= 8)
+		cmd++;
+
+	*cs++ = cmd;
+	*cs++ = i915_mmio_reg_offset(GEN8_RC6_CTX_INFO);
+	*cs++ = ce->timeline->hwsp_offset + 8;
+	*cs++ = 0;
+	intel_ring_advance(rq, cs);
+
+	result = rq->hwsp_seqno + 2;
+	i915_request_add(rq);
+
+	return result;
+}
+
+static struct intel_engine_cs **
+randomised_engines(struct intel_gt *gt,
+		   struct rnd_state *prng,
+		   unsigned int *count)
+{
+	struct intel_engine_cs *engine, **engines;
+	enum intel_engine_id id;
+	int n;
+
+	n = 0;
+	for_each_engine(engine, gt, id)
+		n++;
+	if (!n)
+		return NULL;
+
+	engines = kmalloc_array(n, sizeof(*engines), GFP_KERNEL);
+	if (!engines)
+		return NULL;
+
+	n = 0;
+	for_each_engine(engine, gt, id)
+		engines[n++] = engine;
+
+	i915_prandom_shuffle(engines, sizeof(*engines), n, prng);
+
+	*count = n;
+	return engines;
+}
+
+int live_rc6_ctx_wa(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs **engines;
+	unsigned int n, count;
+	I915_RND_STATE(prng);
+	int err = 0;
+
+	/* A read of CTX_INFO upsets rc6. Poke the bear! */
+	if (INTEL_GEN(gt->i915) < 8)
+		return 0;
+
+	engines = randomised_engines(gt, &prng, &count);
+	if (!engines)
+		return 0;
+
+	for (n = 0; n < count; n++) {
+		struct intel_engine_cs *engine = engines[n];
+		int pass;
+
+		for (pass = 0; pass < 2; pass++) {
+			struct intel_context *ce;
+			unsigned int resets =
+				i915_reset_engine_count(&gt->i915->gpu_error,
+							engine);
+			const u32 *res;
+
+			/* Use a sacrifical context */
+			ce = intel_context_create(engine);
+			if (IS_ERR(ce)) {
+				err = PTR_ERR(ce);
+				goto out;
+			}
+
+			intel_engine_pm_get(engine);
+			res = __live_rc6_ctx(ce);
+			intel_engine_pm_put(engine);
+			intel_context_put(ce);
+			if (IS_ERR(res)) {
+				err = PTR_ERR(res);
+				goto out;
+			}
+
+			if (intel_gt_wait_for_idle(gt, HZ / 5) == -ETIME) {
+				intel_gt_set_wedged(gt);
+				err = -ETIME;
+				goto out;
+			}
+
+			intel_gt_pm_wait_for_idle(gt);
+			pr_debug("%s: CTX_INFO=%0x\n",
+				 engine->name, READ_ONCE(*res));
+
+			if (resets !=
+			    i915_reset_engine_count(&gt->i915->gpu_error,
+						    engine)) {
+				pr_err("%s: GPU reset required\n",
+				       engine->name);
+				add_taint_for_CI(TAINT_WARN);
+				err = -EIO;
+				goto out;
+			}
+		}
+	}
+
+out:
+	kfree(engines);
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.h b/drivers/gpu/drm/i915/gt/selftest_rc6.h
new file mode 100644
index 000000000000..762fd442d7b2
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.h
@@ -0,0 +1,13 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef SELFTEST_RC6_H
+#define SELFTEST_RC6_H
+
+int live_rc6_ctx_wa(void *arg);
+int live_rc6_manual(void *arg);
+
+#endif /* SELFTEST_RC6_H */
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index f04a59fe5d2c..e2d78cc22fb4 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -458,7 +458,7 @@ tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value)
 		goto out;
 	}
 
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq))
 		goto out_unpin;
 
@@ -675,9 +675,7 @@ static int live_hwsp_wrap(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		intel_engine_pm_get(engine);
-		rq = i915_request_create(engine->kernel_context);
-		intel_engine_pm_put(engine);
+		rq = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			goto out;
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index abce6e4ec9c0..ac1921854cbf 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -264,22 +264,15 @@ static int
 switch_to_scratch_context(struct intel_engine_cs *engine,
 			  struct igt_spinner *spin)
 {
-	struct i915_gem_context *ctx;
 	struct intel_context *ce;
 	struct i915_request *rq;
 	int err = 0;
 
-	ctx = kernel_context(engine->i915);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-
-	GEM_BUG_ON(i915_gem_context_is_bannable(ctx));
-
-	ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
-	GEM_BUG_ON(IS_ERR(ce));
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
 
 	rq = igt_spinner_create_request(spin, ce, MI_NOOP);
-
 	intel_context_put(ce);
 
 	if (IS_ERR(rq)) {
@@ -293,7 +286,6 @@ err:
 	if (err && spin)
 		igt_spinner_end(spin);
 
-	kernel_context_close(ctx);
 	return err;
 }
 
@@ -367,20 +359,17 @@ out_ctx:
 	return err;
 }
 
-static struct i915_vma *create_batch(struct i915_gem_context *ctx)
+static struct i915_vma *create_batch(struct i915_address_space *vm)
 {
 	struct drm_i915_gem_object *obj;
-	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	int err;
 
-	obj = i915_gem_object_create_internal(ctx->i915, 16 * PAGE_SIZE);
+	obj = i915_gem_object_create_internal(vm->i915, 16 * PAGE_SIZE);
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
 	vma = i915_vma_instance(obj, vm, NULL);
-	i915_vm_put(vm);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_obj;
@@ -452,8 +441,7 @@ static int whitelist_writable_count(struct intel_engine_cs *engine)
 	return count;
 }
 
-static int check_dirty_whitelist(struct i915_gem_context *ctx,
-				 struct intel_engine_cs *engine)
+static int check_dirty_whitelist(struct intel_context *ce)
 {
 	const u32 values[] = {
 		0x00000000,
@@ -481,19 +469,17 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 		0xffff00ff,
 		0xffffffff,
 	};
-	struct i915_address_space *vm;
+	struct intel_engine_cs *engine = ce->engine;
 	struct i915_vma *scratch;
 	struct i915_vma *batch;
 	int err = 0, i, v;
 	u32 *cs, *results;
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
-	scratch = create_scratch(vm, 2 * ARRAY_SIZE(values) + 1);
-	i915_vm_put(vm);
+	scratch = create_scratch(ce->vm, 2 * ARRAY_SIZE(values) + 1);
 	if (IS_ERR(scratch))
 		return PTR_ERR(scratch);
 
-	batch = create_batch(ctx);
+	batch = create_batch(ce->vm);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
 		goto out_scratch;
@@ -518,7 +504,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 
 		srm = MI_STORE_REGISTER_MEM;
 		lrm = MI_LOAD_REGISTER_MEM;
-		if (INTEL_GEN(ctx->i915) >= 8)
+		if (INTEL_GEN(engine->i915) >= 8)
 			lrm++, srm++;
 
 		pr_debug("%s: Writing garbage to %x\n",
@@ -577,7 +563,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 		i915_gem_object_unpin_map(batch->obj);
 		intel_gt_chipset_flush(engine->gt);
 
-		rq = igt_request_alloc(ctx, engine);
+		rq = intel_context_create_request(ce);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			goto out_batch;
@@ -696,7 +682,7 @@ out_unpin:
 			break;
 	}
 
-	if (igt_flush_test(ctx->i915))
+	if (igt_flush_test(engine->i915))
 		err = -EIO;
 out_batch:
 	i915_vma_unpin_and_release(&batch, 0);
@@ -709,38 +695,31 @@ static int live_dirty_whitelist(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
-	struct drm_file *file;
-	int err = 0;
 
 	/* Can the user write to the whitelisted registers? */
 
 	if (INTEL_GEN(gt->i915) < 7) /* minimum requirement for LRI, SRM, LRM */
 		return 0;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	ctx = live_context(gt->i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out_file;
-	}
-
 	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+		int err;
+
 		if (engine->whitelist.count == 0)
 			continue;
 
-		err = check_dirty_whitelist(ctx, engine);
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce))
+			return PTR_ERR(ce);
+
+		err = check_dirty_whitelist(ce);
+		intel_context_put(ce);
 		if (err)
-			goto out_file;
+			return err;
 	}
 
-out_file:
-	mock_file_free(gt->i915, file);
-	return err;
+	return 0;
 }
 
 static int live_reset_whitelist(void *arg)
@@ -830,12 +809,15 @@ err_req:
 static int scrub_whitelisted_registers(struct i915_gem_context *ctx,
 				       struct intel_engine_cs *engine)
 {
+	struct i915_address_space *vm;
 	struct i915_request *rq;
 	struct i915_vma *batch;
 	int i, err = 0;
 	u32 *cs;
 
-	batch = create_batch(ctx);
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	batch = create_batch(vm);
+	i915_vm_put(vm);
 	if (IS_ERR(batch))
 		return PTR_ERR(batch);
 
diff --git a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
index 2a77c051f36a..aeb1d1f616e8 100644
--- a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
@@ -15,7 +15,7 @@ void mock_timeline_init(struct intel_timeline *timeline, u64 context)
 
 	mutex_init(&timeline->mutex);
 
-	INIT_ACTIVE_FENCE(&timeline->last_request, &timeline->mutex);
+	INIT_ACTIVE_FENCE(&timeline->last_request);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
diff --git a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.h b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.h
index 689efc66c908..d2bcc3df6183 100644
--- a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.h
+++ b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.h
@@ -7,6 +7,8 @@
 #ifndef __MOCK_TIMELINE__
 #define __MOCK_TIMELINE__
 
+#include <linux/types.h>
+
 struct intel_timeline;
 
 void mock_timeline_init(struct intel_timeline *timeline, u64 context);
diff --git a/drivers/gpu/drm/i915/gt/uc/Makefile b/drivers/gpu/drm/i915/gt/uc/Makefile
deleted file mode 100644
index bec94d434cb6..000000000000
--- a/drivers/gpu/drm/i915/gt/uc/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/../..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 3ee4a4e7689d..5d00a3b2d914 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -32,18 +32,17 @@
  * just the HuC, but more are expected to land in the future).
  */
 
-static void gen8_guc_raise_irq(struct intel_guc *guc)
+void intel_guc_notify(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 
-	intel_uncore_write(gt->uncore, GUC_SEND_INTERRUPT, GUC_SEND_TRIGGER);
-}
-
-static void gen11_guc_raise_irq(struct intel_guc *guc)
-{
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	intel_uncore_write(gt->uncore, GEN11_GUC_HOST_INTERRUPT, 0);
+	/*
+	 * On Gen11+, the value written to the register is passes as a payload
+	 * to the FW. However, the FW currently treats all values the same way
+	 * (H2G interrupt), so we can just write the value that the HW expects
+	 * on older gens.
+	 */
+	intel_uncore_write(gt->uncore, guc->notify_reg, GUC_SEND_TRIGGER);
 }
 
 static inline i915_reg_t guc_send_reg(struct intel_guc *guc, u32 i)
@@ -177,15 +176,13 @@ void intel_guc_init_early(struct intel_guc *guc)
 
 	mutex_init(&guc->send_mutex);
 	spin_lock_init(&guc->irq_lock);
-	guc->send = intel_guc_send_nop;
-	guc->handler = intel_guc_to_host_event_handler_nop;
 	if (INTEL_GEN(i915) >= 11) {
-		guc->notify = gen11_guc_raise_irq;
+		guc->notify_reg = GEN11_GUC_HOST_INTERRUPT;
 		guc->interrupts.reset = gen11_reset_guc_interrupts;
 		guc->interrupts.enable = gen11_enable_guc_interrupts;
 		guc->interrupts.disable = gen11_disable_guc_interrupts;
 	} else {
-		guc->notify = gen8_guc_raise_irq;
+		guc->notify_reg = GUC_SEND_INTERRUPT;
 		guc->interrupts.reset = gen9_reset_guc_interrupts;
 		guc->interrupts.enable = gen9_enable_guc_interrupts;
 		guc->interrupts.disable = gen9_disable_guc_interrupts;
@@ -401,18 +398,8 @@ void intel_guc_fini(struct intel_guc *guc)
 	intel_guc_log_destroy(&guc->log);
 	intel_uc_fw_fini(&guc->fw);
 	intel_uc_fw_cleanup_fetch(&guc->fw);
-}
 
-int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len,
-		       u32 *response_buf, u32 response_buf_size)
-{
-	WARN(1, "Unexpected send: action=%#x\n", *action);
-	return -ENODEV;
-}
-
-void intel_guc_to_host_event_handler_nop(struct intel_guc *guc)
-{
-	WARN(1, "Unexpected event: no suitable handler\n");
+	intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_DISABLED);
 }
 
 /*
@@ -704,3 +691,37 @@ err:
 	i915_gem_object_put(obj);
 	return vma;
 }
+
+/**
+ * intel_guc_allocate_and_map_vma() - Allocate and map VMA for GuC usage
+ * @guc:	the guc
+ * @size:	size of area to allocate (both virtual space and memory)
+ * @out_vma:	return variable for the allocated vma pointer
+ * @out_vaddr:	return variable for the obj mapping
+ *
+ * This wrapper calls intel_guc_allocate_vma() and then maps the allocated
+ * object with I915_MAP_WB.
+ *
+ * Return:	0 if successful, a negative errno code otherwise.
+ */
+int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size,
+				   struct i915_vma **out_vma, void **out_vaddr)
+{
+	struct i915_vma *vma;
+	void *vaddr;
+
+	vma = intel_guc_allocate_vma(guc, size);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
+	if (IS_ERR(vaddr)) {
+		i915_vma_unpin_and_release(&vma, 0);
+		return PTR_ERR(vaddr);
+	}
+
+	*out_vma = vma;
+	*out_vaddr = vaddr;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index e6400204a2bd..910d49590068 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -20,8 +20,8 @@ struct __guc_ads_blob;
 
 /*
  * Top level structure of GuC. It handles firmware loading and manages client
- * pool and doorbells. intel_guc owns a intel_guc_client to replace the legacy
- * ExecList submission.
+ * pool. intel_guc owns a intel_guc_client to replace the legacy ExecList
+ * submission.
  */
 struct intel_guc {
 	struct intel_uc_fw fw;
@@ -46,13 +46,13 @@ struct intel_guc {
 
 	struct i915_vma *stage_desc_pool;
 	void *stage_desc_pool_vaddr;
-	struct ida stage_ids;
 
-	struct intel_guc_client *execbuf_client;
+	struct i915_vma *workqueue;
+	void *workqueue_vaddr;
+	spinlock_t wq_lock;
 
-	DECLARE_BITMAP(doorbell_bitmap, GUC_NUM_DOORBELLS);
-	/* Cyclic counter mod pagesize	*/
-	u32 db_cacheline;
+	struct i915_vma *proc_desc;
+	void *proc_desc_vaddr;
 
 	/* Control params for fw initialization */
 	u32 params[GUC_CTL_MAX_DWORDS];
@@ -64,44 +64,33 @@ struct intel_guc {
 		enum forcewake_domains fw_domains;
 	} send_regs;
 
+	/* register used to send interrupts to the GuC FW */
+	i915_reg_t notify_reg;
+
 	/* Store msg (e.g. log flush) that we see while CTBs are disabled */
 	u32 mmio_msg;
 
 	/* To serialize the intel_guc_send actions */
 	struct mutex send_mutex;
-
-	/* GuC's FW specific send function */
-	int (*send)(struct intel_guc *guc, const u32 *data, u32 len,
-		    u32 *response_buf, u32 response_buf_size);
-
-	/* GuC's FW specific event handler function */
-	void (*handler)(struct intel_guc *guc);
-
-	/* GuC's FW specific notify function */
-	void (*notify)(struct intel_guc *guc);
 };
 
 static
 inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len)
 {
-	return guc->send(guc, action, len, NULL, 0);
+	return intel_guc_ct_send(&guc->ct, action, len, NULL, 0);
 }
 
 static inline int
 intel_guc_send_and_receive(struct intel_guc *guc, const u32 *action, u32 len,
 			   u32 *response_buf, u32 response_buf_size)
 {
-	return guc->send(guc, action, len, response_buf, response_buf_size);
-}
-
-static inline void intel_guc_notify(struct intel_guc *guc)
-{
-	guc->notify(guc);
+	return intel_guc_ct_send(&guc->ct, action, len,
+				 response_buf, response_buf_size);
 }
 
 static inline void intel_guc_to_host_event_handler(struct intel_guc *guc)
 {
-	guc->handler(guc);
+	intel_guc_ct_event_handler(&guc->ct);
 }
 
 /* GuC addresses above GUC_GGTT_TOP also don't map through the GTT */
@@ -136,12 +125,9 @@ void intel_guc_init_send_regs(struct intel_guc *guc);
 void intel_guc_write_params(struct intel_guc *guc);
 int intel_guc_init(struct intel_guc *guc);
 void intel_guc_fini(struct intel_guc *guc);
-int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len,
-		       u32 *response_buf, u32 response_buf_size);
+void intel_guc_notify(struct intel_guc *guc);
 int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
 			u32 *response_buf, u32 response_buf_size);
-void intel_guc_to_host_event_handler(struct intel_guc *guc);
-void intel_guc_to_host_event_handler_nop(struct intel_guc *guc);
 int intel_guc_to_host_process_recv_msg(struct intel_guc *guc,
 				       const u32 *payload, u32 len);
 int intel_guc_sample_forcewake(struct intel_guc *guc);
@@ -149,6 +135,8 @@ int intel_guc_auth_huc(struct intel_guc *guc, u32 rsa_offset);
 int intel_guc_suspend(struct intel_guc *guc);
 int intel_guc_resume(struct intel_guc *guc);
 struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size);
+int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size,
+				   struct i915_vma **out_vma, void **out_vaddr);
 
 static inline bool intel_guc_is_supported(struct intel_guc *guc)
 {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
index ca6674b8e00c..101728006ae9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -93,7 +93,8 @@ static void __guc_ads_init(struct intel_guc *guc)
 		 */
 		blob->ads.golden_context_lrca[engine_class] = 0;
 		blob->ads.eng_state_size[engine_class] =
-			intel_engine_context_size(dev_priv, engine_class) -
+			intel_engine_context_size(guc_to_gt(guc),
+						  engine_class) -
 			skipped_size;
 	}
 
@@ -135,32 +136,19 @@ static void __guc_ads_init(struct intel_guc *guc)
 int intel_guc_ads_create(struct intel_guc *guc)
 {
 	const u32 size = PAGE_ALIGN(sizeof(struct __guc_ads_blob));
-	struct i915_vma *vma;
-	void *blob;
 	int ret;
 
 	GEM_BUG_ON(guc->ads_vma);
 
-	vma = intel_guc_allocate_vma(guc, size);
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+	ret = intel_guc_allocate_and_map_vma(guc, size, &guc->ads_vma,
+					     (void **)&guc->ads_blob);
 
-	blob = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(blob)) {
-		ret = PTR_ERR(blob);
-		goto err_vma;
-	}
-
-	guc->ads_vma = vma;
-	guc->ads_blob = blob;
+	if (ret)
+		return ret;
 
 	__guc_ads_init(guc);
 
 	return 0;
-
-err_vma:
-	i915_vma_unpin_and_release(&guc->ads_vma, 0);
-	return ret;
 }
 
 void intel_guc_ads_destroy(struct intel_guc *guc)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index b49115517510..c6f971a049f9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -37,13 +37,10 @@ static void ct_incoming_request_worker_func(struct work_struct *w);
  */
 void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 {
-	/* we're using static channel owners */
-	ct->host_channel.owner = CTB_OWNER_HOST;
-
-	spin_lock_init(&ct->lock);
-	INIT_LIST_HEAD(&ct->pending_requests);
-	INIT_LIST_HEAD(&ct->incoming_requests);
-	INIT_WORK(&ct->worker, ct_incoming_request_worker_func);
+	spin_lock_init(&ct->requests.lock);
+	INIT_LIST_HEAD(&ct->requests.pending);
+	INIT_LIST_HEAD(&ct->requests.incoming);
+	INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
 }
 
 static inline struct intel_guc *ct_to_guc(struct intel_guc_ct *ct)
@@ -64,14 +61,13 @@ static inline const char *guc_ct_buffer_type_to_str(u32 type)
 }
 
 static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc,
-				    u32 cmds_addr, u32 size, u32 owner)
+				    u32 cmds_addr, u32 size)
 {
-	CT_DEBUG_DRIVER("CT: desc %p init addr=%#x size=%u owner=%u\n",
-			desc, cmds_addr, size, owner);
+	CT_DEBUG_DRIVER("CT: init addr=%#x size=%u\n", cmds_addr, size);
 	memset(desc, 0, sizeof(*desc));
 	desc->addr = cmds_addr;
 	desc->size = size;
-	desc->owner = owner;
+	desc->owner = CTB_OWNER_HOST;
 }
 
 static void guc_ct_buffer_desc_reset(struct guc_ct_buffer_desc *desc)
@@ -104,12 +100,11 @@ static int guc_action_register_ct_buffer(struct intel_guc *guc,
 }
 
 static int guc_action_deregister_ct_buffer(struct intel_guc *guc,
-					   u32 owner,
 					   u32 type)
 {
 	u32 action[] = {
 		INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER,
-		owner,
+		CTB_OWNER_HOST,
 		type
 	};
 	int err;
@@ -117,20 +112,27 @@ static int guc_action_deregister_ct_buffer(struct intel_guc *guc,
 	/* Can't use generic send(), CT deregistration must go over MMIO */
 	err = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
 	if (err)
-		DRM_ERROR("CT: deregister %s buffer failed; owner=%d err=%d\n",
-			  guc_ct_buffer_type_to_str(type), owner, err);
+		DRM_ERROR("CT: deregister %s buffer failed; err=%d\n",
+			  guc_ct_buffer_type_to_str(type), err);
 	return err;
 }
 
-static int ctch_init(struct intel_guc *guc,
-		     struct intel_guc_ct_channel *ctch)
+/**
+ * intel_guc_ct_init - Init buffer-based communication
+ * @ct: pointer to CT struct
+ *
+ * Allocate memory required for buffer-based communication.
+ *
+ * Return: 0 on success, a negative errno code on failure.
+ */
+int intel_guc_ct_init(struct intel_guc_ct *ct)
 {
-	struct i915_vma *vma;
+	struct intel_guc *guc = ct_to_guc(ct);
 	void *blob;
 	int err;
 	int i;
 
-	GEM_BUG_ON(ctch->vma);
+	GEM_BUG_ON(ct->vma);
 
 	/* We allocate 1 page to hold both descriptors and both buffers.
 	 *       ___________.....................
@@ -154,71 +156,65 @@ static int ctch_init(struct intel_guc *guc,
 	 * other code will need updating as well.
 	 */
 
-	/* allocate vma */
-	vma = intel_guc_allocate_vma(guc, PAGE_SIZE);
-	if (IS_ERR(vma)) {
-		err = PTR_ERR(vma);
-		goto err_out;
+	err = intel_guc_allocate_and_map_vma(guc, PAGE_SIZE, &ct->vma, &blob);
+	if (err) {
+		DRM_ERROR("CT: channel allocation failed; err=%d\n", err);
+		return err;
 	}
-	ctch->vma = vma;
 
-	/* map first page */
-	blob = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(blob)) {
-		err = PTR_ERR(blob);
-		goto err_vma;
-	}
 	CT_DEBUG_DRIVER("CT: vma base=%#x\n",
-			intel_guc_ggtt_offset(guc, ctch->vma));
+			intel_guc_ggtt_offset(guc, ct->vma));
 
 	/* store pointers to desc and cmds */
-	for (i = 0; i < ARRAY_SIZE(ctch->ctbs); i++) {
-		GEM_BUG_ON((i != CTB_SEND) && (i != CTB_RECV));
-		ctch->ctbs[i].desc = blob + PAGE_SIZE/4 * i;
-		ctch->ctbs[i].cmds = blob + PAGE_SIZE/4 * i + PAGE_SIZE/2;
+	for (i = 0; i < ARRAY_SIZE(ct->ctbs); i++) {
+		GEM_BUG_ON((i !=  CTB_SEND) && (i != CTB_RECV));
+		ct->ctbs[i].desc = blob + PAGE_SIZE/4 * i;
+		ct->ctbs[i].cmds = blob + PAGE_SIZE/4 * i + PAGE_SIZE/2;
 	}
 
 	return 0;
-
-err_vma:
-	i915_vma_unpin_and_release(&ctch->vma, 0);
-err_out:
-	CT_DEBUG_DRIVER("CT: channel %d initialization failed; err=%d\n",
-			ctch->owner, err);
-	return err;
 }
 
-static void ctch_fini(struct intel_guc *guc,
-		      struct intel_guc_ct_channel *ctch)
+/**
+ * intel_guc_ct_fini - Fini buffer-based communication
+ * @ct: pointer to CT struct
+ *
+ * Deallocate memory required for buffer-based communication.
+ */
+void intel_guc_ct_fini(struct intel_guc_ct *ct)
 {
-	GEM_BUG_ON(ctch->enabled);
+	GEM_BUG_ON(ct->enabled);
 
-	i915_vma_unpin_and_release(&ctch->vma, I915_VMA_RELEASE_MAP);
+	i915_vma_unpin_and_release(&ct->vma, I915_VMA_RELEASE_MAP);
 }
 
-static int ctch_enable(struct intel_guc *guc,
-		       struct intel_guc_ct_channel *ctch)
+/**
+ * intel_guc_ct_enable - Enable buffer based command transport.
+ * @ct: pointer to CT struct
+ *
+ * Return: 0 on success, a negative errno code on failure.
+ */
+int intel_guc_ct_enable(struct intel_guc_ct *ct)
 {
+	struct intel_guc *guc = ct_to_guc(ct);
 	u32 base;
 	int err;
 	int i;
 
-	GEM_BUG_ON(!ctch->vma);
-
-	GEM_BUG_ON(ctch->enabled);
+	GEM_BUG_ON(ct->enabled);
 
 	/* vma should be already allocated and map'ed */
-	base = intel_guc_ggtt_offset(guc, ctch->vma);
+	GEM_BUG_ON(!ct->vma);
+	base = intel_guc_ggtt_offset(guc, ct->vma);
 
 	/* (re)initialize descriptors
 	 * cmds buffers are in the second half of the blob page
 	 */
-	for (i = 0; i < ARRAY_SIZE(ctch->ctbs); i++) {
+	for (i = 0; i < ARRAY_SIZE(ct->ctbs); i++) {
 		GEM_BUG_ON((i != CTB_SEND) && (i != CTB_RECV));
-		guc_ct_buffer_desc_init(ctch->ctbs[i].desc,
+		guc_ct_buffer_desc_init(ct->ctbs[i].desc,
 					base + PAGE_SIZE/4 * i + PAGE_SIZE/2,
-					PAGE_SIZE/4,
-					ctch->owner);
+					PAGE_SIZE/4);
 	}
 
 	/* register buffers, starting wirh RECV buffer
@@ -236,38 +232,42 @@ static int ctch_enable(struct intel_guc *guc,
 	if (unlikely(err))
 		goto err_deregister;
 
-	ctch->enabled = true;
+	ct->enabled = true;
 
 	return 0;
 
 err_deregister:
 	guc_action_deregister_ct_buffer(guc,
-					ctch->owner,
 					INTEL_GUC_CT_BUFFER_TYPE_RECV);
 err_out:
-	DRM_ERROR("CT: can't open channel %d; err=%d\n", ctch->owner, err);
+	DRM_ERROR("CT: can't open channel; err=%d\n", err);
 	return err;
 }
 
-static void ctch_disable(struct intel_guc *guc,
-			 struct intel_guc_ct_channel *ctch)
+/**
+ * intel_guc_ct_disable - Disable buffer based command transport.
+ * @ct: pointer to CT struct
+ */
+void intel_guc_ct_disable(struct intel_guc_ct *ct)
 {
-	GEM_BUG_ON(!ctch->enabled);
+	struct intel_guc *guc = ct_to_guc(ct);
 
-	ctch->enabled = false;
+	GEM_BUG_ON(!ct->enabled);
 
-	guc_action_deregister_ct_buffer(guc,
-					ctch->owner,
-					INTEL_GUC_CT_BUFFER_TYPE_SEND);
-	guc_action_deregister_ct_buffer(guc,
-					ctch->owner,
-					INTEL_GUC_CT_BUFFER_TYPE_RECV);
+	ct->enabled = false;
+
+	if (intel_guc_is_running(guc)) {
+		guc_action_deregister_ct_buffer(guc,
+						INTEL_GUC_CT_BUFFER_TYPE_SEND);
+		guc_action_deregister_ct_buffer(guc,
+						INTEL_GUC_CT_BUFFER_TYPE_RECV);
+	}
 }
 
-static u32 ctch_get_next_fence(struct intel_guc_ct_channel *ctch)
+static u32 ct_get_next_fence(struct intel_guc_ct *ct)
 {
 	/* For now it's trivial */
-	return ++ctch->next_fence;
+	return ++ct->requests.next_fence;
 }
 
 /**
@@ -440,35 +440,34 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status)
 	return err;
 }
 
-static int ctch_send(struct intel_guc_ct *ct,
-		     struct intel_guc_ct_channel *ctch,
-		     const u32 *action,
-		     u32 len,
-		     u32 *response_buf,
-		     u32 response_buf_size,
-		     u32 *status)
+static int ct_send(struct intel_guc_ct *ct,
+		   const u32 *action,
+		   u32 len,
+		   u32 *response_buf,
+		   u32 response_buf_size,
+		   u32 *status)
 {
-	struct intel_guc_ct_buffer *ctb = &ctch->ctbs[CTB_SEND];
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs[CTB_SEND];
 	struct guc_ct_buffer_desc *desc = ctb->desc;
 	struct ct_request request;
 	unsigned long flags;
 	u32 fence;
 	int err;
 
-	GEM_BUG_ON(!ctch->enabled);
+	GEM_BUG_ON(!ct->enabled);
 	GEM_BUG_ON(!len);
 	GEM_BUG_ON(len & ~GUC_CT_MSG_LEN_MASK);
 	GEM_BUG_ON(!response_buf && response_buf_size);
 
-	fence = ctch_get_next_fence(ctch);
+	fence = ct_get_next_fence(ct);
 	request.fence = fence;
 	request.status = 0;
 	request.response_len = response_buf_size;
 	request.response_buf = response_buf;
 
-	spin_lock_irqsave(&ct->lock, flags);
-	list_add_tail(&request.link, &ct->pending_requests);
-	spin_unlock_irqrestore(&ct->lock, flags);
+	spin_lock_irqsave(&ct->requests.lock, flags);
+	list_add_tail(&request.link, &ct->requests.pending);
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
 	err = ctb_write(ctb, action, len, fence, !!response_buf);
 	if (unlikely(err))
@@ -501,9 +500,9 @@ static int ctch_send(struct intel_guc_ct *ct,
 	}
 
 unlink:
-	spin_lock_irqsave(&ct->lock, flags);
+	spin_lock_irqsave(&ct->requests.lock, flags);
 	list_del(&request.link);
-	spin_unlock_irqrestore(&ct->lock, flags);
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
 	return err;
 }
@@ -511,18 +510,21 @@ unlink:
 /*
  * Command Transport (CT) buffer based GuC send function.
  */
-int intel_guc_send_ct(struct intel_guc *guc, const u32 *action, u32 len,
+int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
 		      u32 *response_buf, u32 response_buf_size)
 {
-	struct intel_guc_ct *ct = &guc->ct;
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
+	struct intel_guc *guc = ct_to_guc(ct);
 	u32 status = ~0; /* undefined */
 	int ret;
 
+	if (unlikely(!ct->enabled)) {
+		WARN(1, "Unexpected send: action=%#x\n", *action);
+		return -ENODEV;
+	}
+
 	mutex_lock(&guc->send_mutex);
 
-	ret = ctch_send(ct, ctch, action, len, response_buf, response_buf_size,
-			&status);
+	ret = ct_send(ct, action, len, response_buf, response_buf_size, &status);
 	if (unlikely(ret < 0)) {
 		DRM_ERROR("CT: send action %#X failed; err=%d status=%#X\n",
 			  action[0], ret, status);
@@ -653,8 +655,8 @@ static int ct_handle_response(struct intel_guc_ct *ct, const u32 *msg)
 
 	CT_DEBUG_DRIVER("CT: response fence %u status %#x\n", fence, status);
 
-	spin_lock(&ct->lock);
-	list_for_each_entry(req, &ct->pending_requests, link) {
+	spin_lock(&ct->requests.lock);
+	list_for_each_entry(req, &ct->requests.pending, link) {
 		if (unlikely(fence != req->fence)) {
 			CT_DEBUG_DRIVER("CT: request %u awaits response\n",
 					req->fence);
@@ -672,7 +674,7 @@ static int ct_handle_response(struct intel_guc_ct *ct, const u32 *msg)
 		found = true;
 		break;
 	}
-	spin_unlock(&ct->lock);
+	spin_unlock(&ct->requests.lock);
 
 	if (!found)
 		DRM_ERROR("CT: unsolicited response %*ph\n", 4 * msglen, msg);
@@ -710,13 +712,13 @@ static bool ct_process_incoming_requests(struct intel_guc_ct *ct)
 	u32 *payload;
 	bool done;
 
-	spin_lock_irqsave(&ct->lock, flags);
-	request = list_first_entry_or_null(&ct->incoming_requests,
+	spin_lock_irqsave(&ct->requests.lock, flags);
+	request = list_first_entry_or_null(&ct->requests.incoming,
 					   struct ct_incoming_request, link);
 	if (request)
 		list_del(&request->link);
-	done = !!list_empty(&ct->incoming_requests);
-	spin_unlock_irqrestore(&ct->lock, flags);
+	done = !!list_empty(&ct->requests.incoming);
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
 	if (!request)
 		return true;
@@ -734,12 +736,13 @@ static bool ct_process_incoming_requests(struct intel_guc_ct *ct)
 
 static void ct_incoming_request_worker_func(struct work_struct *w)
 {
-	struct intel_guc_ct *ct = container_of(w, struct intel_guc_ct, worker);
+	struct intel_guc_ct *ct =
+		container_of(w, struct intel_guc_ct, requests.worker);
 	bool done;
 
 	done = ct_process_incoming_requests(ct);
 	if (!done)
-		queue_work(system_unbound_wq, &ct->worker);
+		queue_work(system_unbound_wq, &ct->requests.worker);
 }
 
 /**
@@ -777,23 +780,28 @@ static int ct_handle_request(struct intel_guc_ct *ct, const u32 *msg)
 	}
 	memcpy(request->msg, msg, 4 * msglen);
 
-	spin_lock_irqsave(&ct->lock, flags);
-	list_add_tail(&request->link, &ct->incoming_requests);
-	spin_unlock_irqrestore(&ct->lock, flags);
+	spin_lock_irqsave(&ct->requests.lock, flags);
+	list_add_tail(&request->link, &ct->requests.incoming);
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
-	queue_work(system_unbound_wq, &ct->worker);
+	queue_work(system_unbound_wq, &ct->requests.worker);
 	return 0;
 }
 
-static void ct_process_host_channel(struct intel_guc_ct *ct)
+/*
+ * When we're communicating with the GuC over CT, GuC uses events
+ * to notify us about new messages being posted on the RECV buffer.
+ */
+void intel_guc_ct_event_handler(struct intel_guc_ct *ct)
 {
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-	struct intel_guc_ct_buffer *ctb = &ctch->ctbs[CTB_RECV];
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs[CTB_RECV];
 	u32 msg[GUC_CT_MSG_LEN_MASK + 1]; /* one extra dw for the header */
 	int err = 0;
 
-	if (!ctch->enabled)
+	if (unlikely(!ct->enabled)) {
+		WARN(1, "Unexpected GuC event received while CT disabled!\n");
 		return;
+	}
 
 	do {
 		err = ctb_read(ctb, msg);
@@ -812,86 +820,3 @@ static void ct_process_host_channel(struct intel_guc_ct *ct)
 	}
 }
 
-/*
- * When we're communicating with the GuC over CT, GuC uses events
- * to notify us about new messages being posted on the RECV buffer.
- */
-void intel_guc_to_host_event_handler_ct(struct intel_guc *guc)
-{
-	struct intel_guc_ct *ct = &guc->ct;
-
-	ct_process_host_channel(ct);
-}
-
-/**
- * intel_guc_ct_init - Init CT communication
- * @ct: pointer to CT struct
- *
- * Allocate memory required for communication via
- * the CT channel.
- *
- * Return: 0 on success, a negative errno code on failure.
- */
-int intel_guc_ct_init(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-	int err;
-
-	err = ctch_init(guc, ctch);
-	if (unlikely(err)) {
-		DRM_ERROR("CT: can't open channel %d; err=%d\n",
-			  ctch->owner, err);
-		return err;
-	}
-
-	GEM_BUG_ON(!ctch->vma);
-	return 0;
-}
-
-/**
- * intel_guc_ct_fini - Fini CT communication
- * @ct: pointer to CT struct
- *
- * Deallocate memory required for communication via
- * the CT channel.
- */
-void intel_guc_ct_fini(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-
-	ctch_fini(guc, ctch);
-}
-
-/**
- * intel_guc_ct_enable - Enable buffer based command transport.
- * @ct: pointer to CT struct
- *
- * Return: 0 on success, a negative errno code on failure.
- */
-int intel_guc_ct_enable(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-
-	if (ctch->enabled)
-		return 0;
-
-	return ctch_enable(guc, ctch);
-}
-
-/**
- * intel_guc_ct_disable - Disable buffer based command transport.
- * @ct: pointer to CT struct
- */
-void intel_guc_ct_disable(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-
-	if (!ctch->enabled)
-		return;
-
-	ctch_disable(guc, ctch);
-}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
index 7c24d83f5c24..3e7fe237cfa5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
@@ -35,44 +35,28 @@ struct intel_guc_ct_buffer {
 	u32 *cmds;
 };
 
-/** Represents pair of command transport buffers.
- *
- * Buffers go in pairs to allow bi-directional communication.
- * To simplify the code we place both of them in the same vma.
- * Buffers from the same pair must share unique owner id.
- *
- * @vma: pointer to the vma with pair of CT buffers
- * @ctbs: buffers for sending(0) and receiving(1) commands
- * @owner: unique identifier
- * @next_fence: fence to be used with next send command
- */
-struct intel_guc_ct_channel {
-	struct i915_vma *vma;
-	struct intel_guc_ct_buffer ctbs[2];
-	u32 owner;
-	u32 next_fence;
-	bool enabled;
-};
 
-/** Holds all command transport channels.
+/** Top-level structure for Command Transport related data
  *
- * @host_channel: main channel used by the host
+ * Includes a pair of CT buffers for bi-directional communication and tracking
+ * for the H2G and G2H requests sent and received through the buffers.
  */
 struct intel_guc_ct {
-	struct intel_guc_ct_channel host_channel;
-	/* other channels are tbd */
+	struct i915_vma *vma;
+	bool enabled;
 
-	/** @lock: protects pending requests list */
-	spinlock_t lock;
+	/* buffers for sending(0) and receiving(1) commands */
+	struct intel_guc_ct_buffer ctbs[2];
 
-	/** @pending_requests: list of requests waiting for response */
-	struct list_head pending_requests;
+	struct {
+		u32 next_fence; /* fence to be used with next request to send */
 
-	/** @incoming_requests: list of incoming requests */
-	struct list_head incoming_requests;
+		spinlock_t lock; /* protects pending requests list */
+		struct list_head pending; /* requests waiting for response */
 
-	/** @worker: worker for handling incoming requests */
-	struct work_struct worker;
+		struct list_head incoming; /* incoming requests */
+		struct work_struct worker; /* handler for incoming requests */
+	} requests;
 };
 
 void intel_guc_ct_init_early(struct intel_guc_ct *ct);
@@ -81,13 +65,13 @@ void intel_guc_ct_fini(struct intel_guc_ct *ct);
 int intel_guc_ct_enable(struct intel_guc_ct *ct);
 void intel_guc_ct_disable(struct intel_guc_ct *ct);
 
-static inline void intel_guc_ct_stop(struct intel_guc_ct *ct)
+static inline bool intel_guc_ct_enabled(struct intel_guc_ct *ct)
 {
-	ct->host_channel.enabled = false;
+	return ct->enabled;
 }
 
-int intel_guc_send_ct(struct intel_guc *guc, const u32 *action, u32 len,
+int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
 		      u32 *response_buf, u32 response_buf_size);
-void intel_guc_to_host_event_handler_ct(struct intel_guc *guc);
+void intel_guc_ct_event_handler(struct intel_guc_ct *ct);
 
 #endif /* _INTEL_GUC_CT_H_ */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
index 5528224448f6..3a1c47d600ea 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
@@ -149,7 +149,7 @@ int intel_guc_fw_upload(struct intel_guc *guc)
 	 * Current uCode expects the code to be loaded at 8k; locations below
 	 * this are used for the stack.
 	 */
-	ret = intel_uc_fw_upload(&guc->fw, gt, 0x2000, UOS_MOVE);
+	ret = intel_uc_fw_upload(&guc->fw, 0x2000, UOS_MOVE);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
index a26a85d50209..a6b733c146c9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
@@ -31,7 +31,6 @@
 
 #define GUC_DOORBELL_INVALID		256
 
-#define GUC_DB_SIZE			(PAGE_SIZE)
 #define GUC_WQ_SIZE			(PAGE_SIZE * 2)
 
 /* Work queue item header definitions */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 2498c55e0ea5..9e42324fdecd 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -18,15 +18,6 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
-enum {
-	GUC_PREEMPT_NONE = 0,
-	GUC_PREEMPT_INPROGRESS,
-	GUC_PREEMPT_FINISHED,
-};
-#define GUC_PREEMPT_BREADCRUMB_DWORDS	0x8
-#define GUC_PREEMPT_BREADCRUMB_BYTES	\
-	(sizeof(u32) * GUC_PREEMPT_BREADCRUMB_DWORDS)
-
 /**
  * DOC: GuC-based command submission
  *
@@ -36,25 +27,14 @@ enum {
  * code) matches the old submission model and will be updated as part of the
  * upgrade to the new flow.
  *
- * GuC client:
- * A intel_guc_client refers to a submission path through GuC. Currently, there
- * is only one client, which is charged with all submissions to the GuC. This
- * struct is the owner of a doorbell, a process descriptor and a workqueue (all
- * of them inside a single gem object that contains all required pages for these
- * elements).
- *
  * GuC stage descriptor:
  * During initialization, the driver allocates a static pool of 1024 such
- * descriptors, and shares them with the GuC.
- * Currently, there exists a 1:1 mapping between a intel_guc_client and a
- * guc_stage_desc (via the client's stage_id), so effectively only one
- * gets used. This stage descriptor lets the GuC know about the doorbell,
- * workqueue and process descriptor. Theoretically, it also lets the GuC
- * know about our HW contexts (context ID, etc...), but we actually
- * employ a kind of submission where the GuC uses the LRCA sent via the work
- * item instead (the single guc_stage_desc associated to execbuf client
- * contains information about the default kernel context only, but this is
- * essentially unused). This is called a "proxy" submission.
+ * descriptors, and shares them with the GuC. Currently, we only use one
+ * descriptor. This stage descriptor lets the GuC know about the workqueue and
+ * process descriptor. Theoretically, it also lets the GuC know about our HW
+ * contexts (context ID, etc...), but we actually employ a kind of submission
+ * where the GuC uses the LRCA sent via the work item instead. This is called
+ * a "proxy" submission.
  *
  * The Scratch registers:
  * There are 16 MMIO-based registers start from 0xC180. The kernel driver writes
@@ -63,11 +43,6 @@ enum {
  * Firmware writes a success/fail code back to the action register after
  * processes the request. The kernel driver polls waiting for this update and
  * then proceeds.
- * See intel_guc_send()
- *
- * Doorbells:
- * Doorbells are interrupts to uKernel. A doorbell is a single cache line (QW)
- * mapped into process space.
  *
  * Work Items:
  * There are several types of work items that the host may place into a
@@ -84,213 +59,45 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 	return rb_entry(rb, struct i915_priolist, node);
 }
 
-static inline bool is_high_priority(struct intel_guc_client *client)
+static struct guc_stage_desc *__get_stage_desc(struct intel_guc *guc, u32 id)
 {
-	return (client->priority == GUC_CLIENT_PRIORITY_KMD_HIGH ||
-		client->priority == GUC_CLIENT_PRIORITY_HIGH);
-}
-
-static int reserve_doorbell(struct intel_guc_client *client)
-{
-	unsigned long offset;
-	unsigned long end;
-	u16 id;
-
-	GEM_BUG_ON(client->doorbell_id != GUC_DOORBELL_INVALID);
+	struct guc_stage_desc *base = guc->stage_desc_pool_vaddr;
 
-	/*
-	 * The bitmap tracks which doorbell registers are currently in use.
-	 * It is split into two halves; the first half is used for normal
-	 * priority contexts, the second half for high-priority ones.
-	 */
-	offset = 0;
-	end = GUC_NUM_DOORBELLS / 2;
-	if (is_high_priority(client)) {
-		offset = end;
-		end += offset;
-	}
-
-	id = find_next_zero_bit(client->guc->doorbell_bitmap, end, offset);
-	if (id == end)
-		return -ENOSPC;
-
-	__set_bit(id, client->guc->doorbell_bitmap);
-	client->doorbell_id = id;
-	DRM_DEBUG_DRIVER("client %u (high prio=%s) reserved doorbell: %d\n",
-			 client->stage_id, yesno(is_high_priority(client)),
-			 id);
-	return 0;
+	return &base[id];
 }
 
-static bool has_doorbell(struct intel_guc_client *client)
+static int guc_workqueue_create(struct intel_guc *guc)
 {
-	if (client->doorbell_id == GUC_DOORBELL_INVALID)
-		return false;
-
-	return test_bit(client->doorbell_id, client->guc->doorbell_bitmap);
+	return intel_guc_allocate_and_map_vma(guc, GUC_WQ_SIZE, &guc->workqueue,
+					      &guc->workqueue_vaddr);
 }
 
-static void unreserve_doorbell(struct intel_guc_client *client)
+static void guc_workqueue_destroy(struct intel_guc *guc)
 {
-	GEM_BUG_ON(!has_doorbell(client));
-
-	__clear_bit(client->doorbell_id, client->guc->doorbell_bitmap);
-	client->doorbell_id = GUC_DOORBELL_INVALID;
+	i915_vma_unpin_and_release(&guc->workqueue, I915_VMA_RELEASE_MAP);
 }
 
 /*
- * Tell the GuC to allocate or deallocate a specific doorbell
- */
-
-static int __guc_allocate_doorbell(struct intel_guc *guc, u32 stage_id)
-{
-	u32 action[] = {
-		INTEL_GUC_ACTION_ALLOCATE_DOORBELL,
-		stage_id
-	};
-
-	return intel_guc_send(guc, action, ARRAY_SIZE(action));
-}
-
-static int __guc_deallocate_doorbell(struct intel_guc *guc, u32 stage_id)
-{
-	u32 action[] = {
-		INTEL_GUC_ACTION_DEALLOCATE_DOORBELL,
-		stage_id
-	};
-
-	return intel_guc_send(guc, action, ARRAY_SIZE(action));
-}
-
-static struct guc_stage_desc *__get_stage_desc(struct intel_guc_client *client)
-{
-	struct guc_stage_desc *base = client->guc->stage_desc_pool_vaddr;
-
-	return &base[client->stage_id];
-}
-
-/*
- * Initialise, update, or clear doorbell data shared with the GuC
- *
- * These functions modify shared data and so need access to the mapped
- * client object which contains the page being used for the doorbell
+ * Initialise the process descriptor shared with the GuC firmware.
  */
-
-static void __update_doorbell_desc(struct intel_guc_client *client, u16 new_id)
-{
-	struct guc_stage_desc *desc;
-
-	/* Update the GuC's idea of the doorbell ID */
-	desc = __get_stage_desc(client);
-	desc->db_id = new_id;
-}
-
-static struct guc_doorbell_info *__get_doorbell(struct intel_guc_client *client)
-{
-	return client->vaddr + client->doorbell_offset;
-}
-
-static bool __doorbell_valid(struct intel_guc *guc, u16 db_id)
-{
-	struct intel_uncore *uncore = guc_to_gt(guc)->uncore;
-
-	GEM_BUG_ON(db_id >= GUC_NUM_DOORBELLS);
-	return intel_uncore_read(uncore, GEN8_DRBREGL(db_id)) & GEN8_DRB_VALID;
-}
-
-static void __init_doorbell(struct intel_guc_client *client)
-{
-	struct guc_doorbell_info *doorbell;
-
-	doorbell = __get_doorbell(client);
-	doorbell->db_status = GUC_DOORBELL_ENABLED;
-	doorbell->cookie = 0;
-}
-
-static void __fini_doorbell(struct intel_guc_client *client)
-{
-	struct guc_doorbell_info *doorbell;
-	u16 db_id = client->doorbell_id;
-
-	doorbell = __get_doorbell(client);
-	doorbell->db_status = GUC_DOORBELL_DISABLED;
-
-	/* Doorbell release flow requires that we wait for GEN8_DRB_VALID bit
-	 * to go to zero after updating db_status before we call the GuC to
-	 * release the doorbell
-	 */
-	if (wait_for_us(!__doorbell_valid(client->guc, db_id), 10))
-		WARN_ONCE(true, "Doorbell never became invalid after disable\n");
-}
-
-static int create_doorbell(struct intel_guc_client *client)
+static int guc_proc_desc_create(struct intel_guc *guc)
 {
-	int ret;
-
-	if (WARN_ON(!has_doorbell(client)))
-		return -ENODEV; /* internal setup error, should never happen */
-
-	__update_doorbell_desc(client, client->doorbell_id);
-	__init_doorbell(client);
-
-	ret = __guc_allocate_doorbell(client->guc, client->stage_id);
-	if (ret) {
-		__fini_doorbell(client);
-		__update_doorbell_desc(client, GUC_DOORBELL_INVALID);
-		DRM_DEBUG_DRIVER("Couldn't create client %u doorbell: %d\n",
-				 client->stage_id, ret);
-		return ret;
-	}
+	const u32 size = PAGE_ALIGN(sizeof(struct guc_process_desc));
 
-	return 0;
+	return intel_guc_allocate_and_map_vma(guc, size, &guc->proc_desc,
+					      &guc->proc_desc_vaddr);
 }
 
-static int destroy_doorbell(struct intel_guc_client *client)
+static void guc_proc_desc_destroy(struct intel_guc *guc)
 {
-	int ret;
-
-	GEM_BUG_ON(!has_doorbell(client));
-
-	__fini_doorbell(client);
-	ret = __guc_deallocate_doorbell(client->guc, client->stage_id);
-	if (ret)
-		DRM_ERROR("Couldn't destroy client %u doorbell: %d\n",
-			  client->stage_id, ret);
-
-	__update_doorbell_desc(client, GUC_DOORBELL_INVALID);
-
-	return ret;
+	i915_vma_unpin_and_release(&guc->proc_desc, I915_VMA_RELEASE_MAP);
 }
 
-static unsigned long __select_cacheline(struct intel_guc *guc)
-{
-	unsigned long offset;
-
-	/* Doorbell uses a single cache line within a page */
-	offset = offset_in_page(guc->db_cacheline);
-
-	/* Moving to next cache line to reduce contention */
-	guc->db_cacheline += cache_line_size();
-
-	DRM_DEBUG_DRIVER("reserved cacheline 0x%lx, next 0x%x, linesize %u\n",
-			 offset, guc->db_cacheline, cache_line_size());
-	return offset;
-}
-
-static inline struct guc_process_desc *
-__get_process_desc(struct intel_guc_client *client)
-{
-	return client->vaddr + client->proc_desc_offset;
-}
-
-/*
- * Initialise the process descriptor shared with the GuC firmware.
- */
-static void guc_proc_desc_init(struct intel_guc_client *client)
+static void guc_proc_desc_init(struct intel_guc *guc)
 {
 	struct guc_process_desc *desc;
 
-	desc = memset(__get_process_desc(client), 0, sizeof(*desc));
+	desc = memset(guc->proc_desc_vaddr, 0, sizeof(*desc));
 
 	/*
 	 * XXX: pDoorbell and WQVBaseAddress are pointers in process address
@@ -301,47 +108,27 @@ static void guc_proc_desc_init(struct intel_guc_client *client)
 	desc->wq_base_addr = 0;
 	desc->db_base_addr = 0;
 
-	desc->stage_id = client->stage_id;
 	desc->wq_size_bytes = GUC_WQ_SIZE;
 	desc->wq_status = WQ_STATUS_ACTIVE;
-	desc->priority = client->priority;
+	desc->priority = GUC_CLIENT_PRIORITY_KMD_NORMAL;
 }
 
-static void guc_proc_desc_fini(struct intel_guc_client *client)
+static void guc_proc_desc_fini(struct intel_guc *guc)
 {
-	struct guc_process_desc *desc;
-
-	desc = __get_process_desc(client);
-	memset(desc, 0, sizeof(*desc));
+	memset(guc->proc_desc_vaddr, 0, sizeof(struct guc_process_desc));
 }
 
 static int guc_stage_desc_pool_create(struct intel_guc *guc)
 {
-	struct i915_vma *vma;
-	void *vaddr;
-
-	vma = intel_guc_allocate_vma(guc,
-				     PAGE_ALIGN(sizeof(struct guc_stage_desc) *
-				     GUC_MAX_STAGE_DESCRIPTORS));
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
-
-	vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(vaddr)) {
-		i915_vma_unpin_and_release(&vma, 0);
-		return PTR_ERR(vaddr);
-	}
-
-	guc->stage_desc_pool = vma;
-	guc->stage_desc_pool_vaddr = vaddr;
-	ida_init(&guc->stage_ids);
+	u32 size = PAGE_ALIGN(sizeof(struct guc_stage_desc) *
+			      GUC_MAX_STAGE_DESCRIPTORS);
 
-	return 0;
+	return intel_guc_allocate_and_map_vma(guc, size, &guc->stage_desc_pool,
+					      &guc->stage_desc_pool_vaddr);
 }
 
 static void guc_stage_desc_pool_destroy(struct intel_guc *guc)
 {
-	ida_destroy(&guc->stage_ids);
 	i915_vma_unpin_and_release(&guc->stage_desc_pool, I915_VMA_RELEASE_MAP);
 }
 
@@ -349,63 +136,49 @@ static void guc_stage_desc_pool_destroy(struct intel_guc *guc)
  * Initialise/clear the stage descriptor shared with the GuC firmware.
  *
  * This descriptor tells the GuC where (in GGTT space) to find the important
- * data structures relating to this client (doorbell, process descriptor,
- * write queue, etc).
+ * data structures related to work submission (process descriptor, write queue,
+ * etc).
  */
-static void guc_stage_desc_init(struct intel_guc_client *client)
+static void guc_stage_desc_init(struct intel_guc *guc)
 {
-	struct intel_guc *guc = client->guc;
 	struct guc_stage_desc *desc;
-	u32 gfx_addr;
 
-	desc = __get_stage_desc(client);
+	/* we only use 1 stage desc, so hardcode it to 0 */
+	desc = __get_stage_desc(guc, 0);
 	memset(desc, 0, sizeof(*desc));
 
 	desc->attribute = GUC_STAGE_DESC_ATTR_ACTIVE |
 			  GUC_STAGE_DESC_ATTR_KERNEL;
-	if (is_high_priority(client))
-		desc->attribute |= GUC_STAGE_DESC_ATTR_PREEMPT;
-	desc->stage_id = client->stage_id;
-	desc->priority = client->priority;
-	desc->db_id = client->doorbell_id;
 
-	/*
-	 * The doorbell, process descriptor, and workqueue are all parts
-	 * of the client object, which the GuC will reference via the GGTT
-	 */
-	gfx_addr = intel_guc_ggtt_offset(guc, client->vma);
-	desc->db_trigger_phy = sg_dma_address(client->vma->pages->sgl) +
-				client->doorbell_offset;
-	desc->db_trigger_cpu = ptr_to_u64(__get_doorbell(client));
-	desc->db_trigger_uk = gfx_addr + client->doorbell_offset;
-	desc->process_desc = gfx_addr + client->proc_desc_offset;
-	desc->wq_addr = gfx_addr + GUC_DB_SIZE;
-	desc->wq_size = GUC_WQ_SIZE;
+	desc->stage_id = 0;
+	desc->priority = GUC_CLIENT_PRIORITY_KMD_NORMAL;
 
-	desc->desc_private = ptr_to_u64(client);
+	desc->process_desc = intel_guc_ggtt_offset(guc, guc->proc_desc);
+	desc->wq_addr = intel_guc_ggtt_offset(guc, guc->workqueue);
+	desc->wq_size = GUC_WQ_SIZE;
 }
 
-static void guc_stage_desc_fini(struct intel_guc_client *client)
+static void guc_stage_desc_fini(struct intel_guc *guc)
 {
 	struct guc_stage_desc *desc;
 
-	desc = __get_stage_desc(client);
+	desc = __get_stage_desc(guc, 0);
 	memset(desc, 0, sizeof(*desc));
 }
 
 /* Construct a Work Item and append it to the GuC's Work Queue */
-static void guc_wq_item_append(struct intel_guc_client *client,
+static void guc_wq_item_append(struct intel_guc *guc,
 			       u32 target_engine, u32 context_desc,
 			       u32 ring_tail, u32 fence_id)
 {
 	/* wqi_len is in DWords, and does not include the one-word header */
 	const size_t wqi_size = sizeof(struct guc_wq_item);
 	const u32 wqi_len = wqi_size / sizeof(u32) - 1;
-	struct guc_process_desc *desc = __get_process_desc(client);
+	struct guc_process_desc *desc = guc->proc_desc_vaddr;
 	struct guc_wq_item *wqi;
 	u32 wq_off;
 
-	lockdep_assert_held(&client->wq_lock);
+	lockdep_assert_held(&guc->wq_lock);
 
 	/* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we
 	 * should not have the case where structure wqi is across page, neither
@@ -425,58 +198,30 @@ static void guc_wq_item_append(struct intel_guc_client *client,
 			      GUC_WQ_SIZE) < wqi_size);
 	GEM_BUG_ON(wq_off & (wqi_size - 1));
 
-	/* WQ starts from the page after doorbell / process_desc */
-	wqi = client->vaddr + wq_off + GUC_DB_SIZE;
-
-	if (I915_SELFTEST_ONLY(client->use_nop_wqi)) {
-		wqi->header = WQ_TYPE_NOOP | (wqi_len << WQ_LEN_SHIFT);
-	} else {
-		/* Now fill in the 4-word work queue item */
-		wqi->header = WQ_TYPE_INORDER |
-			      (wqi_len << WQ_LEN_SHIFT) |
-			      (target_engine << WQ_TARGET_SHIFT) |
-			      WQ_NO_WCFLUSH_WAIT;
-		wqi->context_desc = context_desc;
-		wqi->submit_element_info = ring_tail << WQ_RING_TAIL_SHIFT;
-		GEM_BUG_ON(ring_tail > WQ_RING_TAIL_MAX);
-		wqi->fence_id = fence_id;
-	}
+	wqi = guc->workqueue_vaddr + wq_off;
+
+	/* Now fill in the 4-word work queue item */
+	wqi->header = WQ_TYPE_INORDER |
+		      (wqi_len << WQ_LEN_SHIFT) |
+		      (target_engine << WQ_TARGET_SHIFT) |
+		      WQ_NO_WCFLUSH_WAIT;
+	wqi->context_desc = context_desc;
+	wqi->submit_element_info = ring_tail << WQ_RING_TAIL_SHIFT;
+	GEM_BUG_ON(ring_tail > WQ_RING_TAIL_MAX);
+	wqi->fence_id = fence_id;
 
 	/* Make the update visible to GuC */
 	WRITE_ONCE(desc->tail, (wq_off + wqi_size) & (GUC_WQ_SIZE - 1));
 }
 
-static void guc_ring_doorbell(struct intel_guc_client *client)
-{
-	struct guc_doorbell_info *db;
-	u32 cookie;
-
-	lockdep_assert_held(&client->wq_lock);
-
-	/* pointer of current doorbell cacheline */
-	db = __get_doorbell(client);
-
-	/*
-	 * We're not expecting the doorbell cookie to change behind our back,
-	 * we also need to treat 0 as a reserved value.
-	 */
-	cookie = READ_ONCE(db->cookie);
-	WARN_ON_ONCE(xchg(&db->cookie, cookie + 1 ?: cookie + 2) != cookie);
-
-	/* XXX: doorbell was lost and need to acquire it again */
-	GEM_BUG_ON(db->db_status != GUC_DOORBELL_ENABLED);
-}
-
 static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
-	struct intel_guc_client *client = guc->execbuf_client;
 	struct intel_engine_cs *engine = rq->engine;
-	u32 ctx_desc = lower_32_bits(rq->hw_context->lrc_desc);
+	u32 ctx_desc = lower_32_bits(rq->context->lrc_desc);
 	u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64);
 
-	guc_wq_item_append(client, engine->guc_id, ctx_desc,
+	guc_wq_item_append(guc, engine->guc_id, ctx_desc,
 			   ring_tail, rq->fence.seqno);
-	guc_ring_doorbell(client);
 }
 
 /*
@@ -488,10 +233,9 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
  */
 static void flush_ggtt_writes(struct i915_vma *vma)
 {
-	struct drm_i915_private *i915 = vma->vm->i915;
-
 	if (i915_vma_is_map_and_fenceable(vma))
-		intel_uncore_posting_read_fw(&i915->uncore, GUC_STATUS);
+		intel_uncore_posting_read_fw(vma->vm->gt->uncore,
+					     GUC_STATUS);
 }
 
 static void guc_submit(struct intel_engine_cs *engine,
@@ -499,9 +243,8 @@ static void guc_submit(struct intel_engine_cs *engine,
 		       struct i915_request **end)
 {
 	struct intel_guc *guc = &engine->gt->uc.guc;
-	struct intel_guc_client *client = guc->execbuf_client;
 
-	spin_lock(&client->wq_lock);
+	spin_lock(&guc->wq_lock);
 
 	do {
 		struct i915_request *rq = *out++;
@@ -510,7 +253,7 @@ static void guc_submit(struct intel_engine_cs *engine,
 		guc_add_request(guc, rq);
 	} while (out != end);
 
-	spin_unlock(&client->wq_lock);
+	spin_unlock(&guc->wq_lock);
 }
 
 static inline int rq_prio(const struct i915_request *rq)
@@ -529,7 +272,7 @@ static struct i915_request *schedule_in(struct i915_request *rq, int idx)
 	 * required if we generalise the inflight tracking.
 	 */
 
-	intel_gt_pm_get(rq->engine->gt);
+	__intel_gt_pm_get(rq->engine->gt);
 	return i915_request_get(rq);
 }
 
@@ -537,7 +280,7 @@ static void schedule_out(struct i915_request *rq)
 {
 	trace_i915_request_out(rq);
 
-	intel_gt_pm_put(rq->engine->gt);
+	intel_gt_pm_put_async(rq->engine->gt);
 	i915_request_put(rq);
 }
 
@@ -572,7 +315,7 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			if (last && rq->hw_context != last->hw_context) {
+			if (last && rq->context != last->context) {
 				if (port == last_port)
 					goto done;
 
@@ -631,7 +374,7 @@ static void guc_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * Prevent request submission to the hardware until we have
@@ -658,7 +401,7 @@ cancel_port_requests(struct intel_engine_execlists * const execlists)
 		memset(execlists->inflight, 0, sizeof(execlists->inflight));
 }
 
-static void guc_reset(struct intel_engine_cs *engine, bool stalled)
+static void guc_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq;
@@ -677,20 +420,20 @@ static void guc_reset(struct intel_engine_cs *engine, bool stalled)
 		stalled = false;
 
 	__i915_request_reset(rq, stalled);
-	intel_lr_context_reset(engine, rq->hw_context, rq->head, stalled);
+	intel_lr_context_reset(engine, rq->context, rq->head, stalled);
 
 out_unlock:
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
-static void guc_cancel_requests(struct intel_engine_cs *engine)
+static void guc_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq, *rn;
 	struct rb_node *rb;
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * Before we call engine->cancel_requests(), we should have exclusive
@@ -751,8 +494,8 @@ static void guc_reset_finish(struct intel_engine_cs *engine)
 		/* And kick in case we missed a new request submission. */
 		tasklet_hi_schedule(&execlists->tasklet);
 
-	GEM_TRACE("%s: depth->%d\n", engine->name,
-		  atomic_read(&execlists->tasklet.count));
+	ENGINE_TRACE(engine, "depth->%d\n",
+		     atomic_read(&execlists->tasklet.count));
 }
 
 /*
@@ -761,213 +504,6 @@ static void guc_reset_finish(struct intel_engine_cs *engine)
  * path of guc_submit() above.
  */
 
-/* Check that a doorbell register is in the expected state */
-static bool doorbell_ok(struct intel_guc *guc, u16 db_id)
-{
-	bool valid;
-
-	GEM_BUG_ON(db_id >= GUC_NUM_DOORBELLS);
-
-	valid = __doorbell_valid(guc, db_id);
-
-	if (test_bit(db_id, guc->doorbell_bitmap) == valid)
-		return true;
-
-	DRM_DEBUG_DRIVER("Doorbell %u has unexpected state: valid=%s\n",
-			 db_id, yesno(valid));
-
-	return false;
-}
-
-static bool guc_verify_doorbells(struct intel_guc *guc)
-{
-	bool doorbells_ok = true;
-	u16 db_id;
-
-	for (db_id = 0; db_id < GUC_NUM_DOORBELLS; ++db_id)
-		if (!doorbell_ok(guc, db_id))
-			doorbells_ok = false;
-
-	return doorbells_ok;
-}
-
-/**
- * guc_client_alloc() - Allocate an intel_guc_client
- * @guc:	the intel_guc structure
- * @priority:	four levels priority _CRITICAL, _HIGH, _NORMAL and _LOW
- *		The kernel client to replace ExecList submission is created with
- *		NORMAL priority. Priority of a client for scheduler can be HIGH,
- *		while a preemption context can use CRITICAL.
- *
- * Return:	An intel_guc_client object if success, else NULL.
- */
-static struct intel_guc_client *
-guc_client_alloc(struct intel_guc *guc, u32 priority)
-{
-	struct intel_guc_client *client;
-	struct i915_vma *vma;
-	void *vaddr;
-	int ret;
-
-	client = kzalloc(sizeof(*client), GFP_KERNEL);
-	if (!client)
-		return ERR_PTR(-ENOMEM);
-
-	client->guc = guc;
-	client->priority = priority;
-	client->doorbell_id = GUC_DOORBELL_INVALID;
-	spin_lock_init(&client->wq_lock);
-
-	ret = ida_simple_get(&guc->stage_ids, 0, GUC_MAX_STAGE_DESCRIPTORS,
-			     GFP_KERNEL);
-	if (ret < 0)
-		goto err_client;
-
-	client->stage_id = ret;
-
-	/* The first page is doorbell/proc_desc. Two followed pages are wq. */
-	vma = intel_guc_allocate_vma(guc, GUC_DB_SIZE + GUC_WQ_SIZE);
-	if (IS_ERR(vma)) {
-		ret = PTR_ERR(vma);
-		goto err_id;
-	}
-
-	/* We'll keep just the first (doorbell/proc) page permanently kmap'd. */
-	client->vma = vma;
-
-	vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(vaddr)) {
-		ret = PTR_ERR(vaddr);
-		goto err_vma;
-	}
-	client->vaddr = vaddr;
-
-	ret = reserve_doorbell(client);
-	if (ret)
-		goto err_vaddr;
-
-	client->doorbell_offset = __select_cacheline(guc);
-
-	/*
-	 * Since the doorbell only requires a single cacheline, we can save
-	 * space by putting the application process descriptor in the same
-	 * page. Use the half of the page that doesn't include the doorbell.
-	 */
-	if (client->doorbell_offset >= (GUC_DB_SIZE / 2))
-		client->proc_desc_offset = 0;
-	else
-		client->proc_desc_offset = (GUC_DB_SIZE / 2);
-
-	DRM_DEBUG_DRIVER("new priority %u client %p: stage_id %u\n",
-			 priority, client, client->stage_id);
-	DRM_DEBUG_DRIVER("doorbell id %u, cacheline offset 0x%lx\n",
-			 client->doorbell_id, client->doorbell_offset);
-
-	return client;
-
-err_vaddr:
-	i915_gem_object_unpin_map(client->vma->obj);
-err_vma:
-	i915_vma_unpin_and_release(&client->vma, 0);
-err_id:
-	ida_simple_remove(&guc->stage_ids, client->stage_id);
-err_client:
-	kfree(client);
-	return ERR_PTR(ret);
-}
-
-static void guc_client_free(struct intel_guc_client *client)
-{
-	unreserve_doorbell(client);
-	i915_vma_unpin_and_release(&client->vma, I915_VMA_RELEASE_MAP);
-	ida_simple_remove(&client->guc->stage_ids, client->stage_id);
-	kfree(client);
-}
-
-static inline bool ctx_save_restore_disabled(struct intel_context *ce)
-{
-	u32 sr = ce->lrc_reg_state[CTX_CONTEXT_CONTROL + 1];
-
-#define SR_DISABLED \
-	_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT | \
-			   CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT)
-
-	return (sr & SR_DISABLED) == SR_DISABLED;
-
-#undef SR_DISABLED
-}
-
-static int guc_clients_create(struct intel_guc *guc)
-{
-	struct intel_guc_client *client;
-
-	GEM_BUG_ON(guc->execbuf_client);
-
-	client = guc_client_alloc(guc, GUC_CLIENT_PRIORITY_KMD_NORMAL);
-	if (IS_ERR(client)) {
-		DRM_ERROR("Failed to create GuC client for submission!\n");
-		return PTR_ERR(client);
-	}
-	guc->execbuf_client = client;
-
-	return 0;
-}
-
-static void guc_clients_destroy(struct intel_guc *guc)
-{
-	struct intel_guc_client *client;
-
-	client = fetch_and_zero(&guc->execbuf_client);
-	if (client)
-		guc_client_free(client);
-}
-
-static int __guc_client_enable(struct intel_guc_client *client)
-{
-	int ret;
-
-	guc_proc_desc_init(client);
-	guc_stage_desc_init(client);
-
-	ret = create_doorbell(client);
-	if (ret)
-		goto fail;
-
-	return 0;
-
-fail:
-	guc_stage_desc_fini(client);
-	guc_proc_desc_fini(client);
-	return ret;
-}
-
-static void __guc_client_disable(struct intel_guc_client *client)
-{
-	/*
-	 * By the time we're here, GuC may have already been reset. if that is
-	 * the case, instead of trying (in vain) to communicate with it, let's
-	 * just cleanup the doorbell HW and our internal state.
-	 */
-	if (intel_guc_is_running(client->guc))
-		destroy_doorbell(client);
-	else
-		__fini_doorbell(client);
-
-	guc_stage_desc_fini(client);
-	guc_proc_desc_fini(client);
-}
-
-static int guc_clients_enable(struct intel_guc *guc)
-{
-	return __guc_client_enable(guc->execbuf_client);
-}
-
-static void guc_clients_disable(struct intel_guc *guc)
-{
-	if (guc->execbuf_client)
-		__guc_client_disable(guc->execbuf_client);
-}
-
 /*
  * Set up the memory resources to be shared with the GuC (via the GGTT)
  * at firmware loading time.
@@ -988,13 +524,20 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	 */
 	GEM_BUG_ON(!guc->stage_desc_pool);
 
-	WARN_ON(!guc_verify_doorbells(guc));
-	ret = guc_clients_create(guc);
+	ret = guc_workqueue_create(guc);
 	if (ret)
 		goto err_pool;
 
+	ret = guc_proc_desc_create(guc);
+	if (ret)
+		goto err_workqueue;
+
+	spin_lock_init(&guc->wq_lock);
+
 	return 0;
 
+err_workqueue:
+	guc_workqueue_destroy(guc);
 err_pool:
 	guc_stage_desc_pool_destroy(guc);
 	return ret;
@@ -1002,83 +545,37 @@ err_pool:
 
 void intel_guc_submission_fini(struct intel_guc *guc)
 {
-	guc_clients_destroy(guc);
-	WARN_ON(!guc_verify_doorbells(guc));
-
-	if (guc->stage_desc_pool)
+	if (guc->stage_desc_pool) {
+		guc_proc_desc_destroy(guc);
+		guc_workqueue_destroy(guc);
 		guc_stage_desc_pool_destroy(guc);
+	}
 }
 
 static void guc_interrupts_capture(struct intel_gt *gt)
 {
-	struct intel_rps *rps = &gt->rps;
 	struct intel_uncore *uncore = gt->uncore;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int irqs;
+	u32 irqs = GT_CONTEXT_SWITCH_INTERRUPT;
+	u32 dmask = irqs << 16 | irqs;
 
-	/* tell all command streamers to forward interrupts (but not vblank)
-	 * to GuC
-	 */
-	irqs = _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, gt, id)
-		ENGINE_WRITE(engine, RING_MODE_GEN7, irqs);
-
-	/* route USER_INTERRUPT to Host, all others are sent to GuC. */
-	irqs = GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
-	       GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
-	/* These three registers have the same bit definitions */
-	intel_uncore_write(uncore, GUC_BCS_RCS_IER, ~irqs);
-	intel_uncore_write(uncore, GUC_VCS2_VCS1_IER, ~irqs);
-	intel_uncore_write(uncore, GUC_WD_VECS_IER, ~irqs);
+	GEM_BUG_ON(INTEL_GEN(gt->i915) < 11);
 
-	/*
-	 * The REDIRECT_TO_GUC bit of the PMINTRMSK register directs all
-	 * (unmasked) PM interrupts to the GuC. All other bits of this
-	 * register *disable* generation of a specific interrupt.
-	 *
-	 * 'pm_intrmsk_mbz' indicates bits that are NOT to be set when
-	 * writing to the PM interrupt mask register, i.e. interrupts
-	 * that must not be disabled.
-	 *
-	 * If the GuC is handling these interrupts, then we must not let
-	 * the PM code disable ANY interrupt that the GuC is expecting.
-	 * So for each ENABLED (0) bit in this register, we must SET the
-	 * bit in pm_intrmsk_mbz so that it's left enabled for the GuC.
-	 * GuC needs ARAT expired interrupt unmasked hence it is set in
-	 * pm_intrmsk_mbz.
-	 *
-	 * Here we CLEAR REDIRECT_TO_GUC bit in pm_intrmsk_mbz, which will
-	 * result in the register bit being left SET!
-	 */
-	rps->pm_intrmsk_mbz |= ARAT_EXPIRED_INTRMSK;
-	rps->pm_intrmsk_mbz &= ~GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
+	/* Don't handle the ctx switch interrupt in GuC submission mode */
+	intel_uncore_rmw(uncore, GEN11_RENDER_COPY_INTR_ENABLE, dmask, 0);
+	intel_uncore_rmw(uncore, GEN11_VCS_VECS_INTR_ENABLE, dmask, 0);
 }
 
 static void guc_interrupts_release(struct intel_gt *gt)
 {
-	struct intel_rps *rps = &gt->rps;
 	struct intel_uncore *uncore = gt->uncore;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int irqs;
+	u32 irqs = GT_CONTEXT_SWITCH_INTERRUPT;
+	u32 dmask = irqs << 16 | irqs;
 
-	/*
-	 * tell all command streamers NOT to forward interrupts or vblank
-	 * to GuC.
-	 */
-	irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_NEVER);
-	irqs |= _MASKED_BIT_DISABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, gt, id)
-		ENGINE_WRITE(engine, RING_MODE_GEN7, irqs);
-
-	/* route all GT interrupts to the host */
-	intel_uncore_write(uncore, GUC_BCS_RCS_IER, 0);
-	intel_uncore_write(uncore, GUC_VCS2_VCS1_IER, 0);
-	intel_uncore_write(uncore, GUC_WD_VECS_IER, 0);
-
-	rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
-	rps->pm_intrmsk_mbz &= ~ARAT_EXPIRED_INTRMSK;
+	GEM_BUG_ON(INTEL_GEN(gt->i915) < 11);
+
+	/* Handle ctx switch interrupts again */
+	intel_uncore_rmw(uncore, GEN11_RENDER_COPY_INTR_ENABLE, 0, dmask);
+	intel_uncore_rmw(uncore, GEN11_VCS_VECS_INTR_ENABLE, 0, dmask);
 }
 
 static void guc_set_default_submission(struct intel_engine_cs *engine)
@@ -1102,11 +599,10 @@ static void guc_set_default_submission(struct intel_engine_cs *engine)
 	engine->park = engine->unpark = NULL;
 
 	engine->reset.prepare = guc_reset_prepare;
-	engine->reset.reset = guc_reset;
+	engine->reset.rewind = guc_reset_rewind;
+	engine->reset.cancel = guc_reset_cancel;
 	engine->reset.finish = guc_reset_finish;
 
-	engine->cancel_requests = guc_cancel_requests;
-
 	engine->flags &= ~I915_ENGINE_SUPPORTS_STATS;
 	engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
 
@@ -1119,16 +615,11 @@ static void guc_set_default_submission(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->irq_enable || engine->irq_disable);
 }
 
-int intel_guc_submission_enable(struct intel_guc *guc)
+void intel_guc_submission_enable(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	int err;
-
-	err = i915_inject_probe_error(gt->i915, -ENXIO);
-	if (err)
-		return err;
 
 	/*
 	 * We're using GuC work items for submitting work through GuC. Since
@@ -1143,11 +634,8 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 		     sizeof(struct guc_wq_item) *
 		     I915_NUM_ENGINES > GUC_WQ_SIZE);
 
-	GEM_BUG_ON(!guc->execbuf_client);
-
-	err = guc_clients_enable(guc);
-	if (err)
-		return err;
+	guc_proc_desc_init(guc);
+	guc_stage_desc_init(guc);
 
 	/* Take over from manual control of ELSP (execlists) */
 	guc_interrupts_capture(gt);
@@ -1156,8 +644,6 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 		engine->set_default_submission = guc_set_default_submission;
 		engine->set_default_submission(engine);
 	}
-
-	return 0;
 }
 
 void intel_guc_submission_disable(struct intel_guc *guc)
@@ -1166,8 +652,12 @@ void intel_guc_submission_disable(struct intel_guc *guc)
 
 	GEM_BUG_ON(gt->awake); /* GT should be parked first */
 
+	/* Note: By the time we're here, GuC may have already been reset */
+
 	guc_interrupts_release(gt);
-	guc_clients_disable(guc);
+
+	guc_stage_desc_fini(guc);
+	guc_proc_desc_fini(guc);
 }
 
 static bool __guc_submission_support(struct intel_guc *guc)
@@ -1186,6 +676,7 @@ void intel_guc_submission_init_early(struct intel_guc *guc)
 	guc->submission_supported = __guc_submission_support(guc);
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftest_guc.c"
-#endif
+bool intel_engine_in_guc_submission_mode(const struct intel_engine_cs *engine)
+{
+	return engine->set_default_submission == guc_set_default_submission;
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
index 54d716828352..e402a2932592 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
@@ -6,62 +6,18 @@
 #ifndef _INTEL_GUC_SUBMISSION_H_
 #define _INTEL_GUC_SUBMISSION_H_
 
-#include <linux/spinlock.h>
+#include <linux/types.h>
 
-#include "gt/intel_engine_types.h"
-
-#include "i915_gem.h"
-#include "i915_selftest.h"
-
-struct drm_i915_private;
-
-/*
- * This structure primarily describes the GEM object shared with the GuC.
- * The specs sometimes refer to this object as a "GuC context", but we use
- * the term "client" to avoid confusion with hardware contexts. This
- * GEM object is held for the entire lifetime of our interaction with
- * the GuC, being allocated before the GuC is loaded with its firmware.
- * Because there's no way to update the address used by the GuC after
- * initialisation, the shared object must stay pinned into the GGTT as
- * long as the GuC is in use. We also keep the first page (only) mapped
- * into kernel address space, as it includes shared data that must be
- * updated on every request submission.
- *
- * The single GEM object described here is actually made up of several
- * separate areas, as far as the GuC is concerned. The first page (kept
- * kmap'd) includes the "process descriptor" which holds sequence data for
- * the doorbell, and one cacheline which actually *is* the doorbell; a
- * write to this will "ring the doorbell" (i.e. send an interrupt to the
- * GuC). The subsequent  pages of the client object constitute the work
- * queue (a circular array of work items), again described in the process
- * descriptor. Work queue pages are mapped momentarily as required.
- */
-struct intel_guc_client {
-	struct i915_vma *vma;
-	void *vaddr;
-	struct intel_guc *guc;
-
-	/* bitmap of (host) engine ids */
-	u32 priority;
-	u32 stage_id;
-	u32 proc_desc_offset;
-
-	u16 doorbell_id;
-	unsigned long doorbell_offset;
-
-	/* Protects GuC client's WQ access */
-	spinlock_t wq_lock;
-
-	/* For testing purposes, use nop WQ items instead of real ones */
-	I915_SELFTEST_DECLARE(bool use_nop_wqi);
-};
+struct intel_guc;
+struct intel_engine_cs;
 
 void intel_guc_submission_init_early(struct intel_guc *guc);
 int intel_guc_submission_init(struct intel_guc *guc);
-int intel_guc_submission_enable(struct intel_guc *guc);
+void intel_guc_submission_enable(struct intel_guc *guc);
 void intel_guc_submission_disable(struct intel_guc *guc);
 void intel_guc_submission_fini(struct intel_guc *guc);
 int intel_guc_preempt_work_create(struct intel_guc *guc);
 void intel_guc_preempt_work_destroy(struct intel_guc *guc);
+bool intel_engine_in_guc_submission_mode(const struct intel_engine_cs *engine);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
index d654340d4d03..eee193bf2cc4 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
@@ -39,5 +39,5 @@ void intel_huc_fw_init_early(struct intel_huc *huc)
 int intel_huc_fw_upload(struct intel_huc *huc)
 {
 	/* HW doesn't look at destination address for HuC, so set it to 0 */
-	return intel_uc_fw_upload(&huc->fw, huc_to_gt(huc), 0, HUC_UKERNEL);
+	return intel_uc_fw_upload(&huc->fw, 0, HUC_UKERNEL);
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 629b19377a29..64934a876a50 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -12,6 +12,9 @@
 
 #include "i915_drv.h"
 
+static const struct intel_uc_ops uc_ops_off;
+static const struct intel_uc_ops uc_ops_on;
+
 /* Reset GuC providing us with fresh state for both GuC and HuC.
  */
 static int __intel_uc_reset_hw(struct intel_uc *uc)
@@ -89,6 +92,11 @@ void intel_uc_init_early(struct intel_uc *uc)
 	intel_huc_init_early(&uc->huc);
 
 	__confirm_options(uc);
+
+	if (intel_uc_uses_guc(uc))
+		uc->ops = &uc_ops_on;
+	else
+		uc->ops = &uc_ops_off;
 }
 
 void intel_uc_driver_late_release(struct intel_uc *uc)
@@ -123,6 +131,11 @@ static void __uc_free_load_err_log(struct intel_uc *uc)
 		i915_gem_object_put(log);
 }
 
+static inline bool guc_communication_enabled(struct intel_guc *guc)
+{
+	return intel_guc_ct_enabled(&guc->ct);
+}
+
 /*
  * Events triggered while CT buffers are disabled are logged in the SCRATCH_15
  * register using the same bits used in the CT message payload. Since our
@@ -158,7 +171,7 @@ static void guc_handle_mmio_msg(struct intel_guc *guc)
 	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
 
 	/* we need communication to be enabled to reply to GuC */
-	GEM_BUG_ON(guc->handler == intel_guc_to_host_event_handler_nop);
+	GEM_BUG_ON(!guc_communication_enabled(guc));
 
 	if (!guc->mmio_msg)
 		return;
@@ -185,11 +198,6 @@ static void guc_disable_interrupts(struct intel_guc *guc)
 	guc->interrupts.disable(guc);
 }
 
-static inline bool guc_communication_enabled(struct intel_guc *guc)
-{
-	return guc->send != intel_guc_send_nop;
-}
-
 static int guc_enable_communication(struct intel_guc *guc)
 {
 	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
@@ -205,9 +213,6 @@ static int guc_enable_communication(struct intel_guc *guc)
 	if (ret)
 		return ret;
 
-	guc->send = intel_guc_send_ct;
-	guc->handler = intel_guc_to_host_event_handler_ct;
-
 	/* check for mmio messages received before/during the CT enable */
 	guc_get_mmio_msg(guc);
 	guc_handle_mmio_msg(guc);
@@ -216,7 +221,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 
 	/* check for CT messages received before we enabled interrupts */
 	spin_lock_irq(&i915->irq_lock);
-	intel_guc_to_host_event_handler_ct(guc);
+	intel_guc_ct_event_handler(&guc->ct);
 	spin_unlock_irq(&i915->irq_lock);
 
 	DRM_INFO("GuC communication enabled\n");
@@ -224,7 +229,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 	return 0;
 }
 
-static void __guc_stop_communication(struct intel_guc *guc)
+static void guc_disable_communication(struct intel_guc *guc)
 {
 	/*
 	 * Events generated during or after CT disable are logged by guc in
@@ -235,23 +240,6 @@ static void __guc_stop_communication(struct intel_guc *guc)
 
 	guc_disable_interrupts(guc);
 
-	guc->send = intel_guc_send_nop;
-	guc->handler = intel_guc_to_host_event_handler_nop;
-}
-
-static void guc_stop_communication(struct intel_guc *guc)
-{
-	intel_guc_ct_stop(&guc->ct);
-
-	__guc_stop_communication(guc);
-
-	DRM_INFO("GuC communication stopped\n");
-}
-
-static void guc_disable_communication(struct intel_guc *guc)
-{
-	__guc_stop_communication(guc);
-
 	intel_guc_ct_disable(&guc->ct);
 
 	/*
@@ -265,41 +253,33 @@ static void guc_disable_communication(struct intel_guc *guc)
 	DRM_INFO("GuC communication disabled\n");
 }
 
-void intel_uc_fetch_firmwares(struct intel_uc *uc)
+static void __uc_fetch_firmwares(struct intel_uc *uc)
 {
-	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
 	int err;
 
-	if (!intel_uc_uses_guc(uc))
-		return;
+	GEM_BUG_ON(!intel_uc_uses_guc(uc));
 
-	err = intel_uc_fw_fetch(&uc->guc.fw, i915);
+	err = intel_uc_fw_fetch(&uc->guc.fw);
 	if (err)
 		return;
 
 	if (intel_uc_uses_huc(uc))
-		intel_uc_fw_fetch(&uc->huc.fw, i915);
+		intel_uc_fw_fetch(&uc->huc.fw);
 }
 
-void intel_uc_cleanup_firmwares(struct intel_uc *uc)
+static void __uc_cleanup_firmwares(struct intel_uc *uc)
 {
-	if (!intel_uc_uses_guc(uc))
-		return;
-
-	if (intel_uc_uses_huc(uc))
-		intel_uc_fw_cleanup_fetch(&uc->huc.fw);
-
+	intel_uc_fw_cleanup_fetch(&uc->huc.fw);
 	intel_uc_fw_cleanup_fetch(&uc->guc.fw);
 }
 
-void intel_uc_init(struct intel_uc *uc)
+static void __uc_init(struct intel_uc *uc)
 {
 	struct intel_guc *guc = &uc->guc;
 	struct intel_huc *huc = &uc->huc;
 	int ret;
 
-	if (!intel_uc_uses_guc(uc))
-		return;
+	GEM_BUG_ON(!intel_uc_uses_guc(uc));
 
 	/* XXX: GuC submission is unavailable for now */
 	GEM_BUG_ON(intel_uc_supports_guc_submission(uc));
@@ -314,17 +294,10 @@ void intel_uc_init(struct intel_uc *uc)
 		intel_huc_init(huc);
 }
 
-void intel_uc_fini(struct intel_uc *uc)
+static void __uc_fini(struct intel_uc *uc)
 {
-	struct intel_guc *guc = &uc->guc;
-
-	if (!intel_uc_uses_guc(uc))
-		return;
-
-	if (intel_uc_uses_huc(uc))
-		intel_huc_fini(&uc->huc);
-
-	intel_guc_fini(guc);
+	intel_huc_fini(&uc->huc);
+	intel_guc_fini(&uc->guc);
 
 	__uc_free_load_err_log(uc);
 }
@@ -342,14 +315,6 @@ static int __uc_sanitize(struct intel_uc *uc)
 	return __intel_uc_reset_hw(uc);
 }
 
-void intel_uc_sanitize(struct intel_uc *uc)
-{
-	if (!intel_uc_supports_guc(uc))
-		return;
-
-	__uc_sanitize(uc);
-}
-
 /* Initialize and verify the uC regs related to uC positioning in WOPCM */
 static int uc_init_wopcm(struct intel_uc *uc)
 {
@@ -413,13 +378,8 @@ static bool uc_is_wopcm_locked(struct intel_uc *uc)
 	       (intel_uncore_read(uncore, DMA_GUC_WOPCM_OFFSET) & GUC_WOPCM_OFFSET_VALID);
 }
 
-int intel_uc_init_hw(struct intel_uc *uc)
+static int __uc_check_hw(struct intel_uc *uc)
 {
-	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
-	struct intel_guc *guc = &uc->guc;
-	struct intel_huc *huc = &uc->huc;
-	int ret, attempts;
-
 	if (!intel_uc_supports_guc(uc))
 		return 0;
 
@@ -428,11 +388,24 @@ int intel_uc_init_hw(struct intel_uc *uc)
 	 * before on this system after reboot, otherwise we risk GPU hangs.
 	 * To check if GuC was loaded before we look at WOPCM registers.
 	 */
-	if (!intel_uc_uses_guc(uc) && !uc_is_wopcm_locked(uc))
-		return 0;
+	if (uc_is_wopcm_locked(uc))
+		return -EIO;
+
+	return 0;
+}
+
+static int __uc_init_hw(struct intel_uc *uc)
+{
+	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
+	struct intel_guc *guc = &uc->guc;
+	struct intel_huc *huc = &uc->huc;
+	int ret, attempts;
+
+	GEM_BUG_ON(!intel_uc_supports_guc(uc));
+	GEM_BUG_ON(!intel_uc_uses_guc(uc));
 
 	if (!intel_uc_fw_is_available(&guc->fw)) {
-		ret = uc_is_wopcm_locked(uc) ||
+		ret = __uc_check_hw(uc) ||
 		      intel_uc_fw_is_overridden(&guc->fw) ||
 		      intel_uc_supports_guc_submission(uc) ?
 		      intel_uc_fw_status_to_error(guc->fw.status) : 0;
@@ -486,11 +459,8 @@ int intel_uc_init_hw(struct intel_uc *uc)
 	if (ret)
 		goto err_communication;
 
-	if (intel_uc_supports_guc_submission(uc)) {
-		ret = intel_guc_submission_enable(guc);
-		if (ret)
-			goto err_communication;
-	}
+	if (intel_uc_supports_guc_submission(uc))
+		intel_guc_submission_enable(guc);
 
 	dev_info(i915->drm.dev, "%s firmware %s version %u.%u %s:%s\n",
 		 intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc->fw.path,
@@ -531,7 +501,7 @@ err_out:
 	return -EIO;
 }
 
-void intel_uc_fini_hw(struct intel_uc *uc)
+static void __uc_fini_hw(struct intel_uc *uc)
 {
 	struct intel_guc *guc = &uc->guc;
 
@@ -560,7 +530,7 @@ void intel_uc_reset_prepare(struct intel_uc *uc)
 	if (!intel_guc_is_running(guc))
 		return;
 
-	guc_stop_communication(guc);
+	guc_disable_communication(guc);
 	__uc_sanitize(uc);
 }
 
@@ -631,3 +601,20 @@ int intel_uc_runtime_resume(struct intel_uc *uc)
 	 */
 	return __uc_resume(uc, true);
 }
+
+static const struct intel_uc_ops uc_ops_off = {
+	.init_hw = __uc_check_hw,
+};
+
+static const struct intel_uc_ops uc_ops_on = {
+	.sanitize = __uc_sanitize,
+
+	.init_fw = __uc_fetch_firmwares,
+	.fini_fw = __uc_cleanup_firmwares,
+
+	.init = __uc_init,
+	.fini = __uc_fini,
+
+	.init_hw = __uc_init_hw,
+	.fini_hw = __uc_fini_hw,
+};
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h
index 527995c21196..49c913524686 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h
@@ -10,7 +10,20 @@
 #include "intel_huc.h"
 #include "i915_params.h"
 
+struct intel_uc;
+
+struct intel_uc_ops {
+	int (*sanitize)(struct intel_uc *uc);
+	void (*init_fw)(struct intel_uc *uc);
+	void (*fini_fw)(struct intel_uc *uc);
+	void (*init)(struct intel_uc *uc);
+	void (*fini)(struct intel_uc *uc);
+	int (*init_hw)(struct intel_uc *uc);
+	void (*fini_hw)(struct intel_uc *uc);
+};
+
 struct intel_uc {
+	struct intel_uc_ops const *ops;
 	struct intel_guc guc;
 	struct intel_huc huc;
 
@@ -21,13 +34,6 @@ struct intel_uc {
 void intel_uc_init_early(struct intel_uc *uc);
 void intel_uc_driver_late_release(struct intel_uc *uc);
 void intel_uc_init_mmio(struct intel_uc *uc);
-void intel_uc_fetch_firmwares(struct intel_uc *uc);
-void intel_uc_cleanup_firmwares(struct intel_uc *uc);
-void intel_uc_sanitize(struct intel_uc *uc);
-void intel_uc_init(struct intel_uc *uc);
-int intel_uc_init_hw(struct intel_uc *uc);
-void intel_uc_fini_hw(struct intel_uc *uc);
-void intel_uc_fini(struct intel_uc *uc);
 void intel_uc_reset_prepare(struct intel_uc *uc);
 void intel_uc_suspend(struct intel_uc *uc);
 void intel_uc_runtime_suspend(struct intel_uc *uc);
@@ -64,4 +70,20 @@ static inline bool intel_uc_uses_huc(struct intel_uc *uc)
 	return intel_huc_is_enabled(&uc->huc);
 }
 
+#define intel_uc_ops_function(_NAME, _OPS, _TYPE, _RET) \
+static inline _TYPE intel_uc_##_NAME(struct intel_uc *uc) \
+{ \
+	if (uc->ops->_OPS) \
+		return uc->ops->_OPS(uc); \
+	return _RET; \
+}
+intel_uc_ops_function(sanitize, sanitize, int, 0);
+intel_uc_ops_function(fetch_firmwares, init_fw, void, );
+intel_uc_ops_function(cleanup_firmwares, fini_fw, void, );
+intel_uc_ops_function(init, init, void, );
+intel_uc_ops_function(fini, fini, void, );
+intel_uc_ops_function(init_hw, init_hw, int, 0);
+intel_uc_ops_function(fini_hw, fini_hw, void, );
+#undef intel_uc_ops_function
+
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 66a30ab7044a..8ee0a0c7f447 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -11,7 +11,6 @@
 #include "intel_uc_fw_abi.h"
 #include "i915_drv.h"
 
-#ifdef CONFIG_DRM_I915_DEBUG_GUC
 static inline struct intel_gt *__uc_fw_to_gt(struct intel_uc_fw *uc_fw)
 {
 	GEM_BUG_ON(uc_fw->status == INTEL_UC_FIRMWARE_UNINITIALIZED);
@@ -22,6 +21,7 @@ static inline struct intel_gt *__uc_fw_to_gt(struct intel_uc_fw *uc_fw)
 	return container_of(uc_fw, struct intel_gt, uc.huc.fw);
 }
 
+#ifdef CONFIG_DRM_I915_DEBUG_GUC
 void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 			       enum intel_uc_fw_status status)
 {
@@ -219,10 +219,9 @@ void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw,
 				  INTEL_UC_FIRMWARE_NOT_SUPPORTED);
 }
 
-static void __force_fw_fetch_failures(struct intel_uc_fw *uc_fw,
-				      struct drm_i915_private *i915,
-				      int e)
+static void __force_fw_fetch_failures(struct intel_uc_fw *uc_fw, int e)
 {
+	struct drm_i915_private *i915 = __uc_fw_to_gt(uc_fw)->i915;
 	bool user = e == -EINVAL;
 
 	if (i915_inject_probe_error(i915, e)) {
@@ -260,14 +259,14 @@ static void __force_fw_fetch_failures(struct intel_uc_fw *uc_fw,
 /**
  * intel_uc_fw_fetch - fetch uC firmware
  * @uc_fw: uC firmware
- * @i915: device private
  *
  * Fetch uC firmware into GEM obj.
  *
  * Return: 0 on success, a negative errno code on failure.
  */
-int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw, struct drm_i915_private *i915)
+int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 {
+	struct drm_i915_private *i915 = __uc_fw_to_gt(uc_fw)->i915;
 	struct device *dev = i915->drm.dev;
 	struct drm_i915_gem_object *obj;
 	const struct firmware *fw = NULL;
@@ -282,8 +281,8 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw, struct drm_i915_private *i915)
 	if (err)
 		return err;
 
-	__force_fw_fetch_failures(uc_fw, i915, -EINVAL);
-	__force_fw_fetch_failures(uc_fw, i915, -ESTALE);
+	__force_fw_fetch_failures(uc_fw, -EINVAL);
+	__force_fw_fetch_failures(uc_fw, -ESTALE);
 
 	err = request_firmware(&fw, uc_fw->path, dev);
 	if (err)
@@ -390,8 +389,9 @@ fail:
 	return err;
 }
 
-static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw, struct i915_ggtt *ggtt)
+static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw)
 {
+	struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt;
 	struct drm_mm_node *node = &ggtt->uc_fw;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(node));
@@ -401,13 +401,12 @@ static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw, struct i915_ggtt *ggtt)
 	return lower_32_bits(node->start);
 }
 
-static void intel_uc_fw_ggtt_bind(struct intel_uc_fw *uc_fw,
-				  struct intel_gt *gt)
+static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw)
 {
 	struct drm_i915_gem_object *obj = uc_fw->obj;
-	struct i915_ggtt *ggtt = gt->ggtt;
+	struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt;
 	struct i915_vma dummy = {
-		.node.start = uc_fw_ggtt_offset(uc_fw, ggtt),
+		.node.start = uc_fw_ggtt_offset(uc_fw),
 		.node.size = obj->base.size,
 		.pages = obj->mm.pages,
 		.vm = &ggtt->vm,
@@ -422,19 +421,18 @@ static void intel_uc_fw_ggtt_bind(struct intel_uc_fw *uc_fw,
 	ggtt->vm.insert_entries(&ggtt->vm, &dummy, I915_CACHE_NONE, 0);
 }
 
-static void intel_uc_fw_ggtt_unbind(struct intel_uc_fw *uc_fw,
-				    struct intel_gt *gt)
+static void uc_fw_unbind_ggtt(struct intel_uc_fw *uc_fw)
 {
 	struct drm_i915_gem_object *obj = uc_fw->obj;
-	struct i915_ggtt *ggtt = gt->ggtt;
-	u64 start = uc_fw_ggtt_offset(uc_fw, ggtt);
+	struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt;
+	u64 start = uc_fw_ggtt_offset(uc_fw);
 
 	ggtt->vm.clear_range(&ggtt->vm, start, obj->base.size);
 }
 
-static int uc_fw_xfer(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
-		      u32 wopcm_offset, u32 dma_flags)
+static int uc_fw_xfer(struct intel_uc_fw *uc_fw, u32 dst_offset, u32 dma_flags)
 {
+	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
 	struct intel_uncore *uncore = gt->uncore;
 	u64 offset;
 	int ret;
@@ -446,13 +444,13 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	/* Set the source address for the uCode */
-	offset = uc_fw_ggtt_offset(uc_fw, gt->ggtt);
+	offset = uc_fw_ggtt_offset(uc_fw);
 	GEM_BUG_ON(upper_32_bits(offset) & 0xFFFF0000);
 	intel_uncore_write_fw(uncore, DMA_ADDR_0_LOW, lower_32_bits(offset));
 	intel_uncore_write_fw(uncore, DMA_ADDR_0_HIGH, upper_32_bits(offset));
 
 	/* Set the DMA destination */
-	intel_uncore_write_fw(uncore, DMA_ADDR_1_LOW, wopcm_offset);
+	intel_uncore_write_fw(uncore, DMA_ADDR_1_LOW, dst_offset);
 	intel_uncore_write_fw(uncore, DMA_ADDR_1_HIGH, DMA_ADDRESS_SPACE_WOPCM);
 
 	/*
@@ -484,17 +482,16 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 /**
  * intel_uc_fw_upload - load uC firmware using custom loader
  * @uc_fw: uC firmware
- * @gt: the intel_gt structure
- * @wopcm_offset: destination offset in wopcm
+ * @dst_offset: destination offset
  * @dma_flags: flags for flags for dma ctrl
  *
  * Loads uC firmware and updates internal flags.
  *
  * Return: 0 on success, non-zero on failure.
  */
-int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
-		       u32 wopcm_offset, u32 dma_flags)
+int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, u32 dst_offset, u32 dma_flags)
 {
+	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
 	int err;
 
 	/* make sure the status was cleared the last time we reset the uc */
@@ -508,9 +505,9 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 		return -ENOEXEC;
 
 	/* Call custom loader */
-	intel_uc_fw_ggtt_bind(uc_fw, gt);
-	err = uc_fw_xfer(uc_fw, gt, wopcm_offset, dma_flags);
-	intel_uc_fw_ggtt_unbind(uc_fw, gt);
+	uc_fw_bind_ggtt(uc_fw);
+	err = uc_fw_xfer(uc_fw, dst_offset, dma_flags);
+	uc_fw_unbind_ggtt(uc_fw);
 	if (err)
 		goto fail;
 
@@ -547,10 +544,7 @@ int intel_uc_fw_init(struct intel_uc_fw *uc_fw)
 
 void intel_uc_fw_fini(struct intel_uc_fw *uc_fw)
 {
-	if (!intel_uc_fw_is_available(uc_fw))
-		return;
-
-	i915_gem_object_unpin_pages(uc_fw->obj);
+	intel_uc_fw_cleanup_fetch(uc_fw);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
index 7a0a5989afc9..1f30543d0d2d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
@@ -229,10 +229,9 @@ static inline u32 intel_uc_fw_get_upload_size(struct intel_uc_fw *uc_fw)
 void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw,
 			    enum intel_uc_fw_type type, bool supported,
 			    enum intel_platform platform, u8 rev);
-int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw, struct drm_i915_private *i915);
+int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw);
 void intel_uc_fw_cleanup_fetch(struct intel_uc_fw *uc_fw);
-int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
-		       u32 wopcm_offset, u32 dma_flags);
+int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, u32 offset, u32 dma_flags);
 int intel_uc_fw_init(struct intel_uc_fw *uc_fw);
 void intel_uc_fw_fini(struct intel_uc_fw *uc_fw);
 size_t intel_uc_fw_copy_rsa(struct intel_uc_fw *uc_fw, void *dst, u32 max_len);
diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
deleted file mode 100644
index d8a80388bd31..000000000000
--- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
+++ /dev/null
@@ -1,299 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2017 Intel Corporation
- */
-
-#include "i915_selftest.h"
-#include "gem/i915_gem_pm.h"
-
-/* max doorbell number + negative test for each client type */
-#define ATTEMPTS (GUC_NUM_DOORBELLS + GUC_CLIENT_PRIORITY_NUM)
-
-static struct intel_guc_client *clients[ATTEMPTS];
-
-static bool available_dbs(struct intel_guc *guc, u32 priority)
-{
-	unsigned long offset;
-	unsigned long end;
-	u16 id;
-
-	/* first half is used for normal priority, second half for high */
-	offset = 0;
-	end = GUC_NUM_DOORBELLS / 2;
-	if (priority <= GUC_CLIENT_PRIORITY_HIGH) {
-		offset = end;
-		end += offset;
-	}
-
-	id = find_next_zero_bit(guc->doorbell_bitmap, end, offset);
-	if (id < end)
-		return true;
-
-	return false;
-}
-
-static int check_all_doorbells(struct intel_guc *guc)
-{
-	u16 db_id;
-
-	pr_info_once("Max number of doorbells: %d", GUC_NUM_DOORBELLS);
-	for (db_id = 0; db_id < GUC_NUM_DOORBELLS; ++db_id) {
-		if (!doorbell_ok(guc, db_id)) {
-			pr_err("doorbell %d, not ok\n", db_id);
-			return -EIO;
-		}
-	}
-
-	return 0;
-}
-
-static int ring_doorbell_nop(struct intel_guc_client *client)
-{
-	struct guc_process_desc *desc = __get_process_desc(client);
-	int err;
-
-	client->use_nop_wqi = true;
-
-	spin_lock_irq(&client->wq_lock);
-
-	guc_wq_item_append(client, 0, 0, 0, 0);
-	guc_ring_doorbell(client);
-
-	spin_unlock_irq(&client->wq_lock);
-
-	client->use_nop_wqi = false;
-
-	/* if there are no issues GuC will update the WQ head and keep the
-	 * WQ in active status
-	 */
-	err = wait_for(READ_ONCE(desc->head) == READ_ONCE(desc->tail), 10);
-	if (err) {
-		pr_err("doorbell %u ring failed!\n", client->doorbell_id);
-		return -EIO;
-	}
-
-	if (desc->wq_status != WQ_STATUS_ACTIVE) {
-		pr_err("doorbell %u ring put WQ in bad state (%u)!\n",
-		       client->doorbell_id, desc->wq_status);
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/*
- * Basic client sanity check, handy to validate create_clients.
- */
-static int validate_client(struct intel_guc_client *client, int client_priority)
-{
-	if (client->priority != client_priority ||
-	    client->doorbell_id == GUC_DOORBELL_INVALID)
-		return -EINVAL;
-	else
-		return 0;
-}
-
-static bool client_doorbell_in_sync(struct intel_guc_client *client)
-{
-	return !client || doorbell_ok(client->guc, client->doorbell_id);
-}
-
-/*
- * Check that we're able to synchronize guc_clients with their doorbells
- *
- * We're creating clients and reserving doorbells once, at module load. During
- * module lifetime, GuC, doorbell HW, and i915 state may go out of sync due to
- * GuC being reset. In other words - GuC clients are still around, but the
- * status of their doorbells may be incorrect. This is the reason behind
- * validating that the doorbells status expected by the driver matches what the
- * GuC/HW have.
- */
-static int igt_guc_clients(void *arg)
-{
-	struct intel_gt *gt = arg;
-	struct intel_guc *guc = &gt->uc.guc;
-	intel_wakeref_t wakeref;
-	int err = 0;
-
-	GEM_BUG_ON(!HAS_GT_UC(gt->i915));
-	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
-
-	err = check_all_doorbells(guc);
-	if (err)
-		goto unlock;
-
-	/*
-	 * Get rid of clients created during driver load because the test will
-	 * recreate them.
-	 */
-	guc_clients_disable(guc);
-	guc_clients_destroy(guc);
-	if (guc->execbuf_client) {
-		pr_err("guc_clients_destroy lied!\n");
-		err = -EINVAL;
-		goto unlock;
-	}
-
-	err = guc_clients_create(guc);
-	if (err) {
-		pr_err("Failed to create clients\n");
-		goto unlock;
-	}
-	GEM_BUG_ON(!guc->execbuf_client);
-
-	err = validate_client(guc->execbuf_client,
-			      GUC_CLIENT_PRIORITY_KMD_NORMAL);
-	if (err) {
-		pr_err("execbug client validation failed\n");
-		goto out;
-	}
-
-	/* the client should now have reserved a doorbell */
-	if (!has_doorbell(guc->execbuf_client)) {
-		pr_err("guc_clients_create didn't reserve doorbells\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	/* Now enable the clients */
-	guc_clients_enable(guc);
-
-	/* each client should now have received a doorbell */
-	if (!client_doorbell_in_sync(guc->execbuf_client)) {
-		pr_err("failed to initialize the doorbells\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	/*
-	 * Basic test - an attempt to reallocate a valid doorbell to the
-	 * client it is currently assigned should not cause a failure.
-	 */
-	err = create_doorbell(guc->execbuf_client);
-
-out:
-	/*
-	 * Leave clean state for other test, plus the driver always destroy the
-	 * clients during unload.
-	 */
-	guc_clients_disable(guc);
-	guc_clients_destroy(guc);
-	guc_clients_create(guc);
-	guc_clients_enable(guc);
-unlock:
-	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
-	return err;
-}
-
-/*
- * Create as many clients as number of doorbells. Note that there's already
- * client(s)/doorbell(s) created during driver load, but this test creates
- * its own and do not interact with the existing ones.
- */
-static int igt_guc_doorbells(void *arg)
-{
-	struct intel_gt *gt = arg;
-	struct intel_guc *guc = &gt->uc.guc;
-	intel_wakeref_t wakeref;
-	int i, err = 0;
-	u16 db_id;
-
-	GEM_BUG_ON(!HAS_GT_UC(gt->i915));
-	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
-
-	err = check_all_doorbells(guc);
-	if (err)
-		goto unlock;
-
-	for (i = 0; i < ATTEMPTS; i++) {
-		clients[i] = guc_client_alloc(guc, i % GUC_CLIENT_PRIORITY_NUM);
-
-		if (!clients[i]) {
-			pr_err("[%d] No guc client\n", i);
-			err = -EINVAL;
-			goto out;
-		}
-
-		if (IS_ERR(clients[i])) {
-			if (PTR_ERR(clients[i]) != -ENOSPC) {
-				pr_err("[%d] unexpected error\n", i);
-				err = PTR_ERR(clients[i]);
-				goto out;
-			}
-
-			if (available_dbs(guc, i % GUC_CLIENT_PRIORITY_NUM)) {
-				pr_err("[%d] non-db related alloc fail\n", i);
-				err = -EINVAL;
-				goto out;
-			}
-
-			/* expected, ran out of dbs for this client type */
-			continue;
-		}
-
-		/*
-		 * The check below is only valid because we keep a doorbell
-		 * assigned during the whole life of the client.
-		 */
-		if (clients[i]->stage_id >= GUC_NUM_DOORBELLS) {
-			pr_err("[%d] more clients than doorbells (%d >= %d)\n",
-			       i, clients[i]->stage_id, GUC_NUM_DOORBELLS);
-			err = -EINVAL;
-			goto out;
-		}
-
-		err = validate_client(clients[i], i % GUC_CLIENT_PRIORITY_NUM);
-		if (err) {
-			pr_err("[%d] client_alloc sanity check failed!\n", i);
-			err = -EINVAL;
-			goto out;
-		}
-
-		db_id = clients[i]->doorbell_id;
-
-		err = __guc_client_enable(clients[i]);
-		if (err) {
-			pr_err("[%d] Failed to create a doorbell\n", i);
-			goto out;
-		}
-
-		/* doorbell id shouldn't change, we are holding the mutex */
-		if (db_id != clients[i]->doorbell_id) {
-			pr_err("[%d] doorbell id changed (%d != %d)\n",
-			       i, db_id, clients[i]->doorbell_id);
-			err = -EINVAL;
-			goto out;
-		}
-
-		err = check_all_doorbells(guc);
-		if (err)
-			goto out;
-
-		err = ring_doorbell_nop(clients[i]);
-		if (err)
-			goto out;
-	}
-
-out:
-	for (i = 0; i < ATTEMPTS; i++)
-		if (!IS_ERR_OR_NULL(clients[i])) {
-			__guc_client_disable(clients[i]);
-			guc_client_free(clients[i]);
-		}
-unlock:
-	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
-	return err;
-}
-
-int intel_guc_live_selftest(struct drm_i915_private *i915)
-{
-	static const struct i915_subtest tests[] = {
-		SUBTEST(igt_guc_clients),
-		SUBTEST(igt_guc_doorbells),
-	};
-
-	if (!USES_GUC_SUBMISSION(i915))
-		return 0;
-
-	return intel_gt_live_subtests(tests, &i915->gt);
-}
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.h b/drivers/gpu/drm/i915/gvt/cmd_parser.h
index 286703643002..ab25d151932a 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.h
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.h
@@ -38,6 +38,10 @@
 
 #define GVT_CMD_HASH_BITS 7
 
+struct intel_gvt;
+struct intel_shadow_wa_ctx;
+struct intel_vgpu_workload;
+
 void intel_gvt_clean_cmd_parser(struct intel_gvt *gvt);
 
 int intel_gvt_init_cmd_parser(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/display.h b/drivers/gpu/drm/i915/gvt/display.h
index a87f33e6a23c..b59b34046e1e 100644
--- a/drivers/gpu/drm/i915/gvt/display.h
+++ b/drivers/gpu/drm/i915/gvt/display.h
@@ -35,6 +35,11 @@
 #ifndef _GVT_DISPLAY_H_
 #define _GVT_DISPLAY_H_
 
+#include <linux/types.h>
+
+struct intel_gvt;
+struct intel_vgpu;
+
 #define SBI_REG_MAX	20
 #define DPCD_SIZE	0x700
 
diff --git a/drivers/gpu/drm/i915/gvt/edid.h b/drivers/gpu/drm/i915/gvt/edid.h
index f6dfc8b795ec..dfe0cbc6aad8 100644
--- a/drivers/gpu/drm/i915/gvt/edid.h
+++ b/drivers/gpu/drm/i915/gvt/edid.h
@@ -35,6 +35,10 @@
 #ifndef _GVT_EDID_H_
 #define _GVT_EDID_H_
 
+#include <linux/types.h>
+
+struct intel_vgpu;
+
 #define EDID_SIZE		128
 #define EDID_ADDR		0x50 /* Linux hvm EDID addr */
 
diff --git a/drivers/gpu/drm/i915/gvt/execlist.h b/drivers/gpu/drm/i915/gvt/execlist.h
index 5ccc2c695848..5c0c1fd30c83 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.h
+++ b/drivers/gpu/drm/i915/gvt/execlist.h
@@ -35,6 +35,8 @@
 #ifndef _GVT_EXECLIST_H_
 #define _GVT_EXECLIST_H_
 
+#include <linux/types.h>
+
 struct execlist_ctx_descriptor_format {
 	union {
 		u32 ldw;
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.h b/drivers/gpu/drm/i915/gvt/fb_decoder.h
index 60c155085029..67b6ede9e707 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.h
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.h
@@ -36,6 +36,8 @@
 #ifndef _GVT_FB_DECODER_H_
 #define _GVT_FB_DECODER_H_
 
+#include <linux/types.h>
+
 #define _PLANE_CTL_FORMAT_SHIFT		24
 #define _PLANE_CTL_TILED_SHIFT		10
 #define _PIPE_V_SRCSZ_SHIFT		0
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 4b04af569c05..34cb404ba4b7 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1282,7 +1282,7 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
-	};
+	}
 
 	/* direct shadow */
 	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, page_size,
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 1043e6d564df..6d28d72e6c7e 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2691,7 +2691,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	return 0;
 }
 
-static int init_broadwell_mmio_info(struct intel_gvt *gvt)
+static int init_bdw_mmio_info(struct intel_gvt *gvt)
 {
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
 	int ret;
@@ -3380,20 +3380,20 @@ int intel_gvt_setup_mmio_info(struct intel_gvt *gvt)
 		goto err;
 
 	if (IS_BROADWELL(dev_priv)) {
-		ret = init_broadwell_mmio_info(gvt);
+		ret = init_bdw_mmio_info(gvt);
 		if (ret)
 			goto err;
 	} else if (IS_SKYLAKE(dev_priv)
 		|| IS_KABYLAKE(dev_priv)
 		|| IS_COFFEELAKE(dev_priv)) {
-		ret = init_broadwell_mmio_info(gvt);
+		ret = init_bdw_mmio_info(gvt);
 		if (ret)
 			goto err;
 		ret = init_skl_mmio_info(gvt);
 		if (ret)
 			goto err;
 	} else if (IS_BROXTON(dev_priv)) {
-		ret = init_broadwell_mmio_info(gvt);
+		ret = init_bdw_mmio_info(gvt);
 		if (ret)
 			goto err;
 		ret = init_skl_mmio_info(gvt);
diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h
index b19a3b1ea4c1..b17c4a1599cd 100644
--- a/drivers/gpu/drm/i915/gvt/hypercall.h
+++ b/drivers/gpu/drm/i915/gvt/hypercall.h
@@ -33,6 +33,10 @@
 #ifndef _GVT_HYPERCALL_H_
 #define _GVT_HYPERCALL_H_
 
+#include <linux/types.h>
+
+struct device;
+
 enum hypervisor_type {
 	INTEL_GVT_HYPERVISOR_XEN = 0,
 	INTEL_GVT_HYPERVISOR_KVM,
diff --git a/drivers/gpu/drm/i915/gvt/interrupt.h b/drivers/gpu/drm/i915/gvt/interrupt.h
index 5313fb1b33e1..fcd663811d37 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.h
+++ b/drivers/gpu/drm/i915/gvt/interrupt.h
@@ -32,6 +32,8 @@
 #ifndef _GVT_INTERRUPT_H_
 #define _GVT_INTERRUPT_H_
 
+#include <linux/types.h>
+
 enum intel_gvt_event_type {
 	RCS_MI_USER_INTERRUPT = 0,
 	RCS_DEBUG,
@@ -135,6 +137,7 @@ enum intel_gvt_event_type {
 
 struct intel_gvt_irq;
 struct intel_gvt;
+struct intel_vgpu;
 
 typedef void (*gvt_event_virt_handler_t)(struct intel_gvt_irq *irq,
 	enum intel_gvt_event_type event, struct intel_vgpu *vgpu);
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 5874f1cb4306..2e68f4b02c94 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -36,6 +36,8 @@
 #ifndef _GVT_MMIO_H_
 #define _GVT_MMIO_H_
 
+#include <linux/types.h>
+
 struct intel_gvt;
 struct intel_vgpu;
 
diff --git a/drivers/gpu/drm/i915/gvt/page_track.h b/drivers/gpu/drm/i915/gvt/page_track.h
index fa607a71c3c0..f6eb7135583c 100644
--- a/drivers/gpu/drm/i915/gvt/page_track.h
+++ b/drivers/gpu/drm/i915/gvt/page_track.h
@@ -25,6 +25,9 @@
 #ifndef _GVT_PAGE_TRACK_H_
 #define _GVT_PAGE_TRACK_H_
 
+#include <linux/types.h>
+
+struct intel_vgpu;
 struct intel_vgpu_page_track;
 
 typedef int (*gvt_page_track_handler_t)(
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.h b/drivers/gpu/drm/i915/gvt/sched_policy.h
index 7b59e3e88b8b..3dacdad5f529 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.h
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.h
@@ -34,6 +34,9 @@
 #ifndef __GVT_SCHED_POLICY__
 #define __GVT_SCHED_POLICY__
 
+struct intel_gvt;
+struct intel_vgpu;
+
 struct intel_gvt_sched_policy_ops {
 	int (*init)(struct intel_gvt *gvt);
 	void (*clean)(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 5b2a7d072ec9..685d1e04a5ff 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -35,12 +35,12 @@
 
 #include <linux/kthread.h>
 
-#include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_context.h"
 #include "gt/intel_ring.h"
 
 #include "i915_drv.h"
+#include "i915_gem_gtt.h"
 #include "gvt.h"
 
 #define RING_CTX_OFF(x) \
@@ -59,7 +59,7 @@ static void set_context_pdp_root_pointer(
 static void update_shadow_pdps(struct intel_vgpu_workload *workload)
 {
 	struct drm_i915_gem_object *ctx_obj =
-		workload->req->hw_context->state->obj;
+		workload->req->context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 
@@ -130,7 +130,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	struct intel_gvt *gvt = vgpu->gvt;
 	int ring_id = workload->ring_id;
 	struct drm_i915_gem_object *ctx_obj =
-		workload->req->hw_context->state->obj;
+		workload->req->context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *dst;
@@ -205,9 +205,9 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	return 0;
 }
 
-static inline bool is_gvt_request(struct i915_request *req)
+static inline bool is_gvt_request(struct i915_request *rq)
 {
-	return i915_gem_context_force_single_submission(req->gem_context);
+	return intel_context_force_single_submission(rq->context);
 }
 
 static void save_ring_hw_state(struct intel_vgpu *vgpu, int ring_id)
@@ -307,7 +307,7 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	u32 *cs;
 	int err;
 
-	if (IS_GEN(req->i915, 9) && is_inhibit_context(req->hw_context))
+	if (IS_GEN(req->i915, 9) && is_inhibit_context(req->context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/*
@@ -363,11 +363,10 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 }
 
 static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
-					  struct i915_gem_context *ctx)
+					  struct intel_context *ce)
 {
 	struct intel_vgpu_mm *mm = workload->shadow_mm;
-	struct i915_ppgtt *ppgtt =
-		i915_vm_to_ppgtt(i915_gem_context_get_vm_rcu(ctx));
+	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ce->vm);
 	int i = 0;
 
 	if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
@@ -380,8 +379,6 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 			px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
 		}
 	}
-
-	i915_vm_put(&ppgtt->vm);
 }
 
 static int
@@ -529,7 +526,7 @@ static void update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 		container_of(wa_ctx, struct intel_vgpu_workload, wa_ctx);
 	struct i915_request *rq = workload->req;
 	struct execlist_ring_context *shadow_ring_context =
-		(struct execlist_ring_context *)rq->hw_context->lrc_reg_state;
+		(struct execlist_ring_context *)rq->context->lrc_reg_state;
 
 	shadow_ring_context->bb_per_ctx_ptr.val =
 		(shadow_ring_context->bb_per_ctx_ptr.val &
@@ -628,7 +625,7 @@ static int prepare_workload(struct intel_vgpu_workload *workload)
 
 	update_shadow_pdps(workload);
 
-	set_context_ppgtt_from_shadow(workload, s->shadow[ring]->gem_context);
+	set_context_ppgtt_from_shadow(workload, s->shadow[ring]);
 
 	ret = intel_vgpu_sync_oos_pages(workload->vgpu);
 	if (ret) {
@@ -787,7 +784,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 	struct i915_request *rq = workload->req;
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
-	struct drm_i915_gem_object *ctx_obj = rq->hw_context->state->obj;
+	struct drm_i915_gem_object *ctx_obj = rq->context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *src;
@@ -1223,18 +1220,14 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	struct drm_i915_private *i915 = vgpu->gvt->dev_priv;
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	struct i915_ppgtt *ppgtt;
 	enum intel_engine_id i;
 	int ret;
 
-	ctx = i915_gem_context_create_kernel(i915, I915_PRIORITY_MAX);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
+	ppgtt = i915_ppgtt_create(&i915->gt);
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
 
-	i915_gem_context_set_force_single_submission(ctx);
-
-	ppgtt = i915_vm_to_ppgtt(i915_gem_context_get_vm_rcu(ctx));
 	i915_context_ppgtt_root_save(s, ppgtt);
 
 	for_each_engine(engine, i915, i) {
@@ -1243,12 +1236,16 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 		INIT_LIST_HEAD(&s->workload_q_head[i]);
 		s->shadow[i] = ERR_PTR(-EINVAL);
 
-		ce = intel_context_create(ctx, engine);
+		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			ret = PTR_ERR(ce);
 			goto out_shadow_ctx;
 		}
 
+		i915_vm_put(ce->vm);
+		ce->vm = i915_vm_get(&ppgtt->vm);
+		intel_context_set_single_submission(ce);
+
 		if (!USES_GUC_SUBMISSION(i915)) { /* Max ring buffer size */
 			const unsigned int ring_size = 512 * SZ_4K;
 
@@ -1281,7 +1278,6 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	bitmap_zero(s->tlb_handle_pending, I915_NUM_ENGINES);
 
 	i915_vm_put(&ppgtt->vm);
-	i915_gem_context_put(ctx);
 	return 0;
 
 out_shadow_ctx:
@@ -1294,7 +1290,6 @@ out_shadow_ctx:
 		intel_context_put(s->shadow[i]);
 	}
 	i915_vm_put(&ppgtt->vm);
-	i915_gem_context_put(ctx);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index a19e7d89bc8a..f3da5c06f331 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -6,6 +6,7 @@
 
 #include <linux/debugobjects.h>
 
+#include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_ring.h"
 
@@ -91,10 +92,9 @@ static void debug_active_init(struct i915_active *ref)
 
 static void debug_active_activate(struct i915_active *ref)
 {
-	spin_lock_irq(&ref->tree_lock);
+	lockdep_assert_held(&ref->tree_lock);
 	if (!atomic_read(&ref->count)) /* before the first inc */
 		debug_object_activate(ref, &active_debug_desc);
-	spin_unlock_irq(&ref->tree_lock);
 }
 
 static void debug_active_deactivate(struct i915_active *ref)
@@ -186,18 +186,33 @@ active_retire(struct i915_active *ref)
 	__active_retire(ref);
 }
 
+static inline struct dma_fence **
+__active_fence_slot(struct i915_active_fence *active)
+{
+	return (struct dma_fence ** __force)&active->fence;
+}
+
+static inline bool
+active_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	struct i915_active_fence *active =
+		container_of(cb, typeof(*active), cb);
+
+	return cmpxchg(__active_fence_slot(active), fence, NULL) == fence;
+}
+
 static void
 node_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	i915_active_fence_cb(fence, cb);
-	active_retire(container_of(cb, struct active_node, base.cb)->ref);
+	if (active_fence_cb(fence, cb))
+		active_retire(container_of(cb, struct active_node, base.cb)->ref);
 }
 
 static void
 excl_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	i915_active_fence_cb(fence, cb);
-	active_retire(container_of(cb, struct i915_active, excl.cb));
+	if (active_fence_cb(fence, cb))
+		active_retire(container_of(cb, struct i915_active, excl.cb));
 }
 
 static struct i915_active_fence *
@@ -244,7 +259,7 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 	}
 
 	node = prealloc;
-	__i915_active_fence_init(&node->base, &tl->mutex, NULL, node_retire);
+	__i915_active_fence_init(&node->base, NULL, node_retire);
 	node->ref = ref;
 	node->timeline = idx;
 
@@ -262,7 +277,8 @@ out:
 void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
-			struct lock_class_key *key)
+			struct lock_class_key *mkey,
+			struct lock_class_key *wkey)
 {
 	unsigned long bits;
 
@@ -280,9 +296,12 @@ void __i915_active_init(struct i915_active *ref,
 
 	init_llist_head(&ref->preallocated_barriers);
 	atomic_set(&ref->count, 0);
-	__mutex_init(&ref->mutex, "i915_active", key);
-	__i915_active_fence_init(&ref->excl, &ref->mutex, NULL, excl_retire);
+	__mutex_init(&ref->mutex, "i915_active", mkey);
+	__i915_active_fence_init(&ref->excl, NULL, excl_retire);
 	INIT_WORK(&ref->work, active_work);
+#if IS_ENABLED(CONFIG_LOCKDEP)
+	lockdep_init_map(&ref->work.lockdep_map, "i915_active.work", wkey, 0);
+#endif
 }
 
 static bool ____active_del_barrier(struct i915_active *ref,
@@ -376,15 +395,8 @@ void i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f)
 	/* We expect the caller to manage the exclusive timeline ordering */
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
-	/*
-	 * As we don't know which mutex the caller is using, we told a small
-	 * lie to the debug code that it is using the i915_active.mutex;
-	 * and now we must stick to that lie.
-	 */
-	mutex_acquire(&ref->mutex.dep_map, 0, 0, _THIS_IP_);
 	if (!__i915_active_fence_set(&ref->excl, f))
 		atomic_inc(&ref->count);
-	mutex_release(&ref->mutex.dep_map, _THIS_IP_);
 }
 
 bool i915_active_acquire_if_busy(struct i915_active *ref)
@@ -407,8 +419,10 @@ int i915_active_acquire(struct i915_active *ref)
 	if (!atomic_read(&ref->count) && ref->active)
 		err = ref->active(ref);
 	if (!err) {
+		spin_lock_irq(&ref->tree_lock); /* vs __active_retire() */
 		debug_active_activate(ref);
 		atomic_inc(&ref->count);
+		spin_unlock_irq(&ref->tree_lock);
 	}
 
 	mutex_unlock(&ref->mutex);
@@ -461,6 +475,7 @@ int i915_active_wait(struct i915_active *ref)
 	if (wait_var_event_interruptible(ref, i915_active_is_idle(ref)))
 		return -EINTR;
 
+	flush_work(&ref->work);
 	return 0;
 }
 
@@ -590,12 +605,15 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 					    struct intel_engine_cs *engine)
 {
 	intel_engine_mask_t tmp, mask = engine->mask;
+	struct llist_node *pos = NULL, *next;
 	struct intel_gt *gt = engine->gt;
-	struct llist_node *pos, *next;
 	int err;
 
 	GEM_BUG_ON(i915_active_is_idle(ref));
-	GEM_BUG_ON(!llist_empty(&ref->preallocated_barriers));
+
+	/* Wait until the previous preallocation is completed */
+	while (!llist_empty(&ref->preallocated_barriers))
+		cond_resched();
 
 	/*
 	 * Preallocate a node for each physical engine supporting the target
@@ -615,10 +633,6 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 				goto unwind;
 			}
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-			node->base.lock =
-				&engine->kernel_context->timeline->mutex;
-#endif
 			RCU_INIT_POINTER(node->base.fence, NULL);
 			node->base.cb.func = node_retire;
 			node->timeline = idx;
@@ -639,18 +653,27 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 			node->base.cb.node.prev = (void *)engine;
 			atomic_inc(&ref->count);
 		}
+		GEM_BUG_ON(rcu_access_pointer(node->base.fence) != ERR_PTR(-EAGAIN));
 
 		GEM_BUG_ON(barrier_to_engine(node) != engine);
-		llist_add(barrier_to_ll(node), &ref->preallocated_barriers);
+		next = barrier_to_ll(node);
+		next->next = pos;
+		if (!pos)
+			pos = next;
 		intel_engine_pm_get(engine);
 	}
 
+	GEM_BUG_ON(!llist_empty(&ref->preallocated_barriers));
+	llist_add_batch(next, pos, &ref->preallocated_barriers);
+
 	return 0;
 
 unwind:
-	llist_for_each_safe(pos, next, take_preallocated_barriers(ref)) {
+	while (pos) {
 		struct active_node *node = barrier_from_ll(pos);
 
+		pos = pos->next;
+
 		atomic_dec(&ref->count);
 		intel_engine_pm_put(barrier_to_engine(node));
 
@@ -702,12 +725,18 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 	}
 }
 
+static struct dma_fence **ll_to_fence_slot(struct llist_node *node)
+{
+	return __active_fence_slot(&barrier_from_ll(node)->base);
+}
+
 void i915_request_add_active_barriers(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
 	struct llist_node *node, *next;
 	unsigned long flags;
 
+	GEM_BUG_ON(!intel_context_is_barrier(rq->context));
 	GEM_BUG_ON(intel_engine_is_virtual(engine));
 	GEM_BUG_ON(i915_request_timeline(rq) != engine->kernel_context->timeline);
 
@@ -721,19 +750,13 @@ void i915_request_add_active_barriers(struct i915_request *rq)
 	 */
 	spin_lock_irqsave(&rq->lock, flags);
 	llist_for_each_safe(node, next, node) {
-		RCU_INIT_POINTER(barrier_from_ll(node)->base.fence, &rq->fence);
-		smp_wmb(); /* serialise with reuse_idle_barrier */
+		/* serialise with reuse_idle_barrier */
+		smp_store_mb(*ll_to_fence_slot(node), &rq->fence);
 		list_add_tail((struct list_head *)node, &rq->fence.cb_list);
 	}
 	spin_unlock_irqrestore(&rq->lock, flags);
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-#define active_is_held(active) lockdep_is_held((active)->lock)
-#else
-#define active_is_held(active) true
-#endif
-
 /*
  * __i915_active_fence_set: Update the last active fence along its timeline
  * @active: the active tracker
@@ -744,7 +767,7 @@ void i915_request_add_active_barriers(struct i915_request *rq)
  * fence onto this one. Returns the previous fence (if not already completed),
  * which the caller must ensure is executed before the new fence. To ensure
  * that the order of fences within the timeline of the i915_active_fence is
- * maintained, it must be locked by the caller.
+ * understood, it should be locked by the caller.
  */
 struct dma_fence *
 __i915_active_fence_set(struct i915_active_fence *active,
@@ -753,34 +776,41 @@ __i915_active_fence_set(struct i915_active_fence *active,
 	struct dma_fence *prev;
 	unsigned long flags;
 
-	/* NB: must be serialised by an outer timeline mutex (active->lock) */
-	spin_lock_irqsave(fence->lock, flags);
+	if (fence == rcu_access_pointer(active->fence))
+		return fence;
+
 	GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags));
 
-	prev = rcu_dereference_protected(active->fence, active_is_held(active));
+	/*
+	 * Consider that we have two threads arriving (A and B), with
+	 * C already resident as the active->fence.
+	 *
+	 * A does the xchg first, and so it sees C or NULL depending
+	 * on the timing of the interrupt handler. If it is NULL, the
+	 * previous fence must have been signaled and we know that
+	 * we are first on the timeline. If it is still present,
+	 * we acquire the lock on that fence and serialise with the interrupt
+	 * handler, in the process removing it from any future interrupt
+	 * callback. A will then wait on C before executing (if present).
+	 *
+	 * As B is second, it sees A as the previous fence and so waits for
+	 * it to complete its transition and takes over the occupancy for
+	 * itself -- remembering that it needs to wait on A before executing.
+	 *
+	 * Note the strong ordering of the timeline also provides consistent
+	 * nesting rules for the fence->lock; the inner lock is always the
+	 * older lock.
+	 */
+	spin_lock_irqsave(fence->lock, flags);
+	prev = xchg(__active_fence_slot(active), fence);
 	if (prev) {
 		GEM_BUG_ON(prev == fence);
 		spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING);
 		__list_del_entry(&active->cb.node);
 		spin_unlock(prev->lock); /* serialise with prev->cb_list */
-
-		/*
-		 * active->fence is reset by the callback from inside
-		 * interrupt context. We need to serialise our list
-		 * manipulation with the fence->lock to prevent the prev
-		 * being lost inside an interrupt (it can't be replaced as
-		 * no other caller is allowed to enter __i915_active_fence_set
-		 * as we hold the timeline lock). After serialising with
-		 * the callback, we need to double check which ran first,
-		 * our list_del() [decoupling prev from the callback] or
-		 * the callback...
-		 */
-		prev = rcu_access_pointer(active->fence);
 	}
-
-	rcu_assign_pointer(active->fence, fence);
+	GEM_BUG_ON(rcu_access_pointer(active->fence) != fence);
 	list_add_tail(&active->cb.node, &fence->cb_list);
-
 	spin_unlock_irqrestore(fence->lock, flags);
 
 	return prev;
@@ -792,10 +822,6 @@ int i915_active_fence_set(struct i915_active_fence *active,
 	struct dma_fence *fence;
 	int err = 0;
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-	lockdep_assert_held(active->lock);
-#endif
-
 	/* Must maintain timeline ordering wrt previous active requests */
 	rcu_read_lock();
 	fence = __i915_active_fence_set(active, &rq->fence);
@@ -812,7 +838,7 @@ int i915_active_fence_set(struct i915_active_fence *active,
 
 void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	i915_active_fence_cb(fence, cb);
+	active_fence_cb(fence, cb);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index 44859356ce97..b571f675c795 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -61,19 +61,15 @@ void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb);
  */
 static inline void
 __i915_active_fence_init(struct i915_active_fence *active,
-			 struct mutex *lock,
 			 void *fence,
 			 dma_fence_func_t fn)
 {
 	RCU_INIT_POINTER(active->fence, fence);
 	active->cb.func = fn ?: i915_active_noop;
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-	active->lock = lock;
-#endif
 }
 
-#define INIT_ACTIVE_FENCE(A, LOCK) \
-	__i915_active_fence_init((A), (LOCK), NULL, NULL)
+#define INIT_ACTIVE_FENCE(A) \
+	__i915_active_fence_init((A), NULL, NULL)
 
 struct dma_fence *
 __i915_active_fence_set(struct i915_active_fence *active,
@@ -127,15 +123,6 @@ i915_active_fence_isset(const struct i915_active_fence *active)
 	return rcu_access_pointer(active->fence);
 }
 
-static inline void
-i915_active_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
-{
-	struct i915_active_fence *active =
-		container_of(cb, typeof(*active), cb);
-
-	RCU_INIT_POINTER(active->fence, NULL);
-}
-
 /*
  * GPU activity tracking
  *
@@ -165,11 +152,15 @@ i915_active_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
-			struct lock_class_key *key);
+			struct lock_class_key *mkey,
+			struct lock_class_key *wkey);
+
+/* Specialise each class of i915_active to avoid impossible lockdep cycles. */
 #define i915_active_init(ref, active, retire) do {		\
-	static struct lock_class_key __key;				\
+	static struct lock_class_key __mkey;				\
+	static struct lock_class_key __wkey;				\
 									\
-	__i915_active_init(ref, active, retire, &__key);		\
+	__i915_active_init(ref, active, retire, &__mkey, &__wkey);	\
 } while (0)
 
 int i915_active_ref(struct i915_active *ref,
@@ -215,5 +206,6 @@ void i915_active_acquire_barrier(struct i915_active *ref);
 void i915_request_add_active_barriers(struct i915_request *rq);
 
 void i915_active_print(struct i915_active *ref, struct drm_printer *m);
+void i915_active_unlock_wait(struct i915_active *ref);
 
 #endif /* _I915_ACTIVE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index 96aed0ee700a..6360c3e4b765 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -20,21 +20,6 @@
 struct i915_active_fence {
 	struct dma_fence __rcu *fence;
 	struct dma_fence_cb cb;
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-	/*
-	 * Incorporeal!
-	 *
-	 * Updates to the i915_active_request must be serialised under a lock
-	 * to ensure that the timeline is ordered. Normally, this is the
-	 * timeline->mutex, but another mutex may be used so long as it is
-	 * done so consistently.
-	 *
-	 * For lockdep tracking of the above, we store the lock we intend
-	 * to always use for updates of this i915_active_request during
-	 * construction and assert that is held on every update.
-	 */
-	struct mutex *lock;
-#endif
 };
 
 struct active_node;
diff --git a/drivers/gpu/drm/i915/i915_buddy.c b/drivers/gpu/drm/i915/i915_buddy.c
index e9d4200ce3bc..66883af64ca1 100644
--- a/drivers/gpu/drm/i915/i915_buddy.c
+++ b/drivers/gpu/drm/i915/i915_buddy.c
@@ -262,8 +262,10 @@ void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects)
 {
 	struct i915_buddy_block *block, *on;
 
-	list_for_each_entry_safe(block, on, objects, link)
+	list_for_each_entry_safe(block, on, objects, link) {
 		i915_buddy_free(mm, block);
+		cond_resched();
+	}
 	INIT_LIST_HEAD(objects);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index f24096e27bef..a0e437aa65b7 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -235,7 +235,7 @@ static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = {
 	/*
 	 * MI_BATCH_BUFFER_START requires some special handling. It's not
 	 * really a 'skip' action but it doesn't seem like it's worth adding
-	 * a new action. See i915_parse_cmds().
+	 * a new action. See intel_engine_cmd_parser().
 	 */
 	CMD(  MI_BATCH_BUFFER_START,            SMI,   !F,  0xFF,   S  ),
 };
@@ -731,7 +731,7 @@ static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
 			return 0xFF;
 	}
 
-	DRM_DEBUG_DRIVER("CMD: Abnormal rcs cmd length! 0x%08X\n", cmd_header);
+	DRM_DEBUG("CMD: Abnormal rcs cmd length! 0x%08X\n", cmd_header);
 	return 0;
 }
 
@@ -754,7 +754,7 @@ static u32 gen7_bsd_get_cmd_length_mask(u32 cmd_header)
 			return 0xFF;
 	}
 
-	DRM_DEBUG_DRIVER("CMD: Abnormal bsd cmd length! 0x%08X\n", cmd_header);
+	DRM_DEBUG("CMD: Abnormal bsd cmd length! 0x%08X\n", cmd_header);
 	return 0;
 }
 
@@ -767,7 +767,7 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
 	else if (client == INSTR_BC_CLIENT)
 		return 0xFF;
 
-	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	DRM_DEBUG("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
 	return 0;
 }
 
@@ -778,7 +778,7 @@ static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
 	if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
 		return 0xFF;
 
-	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	DRM_DEBUG("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
 	return 0;
 }
 
@@ -1127,79 +1127,71 @@ find_reg(const struct intel_engine_cs *engine, u32 addr)
 /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */
 static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		       struct drm_i915_gem_object *src_obj,
-		       u32 batch_start_offset,
-		       u32 batch_len,
-		       bool *needs_clflush_after)
+		       u32 offset, u32 length)
 {
-	unsigned int src_needs_clflush;
-	unsigned int dst_needs_clflush;
+	bool needs_clflush;
 	void *dst, *src;
 	int ret;
 
-	ret = i915_gem_object_prepare_write(dst_obj, &dst_needs_clflush);
-	if (ret)
-		return ERR_PTR(ret);
-
 	dst = i915_gem_object_pin_map(dst_obj, I915_MAP_FORCE_WB);
-	i915_gem_object_finish_access(dst_obj);
 	if (IS_ERR(dst))
 		return dst;
 
-	ret = i915_gem_object_prepare_read(src_obj, &src_needs_clflush);
+	ret = i915_gem_object_pin_pages(src_obj);
 	if (ret) {
 		i915_gem_object_unpin_map(dst_obj);
 		return ERR_PTR(ret);
 	}
 
+	needs_clflush =
+		!(src_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
+
 	src = ERR_PTR(-ENODEV);
-	if (src_needs_clflush &&
-	    i915_can_memcpy_from_wc(NULL, batch_start_offset, 0)) {
+	if (needs_clflush && i915_has_memcpy_from_wc()) {
 		src = i915_gem_object_pin_map(src_obj, I915_MAP_WC);
 		if (!IS_ERR(src)) {
-			i915_memcpy_from_wc(dst,
-					    src + batch_start_offset,
-					    ALIGN(batch_len, 16));
+			i915_unaligned_memcpy_from_wc(dst,
+						      src + offset,
+						      length);
 			i915_gem_object_unpin_map(src_obj);
 		}
 	}
 	if (IS_ERR(src)) {
 		void *ptr;
-		int offset, n;
+		int x, n;
 
-		offset = offset_in_page(batch_start_offset);
-
-		/* We can avoid clflushing partial cachelines before the write
+		/*
+		 * We can avoid clflushing partial cachelines before the write
 		 * if we only every write full cache-lines. Since we know that
 		 * both the source and destination are in multiples of
 		 * PAGE_SIZE, we can simply round up to the next cacheline.
 		 * We don't care about copying too much here as we only
 		 * validate up to the end of the batch.
 		 */
-		if (dst_needs_clflush & CLFLUSH_BEFORE)
-			batch_len = roundup(batch_len,
-					    boot_cpu_data.x86_clflush_size);
+		if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
+			length = round_up(length,
+					  boot_cpu_data.x86_clflush_size);
 
 		ptr = dst;
-		for (n = batch_start_offset >> PAGE_SHIFT; batch_len; n++) {
-			int len = min_t(int, batch_len, PAGE_SIZE - offset);
+		x = offset_in_page(offset);
+		for (n = offset >> PAGE_SHIFT; length; n++) {
+			int len = min_t(int, length, PAGE_SIZE - x);
 
 			src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
-			if (src_needs_clflush)
-				drm_clflush_virt_range(src + offset, len);
-			memcpy(ptr, src + offset, len);
+			if (needs_clflush)
+				drm_clflush_virt_range(src + x, len);
+			memcpy(ptr, src + x, len);
 			kunmap_atomic(src);
 
 			ptr += len;
-			batch_len -= len;
-			offset = 0;
+			length -= len;
+			x = 0;
 		}
 	}
 
-	i915_gem_object_finish_access(src_obj);
+	i915_gem_object_unpin_pages(src_obj);
 
 	/* dst_obj is returned with vmap pinned */
-	*needs_clflush_after = dst_needs_clflush & CLFLUSH_AFTER;
-
 	return dst;
 }
 
@@ -1211,7 +1203,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 		return true;
 
 	if (desc->flags & CMD_DESC_REJECT) {
-		DRM_DEBUG_DRIVER("CMD: Rejected command: 0x%08X\n", *cmd);
+		DRM_DEBUG("CMD: Rejected command: 0x%08X\n", *cmd);
 		return false;
 	}
 
@@ -1231,8 +1223,8 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 				find_reg(engine, reg_addr);
 
 			if (!reg) {
-				DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
-						 reg_addr, *cmd, engine->name);
+				DRM_DEBUG("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
+					  reg_addr, *cmd, engine->name);
 				return false;
 			}
 
@@ -1242,22 +1234,22 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 			 */
 			if (reg->mask) {
 				if (desc->cmd.value == MI_LOAD_REGISTER_MEM) {
-					DRM_DEBUG_DRIVER("CMD: Rejected LRM to masked register 0x%08X\n",
-							 reg_addr);
+					DRM_DEBUG("CMD: Rejected LRM to masked register 0x%08X\n",
+						  reg_addr);
 					return false;
 				}
 
 				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
-					DRM_DEBUG_DRIVER("CMD: Rejected LRR to masked register 0x%08X\n",
-							 reg_addr);
+					DRM_DEBUG("CMD: Rejected LRR to masked register 0x%08X\n",
+						  reg_addr);
 					return false;
 				}
 
 				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) &&
 				    (offset + 2 > length ||
 				     (cmd[offset + 1] & reg->mask) != reg->value)) {
-					DRM_DEBUG_DRIVER("CMD: Rejected LRI to masked register 0x%08X\n",
-							 reg_addr);
+					DRM_DEBUG("CMD: Rejected LRI to masked register 0x%08X\n",
+						  reg_addr);
 					return false;
 				}
 			}
@@ -1284,8 +1276,8 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 			}
 
 			if (desc->bits[i].offset >= length) {
-				DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n",
-						 *cmd, engine->name);
+				DRM_DEBUG("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n",
+					  *cmd, engine->name);
 				return false;
 			}
 
@@ -1293,11 +1285,11 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 				desc->bits[i].mask;
 
 			if (dword != desc->bits[i].expected) {
-				DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (%s)\n",
-						 *cmd,
-						 desc->bits[i].mask,
-						 desc->bits[i].expected,
-						 dword, engine->name);
+				DRM_DEBUG("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (%s)\n",
+					  *cmd,
+					  desc->bits[i].mask,
+					  desc->bits[i].expected,
+					  dword, engine->name);
 				return false;
 			}
 		}
@@ -1306,17 +1298,17 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 	return true;
 }
 
-static int check_bbstart(const struct i915_gem_context *ctx,
-			 u32 *cmd, u32 offset, u32 length,
-			 u32 batch_len,
-			 u64 batch_start,
-			 u64 shadow_batch_start)
+static int check_bbstart(u32 *cmd, u32 offset, u32 length,
+			 u32 batch_length,
+			 u64 batch_addr,
+			 u64 shadow_addr,
+			 const unsigned long *jump_whitelist)
 {
 	u64 jump_offset, jump_target;
 	u32 target_cmd_offset, target_cmd_index;
 
 	/* For igt compatibility on older platforms */
-	if (CMDPARSER_USES_GGTT(ctx->i915)) {
+	if (!jump_whitelist) {
 		DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
 		return -EACCES;
 	}
@@ -1327,14 +1319,14 @@ static int check_bbstart(const struct i915_gem_context *ctx,
 		return -EINVAL;
 	}
 
-	jump_target = *(u64*)(cmd+1);
-	jump_offset = jump_target - batch_start;
+	jump_target = *(u64 *)(cmd + 1);
+	jump_offset = jump_target - batch_addr;
 
 	/*
 	 * Any underflow of jump_target is guaranteed to be outside the range
 	 * of a u32, so >= test catches both too large and too small
 	 */
-	if (jump_offset >= batch_len) {
+	if (jump_offset >= batch_length) {
 		DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n",
 			  jump_target);
 		return -EINVAL;
@@ -1342,20 +1334,20 @@ static int check_bbstart(const struct i915_gem_context *ctx,
 
 	/*
 	 * This cannot overflow a u32 because we already checked jump_offset
-	 * is within the BB, and the batch_len is a u32
+	 * is within the BB, and the batch_length is a u32
 	 */
 	target_cmd_offset = lower_32_bits(jump_offset);
 	target_cmd_index = target_cmd_offset / sizeof(u32);
 
-	*(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset;
+	*(u64 *)(cmd + 1) = shadow_addr + target_cmd_offset;
 
 	if (target_cmd_index == offset)
 		return 0;
 
-	if (ctx->jump_whitelist_cmds <= target_cmd_index) {
-		DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n");
-		return -EINVAL;
-	} else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) {
+	if (IS_ERR(jump_whitelist))
+		return PTR_ERR(jump_whitelist);
+
+	if (!test_bit(target_cmd_index, jump_whitelist)) {
 		DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
 			  jump_target);
 		return -EINVAL;
@@ -1364,54 +1356,40 @@ static int check_bbstart(const struct i915_gem_context *ctx,
 	return 0;
 }
 
-static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len)
+static unsigned long *alloc_whitelist(u32 batch_length)
 {
-	const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32));
-	const u32 exact_size = BITS_TO_LONGS(batch_cmds);
-	u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds));
-	unsigned long *next_whitelist;
+	unsigned long *jmp;
 
-	if (CMDPARSER_USES_GGTT(ctx->i915))
-		return;
-
-	if (batch_cmds <= ctx->jump_whitelist_cmds) {
-		bitmap_zero(ctx->jump_whitelist, batch_cmds);
-		return;
-	}
-
-again:
-	next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL);
-	if (next_whitelist) {
-		kfree(ctx->jump_whitelist);
-		ctx->jump_whitelist = next_whitelist;
-		ctx->jump_whitelist_cmds =
-			next_size * BITS_PER_BYTE * sizeof(long);
-		return;
-	}
-
-	if (next_size > exact_size) {
-		next_size = exact_size;
-		goto again;
-	}
+	/*
+	 * We expect batch_length to be less than 256KiB for known users,
+	 * i.e. we need at most an 8KiB bitmap allocation which should be
+	 * reasonably cheap due to kmalloc caches.
+	 */
 
-	DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n");
-	bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds);
+	/* Prefer to report transient allocation failure rather than hit oom */
+	jmp = bitmap_zalloc(DIV_ROUND_UP(batch_length, sizeof(u32)),
+			    GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+	if (!jmp)
+		return ERR_PTR(-ENOMEM);
 
-	return;
+	return jmp;
 }
 
 #define LENGTH_BIAS 2
 
+static bool shadow_needs_clflush(struct drm_i915_gem_object *obj)
+{
+	return !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE);
+}
+
 /**
- * i915_parse_cmds() - parse a submitted batch buffer for privilege violations
- * @ctx: the context in which the batch is to execute
+ * intel_engine_cmd_parser() - parse a batch buffer for privilege violations
  * @engine: the engine on which the batch is to execute
- * @batch_obj: the batch buffer in question
- * @batch_start: Canonical base address of batch
- * @batch_start_offset: byte offset in the batch at which execution starts
- * @batch_len: length of the commands in batch_obj
- * @shadow_batch_obj: copy of the batch buffer in question
- * @shadow_batch_start: Canonical base address of shadow_batch_obj
+ * @batch: the batch buffer in question
+ * @batch_offset: byte offset in the batch at which execution starts
+ * @batch_length: length of the commands in batch_obj
+ * @shadow: validated copy of the batch buffer in question
+ * @trampoline: whether to emit a conditional trampoline at the end of the batch
  *
  * Parses the specified batch buffer looking for privilege violations as
  * described in the overview.
@@ -1419,38 +1397,46 @@ again:
  * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
  * if the batch appears legal but should use hardware parsing
  */
-
-int intel_engine_cmd_parser(struct i915_gem_context *ctx,
-			    struct intel_engine_cs *engine,
-			    struct drm_i915_gem_object *batch_obj,
-			    u64 batch_start,
-			    u32 batch_start_offset,
-			    u32 batch_len,
-			    struct drm_i915_gem_object *shadow_batch_obj,
-			    u64 shadow_batch_start)
+int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+			    struct i915_vma *batch,
+			    u32 batch_offset,
+			    u32 batch_length,
+			    struct i915_vma *shadow,
+			    bool trampoline)
 {
 	u32 *cmd, *batch_end, offset = 0;
 	struct drm_i915_cmd_descriptor default_desc = noop_desc;
 	const struct drm_i915_cmd_descriptor *desc = &default_desc;
-	bool needs_clflush_after = false;
+	unsigned long *jump_whitelist;
+	u64 batch_addr, shadow_addr;
 	int ret = 0;
 
-	cmd = copy_batch(shadow_batch_obj, batch_obj,
-			 batch_start_offset, batch_len,
-			 &needs_clflush_after);
+	GEM_BUG_ON(!IS_ALIGNED(batch_offset, sizeof(*cmd)));
+	GEM_BUG_ON(!IS_ALIGNED(batch_length, sizeof(*cmd)));
+	GEM_BUG_ON(range_overflows_t(u64, batch_offset, batch_length,
+				     batch->size));
+	GEM_BUG_ON(!batch_length);
+
+	cmd = copy_batch(shadow->obj, batch->obj, batch_offset, batch_length);
 	if (IS_ERR(cmd)) {
-		DRM_DEBUG_DRIVER("CMD: Failed to copy batch\n");
+		DRM_DEBUG("CMD: Failed to copy batch\n");
 		return PTR_ERR(cmd);
 	}
 
-	init_whitelist(ctx, batch_len);
+	jump_whitelist = NULL;
+	if (!trampoline)
+		/* Defer failure until attempted use */
+		jump_whitelist = alloc_whitelist(batch_length);
+
+	shadow_addr = gen8_canonical_addr(shadow->node.start);
+	batch_addr = gen8_canonical_addr(batch->node.start + batch_offset);
 
 	/*
 	 * We use the batch length as size because the shadow object is as
 	 * large or larger and copy_batch() will write MI_NOPs to the extra
 	 * space. Parsing should be faster in some cases this way.
 	 */
-	batch_end = cmd + (batch_len / sizeof(*batch_end));
+	batch_end = cmd + batch_length / sizeof(*batch_end);
 	do {
 		u32 length;
 
@@ -1459,61 +1445,99 @@ int intel_engine_cmd_parser(struct i915_gem_context *ctx,
 
 		desc = find_cmd(engine, *cmd, desc, &default_desc);
 		if (!desc) {
-			DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
-					 *cmd);
+			DRM_DEBUG("CMD: Unrecognized command: 0x%08X\n", *cmd);
 			ret = -EINVAL;
-			goto err;
+			break;
 		}
 
 		if (desc->flags & CMD_DESC_FIXED)
 			length = desc->length.fixed;
 		else
-			length = ((*cmd & desc->length.mask) + LENGTH_BIAS);
+			length = (*cmd & desc->length.mask) + LENGTH_BIAS;
 
 		if ((batch_end - cmd) < length) {
-			DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
-					 *cmd,
-					 length,
-					 batch_end - cmd);
+			DRM_DEBUG("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
+				  *cmd,
+				  length,
+				  batch_end - cmd);
 			ret = -EINVAL;
-			goto err;
+			break;
 		}
 
 		if (!check_cmd(engine, desc, cmd, length)) {
 			ret = -EACCES;
-			goto err;
+			break;
 		}
 
 		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
-			ret = check_bbstart(ctx, cmd, offset, length,
-					    batch_len, batch_start,
-					    shadow_batch_start);
-
-			if (ret)
-				goto err;
+			ret = check_bbstart(cmd, offset, length, batch_length,
+					    batch_addr, shadow_addr,
+					    jump_whitelist);
 			break;
 		}
 
-		if (ctx->jump_whitelist_cmds > offset)
-			set_bit(offset, ctx->jump_whitelist);
+		if (!IS_ERR_OR_NULL(jump_whitelist))
+			__set_bit(offset, jump_whitelist);
 
 		cmd += length;
 		offset += length;
 		if  (cmd >= batch_end) {
-			DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
+			DRM_DEBUG("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
 			ret = -EINVAL;
-			goto err;
+			break;
 		}
 	} while (1);
 
-	if (needs_clflush_after) {
-		void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
+	if (trampoline) {
+		/*
+		 * With the trampoline, the shadow is executed twice.
+		 *
+		 *   1 - starting at offset 0, in privileged mode
+		 *   2 - starting at offset batch_len, as non-privileged
+		 *
+		 * Only if the batch is valid and safe to execute, do we
+		 * allow the first privileged execution to proceed. If not,
+		 * we terminate the first batch and use the second batchbuffer
+		 * entry to chain to the original unsafe non-privileged batch,
+		 * leaving it to the HW to validate.
+		 */
+		*batch_end = MI_BATCH_BUFFER_END;
+
+		if (ret) {
+			/* Batch unsafe to execute with privileges, cancel! */
+			cmd = page_mask_bits(shadow->obj->mm.mapping);
+			*cmd = MI_BATCH_BUFFER_END;
+
+			/* If batch is unsafe but valid, jump to the original */
+			if (ret == -EACCES) {
+				unsigned int flags;
+
+				flags = MI_BATCH_NON_SECURE_I965;
+				if (IS_HASWELL(engine->i915))
+					flags = MI_BATCH_NON_SECURE_HSW;
+
+				GEM_BUG_ON(!IS_GEN_RANGE(engine->i915, 6, 7));
+				__gen6_emit_bb_start(batch_end,
+						     batch_addr,
+						     flags);
+
+				ret = 0; /* allow execution */
+			}
+		}
+
+		if (shadow_needs_clflush(shadow->obj))
+			drm_clflush_virt_range(batch_end, 8);
+	}
+
+	if (shadow_needs_clflush(shadow->obj)) {
+		void *ptr = page_mask_bits(shadow->obj->mm.mapping);
 
 		drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
 	}
 
-err:
-	i915_gem_object_unpin_map(shadow_batch_obj);
+	if (!IS_ERR_OR_NULL(jump_whitelist))
+		kfree(jump_whitelist);
+	i915_gem_object_unpin_map(shadow->obj);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 8016484ebcd3..d5a9b8a964c2 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -61,24 +61,14 @@ static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node)
 
 static int i915_capabilities(struct seq_file *m, void *data)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	const struct intel_device_info *info = INTEL_INFO(dev_priv);
+	struct drm_i915_private *i915 = node_to_i915(m->private);
 	struct drm_printer p = drm_seq_file_printer(m);
-	const char *msg;
 
-	seq_printf(m, "gen: %d\n", INTEL_GEN(dev_priv));
-	seq_printf(m, "platform: %s\n", intel_platform_name(info->platform));
-	seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(dev_priv));
+	seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(i915));
 
-	msg = "n/a";
-#ifdef CONFIG_INTEL_IOMMU
-	msg = enableddisabled(intel_iommu_gfx_mapped);
-#endif
-	seq_printf(m, "iommu: %s\n", msg);
-
-	intel_device_info_dump_flags(info, &p);
-	intel_device_info_dump_runtime(RUNTIME_INFO(dev_priv), &p);
-	intel_driver_caps_print(&dev_priv->caps, &p);
+	intel_device_info_print_static(INTEL_INFO(i915), &p);
+	intel_device_info_print_runtime(RUNTIME_INFO(i915), &p);
+	intel_driver_caps_print(&i915->caps, &p);
 
 	kernel_param_lock(THIS_MODULE);
 	i915_params_dump(&i915_modparams, &p);
@@ -331,16 +321,15 @@ static void print_context_stats(struct seq_file *m,
 
 		for_each_gem_engine(ce,
 				    i915_gem_context_lock_engines(ctx), it) {
-			intel_context_lock_pinned(ce);
-			if (intel_context_is_pinned(ce)) {
+			if (intel_context_pin_if_active(ce)) {
 				rcu_read_lock();
 				if (ce->state)
 					per_file_stats(0,
 						       ce->state->obj, &kstats);
 				per_file_stats(0, ce->ring->vma->obj, &kstats);
 				rcu_read_unlock();
+				intel_context_unpin(ce);
 			}
-			intel_context_unlock_pinned(ce);
 		}
 		i915_gem_context_unlock_engines(ctx);
 
@@ -377,12 +366,16 @@ static void print_context_stats(struct seq_file *m,
 static int i915_gem_object_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
 
 	seq_printf(m, "%u shrinkable [%u free] objects, %llu bytes\n",
 		   i915->mm.shrink_count,
 		   atomic_read(&i915->mm.free_count),
 		   i915->mm.shrink_memory);
-
+	for_each_memory_region(mr, i915, id)
+		seq_printf(m, "%s: total:%pa, available:%pa bytes\n",
+			   mr->name, &mr->total, &mr->avail);
 	seq_putc(m, '\n');
 
 	print_context_stats(m, i915);
@@ -692,7 +685,7 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
 static ssize_t gpu_state_read(struct file *file, char __user *ubuf,
 			      size_t count, loff_t *pos)
 {
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 	ssize_t ret;
 	void *buf;
 
@@ -705,7 +698,7 @@ static ssize_t gpu_state_read(struct file *file, char __user *ubuf,
 	if (!buf)
 		return -ENOMEM;
 
-	ret = i915_gpu_state_copy_to_buffer(error, buf, *pos, count);
+	ret = i915_gpu_coredump_copy_to_buffer(error, buf, *pos, count);
 	if (ret <= 0)
 		goto out;
 
@@ -721,19 +714,19 @@ out:
 
 static int gpu_state_release(struct inode *inode, struct file *file)
 {
-	i915_gpu_state_put(file->private_data);
+	i915_gpu_coredump_put(file->private_data);
 	return 0;
 }
 
 static int i915_gpu_info_open(struct inode *inode, struct file *file)
 {
 	struct drm_i915_private *i915 = inode->i_private;
-	struct i915_gpu_state *gpu;
+	struct i915_gpu_coredump *gpu;
 	intel_wakeref_t wakeref;
 
 	gpu = NULL;
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		gpu = i915_capture_gpu_state(i915);
+		gpu = i915_gpu_coredump(i915);
 	if (IS_ERR(gpu))
 		return PTR_ERR(gpu);
 
@@ -755,7 +748,7 @@ i915_error_state_write(struct file *filp,
 		       size_t cnt,
 		       loff_t *ppos)
 {
-	struct i915_gpu_state *error = filp->private_data;
+	struct i915_gpu_coredump *error = filp->private_data;
 
 	if (!error)
 		return 0;
@@ -768,7 +761,7 @@ i915_error_state_write(struct file *filp,
 
 static int i915_error_state_open(struct inode *inode, struct file *file)
 {
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 
 	error = i915_first_error_state(inode->i_private);
 	if (IS_ERR(error))
@@ -891,7 +884,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
 		rpcurdown = I915_READ(GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
 		rpprevdown = I915_READ(GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
-		cagf = intel_gpu_freq(rps, intel_get_cagf(rps, rpstat));
+		cagf = intel_rps_read_actual_frequency(rps);
 
 		intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
 
@@ -1011,7 +1004,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 	return ret;
 }
 
-static int ironlake_drpc_info(struct seq_file *m)
+static int ilk_drpc_info(struct seq_file *m)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
 	struct intel_uncore *uncore = &i915->uncore;
@@ -1219,7 +1212,7 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 		else if (INTEL_GEN(dev_priv) >= 6)
 			err = gen6_drpc_info(m);
 		else
-			err = ironlake_drpc_info(m);
+			err = ilk_drpc_info(m);
 	}
 
 	return err;
@@ -1519,15 +1512,14 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 		for_each_gem_engine(ce,
 				    i915_gem_context_lock_engines(ctx), it) {
-			intel_context_lock_pinned(ce);
-			if (intel_context_is_pinned(ce)) {
+			if (intel_context_pin_if_active(ce)) {
 				seq_printf(m, "%s: ", ce->engine->name);
 				if (ce->state)
 					describe_obj(m, ce->state->obj);
 				describe_ctx_ring(m, ce->ring);
 				seq_putc(m, '\n');
+				intel_context_unpin(ce);
 			}
-			intel_context_unlock_pinned(ce);
 		}
 		i915_gem_context_unlock_engines(ctx);
 
@@ -1633,21 +1625,6 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_rps *rps = &dev_priv->gt.rps;
-	u32 act_freq = rps->cur_freq;
-	intel_wakeref_t wakeref;
-
-	with_intel_runtime_pm_if_in_use(&dev_priv->runtime_pm, wakeref) {
-		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-			vlv_punit_get(dev_priv);
-			act_freq = vlv_punit_read(dev_priv,
-						  PUNIT_REG_GPU_FREQ_STS);
-			vlv_punit_put(dev_priv);
-			act_freq = (act_freq >> 8) & 0xff;
-		} else {
-			act_freq = intel_get_cagf(rps,
-						  I915_READ(GEN6_RPSTAT1));
-		}
-	}
 
 	seq_printf(m, "RPS enabled? %d\n", rps->enabled);
 	seq_printf(m, "GPU busy? %s\n", yesno(dev_priv->gt.awake));
@@ -1656,7 +1633,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 	seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive));
 	seq_printf(m, "Frequency requested %d, actual %d\n",
 		   intel_gpu_freq(rps, rps->cur_freq),
-		   intel_gpu_freq(rps, act_freq));
+		   intel_rps_read_actual_frequency(rps));
 	seq_printf(m, "  min hard:%d, soft:%d; max soft:%d, hard:%d\n",
 		   intel_gpu_freq(rps, rps->min_freq),
 		   intel_gpu_freq(rps, rps->min_freq_softlimit),
@@ -1802,30 +1779,12 @@ static void i915_guc_log_info(struct seq_file *m,
 static int i915_guc_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	const struct intel_guc *guc = &dev_priv->gt.uc.guc;
-	struct intel_guc_client *client = guc->execbuf_client;
 
 	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
 	i915_guc_log_info(m, dev_priv);
 
-	if (!USES_GUC_SUBMISSION(dev_priv))
-		return 0;
-
-	GEM_BUG_ON(!guc->execbuf_client);
-
-	seq_printf(m, "\nDoorbell map:\n");
-	seq_printf(m, "\t%*pb\n", GUC_NUM_DOORBELLS, guc->doorbell_bitmap);
-	seq_printf(m, "Doorbell next cacheline: 0x%x\n", guc->db_cacheline);
-
-	seq_printf(m, "\nGuC execbuf client @ %p:\n", client);
-	seq_printf(m, "\tPriority %d, GuC stage index: %u, PD offset 0x%x\n",
-		   client->priority,
-		   client->stage_id,
-		   client->proc_desc_offset);
-	seq_printf(m, "\tDoorbell id %d, offset: 0x%lx\n",
-		   client->doorbell_id, client->doorbell_offset);
 	/* Add more as required ... */
 
 	return 0;
@@ -2020,7 +1979,7 @@ static int i915_psr_sink_status_show(struct seq_file *m, void *data)
 	struct drm_connector *connector = m->private;
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_dp *intel_dp =
-		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+		enc_to_intel_dp(intel_attached_encoder(to_intel_connector(connector)));
 	int ret;
 
 	if (!CAN_PSR(dev_priv)) {
@@ -2367,7 +2326,7 @@ out:
 }
 
 static void intel_seq_print_mode(struct seq_file *m, int tabs,
-				 struct drm_display_mode *mode)
+				 const struct drm_display_mode *mode)
 {
 	int i;
 
@@ -2378,59 +2337,35 @@ static void intel_seq_print_mode(struct seq_file *m, int tabs,
 }
 
 static void intel_encoder_info(struct seq_file *m,
-			       struct intel_crtc *intel_crtc,
-			       struct intel_encoder *intel_encoder)
+			       struct intel_crtc *crtc,
+			       struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct drm_crtc *crtc = &intel_crtc->base;
-	struct intel_connector *intel_connector;
-	struct drm_encoder *encoder;
-
-	encoder = &intel_encoder->base;
-	seq_printf(m, "\tencoder %d: type: %s, connectors:\n",
-		   encoder->base.id, encoder->name);
-	for_each_connector_on_encoder(dev, encoder, intel_connector) {
-		struct drm_connector *connector = &intel_connector->base;
-		seq_printf(m, "\t\tconnector %d: type: %s, status: %s",
-			   connector->base.id,
-			   connector->name,
-			   drm_get_connector_status_name(connector->status));
-		if (connector->status == connector_status_connected) {
-			struct drm_display_mode *mode = &crtc->mode;
-			seq_printf(m, ", mode:\n");
-			intel_seq_print_mode(m, 2, mode);
-		} else {
-			seq_putc(m, '\n');
-		}
-	}
-}
+	struct drm_connector_list_iter conn_iter;
+	struct drm_connector *connector;
 
-static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct drm_crtc *crtc = &intel_crtc->base;
-	struct intel_encoder *intel_encoder;
-	struct drm_plane_state *plane_state = crtc->primary->state;
-	struct drm_framebuffer *fb = plane_state->fb;
+	seq_printf(m, "\t[ENCODER:%d:%s]: connectors:\n",
+		   encoder->base.base.id, encoder->base.name);
 
-	if (fb)
-		seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n",
-			   fb->base.id, plane_state->src_x >> 16,
-			   plane_state->src_y >> 16, fb->width, fb->height);
-	else
-		seq_puts(m, "\tprimary plane disabled\n");
-	for_each_encoder_on_crtc(dev, crtc, intel_encoder)
-		intel_encoder_info(m, intel_crtc, intel_encoder);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
+		const struct drm_connector_state *conn_state =
+			connector->state;
+
+		if (conn_state->best_encoder != &encoder->base)
+			continue;
+
+		seq_printf(m, "\t\t[CONNECTOR:%d:%s]\n",
+			   connector->base.id, connector->name);
+	}
+	drm_connector_list_iter_end(&conn_iter);
 }
 
 static void intel_panel_info(struct seq_file *m, struct intel_panel *panel)
 {
-	struct drm_display_mode *mode = panel->fixed_mode;
+	const struct drm_display_mode *mode = panel->fixed_mode;
 
-	seq_printf(m, "\tfixed mode:\n");
-	intel_seq_print_mode(m, 2, mode);
+	seq_printf(m, "\tfixed mode: " DRM_MODE_FMT "\n", DRM_MODE_ARG(mode));
 }
 
 static void intel_hdcp_info(struct seq_file *m,
@@ -2456,7 +2391,7 @@ static void intel_dp_info(struct seq_file *m,
 			  struct intel_connector *intel_connector)
 {
 	struct intel_encoder *intel_encoder = intel_connector->encoder;
-	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(intel_encoder);
 
 	seq_printf(m, "\tDPCD rev: %x\n", intel_dp->dpcd[DP_DPCD_REV]);
 	seq_printf(m, "\taudio support: %s\n", yesno(intel_dp->has_audio));
@@ -2476,7 +2411,7 @@ static void intel_dp_mst_info(struct seq_file *m,
 {
 	struct intel_encoder *intel_encoder = intel_connector->encoder;
 	struct intel_dp_mst_encoder *intel_mst =
-		enc_to_mst(&intel_encoder->base);
+		enc_to_mst(intel_encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	bool has_audio = drm_dp_mst_port_has_audio(&intel_dp->mst_mgr,
@@ -2489,7 +2424,7 @@ static void intel_hdmi_info(struct seq_file *m,
 			    struct intel_connector *intel_connector)
 {
 	struct intel_encoder *intel_encoder = intel_connector->encoder;
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(intel_encoder);
 
 	seq_printf(m, "\taudio support: %s\n", yesno(intel_hdmi->has_audio));
 	if (intel_connector->hdcp.shim) {
@@ -2508,10 +2443,12 @@ static void intel_connector_info(struct seq_file *m,
 				 struct drm_connector *connector)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct intel_encoder *intel_encoder = intel_connector->encoder;
-	struct drm_display_mode *mode;
+	const struct drm_connector_state *conn_state = connector->state;
+	struct intel_encoder *encoder =
+		to_intel_encoder(conn_state->best_encoder);
+	const struct drm_display_mode *mode;
 
-	seq_printf(m, "connector %d: type %s, status: %s\n",
+	seq_printf(m, "[CONNECTOR:%d:%s]: status: %s\n",
 		   connector->base.id, connector->name,
 		   drm_get_connector_status_name(connector->status));
 
@@ -2525,24 +2462,24 @@ static void intel_connector_info(struct seq_file *m,
 		   drm_get_subpixel_order_name(connector->display_info.subpixel_order));
 	seq_printf(m, "\tCEA rev: %d\n", connector->display_info.cea_rev);
 
-	if (!intel_encoder)
+	if (!encoder)
 		return;
 
 	switch (connector->connector_type) {
 	case DRM_MODE_CONNECTOR_DisplayPort:
 	case DRM_MODE_CONNECTOR_eDP:
-		if (intel_encoder->type == INTEL_OUTPUT_DP_MST)
+		if (encoder->type == INTEL_OUTPUT_DP_MST)
 			intel_dp_mst_info(m, intel_connector);
 		else
 			intel_dp_info(m, intel_connector);
 		break;
 	case DRM_MODE_CONNECTOR_LVDS:
-		if (intel_encoder->type == INTEL_OUTPUT_LVDS)
+		if (encoder->type == INTEL_OUTPUT_LVDS)
 			intel_lvds_info(m, intel_connector);
 		break;
 	case DRM_MODE_CONNECTOR_HDMIA:
-		if (intel_encoder->type == INTEL_OUTPUT_HDMI ||
-		    intel_encoder->type == INTEL_OUTPUT_DDI)
+		if (encoder->type == INTEL_OUTPUT_HDMI ||
+		    encoder->type == INTEL_OUTPUT_DDI)
 			intel_hdmi_info(m, intel_connector);
 		break;
 	default:
@@ -2589,70 +2526,88 @@ static void plane_rotation(char *buf, size_t bufsize, unsigned int rotation)
 		 rotation);
 }
 
-static void intel_plane_info(struct seq_file *m, struct intel_crtc *intel_crtc)
+static void intel_plane_uapi_info(struct seq_file *m, struct intel_plane *plane)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_plane *intel_plane;
+	const struct intel_plane_state *plane_state =
+		to_intel_plane_state(plane->base.state);
+	const struct drm_framebuffer *fb = plane_state->uapi.fb;
+	struct drm_format_name_buf format_name;
+	struct drm_rect src, dst;
+	char rot_str[48];
 
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		struct drm_plane_state *state;
-		struct drm_plane *plane = &intel_plane->base;
-		struct drm_format_name_buf format_name;
-		char rot_str[48];
+	src = drm_plane_state_src(&plane_state->uapi);
+	dst = drm_plane_state_dest(&plane_state->uapi);
 
-		if (!plane->state) {
-			seq_puts(m, "plane->state is NULL!\n");
-			continue;
-		}
+	if (fb)
+		drm_get_format_name(fb->format->format, &format_name);
 
-		state = plane->state;
+	plane_rotation(rot_str, sizeof(rot_str),
+		       plane_state->uapi.rotation);
 
-		if (state->fb) {
-			drm_get_format_name(state->fb->format->format,
-					    &format_name);
-		} else {
-			sprintf(format_name.str, "N/A");
-		}
+	seq_printf(m, "\t\tuapi: fb=%d,%s,%dx%d, src=" DRM_RECT_FP_FMT ", dst=" DRM_RECT_FMT ", rotation=%s\n",
+		   fb ? fb->base.id : 0, fb ? format_name.str : "n/a",
+		   fb ? fb->width : 0, fb ? fb->height : 0,
+		   DRM_RECT_FP_ARG(&src),
+		   DRM_RECT_ARG(&dst),
+		   rot_str);
+}
+
+static void intel_plane_hw_info(struct seq_file *m, struct intel_plane *plane)
+{
+	const struct intel_plane_state *plane_state =
+		to_intel_plane_state(plane->base.state);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	struct drm_format_name_buf format_name;
+	char rot_str[48];
+
+	if (!fb)
+		return;
 
-		plane_rotation(rot_str, sizeof(rot_str), state->rotation);
-
-		seq_printf(m, "\t--Plane id %d: type=%s, crtc_pos=%4dx%4d, crtc_size=%4dx%4d, src_pos=%d.%04ux%d.%04u, src_size=%d.%04ux%d.%04u, format=%s, rotation=%s\n",
-			   plane->base.id,
-			   plane_type(intel_plane->base.type),
-			   state->crtc_x, state->crtc_y,
-			   state->crtc_w, state->crtc_h,
-			   (state->src_x >> 16),
-			   ((state->src_x & 0xffff) * 15625) >> 10,
-			   (state->src_y >> 16),
-			   ((state->src_y & 0xffff) * 15625) >> 10,
-			   (state->src_w >> 16),
-			   ((state->src_w & 0xffff) * 15625) >> 10,
-			   (state->src_h >> 16),
-			   ((state->src_h & 0xffff) * 15625) >> 10,
-			   format_name.str,
-			   rot_str);
+	drm_get_format_name(fb->format->format, &format_name);
+
+	plane_rotation(rot_str, sizeof(rot_str),
+		       plane_state->hw.rotation);
+
+	seq_printf(m, "\t\thw: fb=%d,%s,%dx%d, visible=%s, src=" DRM_RECT_FP_FMT ", dst=" DRM_RECT_FMT ", rotation=%s\n",
+		   fb->base.id, format_name.str,
+		   fb->width, fb->height,
+		   yesno(plane_state->uapi.visible),
+		   DRM_RECT_FP_ARG(&plane_state->uapi.src),
+		   DRM_RECT_ARG(&plane_state->uapi.dst),
+		   rot_str);
+}
+
+static void intel_plane_info(struct seq_file *m, struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	struct intel_plane *plane;
+
+	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
+		seq_printf(m, "\t[PLANE:%d:%s]: type=%s\n",
+			   plane->base.base.id, plane->base.name,
+			   plane_type(plane->base.type));
+		intel_plane_uapi_info(m, plane);
+		intel_plane_hw_info(m, plane);
 	}
 }
 
-static void intel_scaler_info(struct seq_file *m, struct intel_crtc *intel_crtc)
+static void intel_scaler_info(struct seq_file *m, struct intel_crtc *crtc)
 {
-	struct intel_crtc_state *pipe_config;
-	int num_scalers = intel_crtc->num_scalers;
+	const struct intel_crtc_state *crtc_state =
+		to_intel_crtc_state(crtc->base.state);
+	int num_scalers = crtc->num_scalers;
 	int i;
 
-	pipe_config = to_intel_crtc_state(intel_crtc->base.state);
-
 	/* Not all platformas have a scaler */
 	if (num_scalers) {
 		seq_printf(m, "\tnum_scalers=%d, scaler_users=%x scaler_id=%d",
 			   num_scalers,
-			   pipe_config->scaler_state.scaler_users,
-			   pipe_config->scaler_state.scaler_id);
+			   crtc_state->scaler_state.scaler_users,
+			   crtc_state->scaler_state.scaler_id);
 
 		for (i = 0; i < num_scalers; i++) {
-			struct intel_scaler *sc =
-					&pipe_config->scaler_state.scalers[i];
+			const struct intel_scaler *sc =
+				&crtc_state->scaler_state.scalers[i];
 
 			seq_printf(m, ", scalers[%d]: use=%s, mode=%x",
 				   i, yesno(sc->in_use), sc->mode);
@@ -2663,6 +2618,44 @@ static void intel_scaler_info(struct seq_file *m, struct intel_crtc *intel_crtc)
 	}
 }
 
+static void intel_crtc_info(struct seq_file *m, struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	const struct intel_crtc_state *crtc_state =
+		to_intel_crtc_state(crtc->base.state);
+	struct intel_encoder *encoder;
+
+	seq_printf(m, "[CRTC:%d:%s]:\n",
+		   crtc->base.base.id, crtc->base.name);
+
+	seq_printf(m, "\tuapi: enable=%s, active=%s, mode=" DRM_MODE_FMT "\n",
+		   yesno(crtc_state->uapi.enable),
+		   yesno(crtc_state->uapi.active),
+		   DRM_MODE_ARG(&crtc_state->uapi.mode));
+
+	if (crtc_state->hw.enable) {
+		seq_printf(m, "\thw: active=%s, adjusted_mode=" DRM_MODE_FMT "\n",
+			   yesno(crtc_state->hw.active),
+			   DRM_MODE_ARG(&crtc_state->hw.adjusted_mode));
+
+		seq_printf(m, "\tpipe src size=%dx%d, dither=%s, bpp=%d\n",
+			   crtc_state->pipe_src_w, crtc_state->pipe_src_h,
+			   yesno(crtc_state->dither), crtc_state->pipe_bpp);
+
+		intel_scaler_info(m, crtc);
+	}
+
+	for_each_intel_encoder_mask(&dev_priv->drm, encoder,
+				    crtc_state->uapi.encoder_mask)
+		intel_encoder_info(m, crtc, encoder);
+
+	intel_plane_info(m, crtc);
+
+	seq_printf(m, "\tunderrun reporting: cpu=%s pch=%s\n",
+		   yesno(!crtc->cpu_fifo_underrun_disabled),
+		   yesno(!crtc->pch_fifo_underrun_disabled));
+}
+
 static int i915_display_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -2674,52 +2667,22 @@ static int i915_display_info(struct seq_file *m, void *unused)
 
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 
+	drm_modeset_lock_all(dev);
+
 	seq_printf(m, "CRTC info\n");
 	seq_printf(m, "---------\n");
-	for_each_intel_crtc(dev, crtc) {
-		struct intel_crtc_state *pipe_config;
-
-		drm_modeset_lock(&crtc->base.mutex, NULL);
-		pipe_config = to_intel_crtc_state(crtc->base.state);
-
-		seq_printf(m, "CRTC %d: pipe: %c, active=%s, (size=%dx%d), dither=%s, bpp=%d\n",
-			   crtc->base.base.id, pipe_name(crtc->pipe),
-			   yesno(pipe_config->base.active),
-			   pipe_config->pipe_src_w, pipe_config->pipe_src_h,
-			   yesno(pipe_config->dither), pipe_config->pipe_bpp);
-
-		if (pipe_config->base.active) {
-			struct intel_plane *cursor =
-				to_intel_plane(crtc->base.cursor);
-
-			intel_crtc_info(m, crtc);
-
-			seq_printf(m, "\tcursor visible? %s, position (%d, %d), size %dx%d, addr 0x%08x\n",
-				   yesno(cursor->base.state->visible),
-				   cursor->base.state->crtc_x,
-				   cursor->base.state->crtc_y,
-				   cursor->base.state->crtc_w,
-				   cursor->base.state->crtc_h,
-				   cursor->cursor.base);
-			intel_scaler_info(m, crtc);
-			intel_plane_info(m, crtc);
-		}
-
-		seq_printf(m, "\tunderrun reporting: cpu=%s pch=%s \n",
-			   yesno(!crtc->cpu_fifo_underrun_disabled),
-			   yesno(!crtc->pch_fifo_underrun_disabled));
-		drm_modeset_unlock(&crtc->base.mutex);
-	}
+	for_each_intel_crtc(dev, crtc)
+		intel_crtc_info(m, crtc);
 
 	seq_printf(m, "\n");
 	seq_printf(m, "Connector info\n");
 	seq_printf(m, "--------------\n");
-	mutex_lock(&dev->mode_config.mutex);
 	drm_connector_list_iter_begin(dev, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter)
 		intel_connector_info(m, connector);
 	drm_connector_list_iter_end(&conn_iter);
-	mutex_unlock(&dev->mode_config.mutex);
+
+	drm_modeset_unlock_all(dev);
 
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 
@@ -2755,7 +2718,7 @@ static int i915_rcs_topology(struct seq_file *m, void *unused)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct drm_printer p = drm_seq_file_printer(m);
 
-	intel_device_info_dump_topology(&RUNTIME_INFO(dev_priv)->sseu, &p);
+	intel_device_info_print_topology(&RUNTIME_INFO(dev_priv)->sseu, &p);
 
 	return 0;
 }
@@ -3051,11 +3014,11 @@ static int i915_dp_mst_info(struct seq_file *m, void *unused)
 		if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort)
 			continue;
 
-		intel_encoder = intel_attached_encoder(connector);
+		intel_encoder = intel_attached_encoder(to_intel_connector(connector));
 		if (!intel_encoder || intel_encoder->type == INTEL_OUTPUT_DP_MST)
 			continue;
 
-		intel_dig_port = enc_to_dig_port(&intel_encoder->base);
+		intel_dig_port = enc_to_dig_port(intel_encoder);
 		if (!intel_dig_port->dp.can_mst)
 			continue;
 
@@ -3105,7 +3068,7 @@ static ssize_t i915_displayport_test_active_write(struct file *file,
 			continue;
 
 		if (encoder && connector->status == connector_status_connected) {
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			status = kstrtoint(input_buffer, 10, &val);
 			if (status < 0)
 				break;
@@ -3114,9 +3077,9 @@ static ssize_t i915_displayport_test_active_write(struct file *file,
 			 * testing code, only accept an actual value of 1 here
 			 */
 			if (val == 1)
-				intel_dp->compliance.test_active = 1;
+				intel_dp->compliance.test_active = true;
 			else
-				intel_dp->compliance.test_active = 0;
+				intel_dp->compliance.test_active = false;
 		}
 	}
 	drm_connector_list_iter_end(&conn_iter);
@@ -3149,7 +3112,7 @@ static int i915_displayport_test_active_show(struct seq_file *m, void *data)
 			continue;
 
 		if (encoder && connector->status == connector_status_connected) {
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			if (intel_dp->compliance.test_active)
 				seq_puts(m, "1");
 			else
@@ -3199,7 +3162,7 @@ static int i915_displayport_test_data_show(struct seq_file *m, void *data)
 			continue;
 
 		if (encoder && connector->status == connector_status_connected) {
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			if (intel_dp->compliance.test_type ==
 			    DP_TEST_LINK_EDID_READ)
 				seq_printf(m, "%lx",
@@ -3243,7 +3206,7 @@ static int i915_displayport_test_type_show(struct seq_file *m, void *data)
 			continue;
 
 		if (encoder && connector->status == connector_status_connected) {
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			seq_printf(m, "%02lx", intel_dp->compliance.test_type);
 		} else
 			seq_puts(m, "0");
@@ -3854,8 +3817,8 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 #undef SS_MAX
 }
 
-static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
-					 struct sseu_dev_info *sseu)
+static void bdw_sseu_device_status(struct drm_i915_private *dev_priv,
+				   struct sseu_dev_info *sseu)
 {
 	const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
 	u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO);
@@ -3940,7 +3903,7 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 		if (IS_CHERRYVIEW(dev_priv))
 			cherryview_sseu_device_status(dev_priv, &sseu);
 		else if (IS_BROADWELL(dev_priv))
-			broadwell_sseu_device_status(dev_priv, &sseu);
+			bdw_sseu_device_status(dev_priv, &sseu);
 		else if (IS_GEN(dev_priv, 9))
 			gen9_sseu_device_status(dev_priv, &sseu);
 		else if (INTEL_GEN(dev_priv) >= 10)
@@ -4161,11 +4124,11 @@ static int i915_drrs_ctl_set(void *data, u64 val)
 
 		crtc_state = to_intel_crtc_state(crtc->base.state);
 
-		if (!crtc_state->base.active ||
+		if (!crtc_state->hw.active ||
 		    !crtc_state->has_drrs)
 			goto out;
 
-		commit = crtc_state->base.commit;
+		commit = crtc_state->uapi.commit;
 		if (commit) {
 			ret = wait_for_completion_interruptible(&commit->hw_done);
 			if (ret)
@@ -4177,18 +4140,18 @@ static int i915_drrs_ctl_set(void *data, u64 val)
 			struct intel_encoder *encoder;
 			struct intel_dp *intel_dp;
 
-			if (!(crtc_state->base.connector_mask &
+			if (!(crtc_state->uapi.connector_mask &
 			      drm_connector_mask(connector)))
 				continue;
 
-			encoder = intel_attached_encoder(connector);
+			encoder = intel_attached_encoder(to_intel_connector(connector));
 			if (encoder->type != INTEL_OUTPUT_EDP)
 				continue;
 
 			DRM_DEBUG_DRIVER("Manually %sabling DRRS. %llu\n",
 						val ? "en" : "dis", val);
 
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			if (val)
 				intel_edp_drrs_enable(intel_dp,
 						      crtc_state);
@@ -4236,14 +4199,14 @@ i915_fifo_underrun_reset_write(struct file *filp,
 			return ret;
 
 		crtc_state = to_intel_crtc_state(intel_crtc->base.state);
-		commit = crtc_state->base.commit;
+		commit = crtc_state->uapi.commit;
 		if (commit) {
 			ret = wait_for_completion_interruptible(&commit->hw_done);
 			if (!ret)
 				ret = wait_for_completion_interruptible(&commit->flip_done);
 		}
 
-		if (!ret && crtc_state->base.active) {
+		if (!ret && crtc_state->hw.active) {
 			DRM_DEBUG_KMS("Re-arming FIFO underruns on pipe %c\n",
 				      pipe_name(intel_crtc->pipe));
 
@@ -4392,7 +4355,7 @@ static int i915_dpcd_show(struct seq_file *m, void *data)
 {
 	struct drm_connector *connector = m->private;
 	struct intel_dp *intel_dp =
-		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+		enc_to_intel_dp(intel_attached_encoder(to_intel_connector(connector)));
 	u8 buf[16];
 	ssize_t err;
 	int i;
@@ -4427,7 +4390,7 @@ static int i915_panel_show(struct seq_file *m, void *data)
 {
 	struct drm_connector *connector = m->private;
 	struct intel_dp *intel_dp =
-		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+		enc_to_intel_dp(intel_attached_encoder(to_intel_connector(connector)));
 
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
@@ -4505,7 +4468,7 @@ static int i915_dsc_fec_support_show(struct seq_file *m, void *data)
 		} else if (ret) {
 			break;
 		}
-		intel_dp = enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+		intel_dp = enc_to_intel_dp(intel_attached_encoder(to_intel_connector(connector)));
 		crtc_state = to_intel_crtc_state(crtc->state);
 		seq_printf(m, "DSC_Enabled: %s\n",
 			   yesno(crtc_state->dsc.compression_enable));
@@ -4532,8 +4495,8 @@ static ssize_t i915_dsc_fec_support_write(struct file *file,
 	int ret;
 	struct drm_connector *connector =
 		((struct seq_file *)file->private_data)->private;
-	struct intel_encoder *encoder = intel_attached_encoder(connector);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_encoder *encoder = intel_attached_encoder(to_intel_connector(connector));
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	if (len == 0)
 		return 0;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 3c512c571e60..f7385abdd74b 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -61,6 +61,7 @@
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
+#include "gem/i915_gem_mman.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_rc6.h"
@@ -468,6 +469,12 @@ static void vlv_free_s0ix_state(struct drm_i915_private *i915)
 	i915->vlv_s0ix_state = NULL;
 }
 
+static void sanitize_gpu(struct drm_i915_private *i915)
+{
+	if (!INTEL_INFO(i915)->gpu_reset_clobbers_display)
+		__intel_gt_reset(&i915->gt, ALL_ENGINES);
+}
+
 /**
  * i915_driver_early_probe - setup state not requiring device access
  * @dev_priv: device private
@@ -601,6 +608,9 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv)
 	if (ret)
 		goto err_uncore;
 
+	/* As early as possible, scrub existing GPU state before clobbering */
+	sanitize_gpu(dev_priv);
+
 	return 0;
 
 err_uncore:
@@ -618,7 +628,6 @@ err_bridge:
  */
 static void i915_driver_mmio_release(struct drm_i915_private *dev_priv)
 {
-	intel_engines_cleanup(&dev_priv->gt);
 	intel_teardown_mchbar(dev_priv);
 	intel_uncore_fini_mmio(&dev_priv->uncore);
 	pci_dev_put(dev_priv->bridge_dev);
@@ -1052,7 +1061,7 @@ intel_get_dram_info(struct drm_i915_private *dev_priv)
 	 */
 	dram_info->is_16gb_dimm = !IS_GEN9_LP(dev_priv);
 
-	if (INTEL_GEN(dev_priv) < 9)
+	if (INTEL_GEN(dev_priv) < 9 || !HAS_DISPLAY(dev_priv))
 		return;
 
 	if (IS_GEN9_LP(dev_priv))
@@ -1385,7 +1394,7 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv)
 
 static void i915_welcome_messages(struct drm_i915_private *dev_priv)
 {
-	if (drm_debug & DRM_UT_DRIVER) {
+	if (drm_debug_enabled(DRM_UT_DRIVER)) {
 		struct drm_printer p = drm_debug_printer("i915 device info:");
 
 		drm_printf(&p, "pciid=0x%04x rev=0x%02x platform=%s (subplatform=0x%x) gen=%i\n",
@@ -1396,8 +1405,8 @@ static void i915_welcome_messages(struct drm_i915_private *dev_priv)
 					     INTEL_INFO(dev_priv)->platform),
 			   INTEL_GEN(dev_priv));
 
-		intel_device_info_dump_flags(INTEL_INFO(dev_priv), &p);
-		intel_device_info_dump_runtime(RUNTIME_INFO(dev_priv), &p);
+		intel_device_info_print_static(INTEL_INFO(dev_priv), &p);
+		intel_device_info_print_runtime(RUNTIME_INFO(dev_priv), &p);
 	}
 
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG))
@@ -1817,9 +1826,7 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	disable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
-	intel_rc6_ctx_wa_resume(&dev_priv->gt.rc6);
-
-	intel_gt_sanitize(&dev_priv->gt, true);
+	sanitize_gpu(dev_priv);
 
 	ret = i915_ggtt_enable_hw(dev_priv);
 	if (ret)
@@ -2662,18 +2669,12 @@ const struct dev_pm_ops i915_pm_ops = {
 	.runtime_resume = intel_runtime_resume,
 };
 
-static const struct vm_operations_struct i915_gem_vm_ops = {
-	.fault = i915_gem_fault,
-	.open = drm_gem_vm_open,
-	.close = drm_gem_vm_close,
-};
-
 static const struct file_operations i915_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_gem_mmap,
+	.mmap = i915_gem_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
 	.compat_ioctl = i915_compat_ioctl,
@@ -2720,7 +2721,7 @@ static const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_GTT, i915_gem_mmap_gtt_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_OFFSET, i915_gem_mmap_offset_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_SET_TILING, i915_gem_set_tiling_ioctl, DRM_RENDER_ALLOW),
@@ -2762,7 +2763,6 @@ static struct drm_driver driver = {
 
 	.gem_close_object = i915_gem_close_object,
 	.gem_free_object_unlocked = i915_gem_free_object,
-	.gem_vm_ops = &i915_gem_vm_ops,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
@@ -2773,7 +2773,8 @@ static struct drm_driver driver = {
 	.get_scanout_position = i915_get_crtc_scanoutpos,
 
 	.dumb_create = i915_gem_dumb_create,
-	.dumb_map_offset = i915_gem_mmap_gtt,
+	.dumb_map_offset = i915_gem_dumb_mmap_offset,
+
 	.ioctls = i915_ioctls,
 	.num_ioctls = ARRAY_SIZE(i915_ioctls),
 	.fops = &i915_driver_fops,
@@ -2784,7 +2785,3 @@ static struct drm_driver driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
-
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/mock_drm.c"
-#endif
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 21aa08f55811..077af22b8340 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -46,6 +46,7 @@
 #include <linux/dma-resv.h>
 #include <linux/shmem_fs.h>
 #include <linux/stackdepot.h>
+#include <linux/xarray.h>
 
 #include <drm/intel-gtt.h>
 #include <drm/drm_legacy.h> /* for struct drm_dma_handle */
@@ -110,8 +111,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20191101"
-#define DRIVER_TIMESTAMP	1572604873
+#define DRIVER_DATE		"20200114"
+#define DRIVER_TIMESTAMP	1579001978
 
 struct drm_i915_gem_object;
 
@@ -201,8 +202,7 @@ struct drm_i915_file_private {
 		struct list_head request_list;
 	} mm;
 
-	struct idr context_idr;
-	struct mutex context_idr_lock; /* guards context_idr */
+	struct xarray context_xa;
 
 	struct idr vm_idr;
 	struct mutex vm_idr_lock; /* guards vm_idr */
@@ -273,11 +273,11 @@ struct drm_i915_display_funcs {
 	int (*compute_pipe_wm)(struct intel_crtc_state *crtc_state);
 	int (*compute_intermediate_wm)(struct intel_crtc_state *crtc_state);
 	void (*initial_watermarks)(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state);
+				   struct intel_crtc *crtc);
 	void (*atomic_update_watermarks)(struct intel_atomic_state *state,
-					 struct intel_crtc_state *crtc_state);
+					 struct intel_crtc *crtc);
 	void (*optimize_watermarks)(struct intel_atomic_state *state,
-				    struct intel_crtc_state *crtc_state);
+				    struct intel_crtc *crtc);
 	int (*compute_global_watermarks)(struct intel_atomic_state *state);
 	void (*update_wm)(struct intel_crtc *crtc);
 	int (*modeset_calc_cdclk)(struct intel_atomic_state *state);
@@ -290,10 +290,10 @@ struct drm_i915_display_funcs {
 					 struct intel_initial_plane_config *);
 	int (*crtc_compute_clock)(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state);
-	void (*crtc_enable)(struct intel_crtc_state *pipe_config,
-			    struct intel_atomic_state *old_state);
-	void (*crtc_disable)(struct intel_crtc_state *old_crtc_state,
-			     struct intel_atomic_state *old_state);
+	void (*crtc_enable)(struct intel_atomic_state *state,
+			    struct intel_crtc *crtc);
+	void (*crtc_disable)(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc);
 	void (*commit_modeset_enables)(struct intel_atomic_state *state);
 	void (*commit_modeset_disables)(struct intel_atomic_state *state);
 	void (*audio_codec_enable)(struct intel_encoder *encoder,
@@ -366,7 +366,6 @@ struct intel_fbc {
 	unsigned threshold;
 	unsigned int possible_framebuffer_bits;
 	unsigned int busy_bits;
-	unsigned int visible_pipes_mask;
 	struct intel_crtc *crtc;
 
 	struct drm_mm_node compressed_fb;
@@ -374,8 +373,8 @@ struct intel_fbc {
 
 	bool false_color;
 
-	bool enabled;
 	bool active;
+	bool activated;
 	bool flip_pending;
 
 	bool underrun_detected;
@@ -387,9 +386,6 @@ struct intel_fbc {
 	 * these problems.
 	 */
 	struct intel_fbc_state_cache {
-		struct i915_vma *vma;
-		unsigned long flags;
-
 		struct {
 			unsigned int mode_flags;
 			u32 hsw_bdw_pixel_rate;
@@ -418,6 +414,8 @@ struct intel_fbc {
 			const struct drm_format_info *format;
 			unsigned int stride;
 		} fb;
+		u16 gen9_wa_cfb_stride;
+		s8 fence_id;
 	} state_cache;
 
 	/*
@@ -428,9 +426,6 @@ struct intel_fbc {
 	 * are supposed to read from it in order to program the registers.
 	 */
 	struct intel_fbc_reg_params {
-		struct i915_vma *vma;
-		unsigned long flags;
-
 		struct {
 			enum pipe pipe;
 			enum i9xx_plane_id i9xx_plane;
@@ -443,7 +438,9 @@ struct intel_fbc {
 		} fb;
 
 		int cfb_size;
-		unsigned int gen9_wa_cfb_stride;
+		u16 gen9_wa_cfb_stride;
+		s8 fence_id;
+		bool plane_visible;
 	} params;
 
 	const char *no_fbc_reason;
@@ -508,6 +505,7 @@ struct i915_psr {
 	bool dc3co_enabled;
 	u32 dc3co_exit_delay;
 	struct delayed_work idle_work;
+	bool initially_probed;
 };
 
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
@@ -621,19 +619,18 @@ struct i915_gem_mm {
 
 #define I915_ENGINE_WEDGED_TIMEOUT  (60 * HZ)  /* Reset but no recovery? */
 
+/* Amount of SAGV/QGV points, BSpec precisely defines this */
+#define I915_NUM_QGV_POINTS 8
+
 struct ddi_vbt_port_info {
 	/* Non-NULL if port present. */
 	const struct child_device_config *child;
 
 	int max_tmds_clock;
 
-	/*
-	 * This is an index in the HDMI/DVI DDI buffer translation table.
-	 * The special value HDMI_LEVEL_SHIFT_UNKNOWN means the VBT didn't
-	 * populate this field.
-	 */
-#define HDMI_LEVEL_SHIFT_UNKNOWN	0xff
+	/* This is an index in the HDMI/DVI DDI buffer translation table. */
 	u8 hdmi_level_shift;
+	u8 hdmi_level_shift_set:1;
 
 	u8 supports_dvi:1;
 	u8 supports_hdmi:1;
@@ -724,8 +721,7 @@ struct intel_vbt_data {
 
 	int crt_ddc_pin;
 
-	int child_dev_num;
-	struct child_device_config *child_dev;
+	struct list_head display_devices;
 
 	struct ddi_vbt_port_info ddi_port_info[I915_MAX_PORTS];
 	struct sdvo_device_mapping sdvo_mappings[2];
@@ -891,6 +887,10 @@ struct intel_cdclk_state {
 	u8 voltage_level;
 };
 
+struct i915_selftest_stash {
+	atomic_t counter;
+};
+
 struct drm_i915_private {
 	struct drm_device drm;
 
@@ -956,9 +956,6 @@ struct drm_i915_private {
 
 	struct pci_dev *bridge_dev;
 
-	/* Context used internally to idle the GPU and setup initial state */
-	struct i915_gem_context *kernel_context;
-
 	struct intel_engine_cs *engine[I915_NUM_ENGINES];
 	struct rb_root uabi_engines;
 
@@ -1233,7 +1230,8 @@ struct drm_i915_private {
 	} dram_info;
 
 	struct intel_bw_info {
-		unsigned int deratedbw[3]; /* for each QGV point */
+		/* for each QGV point */
+		unsigned int deratedbw[I915_NUM_QGV_POINTS];
 		u8 num_qgv_points;
 		u8 num_planes;
 	} max_bw[6];
@@ -1248,8 +1246,6 @@ struct drm_i915_private {
 	struct intel_gt gt;
 
 	struct {
-		struct notifier_block pm_notifier;
-
 		struct i915_gem_contexts {
 			spinlock_t lock; /* locks list */
 			struct list_head list;
@@ -1257,6 +1253,16 @@ struct drm_i915_private {
 			struct llist_head free_list;
 			struct work_struct free_work;
 		} contexts;
+
+		/*
+		 * We replace the local file with a global mappings as the
+		 * backing storage for the mmap is on the device and not
+		 * on the struct file, and we do not want to prolong the
+		 * lifetime of the local fd. To minimise the number of
+		 * anonymous inodes we create, we use a global singleton to
+		 * share the global mapping.
+		 */
+		struct file *mmap_singleton;
 	} gem;
 
 	u8 pch_ssc_use;
@@ -1286,6 +1292,8 @@ struct drm_i915_private {
 	/* Mutex to protect the above hdcp component related values. */
 	struct mutex hdcp_comp_mutex;
 
+	I915_SELFTEST_DECLARE(struct i915_selftest_stash selftest;)
+
 	/*
 	 * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
 	 * will be rejected. Instead look for a better place.
@@ -1844,14 +1852,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags);
 #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
-
-struct i915_vma * __must_check
-i915_gem_object_pin(struct drm_i915_gem_object *obj,
-		    struct i915_address_space *vm,
-		    const struct i915_ggtt_view *view,
-		    u64 size,
-		    u64 alignment,
-		    u64 flags);
+#define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1)
 
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
 
@@ -1864,9 +1865,6 @@ i915_mutex_lock_interruptible(struct drm_device *dev)
 int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
-int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev,
-		      u32 handle, u64 *offset);
-int i915_gem_mmap_gtt_version(void);
 
 int __must_check i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno);
 
@@ -1876,7 +1874,7 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 }
 
 static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
-					  struct intel_engine_cs *engine)
+					  const struct intel_engine_cs *engine)
 {
 	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
 }
@@ -1889,7 +1887,6 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv);
 void i915_gem_suspend(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
-vm_fault_t i915_gem_fault(struct vm_fault *vmf);
 
 int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file);
 void i915_gem_release(struct drm_device *dev, struct drm_file *file);
@@ -1905,7 +1902,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags)
 static inline struct i915_gem_context *
 __i915_gem_context_lookup_rcu(struct drm_i915_file_private *file_priv, u32 id)
 {
-	return idr_find(&file_priv->context_idr, id);
+	return xa_load(&file_priv->context_xa, id);
 }
 
 static inline struct i915_gem_context *
@@ -1958,14 +1955,13 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
 void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-int intel_engine_cmd_parser(struct i915_gem_context *cxt,
-			    struct intel_engine_cs *engine,
-			    struct drm_i915_gem_object *batch_obj,
-			    u64 user_batch_start,
-			    u32 batch_start_offset,
-			    u32 batch_len,
-			    struct drm_i915_gem_object *shadow_batch_obj,
-			    u64 shadow_batch_start);
+int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+			    struct i915_vma *batch,
+			    u32 batch_offset,
+			    u32 batch_length,
+			    struct i915_vma *shadow,
+			    bool trampoline);
+#define I915_CMD_PARSER_TRAMPOLINE_SIZE 8
 
 /* intel_device_info.c */
 static inline struct intel_device_info *
@@ -2032,6 +2028,9 @@ int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 int remap_io_mapping(struct vm_area_struct *vma,
 		     unsigned long addr, unsigned long pfn, unsigned long size,
 		     struct io_mapping *iomap);
+int remap_io_sg(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long size,
+		struct scatterlist *sgl, resource_size_t iobase);
 
 static inline int intel_hws_csb_write_index(struct drm_i915_private *i915)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 905890e3ac24..94f993e4c12f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -44,20 +44,14 @@
 #include "gem/i915_gem_clflush.h"
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
-#include "gem/i915_gem_pm.h"
-#include "gt/intel_context.h"
+#include "gem/i915_gem_mman.h"
+#include "gem/i915_gem_region.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
-#include "gt/intel_gt_requests.h"
-#include "gt/intel_mocs.h"
-#include "gt/intel_reset.h"
-#include "gt/intel_renderstate.h"
-#include "gt/intel_rps.h"
 #include "gt/intel_workarounds.h"
 
 #include "i915_drv.h"
-#include "i915_scatterlist.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
 
@@ -119,33 +113,65 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags)
 {
-	struct i915_vma *vma;
+	struct intel_runtime_pm *rpm = &to_i915(obj->base.dev)->runtime_pm;
 	LIST_HEAD(still_in_list);
-	int ret = 0;
+	intel_wakeref_t wakeref;
+	struct i915_vma *vma;
+	int ret;
+
+	if (!atomic_read(&obj->bind_count))
+		return 0;
+
+	/*
+	 * As some machines use ACPI to handle runtime-resume callbacks, and
+	 * ACPI is quite kmalloc happy, we cannot resume beneath the vm->mutex
+	 * as they are required by the shrinker. Ergo, we wake the device up
+	 * first just in case.
+	 */
+	wakeref = intel_runtime_pm_get(rpm);
 
+try_again:
+	ret = 0;
 	spin_lock(&obj->vma.lock);
 	while (!ret && (vma = list_first_entry_or_null(&obj->vma.list,
 						       struct i915_vma,
 						       obj_link))) {
 		struct i915_address_space *vm = vma->vm;
 
-		ret = -EBUSY;
+		list_move_tail(&vma->obj_link, &still_in_list);
+		if (!i915_vma_is_bound(vma, I915_VMA_BIND_MASK))
+			continue;
+
+		ret = -EAGAIN;
 		if (!i915_vm_tryopen(vm))
 			break;
 
-		list_move_tail(&vma->obj_link, &still_in_list);
+		/* Prevent vma being freed by i915_vma_parked as we unbind */
+		vma = __i915_vma_get(vma);
 		spin_unlock(&obj->vma.lock);
 
-		if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
-		    !i915_vma_is_active(vma))
-			ret = i915_vma_unbind(vma);
+		if (vma) {
+			ret = -EBUSY;
+			if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
+			    !i915_vma_is_active(vma))
+				ret = i915_vma_unbind(vma);
+
+			__i915_vma_put(vma);
+		}
 
 		i915_vm_close(vm);
 		spin_lock(&obj->vma.lock);
 	}
-	list_splice(&still_in_list, &obj->vma.list);
+	list_splice_init(&still_in_list, &obj->vma.list);
 	spin_unlock(&obj->vma.lock);
 
+	if (ret == -EAGAIN && flags & I915_GEM_OBJECT_UNBIND_BARRIER) {
+		rcu_barrier(); /* flush the i915_vm_release() */
+		goto try_again;
+	}
+
+	intel_runtime_pm_put(rpm, wakeref);
+
 	return ret;
 }
 
@@ -175,7 +201,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
 
 static int
 i915_gem_create(struct drm_file *file,
-		struct drm_i915_private *dev_priv,
+		struct intel_memory_region *mr,
 		u64 *size_p,
 		u32 *handle_p)
 {
@@ -184,12 +210,16 @@ i915_gem_create(struct drm_file *file,
 	u64 size;
 	int ret;
 
-	size = round_up(*size_p, PAGE_SIZE);
+	GEM_BUG_ON(!is_power_of_2(mr->min_page_size));
+	size = round_up(*size_p, mr->min_page_size);
 	if (size == 0)
 		return -EINVAL;
 
+	/* For most of the ABI (e.g. mmap) we think in system pages */
+	GEM_BUG_ON(!IS_ALIGNED(size, PAGE_SIZE));
+
 	/* Allocate the new object */
-	obj = i915_gem_object_create_shmem(dev_priv, size);
+	obj = i915_gem_object_create_region(mr, size, 0);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -209,6 +239,7 @@ i915_gem_dumb_create(struct drm_file *file,
 		     struct drm_device *dev,
 		     struct drm_mode_create_dumb *args)
 {
+	enum intel_memory_type mem_type;
 	int cpp = DIV_ROUND_UP(args->bpp, 8);
 	u32 format;
 
@@ -235,7 +266,14 @@ i915_gem_dumb_create(struct drm_file *file,
 		args->pitch = ALIGN(args->pitch, 4096);
 
 	args->size = args->pitch * args->height;
-	return i915_gem_create(file, to_i915(dev),
+
+	mem_type = INTEL_MEMORY_SYSTEM;
+	if (HAS_LMEM(to_i915(dev)))
+		mem_type = INTEL_MEMORY_LOCAL;
+
+	return i915_gem_create(file,
+			       intel_memory_region_by_type(to_i915(dev),
+							   mem_type),
 			       &args->size, &args->handle);
 }
 
@@ -249,12 +287,14 @@ int
 i915_gem_create_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_create *args = data;
 
-	i915_gem_flush_free_objects(dev_priv);
+	i915_gem_flush_free_objects(i915);
 
-	return i915_gem_create(file, dev_priv,
+	return i915_gem_create(file,
+			       intel_memory_region_by_type(i915,
+							   INTEL_MEMORY_SYSTEM),
 			       &args->size, &args->handle);
 }
 
@@ -631,11 +671,12 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		user_data += page_length;
 		offset += page_length;
 	}
+
+	intel_gt_flush_ggtt_writes(ggtt->vm.gt);
 	i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
 
 	i915_gem_object_unlock_fence(obj, fence);
 out_unpin:
-	intel_gt_flush_ggtt_writes(ggtt->vm.gt);
 	if (drm_mm_node_allocated(&node)) {
 		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
 		remove_mappable_node(ggtt, &node);
@@ -855,7 +896,7 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 
 	list_for_each_entry_safe(obj, on,
 				 &i915->ggtt.userfault_list, userfault_link)
-		__i915_gem_object_release_mmap(obj);
+		__i915_gem_object_release_mmap_gtt(obj);
 
 	/*
 	 * The fence will be lost when the device powers down. If any were
@@ -892,22 +933,8 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 u64 alignment,
 			 u64 flags)
 {
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-	struct i915_address_space *vm = &dev_priv->ggtt.vm;
-
-	return i915_gem_object_pin(obj, vm, view, size, alignment,
-				   flags | PIN_GLOBAL);
-}
-
-struct i915_vma *
-i915_gem_object_pin(struct drm_i915_gem_object *obj,
-		    struct i915_address_space *vm,
-		    const struct i915_ggtt_view *view,
-		    u64 size,
-		    u64 alignment,
-		    u64 flags)
-{
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct i915_vma *vma;
 	int ret;
 
@@ -916,17 +943,19 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
-		/* If the required space is larger than the available
+		/*
+		 * If the required space is larger than the available
 		 * aperture, we will not able to find a slot for the
 		 * object and unbinding the object now will be in
 		 * vain. Worse, doing so may cause us to ping-pong
 		 * the object in and out of the Global GTT and
 		 * waste a lot of cycles under the mutex.
 		 */
-		if (obj->base.size > dev_priv->ggtt.mappable_end)
+		if (obj->base.size > ggtt->mappable_end)
 			return ERR_PTR(-E2BIG);
 
-		/* If NONBLOCK is set the caller is optimistically
+		/*
+		 * If NONBLOCK is set the caller is optimistically
 		 * trying to cache the full object within the mappable
 		 * aperture, and *must* have a fallback in place for
 		 * situations where we cannot bind the object. We
@@ -942,11 +971,11 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 		 * we could try to minimise harm to others.
 		 */
 		if (flags & PIN_NONBLOCK &&
-		    obj->base.size > dev_priv->ggtt.mappable_end / 2)
+		    obj->base.size > ggtt->mappable_end / 2)
 			return ERR_PTR(-ENOSPC);
 	}
 
-	vma = i915_vma_instance(obj, vm, view);
+	vma = i915_vma_instance(obj, &ggtt->vm, view);
 	if (IS_ERR(vma))
 		return vma;
 
@@ -956,7 +985,7 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 				return ERR_PTR(-ENOSPC);
 
 			if (flags & PIN_MAPPABLE &&
-			    vma->fence_size > dev_priv->ggtt.mappable_end / 2)
+			    vma->fence_size > ggtt->mappable_end / 2)
 				return ERR_PTR(-ENOSPC);
 		}
 
@@ -966,14 +995,14 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 	}
 
 	if (vma->fence && !i915_gem_object_is_tiled(obj)) {
-		mutex_lock(&vma->vm->mutex);
+		mutex_lock(&ggtt->vm.mutex);
 		ret = i915_vma_revoke_fence(vma);
-		mutex_unlock(&vma->vm->mutex);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (ret)
 			return ERR_PTR(ret);
 	}
 
-	ret = i915_vma_pin(vma, size, alignment, flags);
+	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -1054,172 +1083,6 @@ out:
 	return err;
 }
 
-static int __intel_context_flush_retire(struct intel_context *ce)
-{
-	struct intel_timeline *tl;
-
-	tl = intel_context_timeline_lock(ce);
-	if (IS_ERR(tl))
-		return PTR_ERR(tl);
-
-	intel_context_timeline_unlock(tl);
-	return 0;
-}
-
-static int __intel_engines_record_defaults(struct intel_gt *gt)
-{
-	struct i915_request *requests[I915_NUM_ENGINES] = {};
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err = 0;
-
-	/*
-	 * As we reset the gpu during very early sanitisation, the current
-	 * register state on the GPU should reflect its defaults values.
-	 * We load a context onto the hw (with restore-inhibit), then switch
-	 * over to a second context to save that default register state. We
-	 * can then prime every new context with that state so they all start
-	 * from the same default HW values.
-	 */
-
-	for_each_engine(engine, gt, id) {
-		struct intel_context *ce;
-		struct i915_request *rq;
-
-		/* We must be able to switch to something! */
-		GEM_BUG_ON(!engine->kernel_context);
-		engine->serial++; /* force the kernel context switch */
-
-		ce = intel_context_create(engine->kernel_context->gem_context,
-					  engine);
-		if (IS_ERR(ce)) {
-			err = PTR_ERR(ce);
-			goto out;
-		}
-
-		rq = intel_context_create_request(ce);
-		if (IS_ERR(rq)) {
-			err = PTR_ERR(rq);
-			intel_context_put(ce);
-			goto out;
-		}
-
-		err = intel_engine_emit_ctx_wa(rq);
-		if (err)
-			goto err_rq;
-
-		err = intel_renderstate_emit(rq);
-		if (err)
-			goto err_rq;
-
-err_rq:
-		requests[id] = i915_request_get(rq);
-		i915_request_add(rq);
-		if (err)
-			goto out;
-	}
-
-	/* Flush the default context image to memory, and enable powersaving. */
-	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
-		err = -EIO;
-		goto out;
-	}
-
-	for (id = 0; id < ARRAY_SIZE(requests); id++) {
-		struct i915_request *rq;
-		struct i915_vma *state;
-		void *vaddr;
-
-		rq = requests[id];
-		if (!rq)
-			continue;
-
-		GEM_BUG_ON(!test_bit(CONTEXT_ALLOC_BIT,
-				     &rq->hw_context->flags));
-		state = rq->hw_context->state;
-		if (!state)
-			continue;
-
-		/* Serialise with retirement on another CPU */
-		err = __intel_context_flush_retire(rq->hw_context);
-		if (err)
-			goto out;
-
-		/* We want to be able to unbind the state from the GGTT */
-		GEM_BUG_ON(intel_context_is_pinned(rq->hw_context));
-
-		/*
-		 * As we will hold a reference to the logical state, it will
-		 * not be torn down with the context, and importantly the
-		 * object will hold onto its vma (making it possible for a
-		 * stray GTT write to corrupt our defaults). Unmap the vma
-		 * from the GTT to prevent such accidents and reclaim the
-		 * space.
-		 */
-		err = i915_vma_unbind(state);
-		if (err)
-			goto out;
-
-		i915_gem_object_lock(state->obj);
-		err = i915_gem_object_set_to_cpu_domain(state->obj, false);
-		i915_gem_object_unlock(state->obj);
-		if (err)
-			goto out;
-
-		i915_gem_object_set_cache_coherency(state->obj, I915_CACHE_LLC);
-
-		/* Check we can acquire the image of the context state */
-		vaddr = i915_gem_object_pin_map(state->obj, I915_MAP_FORCE_WB);
-		if (IS_ERR(vaddr)) {
-			err = PTR_ERR(vaddr);
-			goto out;
-		}
-
-		rq->engine->default_state = i915_gem_object_get(state->obj);
-		i915_gem_object_unpin_map(state->obj);
-	}
-
-out:
-	/*
-	 * If we have to abandon now, we expect the engines to be idle
-	 * and ready to be torn-down. The quickest way we can accomplish
-	 * this is by declaring ourselves wedged.
-	 */
-	if (err)
-		intel_gt_set_wedged(gt);
-
-	for (id = 0; id < ARRAY_SIZE(requests); id++) {
-		struct intel_context *ce;
-		struct i915_request *rq;
-
-		rq = requests[id];
-		if (!rq)
-			continue;
-
-		ce = rq->hw_context;
-		i915_request_put(rq);
-		intel_context_put(ce);
-	}
-	return err;
-}
-
-static int intel_engines_verify_workarounds(struct intel_gt *gt)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err = 0;
-
-	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-		return 0;
-
-	for_each_engine(engine, gt, id) {
-		if (intel_engine_verify_workarounds(engine, "load"))
-			err = -EIO;
-	}
-
-	return err;
-}
-
 int i915_gem_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
@@ -1229,8 +1092,6 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		mkwrite_device_info(dev_priv)->page_sizes =
 			I915_GTT_PAGE_SIZE_4K;
 
-	intel_timelines_init(dev_priv);
-
 	ret = i915_gem_init_userptr(dev_priv);
 	if (ret)
 		return ret;
@@ -1238,51 +1099,12 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	intel_uc_fetch_firmwares(&dev_priv->gt.uc);
 	intel_wopcm_init(&dev_priv->wopcm);
 
-	/* This is just a security blanket to placate dragons.
-	 * On some systems, we very sporadically observe that the first TLBs
-	 * used by the CS may be stale, despite us poking the TLB reset. If
-	 * we hold the forcewake during initialisation these problems
-	 * just magically go away.
-	 */
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
 	ret = i915_init_ggtt(dev_priv);
 	if (ret) {
 		GEM_BUG_ON(ret == -EIO);
 		goto err_unlock;
 	}
 
-	intel_gt_init(&dev_priv->gt);
-
-	ret = intel_engines_setup(&dev_priv->gt);
-	if (ret) {
-		GEM_BUG_ON(ret == -EIO);
-		goto err_unlock;
-	}
-
-	ret = i915_gem_init_contexts(dev_priv);
-	if (ret) {
-		GEM_BUG_ON(ret == -EIO);
-		goto err_scratch;
-	}
-
-	ret = intel_engines_init(&dev_priv->gt);
-	if (ret) {
-		GEM_BUG_ON(ret == -EIO);
-		goto err_context;
-	}
-
-	intel_uc_init(&dev_priv->gt.uc);
-
-	ret = intel_gt_init_hw(&dev_priv->gt);
-	if (ret)
-		goto err_uc_init;
-
-	/* Only when the HW is re-initialised, can we replay the requests */
-	ret = intel_gt_resume(&dev_priv->gt);
-	if (ret)
-		goto err_init_hw;
-
 	/*
 	 * Despite its name intel_init_clock_gating applies both display
 	 * clock gating workarounds; GT mmio workarounds and the occasional
@@ -1294,23 +1116,9 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 */
 	intel_init_clock_gating(dev_priv);
 
-	ret = intel_engines_verify_workarounds(&dev_priv->gt);
+	ret = intel_gt_init(&dev_priv->gt);
 	if (ret)
-		goto err_gt;
-
-	ret = __intel_engines_record_defaults(&dev_priv->gt);
-	if (ret)
-		goto err_gt;
-
-	ret = i915_inject_probe_error(dev_priv, -ENODEV);
-	if (ret)
-		goto err_gt;
-
-	ret = i915_inject_probe_error(dev_priv, -EIO);
-	if (ret)
-		goto err_gt;
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
+		goto err_unlock;
 
 	return 0;
 
@@ -1320,31 +1128,12 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 * HW as irrevisibly wedged, but keep enough state around that the
 	 * driver doesn't explode during runtime.
 	 */
-err_gt:
-	intel_gt_set_wedged_on_init(&dev_priv->gt);
-	i915_gem_suspend(dev_priv);
-	i915_gem_suspend_late(dev_priv);
-
-	i915_gem_drain_workqueue(dev_priv);
-err_init_hw:
-	intel_uc_fini_hw(&dev_priv->gt.uc);
-err_uc_init:
-	if (ret != -EIO) {
-		intel_uc_fini(&dev_priv->gt.uc);
-		intel_engines_cleanup(&dev_priv->gt);
-	}
-err_context:
-	if (ret != -EIO)
-		i915_gem_driver_release__contexts(dev_priv);
-err_scratch:
-	intel_gt_driver_release(&dev_priv->gt);
 err_unlock:
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
+	i915_gem_drain_workqueue(dev_priv);
 
 	if (ret != -EIO) {
 		intel_uc_cleanup_firmwares(&dev_priv->gt.uc);
 		i915_gem_cleanup_userptr(dev_priv);
-		intel_timelines_fini(dev_priv);
 	}
 
 	if (ret == -EIO) {
@@ -1388,27 +1177,24 @@ void i915_gem_driver_remove(struct drm_i915_private *dev_priv)
 
 	i915_gem_suspend_late(dev_priv);
 	intel_gt_driver_remove(&dev_priv->gt);
+	dev_priv->uabi_engines = RB_ROOT;
 
 	/* Flush any outstanding unpin_work. */
 	i915_gem_drain_workqueue(dev_priv);
 
-	intel_uc_fini_hw(&dev_priv->gt.uc);
-	intel_uc_fini(&dev_priv->gt.uc);
-
 	i915_gem_drain_freed_objects(dev_priv);
 }
 
 void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 {
-	intel_engines_cleanup(&dev_priv->gt);
 	i915_gem_driver_release__contexts(dev_priv);
+
 	intel_gt_driver_release(&dev_priv->gt);
 
 	intel_wa_list_free(&dev_priv->gt_wa_list);
 
 	intel_uc_cleanup_firmwares(&dev_priv->gt.uc);
 	i915_gem_cleanup_userptr(dev_priv);
-	intel_timelines_fini(dev_priv);
 
 	i915_gem_drain_freed_objects(dev_priv);
 
@@ -1430,6 +1216,7 @@ static void i915_gem_init__mm(struct drm_i915_private *i915)
 void i915_gem_init_early(struct drm_i915_private *dev_priv)
 {
 	i915_gem_init__mm(dev_priv);
+	i915_gem_init__contexts(dev_priv);
 
 	spin_lock_init(&dev_priv->fb_tracking.lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index f6f9675848b8..1753c84d6c0d 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -30,15 +30,18 @@
 
 #include <drm/drm_drv.h>
 
+#include "i915_utils.h"
+
 struct drm_i915_private;
 
 #ifdef CONFIG_DRM_I915_DEBUG_GEM
 
-#define GEM_SHOW_DEBUG() (drm_debug & DRM_UT_DRIVER)
+#define GEM_SHOW_DEBUG() drm_debug_enabled(DRM_UT_DRIVER)
 
 #define GEM_BUG_ON(condition) do { if (unlikely((condition))) {	\
 		GEM_TRACE_ERR("%s:%d GEM_BUG_ON(%s)\n", \
 			      __func__, __LINE__, __stringify(condition)); \
+		GEM_TRACE_DUMP(); \
 		BUG(); \
 		} \
 	} while(0)
@@ -68,9 +71,10 @@ struct drm_i915_private;
 	pr_err(__VA_ARGS__);						\
 	trace_printk(__VA_ARGS__);					\
 } while (0)
-#define GEM_TRACE_DUMP() ftrace_dump(DUMP_ALL)
+#define GEM_TRACE_DUMP() \
+	do { ftrace_dump(DUMP_ALL); add_taint_for_CI(TAINT_WARN); } while (0)
 #define GEM_TRACE_DUMP_ON(expr) \
-	do { if (expr) ftrace_dump(DUMP_ALL); } while (0)
+	do { if (expr) GEM_TRACE_DUMP(); } while (0)
 #else
 #define GEM_TRACE(...) do { } while (0)
 #define GEM_TRACE_ERR(...) do { } while (0)
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 7e62c310290f..0697bedebeef 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -359,9 +359,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
  */
 int i915_gem_evict_vm(struct i915_address_space *vm)
 {
-	struct list_head eviction_list;
-	struct i915_vma *vma, *next;
-	int ret;
+	int ret = 0;
 
 	lockdep_assert_held(&vm->mutex);
 	trace_i915_gem_evict_vm(vm);
@@ -377,21 +375,30 @@ int i915_gem_evict_vm(struct i915_address_space *vm)
 			return ret;
 	}
 
-	INIT_LIST_HEAD(&eviction_list);
-	list_for_each_entry(vma, &vm->bound_list, vm_link) {
-		if (i915_vma_is_pinned(vma))
-			continue;
+	do {
+		struct i915_vma *vma, *vn;
+		LIST_HEAD(eviction_list);
 
-		__i915_vma_pin(vma);
-		list_add(&vma->evict_link, &eviction_list);
-	}
+		list_for_each_entry(vma, &vm->bound_list, vm_link) {
+			if (i915_vma_is_pinned(vma))
+				continue;
+
+			__i915_vma_pin(vma);
+			list_add(&vma->evict_link, &eviction_list);
+		}
+		if (list_empty(&eviction_list))
+			break;
+
+		ret = 0;
+		list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) {
+			__i915_vma_unpin(vma);
+			if (ret == 0)
+				ret = __i915_vma_unbind(vma);
+			if (ret != -EINTR) /* "Get me out of here!" */
+				ret = 0;
+		}
+	} while (ret == 0);
 
-	ret = 0;
-	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
-		__i915_vma_unpin(vma);
-		if (ret == 0)
-			ret = __i915_vma_unbind(vma);
-	}
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index 71efccfde122..d9c34a23cd67 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -412,6 +412,9 @@ int i915_vma_pin_fence(struct i915_vma *vma)
 {
 	int err;
 
+	if (!vma->fence && !i915_gem_object_is_tiled(vma->obj))
+		return 0;
+
 	/*
 	 * Note that we revoke fences on runtime suspend. Therefore the user
 	 * must keep the device awake whilst using the fence.
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index d6ce57d30958..e039eb56900f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1,26 +1,7 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright © 2010 Daniel Vetter
- * Copyright © 2011-2014 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
+ * Copyright © 2020 Intel Corporation
  */
 
 #include <linux/slab.h> /* fault-inject.h is not standalone! */
@@ -45,2098 +26,6 @@
 #include "i915_trace.h"
 #include "i915_vgpu.h"
 
-#define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
-
-#if IS_ENABLED(CONFIG_DRM_I915_TRACE_GTT)
-#define DBG(...) trace_printk(__VA_ARGS__)
-#else
-#define DBG(...)
-#endif
-
-/**
- * DOC: Global GTT views
- *
- * Background and previous state
- *
- * Historically objects could exists (be bound) in global GTT space only as
- * singular instances with a view representing all of the object's backing pages
- * in a linear fashion. This view will be called a normal view.
- *
- * To support multiple views of the same object, where the number of mapped
- * pages is not equal to the backing store, or where the layout of the pages
- * is not linear, concept of a GGTT view was added.
- *
- * One example of an alternative view is a stereo display driven by a single
- * image. In this case we would have a framebuffer looking like this
- * (2x2 pages):
- *
- *    12
- *    34
- *
- * Above would represent a normal GGTT view as normally mapped for GPU or CPU
- * rendering. In contrast, fed to the display engine would be an alternative
- * view which could look something like this:
- *
- *   1212
- *   3434
- *
- * In this example both the size and layout of pages in the alternative view is
- * different from the normal view.
- *
- * Implementation and usage
- *
- * GGTT views are implemented using VMAs and are distinguished via enum
- * i915_ggtt_view_type and struct i915_ggtt_view.
- *
- * A new flavour of core GEM functions which work with GGTT bound objects were
- * added with the _ggtt_ infix, and sometimes with _view postfix to avoid
- * renaming  in large amounts of code. They take the struct i915_ggtt_view
- * parameter encapsulating all metadata required to implement a view.
- *
- * As a helper for callers which are only interested in the normal view,
- * globally const i915_ggtt_view_normal singleton instance exists. All old core
- * GEM API functions, the ones not taking the view parameter, are operating on,
- * or with the normal GGTT view.
- *
- * Code wanting to add or use a new GGTT view needs to:
- *
- * 1. Add a new enum with a suitable name.
- * 2. Extend the metadata in the i915_ggtt_view structure if required.
- * 3. Add support to i915_get_vma_pages().
- *
- * New views are required to build a scatter-gather table from within the
- * i915_get_vma_pages function. This table is stored in the vma.ggtt_view and
- * exists for the lifetime of an VMA.
- *
- * Core API is designed to have copy semantics which means that passed in
- * struct i915_ggtt_view does not need to be persistent (left around after
- * calling the core API functions).
- *
- */
-
-#define as_pd(x) container_of((x), typeof(struct i915_page_directory), pt)
-
-static int
-i915_get_ggtt_vma_pages(struct i915_vma *vma);
-
-static void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
-{
-	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
-
-	/*
-	 * Note that as an uncached mmio write, this will flush the
-	 * WCB of the writes into the GGTT before it triggers the invalidate.
-	 */
-	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
-}
-
-static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
-{
-	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
-	struct drm_i915_private *i915 = ggtt->vm.i915;
-
-	gen6_ggtt_invalidate(ggtt);
-
-	if (INTEL_GEN(i915) >= 12)
-		intel_uncore_write_fw(uncore, GEN12_GUC_TLB_INV_CR,
-				      GEN12_GUC_TLB_INV_CR_INVALIDATE);
-	else
-		intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE);
-}
-
-static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
-{
-	intel_gtt_chipset_flush();
-}
-
-static int ppgtt_bind_vma(struct i915_vma *vma,
-			  enum i915_cache_level cache_level,
-			  u32 flags)
-{
-	u32 pte_flags;
-	int err;
-
-	if (flags & I915_VMA_ALLOC) {
-		err = vma->vm->allocate_va_range(vma->vm,
-						 vma->node.start, vma->size);
-		if (err)
-			return err;
-
-		set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
-	}
-
-	/* Applicable to VLV, and gen8+ */
-	pte_flags = 0;
-	if (i915_gem_object_is_readonly(vma->obj))
-		pte_flags |= PTE_READ_ONLY;
-
-	GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)));
-	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-	wmb();
-
-	return 0;
-}
-
-static void ppgtt_unbind_vma(struct i915_vma *vma)
-{
-	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)))
-		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-}
-
-static int ppgtt_set_pages(struct i915_vma *vma)
-{
-	GEM_BUG_ON(vma->pages);
-
-	vma->pages = vma->obj->mm.pages;
-
-	vma->page_sizes = vma->obj->mm.page_sizes;
-
-	return 0;
-}
-
-static void clear_pages(struct i915_vma *vma)
-{
-	GEM_BUG_ON(!vma->pages);
-
-	if (vma->pages != vma->obj->mm.pages) {
-		sg_free_table(vma->pages);
-		kfree(vma->pages);
-	}
-	vma->pages = NULL;
-
-	memset(&vma->page_sizes, 0, sizeof(vma->page_sizes));
-}
-
-static u64 gen8_pte_encode(dma_addr_t addr,
-			   enum i915_cache_level level,
-			   u32 flags)
-{
-	gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
-
-	if (unlikely(flags & PTE_READ_ONLY))
-		pte &= ~_PAGE_RW;
-
-	switch (level) {
-	case I915_CACHE_NONE:
-		pte |= PPAT_UNCACHED;
-		break;
-	case I915_CACHE_WT:
-		pte |= PPAT_DISPLAY_ELLC;
-		break;
-	default:
-		pte |= PPAT_CACHED;
-		break;
-	}
-
-	return pte;
-}
-
-static u64 gen8_pde_encode(const dma_addr_t addr,
-			   const enum i915_cache_level level)
-{
-	u64 pde = _PAGE_PRESENT | _PAGE_RW;
-	pde |= addr;
-	if (level != I915_CACHE_NONE)
-		pde |= PPAT_CACHED_PDE;
-	else
-		pde |= PPAT_UNCACHED;
-	return pde;
-}
-
-static u64 snb_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= GEN6_PTE_ADDR_ENCODE(addr);
-
-	switch (level) {
-	case I915_CACHE_L3_LLC:
-	case I915_CACHE_LLC:
-		pte |= GEN6_PTE_CACHE_LLC;
-		break;
-	case I915_CACHE_NONE:
-		pte |= GEN6_PTE_UNCACHED;
-		break;
-	default:
-		MISSING_CASE(level);
-	}
-
-	return pte;
-}
-
-static u64 ivb_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= GEN6_PTE_ADDR_ENCODE(addr);
-
-	switch (level) {
-	case I915_CACHE_L3_LLC:
-		pte |= GEN7_PTE_CACHE_L3_LLC;
-		break;
-	case I915_CACHE_LLC:
-		pte |= GEN6_PTE_CACHE_LLC;
-		break;
-	case I915_CACHE_NONE:
-		pte |= GEN6_PTE_UNCACHED;
-		break;
-	default:
-		MISSING_CASE(level);
-	}
-
-	return pte;
-}
-
-static u64 byt_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= GEN6_PTE_ADDR_ENCODE(addr);
-
-	if (!(flags & PTE_READ_ONLY))
-		pte |= BYT_PTE_WRITEABLE;
-
-	if (level != I915_CACHE_NONE)
-		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
-
-	return pte;
-}
-
-static u64 hsw_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= HSW_PTE_ADDR_ENCODE(addr);
-
-	if (level != I915_CACHE_NONE)
-		pte |= HSW_WB_LLC_AGE3;
-
-	return pte;
-}
-
-static u64 iris_pte_encode(dma_addr_t addr,
-			   enum i915_cache_level level,
-			   u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= HSW_PTE_ADDR_ENCODE(addr);
-
-	switch (level) {
-	case I915_CACHE_NONE:
-		break;
-	case I915_CACHE_WT:
-		pte |= HSW_WT_ELLC_LLC_AGE3;
-		break;
-	default:
-		pte |= HSW_WB_ELLC_LLC_AGE3;
-		break;
-	}
-
-	return pte;
-}
-
-static void stash_init(struct pagestash *stash)
-{
-	pagevec_init(&stash->pvec);
-	spin_lock_init(&stash->lock);
-}
-
-static struct page *stash_pop_page(struct pagestash *stash)
-{
-	struct page *page = NULL;
-
-	spin_lock(&stash->lock);
-	if (likely(stash->pvec.nr))
-		page = stash->pvec.pages[--stash->pvec.nr];
-	spin_unlock(&stash->lock);
-
-	return page;
-}
-
-static void stash_push_pagevec(struct pagestash *stash, struct pagevec *pvec)
-{
-	unsigned int nr;
-
-	spin_lock_nested(&stash->lock, SINGLE_DEPTH_NESTING);
-
-	nr = min_t(typeof(nr), pvec->nr, pagevec_space(&stash->pvec));
-	memcpy(stash->pvec.pages + stash->pvec.nr,
-	       pvec->pages + pvec->nr - nr,
-	       sizeof(pvec->pages[0]) * nr);
-	stash->pvec.nr += nr;
-
-	spin_unlock(&stash->lock);
-
-	pvec->nr -= nr;
-}
-
-static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
-{
-	struct pagevec stack;
-	struct page *page;
-
-	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
-		i915_gem_shrink_all(vm->i915);
-
-	page = stash_pop_page(&vm->free_pages);
-	if (page)
-		return page;
-
-	if (!vm->pt_kmap_wc)
-		return alloc_page(gfp);
-
-	/* Look in our global stash of WC pages... */
-	page = stash_pop_page(&vm->i915->mm.wc_stash);
-	if (page)
-		return page;
-
-	/*
-	 * Otherwise batch allocate pages to amortize cost of set_pages_wc.
-	 *
-	 * We have to be careful as page allocation may trigger the shrinker
-	 * (via direct reclaim) which will fill up the WC stash underneath us.
-	 * So we add our WB pages into a temporary pvec on the stack and merge
-	 * them into the WC stash after all the allocations are complete.
-	 */
-	pagevec_init(&stack);
-	do {
-		struct page *page;
-
-		page = alloc_page(gfp);
-		if (unlikely(!page))
-			break;
-
-		stack.pages[stack.nr++] = page;
-	} while (pagevec_space(&stack));
-
-	if (stack.nr && !set_pages_array_wc(stack.pages, stack.nr)) {
-		page = stack.pages[--stack.nr];
-
-		/* Merge spare WC pages to the global stash */
-		if (stack.nr)
-			stash_push_pagevec(&vm->i915->mm.wc_stash, &stack);
-
-		/* Push any surplus WC pages onto the local VM stash */
-		if (stack.nr)
-			stash_push_pagevec(&vm->free_pages, &stack);
-	}
-
-	/* Return unwanted leftovers */
-	if (unlikely(stack.nr)) {
-		WARN_ON_ONCE(set_pages_array_wb(stack.pages, stack.nr));
-		__pagevec_release(&stack);
-	}
-
-	return page;
-}
-
-static void vm_free_pages_release(struct i915_address_space *vm,
-				  bool immediate)
-{
-	struct pagevec *pvec = &vm->free_pages.pvec;
-	struct pagevec stack;
-
-	lockdep_assert_held(&vm->free_pages.lock);
-	GEM_BUG_ON(!pagevec_count(pvec));
-
-	if (vm->pt_kmap_wc) {
-		/*
-		 * When we use WC, first fill up the global stash and then
-		 * only if full immediately free the overflow.
-		 */
-		stash_push_pagevec(&vm->i915->mm.wc_stash, pvec);
-
-		/*
-		 * As we have made some room in the VM's free_pages,
-		 * we can wait for it to fill again. Unless we are
-		 * inside i915_address_space_fini() and must
-		 * immediately release the pages!
-		 */
-		if (pvec->nr <= (immediate ? 0 : PAGEVEC_SIZE - 1))
-			return;
-
-		/*
-		 * We have to drop the lock to allow ourselves to sleep,
-		 * so take a copy of the pvec and clear the stash for
-		 * others to use it as we sleep.
-		 */
-		stack = *pvec;
-		pagevec_reinit(pvec);
-		spin_unlock(&vm->free_pages.lock);
-
-		pvec = &stack;
-		set_pages_array_wb(pvec->pages, pvec->nr);
-
-		spin_lock(&vm->free_pages.lock);
-	}
-
-	__pagevec_release(pvec);
-}
-
-static void vm_free_page(struct i915_address_space *vm, struct page *page)
-{
-	/*
-	 * On !llc, we need to change the pages back to WB. We only do so
-	 * in bulk, so we rarely need to change the page attributes here,
-	 * but doing so requires a stop_machine() from deep inside arch/x86/mm.
-	 * To make detection of the possible sleep more likely, use an
-	 * unconditional might_sleep() for everybody.
-	 */
-	might_sleep();
-	spin_lock(&vm->free_pages.lock);
-	while (!pagevec_space(&vm->free_pages.pvec))
-		vm_free_pages_release(vm, false);
-	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec) >= PAGEVEC_SIZE);
-	pagevec_add(&vm->free_pages.pvec, page);
-	spin_unlock(&vm->free_pages.lock);
-}
-
-static void i915_address_space_fini(struct i915_address_space *vm)
-{
-	spin_lock(&vm->free_pages.lock);
-	if (pagevec_count(&vm->free_pages.pvec))
-		vm_free_pages_release(vm, true);
-	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec));
-	spin_unlock(&vm->free_pages.lock);
-
-	drm_mm_takedown(&vm->mm);
-
-	mutex_destroy(&vm->mutex);
-}
-
-void __i915_vm_close(struct i915_address_space *vm)
-{
-	struct i915_vma *vma, *vn;
-
-	mutex_lock(&vm->mutex);
-	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
-		struct drm_i915_gem_object *obj = vma->obj;
-
-		/* Keep the obj (and hence the vma) alive as _we_ destroy it */
-		if (!kref_get_unless_zero(&obj->base.refcount))
-			continue;
-
-		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
-		WARN_ON(__i915_vma_unbind(vma));
-		i915_vma_destroy(vma);
-
-		i915_gem_object_put(obj);
-	}
-	GEM_BUG_ON(!list_empty(&vm->bound_list));
-	mutex_unlock(&vm->mutex);
-}
-
-static void __i915_vm_release(struct work_struct *work)
-{
-	struct i915_address_space *vm =
-		container_of(work, struct i915_address_space, rcu.work);
-
-	vm->cleanup(vm);
-	i915_address_space_fini(vm);
-
-	kfree(vm);
-}
-
-void i915_vm_release(struct kref *kref)
-{
-	struct i915_address_space *vm =
-		container_of(kref, struct i915_address_space, ref);
-
-	GEM_BUG_ON(i915_is_ggtt(vm));
-	trace_i915_ppgtt_release(vm);
-
-	queue_rcu_work(vm->i915->wq, &vm->rcu);
-}
-
-static void i915_address_space_init(struct i915_address_space *vm, int subclass)
-{
-	kref_init(&vm->ref);
-	INIT_RCU_WORK(&vm->rcu, __i915_vm_release);
-	atomic_set(&vm->open, 1);
-
-	/*
-	 * The vm->mutex must be reclaim safe (for use in the shrinker).
-	 * Do a dummy acquire now under fs_reclaim so that any allocation
-	 * attempt holding the lock is immediately reported by lockdep.
-	 */
-	mutex_init(&vm->mutex);
-	lockdep_set_subclass(&vm->mutex, subclass);
-	i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex);
-
-	GEM_BUG_ON(!vm->total);
-	drm_mm_init(&vm->mm, 0, vm->total);
-	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
-
-	stash_init(&vm->free_pages);
-
-	INIT_LIST_HEAD(&vm->bound_list);
-}
-
-static int __setup_page_dma(struct i915_address_space *vm,
-			    struct i915_page_dma *p,
-			    gfp_t gfp)
-{
-	p->page = vm_alloc_page(vm, gfp | I915_GFP_ALLOW_FAIL);
-	if (unlikely(!p->page))
-		return -ENOMEM;
-
-	p->daddr = dma_map_page_attrs(vm->dma,
-				      p->page, 0, PAGE_SIZE,
-				      PCI_DMA_BIDIRECTIONAL,
-				      DMA_ATTR_SKIP_CPU_SYNC |
-				      DMA_ATTR_NO_WARN);
-	if (unlikely(dma_mapping_error(vm->dma, p->daddr))) {
-		vm_free_page(vm, p->page);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static int setup_page_dma(struct i915_address_space *vm,
-			  struct i915_page_dma *p)
-{
-	return __setup_page_dma(vm, p, __GFP_HIGHMEM);
-}
-
-static void cleanup_page_dma(struct i915_address_space *vm,
-			     struct i915_page_dma *p)
-{
-	dma_unmap_page(vm->dma, p->daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	vm_free_page(vm, p->page);
-}
-
-#define kmap_atomic_px(px) kmap_atomic(px_base(px)->page)
-
-static void
-fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count)
-{
-	kunmap_atomic(memset64(kmap_atomic(p->page), val, count));
-}
-
-#define fill_px(px, v) fill_page_dma(px_base(px), (v), PAGE_SIZE / sizeof(u64))
-#define fill32_px(px, v) do {						\
-	u64 v__ = lower_32_bits(v);					\
-	fill_px((px), v__ << 32 | v__);					\
-} while (0)
-
-static int
-setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
-{
-	unsigned long size;
-
-	/*
-	 * In order to utilize 64K pages for an object with a size < 2M, we will
-	 * need to support a 64K scratch page, given that every 16th entry for a
-	 * page-table operating in 64K mode must point to a properly aligned 64K
-	 * region, including any PTEs which happen to point to scratch.
-	 *
-	 * This is only relevant for the 48b PPGTT where we support
-	 * huge-gtt-pages, see also i915_vma_insert(). However, as we share the
-	 * scratch (read-only) between all vm, we create one 64k scratch page
-	 * for all.
-	 */
-	size = I915_GTT_PAGE_SIZE_4K;
-	if (i915_vm_is_4lvl(vm) &&
-	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) {
-		size = I915_GTT_PAGE_SIZE_64K;
-		gfp |= __GFP_NOWARN;
-	}
-	gfp |= __GFP_ZERO | __GFP_RETRY_MAYFAIL;
-
-	do {
-		unsigned int order = get_order(size);
-		struct page *page;
-		dma_addr_t addr;
-
-		page = alloc_pages(gfp, order);
-		if (unlikely(!page))
-			goto skip;
-
-		addr = dma_map_page_attrs(vm->dma,
-					  page, 0, size,
-					  PCI_DMA_BIDIRECTIONAL,
-					  DMA_ATTR_SKIP_CPU_SYNC |
-					  DMA_ATTR_NO_WARN);
-		if (unlikely(dma_mapping_error(vm->dma, addr)))
-			goto free_page;
-
-		if (unlikely(!IS_ALIGNED(addr, size)))
-			goto unmap_page;
-
-		vm->scratch[0].base.page = page;
-		vm->scratch[0].base.daddr = addr;
-		vm->scratch_order = order;
-		return 0;
-
-unmap_page:
-		dma_unmap_page(vm->dma, addr, size, PCI_DMA_BIDIRECTIONAL);
-free_page:
-		__free_pages(page, order);
-skip:
-		if (size == I915_GTT_PAGE_SIZE_4K)
-			return -ENOMEM;
-
-		size = I915_GTT_PAGE_SIZE_4K;
-		gfp &= ~__GFP_NOWARN;
-	} while (1);
-}
-
-static void cleanup_scratch_page(struct i915_address_space *vm)
-{
-	struct i915_page_dma *p = px_base(&vm->scratch[0]);
-	unsigned int order = vm->scratch_order;
-
-	dma_unmap_page(vm->dma, p->daddr, BIT(order) << PAGE_SHIFT,
-		       PCI_DMA_BIDIRECTIONAL);
-	__free_pages(p->page, order);
-}
-
-static void free_scratch(struct i915_address_space *vm)
-{
-	int i;
-
-	if (!px_dma(&vm->scratch[0])) /* set to 0 on clones */
-		return;
-
-	for (i = 1; i <= vm->top; i++) {
-		if (!px_dma(&vm->scratch[i]))
-			break;
-		cleanup_page_dma(vm, px_base(&vm->scratch[i]));
-	}
-
-	cleanup_scratch_page(vm);
-}
-
-static struct i915_page_table *alloc_pt(struct i915_address_space *vm)
-{
-	struct i915_page_table *pt;
-
-	pt = kmalloc(sizeof(*pt), I915_GFP_ALLOW_FAIL);
-	if (unlikely(!pt))
-		return ERR_PTR(-ENOMEM);
-
-	if (unlikely(setup_page_dma(vm, &pt->base))) {
-		kfree(pt);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	atomic_set(&pt->used, 0);
-	return pt;
-}
-
-static struct i915_page_directory *__alloc_pd(size_t sz)
-{
-	struct i915_page_directory *pd;
-
-	pd = kzalloc(sz, I915_GFP_ALLOW_FAIL);
-	if (unlikely(!pd))
-		return NULL;
-
-	spin_lock_init(&pd->lock);
-	return pd;
-}
-
-static struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
-{
-	struct i915_page_directory *pd;
-
-	pd = __alloc_pd(sizeof(*pd));
-	if (unlikely(!pd))
-		return ERR_PTR(-ENOMEM);
-
-	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
-		kfree(pd);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	return pd;
-}
-
-static void free_pd(struct i915_address_space *vm, struct i915_page_dma *pd)
-{
-	cleanup_page_dma(vm, pd);
-	kfree(pd);
-}
-
-#define free_px(vm, px) free_pd(vm, px_base(px))
-
-static inline void
-write_dma_entry(struct i915_page_dma * const pdma,
-		const unsigned short idx,
-		const u64 encoded_entry)
-{
-	u64 * const vaddr = kmap_atomic(pdma->page);
-
-	vaddr[idx] = encoded_entry;
-	kunmap_atomic(vaddr);
-}
-
-static inline void
-__set_pd_entry(struct i915_page_directory * const pd,
-	       const unsigned short idx,
-	       struct i915_page_dma * const to,
-	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level))
-{
-	/* Each thread pre-pins the pd, and we may have a thread per pde. */
-	GEM_BUG_ON(atomic_read(px_used(pd)) > 2 * ARRAY_SIZE(pd->entry));
-
-	atomic_inc(px_used(pd));
-	pd->entry[idx] = to;
-	write_dma_entry(px_base(pd), idx, encode(to->daddr, I915_CACHE_LLC));
-}
-
-#define set_pd_entry(pd, idx, to) \
-	__set_pd_entry((pd), (idx), px_base(to), gen8_pde_encode)
-
-static inline void
-clear_pd_entry(struct i915_page_directory * const pd,
-	       const unsigned short idx,
-	       const struct i915_page_scratch * const scratch)
-{
-	GEM_BUG_ON(atomic_read(px_used(pd)) == 0);
-
-	write_dma_entry(px_base(pd), idx, scratch->encode);
-	pd->entry[idx] = NULL;
-	atomic_dec(px_used(pd));
-}
-
-static bool
-release_pd_entry(struct i915_page_directory * const pd,
-		 const unsigned short idx,
-		 struct i915_page_table * const pt,
-		 const struct i915_page_scratch * const scratch)
-{
-	bool free = false;
-
-	if (atomic_add_unless(&pt->used, -1, 1))
-		return false;
-
-	spin_lock(&pd->lock);
-	if (atomic_dec_and_test(&pt->used)) {
-		clear_pd_entry(pd, idx, scratch);
-		free = true;
-	}
-	spin_unlock(&pd->lock);
-
-	return free;
-}
-
-static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
-{
-	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
-	enum vgt_g2v_type msg;
-	int i;
-
-	if (create)
-		atomic_inc(px_used(ppgtt->pd)); /* never remove */
-	else
-		atomic_dec(px_used(ppgtt->pd));
-
-	mutex_lock(&dev_priv->vgpu.lock);
-
-	if (i915_vm_is_4lvl(&ppgtt->vm)) {
-		const u64 daddr = px_dma(ppgtt->pd);
-
-		I915_WRITE(vgtif_reg(pdp[0].lo), lower_32_bits(daddr));
-		I915_WRITE(vgtif_reg(pdp[0].hi), upper_32_bits(daddr));
-
-		msg = (create ? VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE :
-				VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY);
-	} else {
-		for (i = 0; i < GEN8_3LVL_PDPES; i++) {
-			const u64 daddr = i915_page_dir_dma_addr(ppgtt, i);
-
-			I915_WRITE(vgtif_reg(pdp[i].lo), lower_32_bits(daddr));
-			I915_WRITE(vgtif_reg(pdp[i].hi), upper_32_bits(daddr));
-		}
-
-		msg = (create ? VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE :
-				VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY);
-	}
-
-	/* g2v_notify atomically (via hv trap) consumes the message packet. */
-	I915_WRITE(vgtif_reg(g2v_notify), msg);
-
-	mutex_unlock(&dev_priv->vgpu.lock);
-}
-
-/* Index shifts into the pagetable are offset by GEN8_PTE_SHIFT [12] */
-#define GEN8_PAGE_SIZE (SZ_4K) /* page and page-directory sizes are the same */
-#define GEN8_PTE_SHIFT (ilog2(GEN8_PAGE_SIZE))
-#define GEN8_PDES (GEN8_PAGE_SIZE / sizeof(u64))
-#define gen8_pd_shift(lvl) ((lvl) * ilog2(GEN8_PDES))
-#define gen8_pd_index(i, lvl) i915_pde_index((i), gen8_pd_shift(lvl))
-#define __gen8_pte_shift(lvl) (GEN8_PTE_SHIFT + gen8_pd_shift(lvl))
-#define __gen8_pte_index(a, lvl) i915_pde_index((a), __gen8_pte_shift(lvl))
-
-static inline unsigned int
-gen8_pd_range(u64 start, u64 end, int lvl, unsigned int *idx)
-{
-	const int shift = gen8_pd_shift(lvl);
-	const u64 mask = ~0ull << gen8_pd_shift(lvl + 1);
-
-	GEM_BUG_ON(start >= end);
-	end += ~mask >> gen8_pd_shift(1);
-
-	*idx = i915_pde_index(start, shift);
-	if ((start ^ end) & mask)
-		return GEN8_PDES - *idx;
-	else
-		return i915_pde_index(end, shift) - *idx;
-}
-
-static inline bool gen8_pd_contains(u64 start, u64 end, int lvl)
-{
-	const u64 mask = ~0ull << gen8_pd_shift(lvl + 1);
-
-	GEM_BUG_ON(start >= end);
-	return (start ^ end) & mask && (start & ~mask) == 0;
-}
-
-static inline unsigned int gen8_pt_count(u64 start, u64 end)
-{
-	GEM_BUG_ON(start >= end);
-	if ((start ^ end) >> gen8_pd_shift(1))
-		return GEN8_PDES - (start & (GEN8_PDES - 1));
-	else
-		return end - start;
-}
-
-static inline unsigned int gen8_pd_top_count(const struct i915_address_space *vm)
-{
-	unsigned int shift = __gen8_pte_shift(vm->top);
-	return (vm->total + (1ull << shift) - 1) >> shift;
-}
-
-static inline struct i915_page_directory *
-gen8_pdp_for_page_index(struct i915_address_space * const vm, const u64 idx)
-{
-	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
-
-	if (vm->top == 2)
-		return ppgtt->pd;
-	else
-		return i915_pd_entry(ppgtt->pd, gen8_pd_index(idx, vm->top));
-}
-
-static inline struct i915_page_directory *
-gen8_pdp_for_page_address(struct i915_address_space * const vm, const u64 addr)
-{
-	return gen8_pdp_for_page_index(vm, addr >> GEN8_PTE_SHIFT);
-}
-
-static void __gen8_ppgtt_cleanup(struct i915_address_space *vm,
-				 struct i915_page_directory *pd,
-				 int count, int lvl)
-{
-	if (lvl) {
-		void **pde = pd->entry;
-
-		do {
-			if (!*pde)
-				continue;
-
-			__gen8_ppgtt_cleanup(vm, *pde, GEN8_PDES, lvl - 1);
-		} while (pde++, --count);
-	}
-
-	free_px(vm, pd);
-}
-
-static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
-{
-	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-
-	if (intel_vgpu_active(vm->i915))
-		gen8_ppgtt_notify_vgt(ppgtt, false);
-
-	__gen8_ppgtt_cleanup(vm, ppgtt->pd, gen8_pd_top_count(vm), vm->top);
-	free_scratch(vm);
-}
-
-static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
-			      struct i915_page_directory * const pd,
-			      u64 start, const u64 end, int lvl)
-{
-	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
-	unsigned int idx, len;
-
-	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
-
-	len = gen8_pd_range(start, end, lvl--, &idx);
-	DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d }\n",
-	    __func__, vm, lvl + 1, start, end,
-	    idx, len, atomic_read(px_used(pd)));
-	GEM_BUG_ON(!len || len >= atomic_read(px_used(pd)));
-
-	do {
-		struct i915_page_table *pt = pd->entry[idx];
-
-		if (atomic_fetch_inc(&pt->used) >> gen8_pd_shift(1) &&
-		    gen8_pd_contains(start, end, lvl)) {
-			DBG("%s(%p):{ lvl:%d, idx:%d, start:%llx, end:%llx } removing pd\n",
-			    __func__, vm, lvl + 1, idx, start, end);
-			clear_pd_entry(pd, idx, scratch);
-			__gen8_ppgtt_cleanup(vm, as_pd(pt), I915_PDES, lvl);
-			start += (u64)I915_PDES << gen8_pd_shift(lvl);
-			continue;
-		}
-
-		if (lvl) {
-			start = __gen8_ppgtt_clear(vm, as_pd(pt),
-						   start, end, lvl);
-		} else {
-			unsigned int count;
-			u64 *vaddr;
-
-			count = gen8_pt_count(start, end);
-			DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d } removing pte\n",
-			    __func__, vm, lvl, start, end,
-			    gen8_pd_index(start, 0), count,
-			    atomic_read(&pt->used));
-			GEM_BUG_ON(!count || count >= atomic_read(&pt->used));
-
-			vaddr = kmap_atomic_px(pt);
-			memset64(vaddr + gen8_pd_index(start, 0),
-				 vm->scratch[0].encode,
-				 count);
-			kunmap_atomic(vaddr);
-
-			atomic_sub(count, &pt->used);
-			start += count;
-		}
-
-		if (release_pd_entry(pd, idx, pt, scratch))
-			free_px(vm, pt);
-	} while (idx++, --len);
-
-	return start;
-}
-
-static void gen8_ppgtt_clear(struct i915_address_space *vm,
-			     u64 start, u64 length)
-{
-	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
-	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
-	GEM_BUG_ON(range_overflows(start, length, vm->total));
-
-	start >>= GEN8_PTE_SHIFT;
-	length >>= GEN8_PTE_SHIFT;
-	GEM_BUG_ON(length == 0);
-
-	__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
-			   start, start + length, vm->top);
-}
-
-static int __gen8_ppgtt_alloc(struct i915_address_space * const vm,
-			      struct i915_page_directory * const pd,
-			      u64 * const start, const u64 end, int lvl)
-{
-	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
-	struct i915_page_table *alloc = NULL;
-	unsigned int idx, len;
-	int ret = 0;
-
-	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
-
-	len = gen8_pd_range(*start, end, lvl--, &idx);
-	DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d }\n",
-	    __func__, vm, lvl + 1, *start, end,
-	    idx, len, atomic_read(px_used(pd)));
-	GEM_BUG_ON(!len || (idx + len - 1) >> gen8_pd_shift(1));
-
-	spin_lock(&pd->lock);
-	GEM_BUG_ON(!atomic_read(px_used(pd))); /* Must be pinned! */
-	do {
-		struct i915_page_table *pt = pd->entry[idx];
-
-		if (!pt) {
-			spin_unlock(&pd->lock);
-
-			DBG("%s(%p):{ lvl:%d, idx:%d } allocating new tree\n",
-			    __func__, vm, lvl + 1, idx);
-
-			pt = fetch_and_zero(&alloc);
-			if (lvl) {
-				if (!pt) {
-					pt = &alloc_pd(vm)->pt;
-					if (IS_ERR(pt)) {
-						ret = PTR_ERR(pt);
-						goto out;
-					}
-				}
-
-				fill_px(pt, vm->scratch[lvl].encode);
-			} else {
-				if (!pt) {
-					pt = alloc_pt(vm);
-					if (IS_ERR(pt)) {
-						ret = PTR_ERR(pt);
-						goto out;
-					}
-				}
-
-				if (intel_vgpu_active(vm->i915) ||
-				    gen8_pt_count(*start, end) < I915_PDES)
-					fill_px(pt, vm->scratch[lvl].encode);
-			}
-
-			spin_lock(&pd->lock);
-			if (likely(!pd->entry[idx]))
-				set_pd_entry(pd, idx, pt);
-			else
-				alloc = pt, pt = pd->entry[idx];
-		}
-
-		if (lvl) {
-			atomic_inc(&pt->used);
-			spin_unlock(&pd->lock);
-
-			ret = __gen8_ppgtt_alloc(vm, as_pd(pt),
-						 start, end, lvl);
-			if (unlikely(ret)) {
-				if (release_pd_entry(pd, idx, pt, scratch))
-					free_px(vm, pt);
-				goto out;
-			}
-
-			spin_lock(&pd->lock);
-			atomic_dec(&pt->used);
-			GEM_BUG_ON(!atomic_read(&pt->used));
-		} else {
-			unsigned int count = gen8_pt_count(*start, end);
-
-			DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d } inserting pte\n",
-			    __func__, vm, lvl, *start, end,
-			    gen8_pd_index(*start, 0), count,
-			    atomic_read(&pt->used));
-
-			atomic_add(count, &pt->used);
-			/* All other pdes may be simultaneously removed */
-			GEM_BUG_ON(atomic_read(&pt->used) > 2 * I915_PDES);
-			*start += count;
-		}
-	} while (idx++, --len);
-	spin_unlock(&pd->lock);
-out:
-	if (alloc)
-		free_px(vm, alloc);
-	return ret;
-}
-
-static int gen8_ppgtt_alloc(struct i915_address_space *vm,
-			    u64 start, u64 length)
-{
-	u64 from;
-	int err;
-
-	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
-	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
-	GEM_BUG_ON(range_overflows(start, length, vm->total));
-
-	start >>= GEN8_PTE_SHIFT;
-	length >>= GEN8_PTE_SHIFT;
-	GEM_BUG_ON(length == 0);
-	from = start;
-
-	err = __gen8_ppgtt_alloc(vm, i915_vm_to_ppgtt(vm)->pd,
-				 &start, start + length, vm->top);
-	if (unlikely(err && from != start))
-		__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
-				   from, start, vm->top);
-
-	return err;
-}
-
-static inline struct sgt_dma {
-	struct scatterlist *sg;
-	dma_addr_t dma, max;
-} sgt_dma(struct i915_vma *vma) {
-	struct scatterlist *sg = vma->pages->sgl;
-	dma_addr_t addr = sg_dma_address(sg);
-	return (struct sgt_dma) { sg, addr, addr + sg->length };
-}
-
-static __always_inline u64
-gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
-		      struct i915_page_directory *pdp,
-		      struct sgt_dma *iter,
-		      u64 idx,
-		      enum i915_cache_level cache_level,
-		      u32 flags)
-{
-	struct i915_page_directory *pd;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
-	gen8_pte_t *vaddr;
-
-	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
-	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
-	do {
-		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
-		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
-
-		iter->dma += I915_GTT_PAGE_SIZE;
-		if (iter->dma >= iter->max) {
-			iter->sg = __sg_next(iter->sg);
-			if (!iter->sg) {
-				idx = 0;
-				break;
-			}
-
-			iter->dma = sg_dma_address(iter->sg);
-			iter->max = iter->dma + iter->sg->length;
-		}
-
-		if (gen8_pd_index(++idx, 0) == 0) {
-			if (gen8_pd_index(idx, 1) == 0) {
-				/* Limited by sg length for 3lvl */
-				if (gen8_pd_index(idx, 2) == 0)
-					break;
-
-				pd = pdp->entry[gen8_pd_index(idx, 2)];
-			}
-
-			kunmap_atomic(vaddr);
-			vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
-		}
-	} while (1);
-	kunmap_atomic(vaddr);
-
-	return idx;
-}
-
-static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
-				   struct sgt_dma *iter,
-				   enum i915_cache_level cache_level,
-				   u32 flags)
-{
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
-	u64 start = vma->node.start;
-	dma_addr_t rem = iter->sg->length;
-
-	GEM_BUG_ON(!i915_vm_is_4lvl(vma->vm));
-
-	do {
-		struct i915_page_directory * const pdp =
-			gen8_pdp_for_page_address(vma->vm, start);
-		struct i915_page_directory * const pd =
-			i915_pd_entry(pdp, __gen8_pte_index(start, 2));
-		gen8_pte_t encode = pte_encode;
-		unsigned int maybe_64K = -1;
-		unsigned int page_size;
-		gen8_pte_t *vaddr;
-		u16 index;
-
-		if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_2M &&
-		    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) &&
-		    rem >= I915_GTT_PAGE_SIZE_2M &&
-		    !__gen8_pte_index(start, 0)) {
-			index = __gen8_pte_index(start, 1);
-			encode |= GEN8_PDE_PS_2M;
-			page_size = I915_GTT_PAGE_SIZE_2M;
-
-			vaddr = kmap_atomic_px(pd);
-		} else {
-			struct i915_page_table *pt =
-				i915_pt_entry(pd, __gen8_pte_index(start, 1));
-
-			index = __gen8_pte_index(start, 0);
-			page_size = I915_GTT_PAGE_SIZE;
-
-			if (!index &&
-			    vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K &&
-			    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
-			    (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
-			     rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE))
-				maybe_64K = __gen8_pte_index(start, 1);
-
-			vaddr = kmap_atomic_px(pt);
-		}
-
-		do {
-			GEM_BUG_ON(iter->sg->length < page_size);
-			vaddr[index++] = encode | iter->dma;
-
-			start += page_size;
-			iter->dma += page_size;
-			rem -= page_size;
-			if (iter->dma >= iter->max) {
-				iter->sg = __sg_next(iter->sg);
-				if (!iter->sg)
-					break;
-
-				rem = iter->sg->length;
-				iter->dma = sg_dma_address(iter->sg);
-				iter->max = iter->dma + rem;
-
-				if (maybe_64K != -1 && index < I915_PDES &&
-				    !(IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
-				      (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
-				       rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE)))
-					maybe_64K = -1;
-
-				if (unlikely(!IS_ALIGNED(iter->dma, page_size)))
-					break;
-			}
-		} while (rem >= page_size && index < I915_PDES);
-
-		kunmap_atomic(vaddr);
-
-		/*
-		 * Is it safe to mark the 2M block as 64K? -- Either we have
-		 * filled whole page-table with 64K entries, or filled part of
-		 * it and have reached the end of the sg table and we have
-		 * enough padding.
-		 */
-		if (maybe_64K != -1 &&
-		    (index == I915_PDES ||
-		     (i915_vm_has_scratch_64K(vma->vm) &&
-		      !iter->sg && IS_ALIGNED(vma->node.start +
-					      vma->node.size,
-					      I915_GTT_PAGE_SIZE_2M)))) {
-			vaddr = kmap_atomic_px(pd);
-			vaddr[maybe_64K] |= GEN8_PDE_IPS_64K;
-			kunmap_atomic(vaddr);
-			page_size = I915_GTT_PAGE_SIZE_64K;
-
-			/*
-			 * We write all 4K page entries, even when using 64K
-			 * pages. In order to verify that the HW isn't cheating
-			 * by using the 4K PTE instead of the 64K PTE, we want
-			 * to remove all the surplus entries. If the HW skipped
-			 * the 64K PTE, it will read/write into the scratch page
-			 * instead - which we detect as missing results during
-			 * selftests.
-			 */
-			if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) {
-				u16 i;
-
-				encode = vma->vm->scratch[0].encode;
-				vaddr = kmap_atomic_px(i915_pt_entry(pd, maybe_64K));
-
-				for (i = 1; i < index; i += 16)
-					memset64(vaddr + i, encode, 15);
-
-				kunmap_atomic(vaddr);
-			}
-		}
-
-		vma->page_sizes.gtt |= page_size;
-	} while (iter->sg);
-}
-
-static void gen8_ppgtt_insert(struct i915_address_space *vm,
-			      struct i915_vma *vma,
-			      enum i915_cache_level cache_level,
-			      u32 flags)
-{
-	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
-	struct sgt_dma iter = sgt_dma(vma);
-
-	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
-		gen8_ppgtt_insert_huge(vma, &iter, cache_level, flags);
-	} else  {
-		u64 idx = vma->node.start >> GEN8_PTE_SHIFT;
-
-		do {
-			struct i915_page_directory * const pdp =
-				gen8_pdp_for_page_index(vm, idx);
-
-			idx = gen8_ppgtt_insert_pte(ppgtt, pdp, &iter, idx,
-						    cache_level, flags);
-		} while (idx);
-
-		vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
-	}
-}
-
-static int gen8_init_scratch(struct i915_address_space *vm)
-{
-	int ret;
-	int i;
-
-	/*
-	 * If everybody agrees to not to write into the scratch page,
-	 * we can reuse it for all vm, keeping contexts and processes separate.
-	 */
-	if (vm->has_read_only &&
-	    vm->i915->kernel_context &&
-	    vm->i915->kernel_context->vm) {
-		struct i915_address_space *clone =
-			rcu_dereference_protected(vm->i915->kernel_context->vm,
-						  true); /* static */
-
-		GEM_BUG_ON(!clone->has_read_only);
-
-		vm->scratch_order = clone->scratch_order;
-		memcpy(vm->scratch, clone->scratch, sizeof(vm->scratch));
-		px_dma(&vm->scratch[0]) = 0; /* no xfer of ownership */
-		return 0;
-	}
-
-	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
-	if (ret)
-		return ret;
-
-	vm->scratch[0].encode =
-		gen8_pte_encode(px_dma(&vm->scratch[0]),
-				I915_CACHE_LLC, vm->has_read_only);
-
-	for (i = 1; i <= vm->top; i++) {
-		if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[i]))))
-			goto free_scratch;
-
-		fill_px(&vm->scratch[i], vm->scratch[i - 1].encode);
-		vm->scratch[i].encode =
-			gen8_pde_encode(px_dma(&vm->scratch[i]),
-					I915_CACHE_LLC);
-	}
-
-	return 0;
-
-free_scratch:
-	free_scratch(vm);
-	return -ENOMEM;
-}
-
-static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
-{
-	struct i915_address_space *vm = &ppgtt->vm;
-	struct i915_page_directory *pd = ppgtt->pd;
-	unsigned int idx;
-
-	GEM_BUG_ON(vm->top != 2);
-	GEM_BUG_ON(gen8_pd_top_count(vm) != GEN8_3LVL_PDPES);
-
-	for (idx = 0; idx < GEN8_3LVL_PDPES; idx++) {
-		struct i915_page_directory *pde;
-
-		pde = alloc_pd(vm);
-		if (IS_ERR(pde))
-			return PTR_ERR(pde);
-
-		fill_px(pde, vm->scratch[1].encode);
-		set_pd_entry(pd, idx, pde);
-		atomic_inc(px_used(pde)); /* keep pinned */
-	}
-	wmb();
-
-	return 0;
-}
-
-static void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-
-	ppgtt->vm.gt = gt;
-	ppgtt->vm.i915 = i915;
-	ppgtt->vm.dma = &i915->drm.pdev->dev;
-	ppgtt->vm.total = BIT_ULL(INTEL_INFO(i915)->ppgtt_size);
-
-	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
-
-	ppgtt->vm.vma_ops.bind_vma    = ppgtt_bind_vma;
-	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
-	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
-	ppgtt->vm.vma_ops.clear_pages = clear_pages;
-}
-
-static struct i915_page_directory *
-gen8_alloc_top_pd(struct i915_address_space *vm)
-{
-	const unsigned int count = gen8_pd_top_count(vm);
-	struct i915_page_directory *pd;
-
-	GEM_BUG_ON(count > ARRAY_SIZE(pd->entry));
-
-	pd = __alloc_pd(offsetof(typeof(*pd), entry[count]));
-	if (unlikely(!pd))
-		return ERR_PTR(-ENOMEM);
-
-	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
-		kfree(pd);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	fill_page_dma(px_base(pd), vm->scratch[vm->top].encode, count);
-	atomic_inc(px_used(pd)); /* mark as pinned */
-	return pd;
-}
-
-/*
- * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
- * with a net effect resembling a 2-level page table in normal x86 terms. Each
- * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
- * space.
- *
- */
-static struct i915_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
-{
-	struct i915_ppgtt *ppgtt;
-	int err;
-
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return ERR_PTR(-ENOMEM);
-
-	ppgtt_init(ppgtt, &i915->gt);
-	ppgtt->vm.top = i915_vm_is_4lvl(&ppgtt->vm) ? 3 : 2;
-
-	/*
-	 * From bdw, there is hw support for read-only pages in the PPGTT.
-	 *
-	 * Gen11 has HSDES#:1807136187 unresolved. Disable ro support
-	 * for now.
-	 *
-	 * Gen12 has inherited the same read-only fault issue from gen11.
-	 */
-	ppgtt->vm.has_read_only = !IS_GEN_RANGE(i915, 11, 12);
-
-	/* There are only few exceptions for gen >=6. chv and bxt.
-	 * And we are not sure about the latter so play safe for now.
-	 */
-	if (IS_CHERRYVIEW(i915) || IS_BROXTON(i915))
-		ppgtt->vm.pt_kmap_wc = true;
-
-	err = gen8_init_scratch(&ppgtt->vm);
-	if (err)
-		goto err_free;
-
-	ppgtt->pd = gen8_alloc_top_pd(&ppgtt->vm);
-	if (IS_ERR(ppgtt->pd)) {
-		err = PTR_ERR(ppgtt->pd);
-		goto err_free_scratch;
-	}
-
-	if (!i915_vm_is_4lvl(&ppgtt->vm)) {
-		err = gen8_preallocate_top_level_pdp(ppgtt);
-		if (err)
-			goto err_free_pd;
-	}
-
-	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
-	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
-	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
-	ppgtt->vm.clear_range = gen8_ppgtt_clear;
-
-	if (intel_vgpu_active(i915))
-		gen8_ppgtt_notify_vgt(ppgtt, true);
-
-	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
-
-	return ppgtt;
-
-err_free_pd:
-	__gen8_ppgtt_cleanup(&ppgtt->vm, ppgtt->pd,
-			     gen8_pd_top_count(&ppgtt->vm), ppgtt->vm.top);
-err_free_scratch:
-	free_scratch(&ppgtt->vm);
-err_free:
-	kfree(ppgtt);
-	return ERR_PTR(err);
-}
-
-/* Write pde (index) from the page directory @pd to the page table @pt */
-static inline void gen6_write_pde(const struct gen6_ppgtt *ppgtt,
-				  const unsigned int pde,
-				  const struct i915_page_table *pt)
-{
-	/* Caller needs to make sure the write completes if necessary */
-	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
-		  ppgtt->pd_addr + pde);
-}
-
-static void gen7_ppgtt_enable(struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-	struct intel_uncore *uncore = gt->uncore;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	u32 ecochk;
-
-	intel_uncore_rmw(uncore, GAC_ECO_BITS, 0, ECOBITS_PPGTT_CACHE64B);
-
-	ecochk = intel_uncore_read(uncore, GAM_ECOCHK);
-	if (IS_HASWELL(i915)) {
-		ecochk |= ECOCHK_PPGTT_WB_HSW;
-	} else {
-		ecochk |= ECOCHK_PPGTT_LLC_IVB;
-		ecochk &= ~ECOCHK_PPGTT_GFDT_IVB;
-	}
-	intel_uncore_write(uncore, GAM_ECOCHK, ecochk);
-
-	for_each_engine(engine, gt, id) {
-		/* GFX_MODE is per-ring on gen7+ */
-		ENGINE_WRITE(engine,
-			     RING_MODE_GEN7,
-			     _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-	}
-}
-
-static void gen6_ppgtt_enable(struct intel_gt *gt)
-{
-	struct intel_uncore *uncore = gt->uncore;
-
-	intel_uncore_rmw(uncore,
-			 GAC_ECO_BITS,
-			 0,
-			 ECOBITS_SNB_BIT | ECOBITS_PPGTT_CACHE64B);
-
-	intel_uncore_rmw(uncore,
-			 GAB_CTL,
-			 0,
-			 GAB_CTL_CONT_AFTER_PAGEFAULT);
-
-	intel_uncore_rmw(uncore,
-			 GAM_ECOCHK,
-			 0,
-			 ECOCHK_SNB_BIT | ECOCHK_PPGTT_CACHE64B);
-
-	if (HAS_PPGTT(uncore->i915)) /* may be disabled for VT-d */
-		intel_uncore_write(uncore,
-				   GFX_MODE,
-				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-}
-
-/* PPGTT support for Sandybdrige/Gen6 and later */
-static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
-				   u64 start, u64 length)
-{
-	struct gen6_ppgtt * const ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
-	const unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
-	const gen6_pte_t scratch_pte = vm->scratch[0].encode;
-	unsigned int pde = first_entry / GEN6_PTES;
-	unsigned int pte = first_entry % GEN6_PTES;
-	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
-
-	while (num_entries) {
-		struct i915_page_table * const pt =
-			i915_pt_entry(ppgtt->base.pd, pde++);
-		const unsigned int count = min(num_entries, GEN6_PTES - pte);
-		gen6_pte_t *vaddr;
-
-		GEM_BUG_ON(px_base(pt) == px_base(&vm->scratch[1]));
-
-		num_entries -= count;
-
-		GEM_BUG_ON(count > atomic_read(&pt->used));
-		if (!atomic_sub_return(count, &pt->used))
-			ppgtt->scan_for_unused_pt = true;
-
-		/*
-		 * Note that the hw doesn't support removing PDE on the fly
-		 * (they are cached inside the context with no means to
-		 * invalidate the cache), so we can only reset the PTE
-		 * entries back to scratch.
-		 */
-
-		vaddr = kmap_atomic_px(pt);
-		memset32(vaddr + pte, scratch_pte, count);
-		kunmap_atomic(vaddr);
-
-		pte = 0;
-	}
-}
-
-static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
-				      struct i915_vma *vma,
-				      enum i915_cache_level cache_level,
-				      u32 flags)
-{
-	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-	struct i915_page_directory * const pd = ppgtt->pd;
-	unsigned first_entry = vma->node.start / I915_GTT_PAGE_SIZE;
-	unsigned act_pt = first_entry / GEN6_PTES;
-	unsigned act_pte = first_entry % GEN6_PTES;
-	const u32 pte_encode = vm->pte_encode(0, cache_level, flags);
-	struct sgt_dma iter = sgt_dma(vma);
-	gen6_pte_t *vaddr;
-
-	GEM_BUG_ON(pd->entry[act_pt] == &vm->scratch[1]);
-
-	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
-	do {
-		GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
-		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
-
-		iter.dma += I915_GTT_PAGE_SIZE;
-		if (iter.dma == iter.max) {
-			iter.sg = __sg_next(iter.sg);
-			if (!iter.sg)
-				break;
-
-			iter.dma = sg_dma_address(iter.sg);
-			iter.max = iter.dma + iter.sg->length;
-		}
-
-		if (++act_pte == GEN6_PTES) {
-			kunmap_atomic(vaddr);
-			vaddr = kmap_atomic_px(i915_pt_entry(pd, ++act_pt));
-			act_pte = 0;
-		}
-	} while (1);
-	kunmap_atomic(vaddr);
-
-	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
-}
-
-static int gen6_alloc_va_range(struct i915_address_space *vm,
-			       u64 start, u64 length)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
-	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_table *pt, *alloc = NULL;
-	intel_wakeref_t wakeref;
-	u64 from = start;
-	unsigned int pde;
-	bool flush = false;
-	int ret = 0;
-
-	wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
-
-	spin_lock(&pd->lock);
-	gen6_for_each_pde(pt, pd, start, length, pde) {
-		const unsigned int count = gen6_pte_count(start, length);
-
-		if (px_base(pt) == px_base(&vm->scratch[1])) {
-			spin_unlock(&pd->lock);
-
-			pt = fetch_and_zero(&alloc);
-			if (!pt)
-				pt = alloc_pt(vm);
-			if (IS_ERR(pt)) {
-				ret = PTR_ERR(pt);
-				goto unwind_out;
-			}
-
-			fill32_px(pt, vm->scratch[0].encode);
-
-			spin_lock(&pd->lock);
-			if (pd->entry[pde] == &vm->scratch[1]) {
-				pd->entry[pde] = pt;
-				if (i915_vma_is_bound(ppgtt->vma,
-						      I915_VMA_GLOBAL_BIND)) {
-					gen6_write_pde(ppgtt, pde, pt);
-					flush = true;
-				}
-			} else {
-				alloc = pt;
-				pt = pd->entry[pde];
-			}
-		}
-
-		atomic_add(count, &pt->used);
-	}
-	spin_unlock(&pd->lock);
-
-	if (flush)
-		gen6_ggtt_invalidate(vm->gt->ggtt);
-
-	goto out;
-
-unwind_out:
-	gen6_ppgtt_clear_range(vm, from, start - from);
-out:
-	if (alloc)
-		free_px(vm, alloc);
-	intel_runtime_pm_put(&vm->i915->runtime_pm, wakeref);
-	return ret;
-}
-
-static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
-{
-	struct i915_address_space * const vm = &ppgtt->base.vm;
-	struct i915_page_directory * const pd = ppgtt->base.pd;
-	int ret;
-
-	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
-	if (ret)
-		return ret;
-
-	vm->scratch[0].encode =
-		vm->pte_encode(px_dma(&vm->scratch[0]),
-			       I915_CACHE_NONE, PTE_READ_ONLY);
-
-	if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[1])))) {
-		cleanup_scratch_page(vm);
-		return -ENOMEM;
-	}
-
-	fill32_px(&vm->scratch[1], vm->scratch[0].encode);
-	memset_p(pd->entry, &vm->scratch[1], I915_PDES);
-
-	return 0;
-}
-
-static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)
-{
-	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_dma * const scratch =
-		px_base(&ppgtt->base.vm.scratch[1]);
-	struct i915_page_table *pt;
-	u32 pde;
-
-	gen6_for_all_pdes(pt, pd, pde)
-		if (px_base(pt) != scratch)
-			free_px(&ppgtt->base.vm, pt);
-}
-
-static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
-
-	i915_vma_destroy(ppgtt->vma);
-
-	gen6_ppgtt_free_pd(ppgtt);
-	free_scratch(vm);
-
-	mutex_destroy(&ppgtt->pin_mutex);
-	kfree(ppgtt->base.pd);
-}
-
-static int pd_vma_set_pages(struct i915_vma *vma)
-{
-	vma->pages = ERR_PTR(-ENODEV);
-	return 0;
-}
-
-static void pd_vma_clear_pages(struct i915_vma *vma)
-{
-	GEM_BUG_ON(!vma->pages);
-
-	vma->pages = NULL;
-}
-
-static int pd_vma_bind(struct i915_vma *vma,
-		       enum i915_cache_level cache_level,
-		       u32 unused)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vma->vm);
-	struct gen6_ppgtt *ppgtt = vma->private;
-	u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE;
-	struct i915_page_table *pt;
-	unsigned int pde;
-
-	px_base(ppgtt->base.pd)->ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);
-	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
-
-	gen6_for_all_pdes(pt, ppgtt->base.pd, pde)
-		gen6_write_pde(ppgtt, pde, pt);
-
-	gen6_ggtt_invalidate(ggtt);
-
-	return 0;
-}
-
-static void pd_vma_unbind(struct i915_vma *vma)
-{
-	struct gen6_ppgtt *ppgtt = vma->private;
-	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_dma * const scratch =
-		px_base(&ppgtt->base.vm.scratch[1]);
-	struct i915_page_table *pt;
-	unsigned int pde;
-
-	if (!ppgtt->scan_for_unused_pt)
-		return;
-
-	/* Free all no longer used page tables */
-	gen6_for_all_pdes(pt, ppgtt->base.pd, pde) {
-		if (px_base(pt) == scratch || atomic_read(&pt->used))
-			continue;
-
-		free_px(&ppgtt->base.vm, pt);
-		pd->entry[pde] = scratch;
-	}
-
-	ppgtt->scan_for_unused_pt = false;
-}
-
-static const struct i915_vma_ops pd_vma_ops = {
-	.set_pages = pd_vma_set_pages,
-	.clear_pages = pd_vma_clear_pages,
-	.bind_vma = pd_vma_bind,
-	.unbind_vma = pd_vma_unbind,
-};
-
-static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
-{
-	struct i915_ggtt *ggtt = ppgtt->base.vm.gt->ggtt;
-	struct i915_vma *vma;
-
-	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
-	GEM_BUG_ON(size > ggtt->vm.total);
-
-	vma = i915_vma_alloc();
-	if (!vma)
-		return ERR_PTR(-ENOMEM);
-
-	i915_active_init(&vma->active, NULL, NULL);
-
-	mutex_init(&vma->pages_mutex);
-	vma->vm = i915_vm_get(&ggtt->vm);
-	vma->ops = &pd_vma_ops;
-	vma->private = ppgtt;
-
-	vma->size = size;
-	vma->fence_size = size;
-	atomic_set(&vma->flags, I915_VMA_GGTT);
-	vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */
-
-	INIT_LIST_HEAD(&vma->obj_link);
-	INIT_LIST_HEAD(&vma->closed_link);
-
-	return vma;
-}
-
-int gen6_ppgtt_pin(struct i915_ppgtt *base)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
-	int err = 0;
-
-	GEM_BUG_ON(!atomic_read(&ppgtt->base.vm.open));
-
-	/*
-	 * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
-	 * which will be pinned into every active context.
-	 * (When vma->pin_count becomes atomic, I expect we will naturally
-	 * need a larger, unpacked, type and kill this redundancy.)
-	 */
-	if (atomic_add_unless(&ppgtt->pin_count, 1, 0))
-		return 0;
-
-	if (mutex_lock_interruptible(&ppgtt->pin_mutex))
-		return -EINTR;
-
-	/*
-	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
-	 * allocator works in address space sizes, so it's multiplied by page
-	 * size. We allocate at the top of the GTT to avoid fragmentation.
-	 */
-	if (!atomic_read(&ppgtt->pin_count)) {
-		err = i915_vma_pin(ppgtt->vma,
-				   0, GEN6_PD_ALIGN,
-				   PIN_GLOBAL | PIN_HIGH);
-	}
-	if (!err)
-		atomic_inc(&ppgtt->pin_count);
-	mutex_unlock(&ppgtt->pin_mutex);
-
-	return err;
-}
-
-void gen6_ppgtt_unpin(struct i915_ppgtt *base)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
-
-	GEM_BUG_ON(!atomic_read(&ppgtt->pin_count));
-	if (atomic_dec_and_test(&ppgtt->pin_count))
-		i915_vma_unpin(ppgtt->vma);
-}
-
-void gen6_ppgtt_unpin_all(struct i915_ppgtt *base)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
-
-	if (!atomic_read(&ppgtt->pin_count))
-		return;
-
-	i915_vma_unpin(ppgtt->vma);
-	atomic_set(&ppgtt->pin_count, 0);
-}
-
-static struct i915_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
-{
-	struct i915_ggtt * const ggtt = &i915->ggtt;
-	struct gen6_ppgtt *ppgtt;
-	int err;
-
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_init(&ppgtt->pin_mutex);
-
-	ppgtt_init(&ppgtt->base, &i915->gt);
-	ppgtt->base.vm.top = 1;
-
-	ppgtt->base.vm.bind_async_flags = I915_VMA_LOCAL_BIND;
-	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
-	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
-	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
-	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
-
-	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
-
-	ppgtt->base.pd = __alloc_pd(sizeof(*ppgtt->base.pd));
-	if (!ppgtt->base.pd) {
-		err = -ENOMEM;
-		goto err_free;
-	}
-
-	err = gen6_ppgtt_init_scratch(ppgtt);
-	if (err)
-		goto err_pd;
-
-	ppgtt->vma = pd_vma_create(ppgtt, GEN6_PD_SIZE);
-	if (IS_ERR(ppgtt->vma)) {
-		err = PTR_ERR(ppgtt->vma);
-		goto err_scratch;
-	}
-
-	return &ppgtt->base;
-
-err_scratch:
-	free_scratch(&ppgtt->base.vm);
-err_pd:
-	kfree(ppgtt->base.pd);
-err_free:
-	kfree(ppgtt);
-	return ERR_PTR(err);
-}
-
-static void gtt_write_workarounds(struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-	struct intel_uncore *uncore = gt->uncore;
-
-	/* This function is for gtt related workarounds. This function is
-	 * called on driver load and after a GPU reset, so you can place
-	 * workarounds here even if they get overwritten by GPU reset.
-	 */
-	/* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt,kbl,glk,cfl,cnl,icl */
-	if (IS_BROADWELL(i915))
-		intel_uncore_write(uncore,
-				   GEN8_L3_LRA_1_GPGPU,
-				   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW);
-	else if (IS_CHERRYVIEW(i915))
-		intel_uncore_write(uncore,
-				   GEN8_L3_LRA_1_GPGPU,
-				   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV);
-	else if (IS_GEN9_LP(i915))
-		intel_uncore_write(uncore,
-				   GEN8_L3_LRA_1_GPGPU,
-				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
-	else if (INTEL_GEN(i915) >= 9 && INTEL_GEN(i915) <= 11)
-		intel_uncore_write(uncore,
-				   GEN8_L3_LRA_1_GPGPU,
-				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
-
-	/*
-	 * To support 64K PTEs we need to first enable the use of the
-	 * Intermediate-Page-Size(IPS) bit of the PDE field via some magical
-	 * mmio, otherwise the page-walker will simply ignore the IPS bit. This
-	 * shouldn't be needed after GEN10.
-	 *
-	 * 64K pages were first introduced from BDW+, although technically they
-	 * only *work* from gen9+. For pre-BDW we instead have the option for
-	 * 32K pages, but we don't currently have any support for it in our
-	 * driver.
-	 */
-	if (HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_64K) &&
-	    INTEL_GEN(i915) <= 10)
-		intel_uncore_rmw(uncore,
-				 GEN8_GAMW_ECO_DEV_RW_IA,
-				 0,
-				 GAMW_ECO_ENABLE_64K_IPS_FIELD);
-
-	if (IS_GEN_RANGE(i915, 8, 11)) {
-		bool can_use_gtt_cache = true;
-
-		/*
-		 * According to the BSpec if we use 2M/1G pages then we also
-		 * need to disable the GTT cache. At least on BDW we can see
-		 * visual corruption when using 2M pages, and not disabling the
-		 * GTT cache.
-		 */
-		if (HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_2M))
-			can_use_gtt_cache = false;
-
-		/* WaGttCachingOffByDefault */
-		intel_uncore_write(uncore,
-				   HSW_GTT_CACHE_EN,
-				   can_use_gtt_cache ? GTT_CACHE_EN_ALL : 0);
-		WARN_ON_ONCE(can_use_gtt_cache &&
-			     intel_uncore_read(uncore,
-					       HSW_GTT_CACHE_EN) == 0);
-	}
-}
-
-int i915_ppgtt_init_hw(struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-
-	gtt_write_workarounds(gt);
-
-	if (IS_GEN(i915, 6))
-		gen6_ppgtt_enable(gt);
-	else if (IS_GEN(i915, 7))
-		gen7_ppgtt_enable(gt);
-
-	return 0;
-}
-
-static struct i915_ppgtt *
-__ppgtt_create(struct drm_i915_private *i915)
-{
-	if (INTEL_GEN(i915) < 8)
-		return gen6_ppgtt_create(i915);
-	else
-		return gen8_ppgtt_create(i915);
-}
-
-struct i915_ppgtt *
-i915_ppgtt_create(struct drm_i915_private *i915)
-{
-	struct i915_ppgtt *ppgtt;
-
-	ppgtt = __ppgtt_create(i915);
-	if (IS_ERR(ppgtt))
-		return ppgtt;
-
-	trace_i915_ppgtt_create(&ppgtt->vm);
-
-	return ppgtt;
-}
-
-/* Certain Gen5 chipsets require require idling the GPU before
- * unmapping anything from the GTT when VT-d is enabled.
- */
-static bool needs_idle_maps(struct drm_i915_private *dev_priv)
-{
-	/* Query intel_iommu to see if we need the workaround. Presumably that
-	 * was loaded first.
-	 */
-	return IS_GEN(dev_priv, 5) && IS_MOBILE(dev_priv) && intel_vtd_active();
-}
-
-static void ggtt_suspend_mappings(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *i915 = ggtt->vm.i915;
-
-	/* Don't bother messing with faults pre GEN6 as we have little
-	 * documentation supporting that it's a good idea.
-	 */
-	if (INTEL_GEN(i915) < 6)
-		return;
-
-	intel_gt_check_and_clear_faults(ggtt->vm.gt);
-
-	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
-
-	ggtt->invalidate(ggtt);
-}
-
-void i915_gem_suspend_gtt_mappings(struct drm_i915_private *i915)
-{
-	ggtt_suspend_mappings(&i915->ggtt);
-}
-
 int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
@@ -2163,368 +52,6 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 	return -ENOSPC;
 }
 
-static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
-{
-	writeq(pte, addr);
-}
-
-static void gen8_ggtt_insert_page(struct i915_address_space *vm,
-				  dma_addr_t addr,
-				  u64 offset,
-				  enum i915_cache_level level,
-				  u32 unused)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	gen8_pte_t __iomem *pte =
-		(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
-
-	gen8_set_pte(pte, gen8_pte_encode(addr, level, 0));
-
-	ggtt->invalidate(ggtt);
-}
-
-static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
-				     enum i915_cache_level level,
-				     u32 flags)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	struct sgt_iter sgt_iter;
-	gen8_pte_t __iomem *gtt_entries;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
-	dma_addr_t addr;
-
-	/*
-	 * Note that we ignore PTE_READ_ONLY here. The caller must be careful
-	 * not to allow the user to override access to a read only page.
-	 */
-
-	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
-	gtt_entries += vma->node.start / I915_GTT_PAGE_SIZE;
-	for_each_sgt_daddr(addr, sgt_iter, vma->pages)
-		gen8_set_pte(gtt_entries++, pte_encode | addr);
-
-	/*
-	 * We want to flush the TLBs only after we're certain all the PTE
-	 * updates have finished.
-	 */
-	ggtt->invalidate(ggtt);
-}
-
-static void gen6_ggtt_insert_page(struct i915_address_space *vm,
-				  dma_addr_t addr,
-				  u64 offset,
-				  enum i915_cache_level level,
-				  u32 flags)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	gen6_pte_t __iomem *pte =
-		(gen6_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
-
-	iowrite32(vm->pte_encode(addr, level, flags), pte);
-
-	ggtt->invalidate(ggtt);
-}
-
-/*
- * Binds an object into the global gtt with the specified cache level. The object
- * will be accessible to the GPU via commands whose operands reference offsets
- * within the global GTT as well as accessible by the GPU through the GMADR
- * mapped BAR (dev_priv->mm.gtt->gtt).
- */
-static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
-				     enum i915_cache_level level,
-				     u32 flags)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	gen6_pte_t __iomem *entries = (gen6_pte_t __iomem *)ggtt->gsm;
-	unsigned int i = vma->node.start / I915_GTT_PAGE_SIZE;
-	struct sgt_iter iter;
-	dma_addr_t addr;
-	for_each_sgt_daddr(addr, iter, vma->pages)
-		iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]);
-
-	/*
-	 * We want to flush the TLBs only after we're certain all the PTE
-	 * updates have finished.
-	 */
-	ggtt->invalidate(ggtt);
-}
-
-static void nop_clear_range(struct i915_address_space *vm,
-			    u64 start, u64 length)
-{
-}
-
-static void gen8_ggtt_clear_range(struct i915_address_space *vm,
-				  u64 start, u64 length)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	unsigned first_entry = start / I915_GTT_PAGE_SIZE;
-	unsigned num_entries = length / I915_GTT_PAGE_SIZE;
-	const gen8_pte_t scratch_pte = vm->scratch[0].encode;
-	gen8_pte_t __iomem *gtt_base =
-		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
-	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
-	int i;
-
-	if (WARN(num_entries > max_entries,
-		 "First entry = %d; Num entries = %d (max=%d)\n",
-		 first_entry, num_entries, max_entries))
-		num_entries = max_entries;
-
-	for (i = 0; i < num_entries; i++)
-		gen8_set_pte(&gtt_base[i], scratch_pte);
-}
-
-static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
-{
-	struct drm_i915_private *dev_priv = vm->i915;
-
-	/*
-	 * Make sure the internal GAM fifo has been cleared of all GTT
-	 * writes before exiting stop_machine(). This guarantees that
-	 * any aperture accesses waiting to start in another process
-	 * cannot back up behind the GTT writes causing a hang.
-	 * The register can be any arbitrary GAM register.
-	 */
-	POSTING_READ(GFX_FLSH_CNTL_GEN6);
-}
-
-struct insert_page {
-	struct i915_address_space *vm;
-	dma_addr_t addr;
-	u64 offset;
-	enum i915_cache_level level;
-};
-
-static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
-{
-	struct insert_page *arg = _arg;
-
-	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
-	bxt_vtd_ggtt_wa(arg->vm);
-
-	return 0;
-}
-
-static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
-					  dma_addr_t addr,
-					  u64 offset,
-					  enum i915_cache_level level,
-					  u32 unused)
-{
-	struct insert_page arg = { vm, addr, offset, level };
-
-	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
-}
-
-struct insert_entries {
-	struct i915_address_space *vm;
-	struct i915_vma *vma;
-	enum i915_cache_level level;
-	u32 flags;
-};
-
-static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
-{
-	struct insert_entries *arg = _arg;
-
-	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags);
-	bxt_vtd_ggtt_wa(arg->vm);
-
-	return 0;
-}
-
-static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
-					     struct i915_vma *vma,
-					     enum i915_cache_level level,
-					     u32 flags)
-{
-	struct insert_entries arg = { vm, vma, level, flags };
-
-	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
-}
-
-struct clear_range {
-	struct i915_address_space *vm;
-	u64 start;
-	u64 length;
-};
-
-static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
-{
-	struct clear_range *arg = _arg;
-
-	gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
-	bxt_vtd_ggtt_wa(arg->vm);
-
-	return 0;
-}
-
-static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
-					  u64 start,
-					  u64 length)
-{
-	struct clear_range arg = { vm, start, length };
-
-	stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
-}
-
-static void gen6_ggtt_clear_range(struct i915_address_space *vm,
-				  u64 start, u64 length)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	unsigned first_entry = start / I915_GTT_PAGE_SIZE;
-	unsigned num_entries = length / I915_GTT_PAGE_SIZE;
-	gen6_pte_t scratch_pte, __iomem *gtt_base =
-		(gen6_pte_t __iomem *)ggtt->gsm + first_entry;
-	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
-	int i;
-
-	if (WARN(num_entries > max_entries,
-		 "First entry = %d; Num entries = %d (max=%d)\n",
-		 first_entry, num_entries, max_entries))
-		num_entries = max_entries;
-
-	scratch_pte = vm->scratch[0].encode;
-	for (i = 0; i < num_entries; i++)
-		iowrite32(scratch_pte, &gtt_base[i]);
-}
-
-static void i915_ggtt_insert_page(struct i915_address_space *vm,
-				  dma_addr_t addr,
-				  u64 offset,
-				  enum i915_cache_level cache_level,
-				  u32 unused)
-{
-	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
-		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
-
-	intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
-}
-
-static void i915_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
-				     enum i915_cache_level cache_level,
-				     u32 unused)
-{
-	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
-		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
-
-	intel_gtt_insert_sg_entries(vma->pages, vma->node.start >> PAGE_SHIFT,
-				    flags);
-}
-
-static void i915_ggtt_clear_range(struct i915_address_space *vm,
-				  u64 start, u64 length)
-{
-	intel_gtt_clear_range(start >> PAGE_SHIFT, length >> PAGE_SHIFT);
-}
-
-static int ggtt_bind_vma(struct i915_vma *vma,
-			 enum i915_cache_level cache_level,
-			 u32 flags)
-{
-	struct drm_i915_private *i915 = vma->vm->i915;
-	struct drm_i915_gem_object *obj = vma->obj;
-	intel_wakeref_t wakeref;
-	u32 pte_flags;
-
-	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
-	pte_flags = 0;
-	if (i915_gem_object_is_readonly(obj))
-		pte_flags |= PTE_READ_ONLY;
-
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-
-	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
-
-	/*
-	 * Without aliasing PPGTT there's no difference between
-	 * GLOBAL/LOCAL_BIND, it's all the same ptes. Hence unconditionally
-	 * upgrade to both bound if we bind either to avoid double-binding.
-	 */
-	atomic_or(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND, &vma->flags);
-
-	return 0;
-}
-
-static void ggtt_unbind_vma(struct i915_vma *vma)
-{
-	struct drm_i915_private *i915 = vma->vm->i915;
-	intel_wakeref_t wakeref;
-
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-}
-
-static int aliasing_gtt_bind_vma(struct i915_vma *vma,
-				 enum i915_cache_level cache_level,
-				 u32 flags)
-{
-	struct drm_i915_private *i915 = vma->vm->i915;
-	u32 pte_flags;
-	int ret;
-
-	/* Currently applicable only to VLV */
-	pte_flags = 0;
-	if (i915_gem_object_is_readonly(vma->obj))
-		pte_flags |= PTE_READ_ONLY;
-
-	if (flags & I915_VMA_LOCAL_BIND) {
-		struct i915_ppgtt *alias = i915_vm_to_ggtt(vma->vm)->alias;
-
-		if (flags & I915_VMA_ALLOC) {
-			ret = alias->vm.allocate_va_range(&alias->vm,
-							  vma->node.start,
-							  vma->size);
-			if (ret)
-				return ret;
-
-			set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
-		}
-
-		GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT,
-				     __i915_vma_flags(vma)));
-		alias->vm.insert_entries(&alias->vm, vma,
-					 cache_level, pte_flags);
-	}
-
-	if (flags & I915_VMA_GLOBAL_BIND) {
-		intel_wakeref_t wakeref;
-
-		with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
-			vma->vm->insert_entries(vma->vm, vma,
-						cache_level, pte_flags);
-		}
-	}
-
-	return 0;
-}
-
-static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
-{
-	struct drm_i915_private *i915 = vma->vm->i915;
-
-	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) {
-		struct i915_address_space *vm = vma->vm;
-		intel_wakeref_t wakeref;
-
-		with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-			vm->clear_range(vm, vma->node.start, vma->size);
-	}
-
-	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) {
-		struct i915_address_space *vm =
-			&i915_vm_to_ggtt(vma->vm)->alias->vm;
-
-		vm->clear_range(vm, vma->node.start, vma->size);
-	}
-}
-
 void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
@@ -2545,1067 +72,6 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 	dma_unmap_sg(kdev, pages->sgl, pages->nents, PCI_DMA_BIDIRECTIONAL);
 }
 
-static int ggtt_set_pages(struct i915_vma *vma)
-{
-	int ret;
-
-	GEM_BUG_ON(vma->pages);
-
-	ret = i915_get_ggtt_vma_pages(vma);
-	if (ret)
-		return ret;
-
-	vma->page_sizes = vma->obj->mm.page_sizes;
-
-	return 0;
-}
-
-static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
-				   unsigned long color,
-				   u64 *start,
-				   u64 *end)
-{
-	if (i915_node_color_differs(node, color))
-		*start += I915_GTT_PAGE_SIZE;
-
-	/* Also leave a space between the unallocated reserved node after the
-	 * GTT and any objects within the GTT, i.e. we use the color adjustment
-	 * to insert a guard page to prevent prefetches crossing over the
-	 * GTT boundary.
-	 */
-	node = list_next_entry(node, node_list);
-	if (node->color != color)
-		*end -= I915_GTT_PAGE_SIZE;
-}
-
-static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
-{
-	struct i915_ppgtt *ppgtt;
-	int err;
-
-	ppgtt = i915_ppgtt_create(ggtt->vm.i915);
-	if (IS_ERR(ppgtt))
-		return PTR_ERR(ppgtt);
-
-	if (GEM_WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
-		err = -ENODEV;
-		goto err_ppgtt;
-	}
-
-	/*
-	 * Note we only pre-allocate as far as the end of the global
-	 * GTT. On 48b / 4-level page-tables, the difference is very,
-	 * very significant! We have to preallocate as GVT/vgpu does
-	 * not like the page directory disappearing.
-	 */
-	err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, ggtt->vm.total);
-	if (err)
-		goto err_ppgtt;
-
-	ggtt->alias = ppgtt;
-	ggtt->vm.bind_async_flags |= ppgtt->vm.bind_async_flags;
-
-	GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != ggtt_bind_vma);
-	ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
-
-	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
-	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
-
-	return 0;
-
-err_ppgtt:
-	i915_vm_put(&ppgtt->vm);
-	return err;
-}
-
-static void fini_aliasing_ppgtt(struct i915_ggtt *ggtt)
-{
-	struct i915_ppgtt *ppgtt;
-
-	ppgtt = fetch_and_zero(&ggtt->alias);
-	if (!ppgtt)
-		return;
-
-	i915_vm_put(&ppgtt->vm);
-
-	ggtt->vm.vma_ops.bind_vma   = ggtt_bind_vma;
-	ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
-}
-
-static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
-{
-	u64 size;
-	int ret;
-
-	if (!USES_GUC(ggtt->vm.i915))
-		return 0;
-
-	GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP);
-	size = ggtt->vm.total - GUC_GGTT_TOP;
-
-	ret = i915_gem_gtt_reserve(&ggtt->vm, &ggtt->uc_fw, size,
-				   GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE,
-				   PIN_NOEVICT);
-	if (ret)
-		DRM_DEBUG_DRIVER("Failed to reserve top of GGTT for GuC\n");
-
-	return ret;
-}
-
-static void ggtt_release_guc_top(struct i915_ggtt *ggtt)
-{
-	if (drm_mm_node_allocated(&ggtt->uc_fw))
-		drm_mm_remove_node(&ggtt->uc_fw);
-}
-
-static void cleanup_init_ggtt(struct i915_ggtt *ggtt)
-{
-	ggtt_release_guc_top(ggtt);
-	if (drm_mm_node_allocated(&ggtt->error_capture))
-		drm_mm_remove_node(&ggtt->error_capture);
-}
-
-static int init_ggtt(struct i915_ggtt *ggtt)
-{
-	/* Let GEM Manage all of the aperture.
-	 *
-	 * However, leave one page at the end still bound to the scratch page.
-	 * There are a number of places where the hardware apparently prefetches
-	 * past the end of the object, and we've seen multiple hangs with the
-	 * GPU head pointer stuck in a batchbuffer bound at the last page of the
-	 * aperture.  One page should be enough to keep any prefetching inside
-	 * of the aperture.
-	 */
-	unsigned long hole_start, hole_end;
-	struct drm_mm_node *entry;
-	int ret;
-
-	/*
-	 * GuC requires all resources that we're sharing with it to be placed in
-	 * non-WOPCM memory. If GuC is not present or not in use we still need a
-	 * small bias as ring wraparound at offset 0 sometimes hangs. No idea
-	 * why.
-	 */
-	ggtt->pin_bias = max_t(u32, I915_GTT_PAGE_SIZE,
-			       intel_wopcm_guc_size(&ggtt->vm.i915->wopcm));
-
-	ret = intel_vgt_balloon(ggtt);
-	if (ret)
-		return ret;
-
-	if (ggtt->mappable_end) {
-		/* Reserve a mappable slot for our lockless error capture */
-		ret = drm_mm_insert_node_in_range(&ggtt->vm.mm, &ggtt->error_capture,
-						  PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
-						  0, ggtt->mappable_end,
-						  DRM_MM_INSERT_LOW);
-		if (ret)
-			return ret;
-	}
-
-	/*
-	 * The upper portion of the GuC address space has a sizeable hole
-	 * (several MB) that is inaccessible by GuC. Reserve this range within
-	 * GGTT as it can comfortably hold GuC/HuC firmware images.
-	 */
-	ret = ggtt_reserve_guc_top(ggtt);
-	if (ret)
-		goto err;
-
-	/* Clear any non-preallocated blocks */
-	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
-		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
-			      hole_start, hole_end);
-		ggtt->vm.clear_range(&ggtt->vm, hole_start,
-				     hole_end - hole_start);
-	}
-
-	/* And finally clear the reserved guard page */
-	ggtt->vm.clear_range(&ggtt->vm, ggtt->vm.total - PAGE_SIZE, PAGE_SIZE);
-
-	return 0;
-
-err:
-	cleanup_init_ggtt(ggtt);
-	return ret;
-}
-
-int i915_init_ggtt(struct drm_i915_private *i915)
-{
-	int ret;
-
-	ret = init_ggtt(&i915->ggtt);
-	if (ret)
-		return ret;
-
-	if (INTEL_PPGTT(i915) == INTEL_PPGTT_ALIASING) {
-		ret = init_aliasing_ppgtt(&i915->ggtt);
-		if (ret)
-			cleanup_init_ggtt(&i915->ggtt);
-	}
-
-	return 0;
-}
-
-static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
-{
-	struct i915_vma *vma, *vn;
-
-	atomic_set(&ggtt->vm.open, 0);
-
-	rcu_barrier(); /* flush the RCU'ed__i915_vm_release */
-	flush_workqueue(ggtt->vm.i915->wq);
-
-	mutex_lock(&ggtt->vm.mutex);
-
-	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link)
-		WARN_ON(__i915_vma_unbind(vma));
-
-	if (drm_mm_node_allocated(&ggtt->error_capture))
-		drm_mm_remove_node(&ggtt->error_capture);
-
-	ggtt_release_guc_top(ggtt);
-	intel_vgt_deballoon(ggtt);
-
-	ggtt->vm.cleanup(&ggtt->vm);
-
-	mutex_unlock(&ggtt->vm.mutex);
-	i915_address_space_fini(&ggtt->vm);
-
-	arch_phys_wc_del(ggtt->mtrr);
-
-	if (ggtt->iomap.size)
-		io_mapping_fini(&ggtt->iomap);
-}
-
-/**
- * i915_ggtt_driver_release - Clean up GGTT hardware initialization
- * @i915: i915 device
- */
-void i915_ggtt_driver_release(struct drm_i915_private *i915)
-{
-	struct pagevec *pvec;
-
-	fini_aliasing_ppgtt(&i915->ggtt);
-
-	ggtt_cleanup_hw(&i915->ggtt);
-
-	pvec = &i915->mm.wc_stash.pvec;
-	if (pvec->nr) {
-		set_pages_array_wb(pvec->pages, pvec->nr);
-		__pagevec_release(pvec);
-	}
-}
-
-static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
-{
-	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
-	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
-	return snb_gmch_ctl << 20;
-}
-
-static unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
-{
-	bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
-	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
-	if (bdw_gmch_ctl)
-		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
-
-#ifdef CONFIG_X86_32
-	/* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * I915_GTT_PAGE_SIZE */
-	if (bdw_gmch_ctl > 4)
-		bdw_gmch_ctl = 4;
-#endif
-
-	return bdw_gmch_ctl << 20;
-}
-
-static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
-{
-	gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
-	gmch_ctrl &= SNB_GMCH_GGMS_MASK;
-
-	if (gmch_ctrl)
-		return 1 << (20 + gmch_ctrl);
-
-	return 0;
-}
-
-static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
-{
-	struct drm_i915_private *dev_priv = ggtt->vm.i915;
-	struct pci_dev *pdev = dev_priv->drm.pdev;
-	phys_addr_t phys_addr;
-	int ret;
-
-	/* For Modern GENs the PTEs and register space are split in the BAR */
-	phys_addr = pci_resource_start(pdev, 0) + pci_resource_len(pdev, 0) / 2;
-
-	/*
-	 * On BXT+/CNL+ writes larger than 64 bit to the GTT pagetable range
-	 * will be dropped. For WC mappings in general we have 64 byte burst
-	 * writes when the WC buffer is flushed, so we can't use it, but have to
-	 * resort to an uncached mapping. The WC issue is easily caught by the
-	 * readback check when writing GTT PTE entries.
-	 */
-	if (IS_GEN9_LP(dev_priv) || INTEL_GEN(dev_priv) >= 10)
-		ggtt->gsm = ioremap(phys_addr, size);
-	else
-		ggtt->gsm = ioremap_wc(phys_addr, size);
-	if (!ggtt->gsm) {
-		DRM_ERROR("Failed to map the ggtt page table\n");
-		return -ENOMEM;
-	}
-
-	ret = setup_scratch_page(&ggtt->vm, GFP_DMA32);
-	if (ret) {
-		DRM_ERROR("Scratch setup failed\n");
-		/* iounmap will also get called at remove, but meh */
-		iounmap(ggtt->gsm);
-		return ret;
-	}
-
-	ggtt->vm.scratch[0].encode =
-		ggtt->vm.pte_encode(px_dma(&ggtt->vm.scratch[0]),
-				    I915_CACHE_NONE, 0);
-
-	return 0;
-}
-
-static void tgl_setup_private_ppat(struct intel_uncore *uncore)
-{
-	/* TGL doesn't support LLC or AGE settings */
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(0), GEN8_PPAT_WB);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(1), GEN8_PPAT_WC);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(2), GEN8_PPAT_WT);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(3), GEN8_PPAT_UC);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(4), GEN8_PPAT_WB);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(5), GEN8_PPAT_WB);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(6), GEN8_PPAT_WB);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB);
-}
-
-static void cnl_setup_private_ppat(struct intel_uncore *uncore)
-{
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(0),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLC);
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(1),
-			   GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(2),
-			   GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(3),
-			   GEN8_PPAT_UC);
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(4),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(5),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(6),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(7),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
-}
-
-/* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
- * bits. When using advanced contexts each context stores its own PAT, but
- * writing this data shouldn't be harmful even in those cases. */
-static void bdw_setup_private_ppat(struct intel_uncore *uncore)
-{
-	u64 pat;
-
-	pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC) |	/* for normal objects, no eLLC */
-	      GEN8_PPAT(1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC) |	/* for something pointing to ptes? */
-	      GEN8_PPAT(2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC) |	/* for scanout with eLLC */
-	      GEN8_PPAT(3, GEN8_PPAT_UC) |			/* Uncached objects, mostly for scanout */
-	      GEN8_PPAT(4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)) |
-	      GEN8_PPAT(5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)) |
-	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
-	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
-
-	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
-	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
-}
-
-static void chv_setup_private_ppat(struct intel_uncore *uncore)
-{
-	u64 pat;
-
-	/*
-	 * Map WB on BDW to snooped on CHV.
-	 *
-	 * Only the snoop bit has meaning for CHV, the rest is
-	 * ignored.
-	 *
-	 * The hardware will never snoop for certain types of accesses:
-	 * - CPU GTT (GMADR->GGTT->no snoop->memory)
-	 * - PPGTT page tables
-	 * - some other special cycles
-	 *
-	 * As with BDW, we also need to consider the following for GT accesses:
-	 * "For GGTT, there is NO pat_sel[2:0] from the entry,
-	 * so RTL will always use the value corresponding to
-	 * pat_sel = 000".
-	 * Which means we must set the snoop bit in PAT entry 0
-	 * in order to keep the global status page working.
-	 */
-
-	pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
-	      GEN8_PPAT(1, 0) |
-	      GEN8_PPAT(2, 0) |
-	      GEN8_PPAT(3, 0) |
-	      GEN8_PPAT(4, CHV_PPAT_SNOOP) |
-	      GEN8_PPAT(5, CHV_PPAT_SNOOP) |
-	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
-	      GEN8_PPAT(7, CHV_PPAT_SNOOP);
-
-	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
-	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
-}
-
-static void gen6_gmch_remove(struct i915_address_space *vm)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-
-	iounmap(ggtt->gsm);
-	cleanup_scratch_page(vm);
-}
-
-static void setup_private_pat(struct intel_uncore *uncore)
-{
-	struct drm_i915_private *i915 = uncore->i915;
-
-	GEM_BUG_ON(INTEL_GEN(i915) < 8);
-
-	if (INTEL_GEN(i915) >= 12)
-		tgl_setup_private_ppat(uncore);
-	else if (INTEL_GEN(i915) >= 10)
-		cnl_setup_private_ppat(uncore);
-	else if (IS_CHERRYVIEW(i915) || IS_GEN9_LP(i915))
-		chv_setup_private_ppat(uncore);
-	else
-		bdw_setup_private_ppat(uncore);
-}
-
-static struct resource pci_resource(struct pci_dev *pdev, int bar)
-{
-	return (struct resource)DEFINE_RES_MEM(pci_resource_start(pdev, bar),
-					       pci_resource_len(pdev, bar));
-}
-
-static int gen8_gmch_probe(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *dev_priv = ggtt->vm.i915;
-	struct pci_dev *pdev = dev_priv->drm.pdev;
-	unsigned int size;
-	u16 snb_gmch_ctl;
-	int err;
-
-	/* TODO: We're not aware of mappable constraints on gen8 yet */
-	if (!IS_DGFX(dev_priv)) {
-		ggtt->gmadr = pci_resource(pdev, 2);
-		ggtt->mappable_end = resource_size(&ggtt->gmadr);
-	}
-
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(39));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39));
-	if (err)
-		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
-
-	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-	if (IS_CHERRYVIEW(dev_priv))
-		size = chv_get_total_gtt_size(snb_gmch_ctl);
-	else
-		size = gen8_get_total_gtt_size(snb_gmch_ctl);
-
-	ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
-	ggtt->vm.cleanup = gen6_gmch_remove;
-	ggtt->vm.insert_page = gen8_ggtt_insert_page;
-	ggtt->vm.clear_range = nop_clear_range;
-	if (intel_scanout_needs_vtd_wa(dev_priv))
-		ggtt->vm.clear_range = gen8_ggtt_clear_range;
-
-	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
-
-	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
-	if (intel_ggtt_update_needs_vtd_wa(dev_priv) ||
-	    IS_CHERRYVIEW(dev_priv) /* fails with concurrent use/update */) {
-		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
-		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
-		if (ggtt->vm.clear_range != nop_clear_range)
-			ggtt->vm.clear_range = bxt_vtd_ggtt_clear_range__BKL;
-	}
-
-	ggtt->invalidate = gen6_ggtt_invalidate;
-
-	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
-	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
-	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
-	ggtt->vm.vma_ops.clear_pages = clear_pages;
-
-	ggtt->vm.pte_encode = gen8_pte_encode;
-
-	setup_private_pat(ggtt->vm.gt->uncore);
-
-	return ggtt_probe_common(ggtt, size);
-}
-
-static int gen6_gmch_probe(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *dev_priv = ggtt->vm.i915;
-	struct pci_dev *pdev = dev_priv->drm.pdev;
-	unsigned int size;
-	u16 snb_gmch_ctl;
-	int err;
-
-	ggtt->gmadr =
-		(struct resource) DEFINE_RES_MEM(pci_resource_start(pdev, 2),
-						 pci_resource_len(pdev, 2));
-	ggtt->mappable_end = resource_size(&ggtt->gmadr);
-
-	/* 64/512MB is the current min/max we actually know of, but this is just
-	 * a coarse sanity check.
-	 */
-	if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) {
-		DRM_ERROR("Unknown GMADR size (%pa)\n", &ggtt->mappable_end);
-		return -ENXIO;
-	}
-
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(40));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40));
-	if (err)
-		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
-	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-
-	size = gen6_get_total_gtt_size(snb_gmch_ctl);
-	ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
-
-	ggtt->vm.clear_range = nop_clear_range;
-	if (!HAS_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv))
-		ggtt->vm.clear_range = gen6_ggtt_clear_range;
-	ggtt->vm.insert_page = gen6_ggtt_insert_page;
-	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
-	ggtt->vm.cleanup = gen6_gmch_remove;
-
-	ggtt->invalidate = gen6_ggtt_invalidate;
-
-	if (HAS_EDRAM(dev_priv))
-		ggtt->vm.pte_encode = iris_pte_encode;
-	else if (IS_HASWELL(dev_priv))
-		ggtt->vm.pte_encode = hsw_pte_encode;
-	else if (IS_VALLEYVIEW(dev_priv))
-		ggtt->vm.pte_encode = byt_pte_encode;
-	else if (INTEL_GEN(dev_priv) >= 7)
-		ggtt->vm.pte_encode = ivb_pte_encode;
-	else
-		ggtt->vm.pte_encode = snb_pte_encode;
-
-	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
-	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
-	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
-	ggtt->vm.vma_ops.clear_pages = clear_pages;
-
-	return ggtt_probe_common(ggtt, size);
-}
-
-static void i915_gmch_remove(struct i915_address_space *vm)
-{
-	intel_gmch_remove();
-}
-
-static int i915_gmch_probe(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *dev_priv = ggtt->vm.i915;
-	phys_addr_t gmadr_base;
-	int ret;
-
-	ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->drm.pdev, NULL);
-	if (!ret) {
-		DRM_ERROR("failed to set up gmch\n");
-		return -EIO;
-	}
-
-	intel_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end);
-
-	ggtt->gmadr =
-		(struct resource) DEFINE_RES_MEM(gmadr_base,
-						 ggtt->mappable_end);
-
-	ggtt->do_idle_maps = needs_idle_maps(dev_priv);
-	ggtt->vm.insert_page = i915_ggtt_insert_page;
-	ggtt->vm.insert_entries = i915_ggtt_insert_entries;
-	ggtt->vm.clear_range = i915_ggtt_clear_range;
-	ggtt->vm.cleanup = i915_gmch_remove;
-
-	ggtt->invalidate = gmch_ggtt_invalidate;
-
-	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
-	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
-	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
-	ggtt->vm.vma_ops.clear_pages = clear_pages;
-
-	if (unlikely(ggtt->do_idle_maps))
-		dev_notice(dev_priv->drm.dev,
-			   "Applying Ironlake quirks for intel_iommu\n");
-
-	return 0;
-}
-
-static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-	int ret;
-
-	ggtt->vm.gt = gt;
-	ggtt->vm.i915 = i915;
-	ggtt->vm.dma = &i915->drm.pdev->dev;
-
-	if (INTEL_GEN(i915) <= 5)
-		ret = i915_gmch_probe(ggtt);
-	else if (INTEL_GEN(i915) < 8)
-		ret = gen6_gmch_probe(ggtt);
-	else
-		ret = gen8_gmch_probe(ggtt);
-	if (ret)
-		return ret;
-
-	if ((ggtt->vm.total - 1) >> 32) {
-		DRM_ERROR("We never expected a Global GTT with more than 32bits"
-			  " of address space! Found %lldM!\n",
-			  ggtt->vm.total >> 20);
-		ggtt->vm.total = 1ULL << 32;
-		ggtt->mappable_end =
-			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
-	}
-
-	if (ggtt->mappable_end > ggtt->vm.total) {
-		DRM_ERROR("mappable aperture extends past end of GGTT,"
-			  " aperture=%pa, total=%llx\n",
-			  &ggtt->mappable_end, ggtt->vm.total);
-		ggtt->mappable_end = ggtt->vm.total;
-	}
-
-	/* GMADR is the PCI mmio aperture into the global GTT. */
-	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20);
-	DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20);
-	DRM_DEBUG_DRIVER("DSM size = %lluM\n",
-			 (u64)resource_size(&intel_graphics_stolen_res) >> 20);
-
-	return 0;
-}
-
-/**
- * i915_ggtt_probe_hw - Probe GGTT hardware location
- * @i915: i915 device
- */
-int i915_ggtt_probe_hw(struct drm_i915_private *i915)
-{
-	int ret;
-
-	ret = ggtt_probe_hw(&i915->ggtt, &i915->gt);
-	if (ret)
-		return ret;
-
-	if (intel_vtd_active())
-		dev_info(i915->drm.dev, "VT-d active for gfx access\n");
-
-	return 0;
-}
-
-static int ggtt_init_hw(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *i915 = ggtt->vm.i915;
-
-	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
-
-	ggtt->vm.is_ggtt = true;
-
-	/* Only VLV supports read-only GGTT mappings */
-	ggtt->vm.has_read_only = IS_VALLEYVIEW(i915);
-
-	if (!HAS_LLC(i915) && !HAS_PPGTT(i915))
-		ggtt->vm.mm.color_adjust = i915_ggtt_color_adjust;
-
-	if (ggtt->mappable_end) {
-		if (!io_mapping_init_wc(&ggtt->iomap,
-					ggtt->gmadr.start,
-					ggtt->mappable_end)) {
-			ggtt->vm.cleanup(&ggtt->vm);
-			return -EIO;
-		}
-
-		ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start,
-					      ggtt->mappable_end);
-	}
-
-	i915_ggtt_init_fences(ggtt);
-
-	return 0;
-}
-
-/**
- * i915_ggtt_init_hw - Initialize GGTT hardware
- * @dev_priv: i915 device
- */
-int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
-{
-	int ret;
-
-	stash_init(&dev_priv->mm.wc_stash);
-
-	/* Note that we use page colouring to enforce a guard page at the
-	 * end of the address space. This is required as the CS may prefetch
-	 * beyond the end of the batch buffer, across the page boundary,
-	 * and beyond the end of the GTT if we do not provide a guard.
-	 */
-	ret = ggtt_init_hw(&dev_priv->ggtt);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv)
-{
-	if (INTEL_GEN(dev_priv) < 6 && !intel_enable_gtt())
-		return -EIO;
-
-	return 0;
-}
-
-void i915_ggtt_enable_guc(struct i915_ggtt *ggtt)
-{
-	GEM_BUG_ON(ggtt->invalidate != gen6_ggtt_invalidate);
-
-	ggtt->invalidate = guc_ggtt_invalidate;
-
-	ggtt->invalidate(ggtt);
-}
-
-void i915_ggtt_disable_guc(struct i915_ggtt *ggtt)
-{
-	/* XXX Temporary pardon for error unload */
-	if (ggtt->invalidate == gen6_ggtt_invalidate)
-		return;
-
-	/* We should only be called after i915_ggtt_enable_guc() */
-	GEM_BUG_ON(ggtt->invalidate != guc_ggtt_invalidate);
-
-	ggtt->invalidate = gen6_ggtt_invalidate;
-
-	ggtt->invalidate(ggtt);
-}
-
-static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
-{
-	struct i915_vma *vma;
-	bool flush = false;
-	int open;
-
-	intel_gt_check_and_clear_faults(ggtt->vm.gt);
-
-	mutex_lock(&ggtt->vm.mutex);
-
-	/* First fill our portion of the GTT with scratch pages */
-	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
-
-	/* Skip rewriting PTE on VMA unbind. */
-	open = atomic_xchg(&ggtt->vm.open, 0);
-
-	/* clflush objects bound into the GGTT and rebind them. */
-	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link) {
-		struct drm_i915_gem_object *obj = vma->obj;
-
-		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
-			continue;
-
-		clear_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
-		WARN_ON(i915_vma_bind(vma,
-				      obj ? obj->cache_level : 0,
-				      PIN_GLOBAL, NULL));
-		if (obj) { /* only used during resume => exclusive access */
-			flush |= fetch_and_zero(&obj->write_domain);
-			obj->read_domains |= I915_GEM_DOMAIN_GTT;
-		}
-	}
-
-	atomic_set(&ggtt->vm.open, open);
-	ggtt->invalidate(ggtt);
-
-	mutex_unlock(&ggtt->vm.mutex);
-
-	if (flush)
-		wbinvd_on_all_cpus();
-}
-
-void i915_gem_restore_gtt_mappings(struct drm_i915_private *i915)
-{
-	struct i915_ggtt *ggtt = &i915->ggtt;
-
-	ggtt_restore_mappings(ggtt);
-
-	if (INTEL_GEN(i915) >= 8)
-		setup_private_pat(ggtt->vm.gt->uncore);
-}
-
-static struct scatterlist *
-rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset,
-	     unsigned int width, unsigned int height,
-	     unsigned int stride,
-	     struct sg_table *st, struct scatterlist *sg)
-{
-	unsigned int column, row;
-	unsigned int src_idx;
-
-	for (column = 0; column < width; column++) {
-		src_idx = stride * (height - 1) + column + offset;
-		for (row = 0; row < height; row++) {
-			st->nents++;
-			/* We don't need the pages, but need to initialize
-			 * the entries so the sg list can be happily traversed.
-			 * The only thing we need are DMA addresses.
-			 */
-			sg_set_page(sg, NULL, I915_GTT_PAGE_SIZE, 0);
-			sg_dma_address(sg) =
-				i915_gem_object_get_dma_address(obj, src_idx);
-			sg_dma_len(sg) = I915_GTT_PAGE_SIZE;
-			sg = sg_next(sg);
-			src_idx -= stride;
-		}
-	}
-
-	return sg;
-}
-
-static noinline struct sg_table *
-intel_rotate_pages(struct intel_rotation_info *rot_info,
-		   struct drm_i915_gem_object *obj)
-{
-	unsigned int size = intel_rotation_info_size(rot_info);
-	struct sg_table *st;
-	struct scatterlist *sg;
-	int ret = -ENOMEM;
-	int i;
-
-	/* Allocate target SG list. */
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st)
-		goto err_st_alloc;
-
-	ret = sg_alloc_table(st, size, GFP_KERNEL);
-	if (ret)
-		goto err_sg_alloc;
-
-	st->nents = 0;
-	sg = st->sgl;
-
-	for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) {
-		sg = rotate_pages(obj, rot_info->plane[i].offset,
-				  rot_info->plane[i].width, rot_info->plane[i].height,
-				  rot_info->plane[i].stride, st, sg);
-	}
-
-	return st;
-
-err_sg_alloc:
-	kfree(st);
-err_st_alloc:
-
-	DRM_DEBUG_DRIVER("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
-			 obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
-
-	return ERR_PTR(ret);
-}
-
-static struct scatterlist *
-remap_pages(struct drm_i915_gem_object *obj, unsigned int offset,
-	    unsigned int width, unsigned int height,
-	    unsigned int stride,
-	    struct sg_table *st, struct scatterlist *sg)
-{
-	unsigned int row;
-
-	for (row = 0; row < height; row++) {
-		unsigned int left = width * I915_GTT_PAGE_SIZE;
-
-		while (left) {
-			dma_addr_t addr;
-			unsigned int length;
-
-			/* We don't need the pages, but need to initialize
-			 * the entries so the sg list can be happily traversed.
-			 * The only thing we need are DMA addresses.
-			 */
-
-			addr = i915_gem_object_get_dma_address_len(obj, offset, &length);
-
-			length = min(left, length);
-
-			st->nents++;
-
-			sg_set_page(sg, NULL, length, 0);
-			sg_dma_address(sg) = addr;
-			sg_dma_len(sg) = length;
-			sg = sg_next(sg);
-
-			offset += length / I915_GTT_PAGE_SIZE;
-			left -= length;
-		}
-
-		offset += stride - width;
-	}
-
-	return sg;
-}
-
-static noinline struct sg_table *
-intel_remap_pages(struct intel_remapped_info *rem_info,
-		  struct drm_i915_gem_object *obj)
-{
-	unsigned int size = intel_remapped_info_size(rem_info);
-	struct sg_table *st;
-	struct scatterlist *sg;
-	int ret = -ENOMEM;
-	int i;
-
-	/* Allocate target SG list. */
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st)
-		goto err_st_alloc;
-
-	ret = sg_alloc_table(st, size, GFP_KERNEL);
-	if (ret)
-		goto err_sg_alloc;
-
-	st->nents = 0;
-	sg = st->sgl;
-
-	for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) {
-		sg = remap_pages(obj, rem_info->plane[i].offset,
-				 rem_info->plane[i].width, rem_info->plane[i].height,
-				 rem_info->plane[i].stride, st, sg);
-	}
-
-	i915_sg_trim(st);
-
-	return st;
-
-err_sg_alloc:
-	kfree(st);
-err_st_alloc:
-
-	DRM_DEBUG_DRIVER("Failed to create remapped mapping for object size %zu! (%ux%u tiles, %u pages)\n",
-			 obj->base.size, rem_info->plane[0].width, rem_info->plane[0].height, size);
-
-	return ERR_PTR(ret);
-}
-
-static noinline struct sg_table *
-intel_partial_pages(const struct i915_ggtt_view *view,
-		    struct drm_i915_gem_object *obj)
-{
-	struct sg_table *st;
-	struct scatterlist *sg, *iter;
-	unsigned int count = view->partial.size;
-	unsigned int offset;
-	int ret = -ENOMEM;
-
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st)
-		goto err_st_alloc;
-
-	ret = sg_alloc_table(st, count, GFP_KERNEL);
-	if (ret)
-		goto err_sg_alloc;
-
-	iter = i915_gem_object_get_sg(obj, view->partial.offset, &offset);
-	GEM_BUG_ON(!iter);
-
-	sg = st->sgl;
-	st->nents = 0;
-	do {
-		unsigned int len;
-
-		len = min(iter->length - (offset << PAGE_SHIFT),
-			  count << PAGE_SHIFT);
-		sg_set_page(sg, NULL, len, 0);
-		sg_dma_address(sg) =
-			sg_dma_address(iter) + (offset << PAGE_SHIFT);
-		sg_dma_len(sg) = len;
-
-		st->nents++;
-		count -= len >> PAGE_SHIFT;
-		if (count == 0) {
-			sg_mark_end(sg);
-			i915_sg_trim(st); /* Drop any unused tail entries. */
-
-			return st;
-		}
-
-		sg = __sg_next(sg);
-		iter = __sg_next(iter);
-		offset = 0;
-	} while (1);
-
-err_sg_alloc:
-	kfree(st);
-err_st_alloc:
-	return ERR_PTR(ret);
-}
-
-static int
-i915_get_ggtt_vma_pages(struct i915_vma *vma)
-{
-	int ret;
-
-	/* The vma->pages are only valid within the lifespan of the borrowed
-	 * obj->mm.pages. When the obj->mm.pages sg_table is regenerated, so
-	 * must be the vma->pages. A simple rule is that vma->pages must only
-	 * be accessed when the obj->mm.pages are pinned.
-	 */
-	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(vma->obj));
-
-	switch (vma->ggtt_view.type) {
-	default:
-		GEM_BUG_ON(vma->ggtt_view.type);
-		/* fall through */
-	case I915_GGTT_VIEW_NORMAL:
-		vma->pages = vma->obj->mm.pages;
-		return 0;
-
-	case I915_GGTT_VIEW_ROTATED:
-		vma->pages =
-			intel_rotate_pages(&vma->ggtt_view.rotated, vma->obj);
-		break;
-
-	case I915_GGTT_VIEW_REMAPPED:
-		vma->pages =
-			intel_remap_pages(&vma->ggtt_view.remapped, vma->obj);
-		break;
-
-	case I915_GGTT_VIEW_PARTIAL:
-		vma->pages = intel_partial_pages(&vma->ggtt_view, vma->obj);
-		break;
-	}
-
-	ret = 0;
-	if (IS_ERR(vma->pages)) {
-		ret = PTR_ERR(vma->pages);
-		vma->pages = NULL;
-		DRM_ERROR("Failed to get pages for VMA view type %u (%d)!\n",
-			  vma->ggtt_view.type, ret);
-	}
-	return ret;
-}
-
 /**
  * i915_gem_gtt_reserve - reserve a node in an address_space (GTT)
  * @vm: the &struct i915_address_space
@@ -3827,6 +293,5 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/mock_gtt.c"
 #include "selftests/i915_gem_gtt.c"
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 402283ce2864..f6226df9f972 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -1,638 +1,21 @@
+/* SPDX-License-Identifier: MIT */
 /*
- * Copyright © 2014 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- * Please try to maintain the following order within this file unless it makes
- * sense to do otherwise. From top to bottom:
- * 1. typedefs
- * 2. #defines, and macros
- * 3. structure definitions
- * 4. function prototypes
- *
- * Within each section, please try to order by generation in ascending order,
- * from top to bottom (ie. gen6 on the top, gen8 on the bottom).
+ * Copyright © 2020 Intel Corporation
  */
 
 #ifndef __I915_GEM_GTT_H__
 #define __I915_GEM_GTT_H__
 
 #include <linux/io-mapping.h>
-#include <linux/kref.h>
-#include <linux/mm.h>
-#include <linux/pagevec.h>
-#include <linux/workqueue.h>
+#include <linux/types.h>
 
 #include <drm/drm_mm.h>
 
-#include "gt/intel_reset.h"
-#include "i915_gem_fence_reg.h"
-#include "i915_request.h"
+#include "gt/intel_gtt.h"
 #include "i915_scatterlist.h"
-#include "i915_selftest.h"
-#include "gt/intel_timeline.h"
 
-#define I915_GTT_PAGE_SIZE_4K	BIT_ULL(12)
-#define I915_GTT_PAGE_SIZE_64K	BIT_ULL(16)
-#define I915_GTT_PAGE_SIZE_2M	BIT_ULL(21)
-
-#define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K
-#define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M
-
-#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE
-
-#define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE
-
-#define I915_FENCE_REG_NONE -1
-#define I915_MAX_NUM_FENCES 32
-/* 32 fences + sign bit for FENCE_REG_NONE */
-#define I915_MAX_NUM_FENCE_BITS 6
-
-struct drm_i915_file_private;
 struct drm_i915_gem_object;
-struct i915_vma;
-struct intel_gt;
-
-typedef u32 gen6_pte_t;
-typedef u64 gen8_pte_t;
-
-#define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)
-
-/* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
-#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
-#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
-#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
-#define GEN6_PTE_CACHE_LLC		(2 << 1)
-#define GEN6_PTE_UNCACHED		(1 << 1)
-#define GEN6_PTE_VALID			(1 << 0)
-
-#define I915_PTES(pte_len)		((unsigned int)(PAGE_SIZE / (pte_len)))
-#define I915_PTE_MASK(pte_len)		(I915_PTES(pte_len) - 1)
-#define I915_PDES			512
-#define I915_PDE_MASK			(I915_PDES - 1)
-#define NUM_PTE(pde_shift)     (1 << (pde_shift - PAGE_SHIFT))
-
-#define GEN6_PTES			I915_PTES(sizeof(gen6_pte_t))
-#define GEN6_PD_SIZE		        (I915_PDES * PAGE_SIZE)
-#define GEN6_PD_ALIGN			(PAGE_SIZE * 16)
-#define GEN6_PDE_SHIFT			22
-#define GEN6_PDE_VALID			(1 << 0)
-
-#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
-
-#define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
-#define BYT_PTE_WRITEABLE		(1 << 1)
-
-/* Cacheability Control is a 4-bit value. The low three bits are stored in bits
- * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
- */
-#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
-					 (((bits) & 0x8) << (11 - 3)))
-#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
-#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
-#define HSW_WB_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x8)
-#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
-#define HSW_WT_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x7)
-#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
-#define HSW_PTE_UNCACHED		(0)
-#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
-#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
-
-/*
- * GEN8 32b style address is defined as a 3 level page table:
- * 31:30 | 29:21 | 20:12 |  11:0
- * PDPE  |  PDE  |  PTE  | offset
- * The difference as compared to normal x86 3 level page table is the PDPEs are
- * programmed via register.
- *
- * GEN8 48b style address is defined as a 4 level page table:
- * 47:39 | 38:30 | 29:21 | 20:12 |  11:0
- * PML4E | PDPE  |  PDE  |  PTE  | offset
- */
-#define GEN8_3LVL_PDPES			4
-
-#define PPAT_UNCACHED			(_PAGE_PWT | _PAGE_PCD)
-#define PPAT_CACHED_PDE			0 /* WB LLC */
-#define PPAT_CACHED			_PAGE_PAT /* WB LLCeLLC */
-#define PPAT_DISPLAY_ELLC		_PAGE_PCD /* WT eLLC */
-
-#define CHV_PPAT_SNOOP			(1<<6)
-#define GEN8_PPAT_AGE(x)		((x)<<4)
-#define GEN8_PPAT_LLCeLLC		(3<<2)
-#define GEN8_PPAT_LLCELLC		(2<<2)
-#define GEN8_PPAT_LLC			(1<<2)
-#define GEN8_PPAT_WB			(3<<0)
-#define GEN8_PPAT_WT			(2<<0)
-#define GEN8_PPAT_WC			(1<<0)
-#define GEN8_PPAT_UC			(0<<0)
-#define GEN8_PPAT_ELLC_OVERRIDE		(0<<2)
-#define GEN8_PPAT(i, x)			((u64)(x) << ((i) * 8))
-
-#define GEN8_PDE_IPS_64K BIT(11)
-#define GEN8_PDE_PS_2M   BIT(7)
-
-#define for_each_sgt_daddr(__dp, __iter, __sgt) \
-	__for_each_sgt_daddr(__dp, __iter, __sgt, I915_GTT_PAGE_SIZE)
-
-struct intel_remapped_plane_info {
-	/* in gtt pages */
-	unsigned int width, height, stride, offset;
-} __packed;
-
-struct intel_remapped_info {
-	struct intel_remapped_plane_info plane[2];
-	unsigned int unused_mbz;
-} __packed;
-
-struct intel_rotation_info {
-	struct intel_remapped_plane_info plane[2];
-} __packed;
-
-struct intel_partial_info {
-	u64 offset;
-	unsigned int size;
-} __packed;
-
-enum i915_ggtt_view_type {
-	I915_GGTT_VIEW_NORMAL = 0,
-	I915_GGTT_VIEW_ROTATED = sizeof(struct intel_rotation_info),
-	I915_GGTT_VIEW_PARTIAL = sizeof(struct intel_partial_info),
-	I915_GGTT_VIEW_REMAPPED = sizeof(struct intel_remapped_info),
-};
-
-static inline void assert_i915_gem_gtt_types(void)
-{
-	BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 8*sizeof(unsigned int));
-	BUILD_BUG_ON(sizeof(struct intel_partial_info) != sizeof(u64) + sizeof(unsigned int));
-	BUILD_BUG_ON(sizeof(struct intel_remapped_info) != 9*sizeof(unsigned int));
-
-	/* Check that rotation/remapped shares offsets for simplicity */
-	BUILD_BUG_ON(offsetof(struct intel_remapped_info, plane[0]) !=
-		     offsetof(struct intel_rotation_info, plane[0]));
-	BUILD_BUG_ON(offsetofend(struct intel_remapped_info, plane[1]) !=
-		     offsetofend(struct intel_rotation_info, plane[1]));
-
-	/* As we encode the size of each branch inside the union into its type,
-	 * we have to be careful that each branch has a unique size.
-	 */
-	switch ((enum i915_ggtt_view_type)0) {
-	case I915_GGTT_VIEW_NORMAL:
-	case I915_GGTT_VIEW_PARTIAL:
-	case I915_GGTT_VIEW_ROTATED:
-	case I915_GGTT_VIEW_REMAPPED:
-		/* gcc complains if these are identical cases */
-		break;
-	}
-}
-
-struct i915_ggtt_view {
-	enum i915_ggtt_view_type type;
-	union {
-		/* Members need to contain no holes/padding */
-		struct intel_partial_info partial;
-		struct intel_rotation_info rotated;
-		struct intel_remapped_info remapped;
-	};
-};
-
-enum i915_cache_level;
-
-struct i915_vma;
-
-struct i915_page_dma {
-	struct page *page;
-	union {
-		dma_addr_t daddr;
-
-		/* For gen6/gen7 only. This is the offset in the GGTT
-		 * where the page directory entries for PPGTT begin
-		 */
-		u32 ggtt_offset;
-	};
-};
-
-struct i915_page_scratch {
-	struct i915_page_dma base;
-	u64 encode;
-};
-
-struct i915_page_table {
-	struct i915_page_dma base;
-	atomic_t used;
-};
-
-struct i915_page_directory {
-	struct i915_page_table pt;
-	spinlock_t lock;
-	void *entry[512];
-};
-
-#define __px_choose_expr(x, type, expr, other) \
-	__builtin_choose_expr( \
-	__builtin_types_compatible_p(typeof(x), type) || \
-	__builtin_types_compatible_p(typeof(x), const type), \
-	({ type __x = (type)(x); expr; }), \
-	other)
-
-#define px_base(px) \
-	__px_choose_expr(px, struct i915_page_dma *, __x, \
-	__px_choose_expr(px, struct i915_page_scratch *, &__x->base, \
-	__px_choose_expr(px, struct i915_page_table *, &__x->base, \
-	__px_choose_expr(px, struct i915_page_directory *, &__x->pt.base, \
-	(void)0))))
-#define px_dma(px) (px_base(px)->daddr)
-
-#define px_pt(px) \
-	__px_choose_expr(px, struct i915_page_table *, __x, \
-	__px_choose_expr(px, struct i915_page_directory *, &__x->pt, \
-	(void)0))
-#define px_used(px) (&px_pt(px)->used)
-
-struct i915_vma_ops {
-	/* Map an object into an address space with the given cache flags. */
-	int (*bind_vma)(struct i915_vma *vma,
-			enum i915_cache_level cache_level,
-			u32 flags);
-	/*
-	 * Unmap an object from an address space. This usually consists of
-	 * setting the valid PTE entries to a reserved scratch page.
-	 */
-	void (*unbind_vma)(struct i915_vma *vma);
-
-	int (*set_pages)(struct i915_vma *vma);
-	void (*clear_pages)(struct i915_vma *vma);
-};
-
-struct pagestash {
-	spinlock_t lock;
-	struct pagevec pvec;
-};
-
-struct i915_address_space {
-	struct kref ref;
-	struct rcu_work rcu;
-
-	struct drm_mm mm;
-	struct intel_gt *gt;
-	struct drm_i915_private *i915;
-	struct device *dma;
-	/* Every address space belongs to a struct file - except for the global
-	 * GTT that is owned by the driver (and so @file is set to NULL). In
-	 * principle, no information should leak from one context to another
-	 * (or between files/processes etc) unless explicitly shared by the
-	 * owner. Tracking the owner is important in order to free up per-file
-	 * objects along with the file, to aide resource tracking, and to
-	 * assign blame.
-	 */
-	struct drm_i915_file_private *file;
-	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
-	u64 reserved;		/* size addr space reserved */
-
-	unsigned int bind_async_flags;
-
-	/*
-	 * Each active user context has its own address space (in full-ppgtt).
-	 * Since the vm may be shared between multiple contexts, we count how
-	 * many contexts keep us "open". Once open hits zero, we are closed
-	 * and do not allow any new attachments, and proceed to shutdown our
-	 * vma and page directories.
-	 */
-	atomic_t open;
-
-	struct mutex mutex; /* protects vma and our lists */
-#define VM_CLASS_GGTT 0
-#define VM_CLASS_PPGTT 1
-
-	struct i915_page_scratch scratch[4];
-	unsigned int scratch_order;
-	unsigned int top;
-
-	/**
-	 * List of vma currently bound.
-	 */
-	struct list_head bound_list;
-
-	struct pagestash free_pages;
-
-	/* Global GTT */
-	bool is_ggtt:1;
-
-	/* Some systems require uncached updates of the page directories */
-	bool pt_kmap_wc:1;
-
-	/* Some systems support read-only mappings for GGTT and/or PPGTT */
-	bool has_read_only:1;
-
-	u64 (*pte_encode)(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags); /* Create a valid PTE */
-#define PTE_READ_ONLY	(1<<0)
-
-	int (*allocate_va_range)(struct i915_address_space *vm,
-				 u64 start, u64 length);
-	void (*clear_range)(struct i915_address_space *vm,
-			    u64 start, u64 length);
-	void (*insert_page)(struct i915_address_space *vm,
-			    dma_addr_t addr,
-			    u64 offset,
-			    enum i915_cache_level cache_level,
-			    u32 flags);
-	void (*insert_entries)(struct i915_address_space *vm,
-			       struct i915_vma *vma,
-			       enum i915_cache_level cache_level,
-			       u32 flags);
-	void (*cleanup)(struct i915_address_space *vm);
-
-	struct i915_vma_ops vma_ops;
-
-	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
-	I915_SELFTEST_DECLARE(bool scrub_64K);
-};
-
-#define i915_is_ggtt(vm) ((vm)->is_ggtt)
-
-static inline bool
-i915_vm_is_4lvl(const struct i915_address_space *vm)
-{
-	return (vm->total - 1) >> 32;
-}
-
-static inline bool
-i915_vm_has_scratch_64K(struct i915_address_space *vm)
-{
-	return vm->scratch_order == get_order(I915_GTT_PAGE_SIZE_64K);
-}
-
-static inline bool
-i915_vm_has_cache_coloring(struct i915_address_space *vm)
-{
-	return i915_is_ggtt(vm) && vm->mm.color_adjust;
-}
-
-/* The Graphics Translation Table is the way in which GEN hardware translates a
- * Graphics Virtual Address into a Physical Address. In addition to the normal
- * collateral associated with any va->pa translations GEN hardware also has a
- * portion of the GTT which can be mapped by the CPU and remain both coherent
- * and correct (in cases like swizzling). That region is referred to as GMADR in
- * the spec.
- */
-struct i915_ggtt {
-	struct i915_address_space vm;
-
-	struct io_mapping iomap;	/* Mapping to our CPU mappable region */
-	struct resource gmadr;          /* GMADR resource */
-	resource_size_t mappable_end;	/* End offset that we can CPU map */
-
-	/** "Graphics Stolen Memory" holds the global PTEs */
-	void __iomem *gsm;
-	void (*invalidate)(struct i915_ggtt *ggtt);
-
-	/** PPGTT used for aliasing the PPGTT with the GTT */
-	struct i915_ppgtt *alias;
-
-	bool do_idle_maps;
-
-	int mtrr;
-
-	/** Bit 6 swizzling required for X tiling */
-	u32 bit_6_swizzle_x;
-	/** Bit 6 swizzling required for Y tiling */
-	u32 bit_6_swizzle_y;
-
-	u32 pin_bias;
-
-	unsigned int num_fences;
-	struct i915_fence_reg fence_regs[I915_MAX_NUM_FENCES];
-	struct list_head fence_list;
-
-	/** List of all objects in gtt_space, currently mmaped by userspace.
-	 * All objects within this list must also be on bound_list.
-	 */
-	struct list_head userfault_list;
-
-	/* Manual runtime pm autosuspend delay for user GGTT mmaps */
-	struct intel_wakeref_auto userfault_wakeref;
-
-	struct drm_mm_node error_capture;
-	struct drm_mm_node uc_fw;
-};
-
-struct i915_ppgtt {
-	struct i915_address_space vm;
-
-	struct i915_page_directory *pd;
-};
-
-struct gen6_ppgtt {
-	struct i915_ppgtt base;
-
-	struct i915_vma *vma;
-	gen6_pte_t __iomem *pd_addr;
-
-	atomic_t pin_count;
-	struct mutex pin_mutex;
-
-	bool scan_for_unused_pt;
-};
-
-#define __to_gen6_ppgtt(base) container_of(base, struct gen6_ppgtt, base)
-
-static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base)
-{
-	BUILD_BUG_ON(offsetof(struct gen6_ppgtt, base));
-	return __to_gen6_ppgtt(base);
-}
-
-/*
- * gen6_for_each_pde() iterates over every pde from start until start+length.
- * If start and start+length are not perfectly divisible, the macro will round
- * down and up as needed. Start=0 and length=2G effectively iterates over
- * every PDE in the system. The macro modifies ALL its parameters except 'pd',
- * so each of the other parameters should preferably be a simple variable, or
- * at most an lvalue with no side-effects!
- */
-#define gen6_for_each_pde(pt, pd, start, length, iter)			\
-	for (iter = gen6_pde_index(start);				\
-	     length > 0 && iter < I915_PDES &&				\
-		     (pt = i915_pt_entry(pd, iter), true);		\
-	     ({ u32 temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT);		\
-		    temp = min(temp - start, length);			\
-		    start += temp, length -= temp; }), ++iter)
-
-#define gen6_for_all_pdes(pt, pd, iter)					\
-	for (iter = 0;							\
-	     iter < I915_PDES &&					\
-		     (pt = i915_pt_entry(pd, iter), true);		\
-	     ++iter)
-
-static inline u32 i915_pte_index(u64 address, unsigned int pde_shift)
-{
-	const u32 mask = NUM_PTE(pde_shift) - 1;
-
-	return (address >> PAGE_SHIFT) & mask;
-}
-
-/* Helper to counts the number of PTEs within the given length. This count
- * does not cross a page table boundary, so the max value would be
- * GEN6_PTES for GEN6, and GEN8_PTES for GEN8.
-*/
-static inline u32 i915_pte_count(u64 addr, u64 length, unsigned int pde_shift)
-{
-	const u64 mask = ~((1ULL << pde_shift) - 1);
-	u64 end;
-
-	GEM_BUG_ON(length == 0);
-	GEM_BUG_ON(offset_in_page(addr | length));
-
-	end = addr + length;
-
-	if ((addr & mask) != (end & mask))
-		return NUM_PTE(pde_shift) - i915_pte_index(addr, pde_shift);
-
-	return i915_pte_index(end, pde_shift) - i915_pte_index(addr, pde_shift);
-}
-
-static inline u32 i915_pde_index(u64 addr, u32 shift)
-{
-	return (addr >> shift) & I915_PDE_MASK;
-}
-
-static inline u32 gen6_pte_index(u32 addr)
-{
-	return i915_pte_index(addr, GEN6_PDE_SHIFT);
-}
-
-static inline u32 gen6_pte_count(u32 addr, u32 length)
-{
-	return i915_pte_count(addr, length, GEN6_PDE_SHIFT);
-}
-
-static inline u32 gen6_pde_index(u32 addr)
-{
-	return i915_pde_index(addr, GEN6_PDE_SHIFT);
-}
-
-static inline struct i915_page_table *
-i915_pt_entry(const struct i915_page_directory * const pd,
-	      const unsigned short n)
-{
-	return pd->entry[n];
-}
-
-static inline struct i915_page_directory *
-i915_pd_entry(const struct i915_page_directory * const pdp,
-	      const unsigned short n)
-{
-	return pdp->entry[n];
-}
-
-static inline dma_addr_t
-i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n)
-{
-	struct i915_page_dma *pt = ppgtt->pd->entry[n];
-
-	return px_dma(pt ?: px_base(&ppgtt->vm.scratch[ppgtt->vm.top]));
-}
-
-static inline struct i915_ggtt *
-i915_vm_to_ggtt(struct i915_address_space *vm)
-{
-	BUILD_BUG_ON(offsetof(struct i915_ggtt, vm));
-	GEM_BUG_ON(!i915_is_ggtt(vm));
-	return container_of(vm, struct i915_ggtt, vm);
-}
-
-static inline struct i915_ppgtt *
-i915_vm_to_ppgtt(struct i915_address_space *vm)
-{
-	BUILD_BUG_ON(offsetof(struct i915_ppgtt, vm));
-	GEM_BUG_ON(i915_is_ggtt(vm));
-	return container_of(vm, struct i915_ppgtt, vm);
-}
-
-int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv);
-int i915_ggtt_init_hw(struct drm_i915_private *dev_priv);
-int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv);
-void i915_ggtt_enable_guc(struct i915_ggtt *ggtt);
-void i915_ggtt_disable_guc(struct i915_ggtt *ggtt);
-int i915_init_ggtt(struct drm_i915_private *dev_priv);
-void i915_ggtt_driver_release(struct drm_i915_private *dev_priv);
-
-static inline bool i915_ggtt_has_aperture(const struct i915_ggtt *ggtt)
-{
-	return ggtt->mappable_end > 0;
-}
-
-int i915_ppgtt_init_hw(struct intel_gt *gt);
-
-struct i915_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv);
-
-static inline struct i915_address_space *
-i915_vm_get(struct i915_address_space *vm)
-{
-	kref_get(&vm->ref);
-	return vm;
-}
-
-void i915_vm_release(struct kref *kref);
-
-static inline void i915_vm_put(struct i915_address_space *vm)
-{
-	kref_put(&vm->ref, i915_vm_release);
-}
-
-static inline struct i915_address_space *
-i915_vm_open(struct i915_address_space *vm)
-{
-	GEM_BUG_ON(!atomic_read(&vm->open));
-	atomic_inc(&vm->open);
-	return i915_vm_get(vm);
-}
-
-static inline bool
-i915_vm_tryopen(struct i915_address_space *vm)
-{
-	if (atomic_add_unless(&vm->open, 1, 0))
-		return i915_vm_get(vm);
-
-	return false;
-}
-
-void __i915_vm_close(struct i915_address_space *vm);
-
-static inline void
-i915_vm_close(struct i915_address_space *vm)
-{
-	GEM_BUG_ON(!atomic_read(&vm->open));
-	if (atomic_dec_and_test(&vm->open))
-		__i915_vm_close(vm);
-
-	i915_vm_put(vm);
-}
-
-int gen6_ppgtt_pin(struct i915_ppgtt *base);
-void gen6_ppgtt_unpin(struct i915_ppgtt *base);
-void gen6_ppgtt_unpin_all(struct i915_ppgtt *base);
-
-void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv);
-void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv);
+struct i915_address_space;
 
 int __must_check i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 					    struct sg_table *pages);
@@ -663,6 +46,6 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 #define PIN_GLOBAL		BIT_ULL(10) /* I915_VMA_GLOBAL_BIND */
 #define PIN_USER		BIT_ULL(11) /* I915_VMA_LOCAL_BIND */
 
-#define PIN_OFFSET_MASK		(-I915_GTT_PAGE_SIZE)
+#define PIN_OFFSET_MASK		I915_GTT_PAGE_MASK
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index cf8a8c3ef047..54fce81d5724 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -2,6 +2,7 @@
  * SPDX-License-Identifier: MIT
  */
 
+#include "gem/i915_gem_mman.h"
 #include "gt/intel_engine_user.h"
 
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/i915_globals.c b/drivers/gpu/drm/i915/i915_globals.c
index be127cd28931..3aa213684293 100644
--- a/drivers/gpu/drm/i915/i915_globals.c
+++ b/drivers/gpu/drm/i915/i915_globals.c
@@ -20,7 +20,10 @@ static LIST_HEAD(globals);
 static atomic_t active;
 static atomic_t epoch;
 static struct park_work {
-	struct rcu_work work;
+	struct delayed_work work;
+	struct rcu_head rcu;
+	unsigned long flags;
+#define PENDING 0
 	int epoch;
 } park;
 
@@ -37,11 +40,33 @@ static void i915_globals_shrink(void)
 		global->shrink();
 }
 
+static void __i915_globals_grace(struct rcu_head *rcu)
+{
+	/* Ratelimit parking as shrinking is quite slow */
+	schedule_delayed_work(&park.work, round_jiffies_up_relative(2 * HZ));
+}
+
+static void __i915_globals_queue_rcu(void)
+{
+	park.epoch = atomic_inc_return(&epoch);
+	if (!atomic_read(&active)) {
+		init_rcu_head(&park.rcu);
+		call_rcu(&park.rcu, __i915_globals_grace);
+	}
+}
+
 static void __i915_globals_park(struct work_struct *work)
 {
+	destroy_rcu_head(&park.rcu);
+
 	/* Confirm nothing woke up in the last grace period */
-	if (park.epoch == atomic_read(&epoch))
-		i915_globals_shrink();
+	if (park.epoch != atomic_read(&epoch)) {
+		__i915_globals_queue_rcu();
+		return;
+	}
+
+	clear_bit(PENDING, &park.flags);
+	i915_globals_shrink();
 }
 
 void __init i915_global_register(struct i915_global *global)
@@ -85,7 +110,7 @@ int __init i915_globals_init(void)
 		}
 	}
 
-	INIT_RCU_WORK(&park.work, __i915_globals_park);
+	INIT_DELAYED_WORK(&park.work, __i915_globals_park);
 	return 0;
 }
 
@@ -103,8 +128,9 @@ void i915_globals_park(void)
 	if (!atomic_dec_and_test(&active))
 		return;
 
-	park.epoch = atomic_inc_return(&epoch);
-	queue_rcu_work(system_wq, &park.work);
+	/* Queue cleanup after the next RCU grace period has freed slabs */
+	if (!test_and_set_bit(PENDING, &park.flags))
+		__i915_globals_queue_rcu();
 }
 
 void i915_globals_unpark(void)
@@ -113,12 +139,21 @@ void i915_globals_unpark(void)
 	atomic_inc(&active);
 }
 
+static void __exit __i915_globals_flush(void)
+{
+	atomic_inc(&active); /* skip shrinking */
+
+	rcu_barrier(); /* wait for the work to be queued */
+	flush_delayed_work(&park.work);
+
+	atomic_dec(&active);
+}
+
 void __exit i915_globals_exit(void)
 {
-	/* Flush any residual park_work */
-	atomic_inc(&epoch);
-	flush_rcu_work(&park.work);
+	GEM_BUG_ON(atomic_read(&active));
 
+	__i915_globals_flush();
 	__i915_globals_cleanup();
 
 	/* And ensure that our DESTROY_BY_RCU slabs are truly destroyed */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 3c85cb0ee99f..4c1836f0a991 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -41,6 +41,7 @@
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_lmem.h"
+#include "gt/intel_gt_pm.h"
 
 #include "i915_drv.h"
 #include "i915_gpu_error.h"
@@ -232,14 +233,13 @@ static void pool_free(struct pagevec *pv, void *addr)
 
 #ifdef CONFIG_DRM_I915_COMPRESS_ERROR
 
-struct compress {
+struct i915_vma_compress {
 	struct pagevec pool;
 	struct z_stream_s zstream;
 	void *tmp;
-	bool wc;
 };
 
-static bool compress_init(struct compress *c)
+static bool compress_init(struct i915_vma_compress *c)
 {
 	struct z_stream_s *zstream = &c->zstream;
 
@@ -261,7 +261,7 @@ static bool compress_init(struct compress *c)
 	return true;
 }
 
-static bool compress_start(struct compress *c)
+static bool compress_start(struct i915_vma_compress *c)
 {
 	struct z_stream_s *zstream = &c->zstream;
 	void *workspace = zstream->workspace;
@@ -272,8 +272,8 @@ static bool compress_start(struct compress *c)
 	return zlib_deflateInit(zstream, Z_DEFAULT_COMPRESSION) == Z_OK;
 }
 
-static void *compress_next_page(struct compress *c,
-				struct drm_i915_error_object *dst)
+static void *compress_next_page(struct i915_vma_compress *c,
+				struct i915_vma_coredump *dst)
 {
 	void *page;
 
@@ -287,14 +287,15 @@ static void *compress_next_page(struct compress *c,
 	return dst->pages[dst->page_count++] = page;
 }
 
-static int compress_page(struct compress *c,
+static int compress_page(struct i915_vma_compress *c,
 			 void *src,
-			 struct drm_i915_error_object *dst)
+			 struct i915_vma_coredump *dst,
+			 bool wc)
 {
 	struct z_stream_s *zstream = &c->zstream;
 
 	zstream->next_in = src;
-	if (c->wc && c->tmp && i915_memcpy_from_wc(c->tmp, src, PAGE_SIZE))
+	if (wc && c->tmp && i915_memcpy_from_wc(c->tmp, src, PAGE_SIZE))
 		zstream->next_in = c->tmp;
 	zstream->avail_in = PAGE_SIZE;
 
@@ -318,8 +319,8 @@ static int compress_page(struct compress *c,
 	return 0;
 }
 
-static int compress_flush(struct compress *c,
-			  struct drm_i915_error_object *dst)
+static int compress_flush(struct i915_vma_compress *c,
+			  struct i915_vma_coredump *dst)
 {
 	struct z_stream_s *zstream = &c->zstream;
 
@@ -347,12 +348,12 @@ end:
 	return 0;
 }
 
-static void compress_finish(struct compress *c)
+static void compress_finish(struct i915_vma_compress *c)
 {
 	zlib_deflateEnd(&c->zstream);
 }
 
-static void compress_fini(struct compress *c)
+static void compress_fini(struct i915_vma_compress *c)
 {
 	kfree(c->zstream.workspace);
 	if (c->tmp)
@@ -367,24 +368,24 @@ static void err_compression_marker(struct drm_i915_error_state_buf *m)
 
 #else
 
-struct compress {
+struct i915_vma_compress {
 	struct pagevec pool;
-	bool wc;
 };
 
-static bool compress_init(struct compress *c)
+static bool compress_init(struct i915_vma_compress *c)
 {
 	return pool_init(&c->pool, ALLOW_FAIL) == 0;
 }
 
-static bool compress_start(struct compress *c)
+static bool compress_start(struct i915_vma_compress *c)
 {
 	return true;
 }
 
-static int compress_page(struct compress *c,
+static int compress_page(struct i915_vma_compress *c,
 			 void *src,
-			 struct drm_i915_error_object *dst)
+			 struct i915_vma_coredump *dst,
+			 bool wc)
 {
 	void *ptr;
 
@@ -392,24 +393,24 @@ static int compress_page(struct compress *c,
 	if (!ptr)
 		return -ENOMEM;
 
-	if (!(c->wc && i915_memcpy_from_wc(ptr, src, PAGE_SIZE)))
+	if (!(wc && i915_memcpy_from_wc(ptr, src, PAGE_SIZE)))
 		memcpy(ptr, src, PAGE_SIZE);
 	dst->pages[dst->page_count++] = ptr;
 
 	return 0;
 }
 
-static int compress_flush(struct compress *c,
-			  struct drm_i915_error_object *dst)
+static int compress_flush(struct i915_vma_compress *c,
+			  struct i915_vma_coredump *dst)
 {
 	return 0;
 }
 
-static void compress_finish(struct compress *c)
+static void compress_finish(struct i915_vma_compress *c)
 {
 }
 
-static void compress_fini(struct compress *c)
+static void compress_fini(struct i915_vma_compress *c)
 {
 	pool_fini(&c->pool);
 }
@@ -422,7 +423,7 @@ static void err_compression_marker(struct drm_i915_error_state_buf *m)
 #endif
 
 static void error_print_instdone(struct drm_i915_error_state_buf *m,
-				 const struct drm_i915_error_engine *ee)
+				 const struct intel_engine_coredump *ee)
 {
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(m->i915)->sseu;
 	int slice;
@@ -453,40 +454,56 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 
 static void error_print_request(struct drm_i915_error_state_buf *m,
 				const char *prefix,
-				const struct drm_i915_error_request *erq,
-				const unsigned long epoch)
+				const struct i915_request_coredump *erq)
 {
 	if (!erq->seqno)
 		return;
 
-	err_printf(m, "%s pid %d, seqno %8x:%08x%s%s, prio %d, emitted %dms, start %08x, head %08x, tail %08x\n",
+	err_printf(m, "%s pid %d, seqno %8x:%08x%s%s, prio %d, start %08x, head %08x, tail %08x\n",
 		   prefix, erq->pid, erq->context, erq->seqno,
 		   test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
 			    &erq->flags) ? "!" : "",
 		   test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 			    &erq->flags) ? "+" : "",
 		   erq->sched_attr.priority,
-		   jiffies_to_msecs(erq->jiffies - epoch),
 		   erq->start, erq->head, erq->tail);
 }
 
 static void error_print_context(struct drm_i915_error_state_buf *m,
 				const char *header,
-				const struct drm_i915_error_context *ctx)
+				const struct i915_gem_context_coredump *ctx)
 {
 	err_printf(m, "%s%s[%d] prio %d, guilty %d active %d\n",
 		   header, ctx->comm, ctx->pid, ctx->sched_attr.priority,
 		   ctx->guilty, ctx->active);
 }
 
+static struct i915_vma_coredump *
+__find_vma(struct i915_vma_coredump *vma, const char *name)
+{
+	while (vma) {
+		if (strcmp(vma->name, name) == 0)
+			return vma;
+		vma = vma->next;
+	}
+
+	return NULL;
+}
+
+static struct i915_vma_coredump *
+find_batch(const struct intel_engine_coredump *ee)
+{
+	return __find_vma(ee->vma, "batch");
+}
+
 static void error_print_engine(struct drm_i915_error_state_buf *m,
-			       const struct drm_i915_error_engine *ee,
-			       const unsigned long epoch)
+			       const struct intel_engine_coredump *ee)
 {
+	struct i915_vma_coredump *batch;
 	int n;
 
 	err_printf(m, "%s command stream:\n", ee->engine->name);
-	err_printf(m, "  IDLE?: %s\n", yesno(ee->idle));
+	err_printf(m, "  CCID:  0x%08x\n", ee->ccid);
 	err_printf(m, "  START: 0x%08x\n", ee->start);
 	err_printf(m, "  HEAD:  0x%08x [0x%08x]\n", ee->head, ee->rq_head);
 	err_printf(m, "  TAIL:  0x%08x [0x%08x, 0x%08x]\n",
@@ -501,9 +518,10 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 
 	error_print_instdone(m, ee);
 
-	if (ee->batchbuffer) {
-		u64 start = ee->batchbuffer->gtt_offset;
-		u64 end = start + ee->batchbuffer->gtt_size;
+	batch = find_batch(ee);
+	if (batch) {
+		u64 start = batch->gtt_offset;
+		u64 end = start + batch->gtt_size;
 
 		err_printf(m, "  batch: [0x%08x_%08x, 0x%08x_%08x]\n",
 			   upper_32_bits(start), lower_32_bits(start),
@@ -535,13 +553,11 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 				   ee->vm_info.pp_dir_base);
 		}
 	}
-	err_printf(m, "  ring->head: 0x%08x\n", ee->cpu_ring_head);
-	err_printf(m, "  ring->tail: 0x%08x\n", ee->cpu_ring_tail);
 	err_printf(m, "  engine reset count: %u\n", ee->reset_count);
 
 	for (n = 0; n < ee->num_ports; n++) {
 		err_printf(m, "  ELSP[%d]:", n);
-		error_print_request(m, " ", &ee->execlist[n], epoch);
+		error_print_request(m, " ", &ee->execlist[n]);
 	}
 
 	error_print_context(m, "  Active context: ", &ee->context);
@@ -556,38 +572,35 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
-static void print_error_obj(struct drm_i915_error_state_buf *m,
+static void print_error_vma(struct drm_i915_error_state_buf *m,
 			    const struct intel_engine_cs *engine,
-			    const char *name,
-			    const struct drm_i915_error_object *obj)
+			    const struct i915_vma_coredump *vma)
 {
 	char out[ASCII85_BUFSZ];
 	int page;
 
-	if (!obj)
+	if (!vma)
 		return;
 
-	if (name) {
-		err_printf(m, "%s --- %s = 0x%08x %08x\n",
-			   engine ? engine->name : "global", name,
-			   upper_32_bits(obj->gtt_offset),
-			   lower_32_bits(obj->gtt_offset));
-	}
+	err_printf(m, "%s --- %s = 0x%08x %08x\n",
+		   engine ? engine->name : "global", vma->name,
+		   upper_32_bits(vma->gtt_offset),
+		   lower_32_bits(vma->gtt_offset));
 
-	if (obj->gtt_page_sizes > I915_GTT_PAGE_SIZE_4K)
-		err_printf(m, "gtt_page_sizes = 0x%08x\n", obj->gtt_page_sizes);
+	if (vma->gtt_page_sizes > I915_GTT_PAGE_SIZE_4K)
+		err_printf(m, "gtt_page_sizes = 0x%08x\n", vma->gtt_page_sizes);
 
 	err_compression_marker(m);
-	for (page = 0; page < obj->page_count; page++) {
+	for (page = 0; page < vma->page_count; page++) {
 		int i, len;
 
 		len = PAGE_SIZE;
-		if (page == obj->page_count - 1)
-			len -= obj->unused;
+		if (page == vma->page_count - 1)
+			len -= vma->unused;
 		len = ascii85_encode_len(len);
 
 		for (i = 0; i < len; i++)
-			err_puts(m, ascii85_encode(obj->pages[page][i], out));
+			err_puts(m, ascii85_encode(vma->pages[page][i], out));
 	}
 	err_puts(m, "\n");
 }
@@ -599,9 +612,10 @@ static void err_print_capabilities(struct drm_i915_error_state_buf *m,
 {
 	struct drm_printer p = i915_error_printer(m);
 
-	intel_device_info_dump_flags(info, &p);
+	intel_device_info_print_static(info, &p);
+	intel_device_info_print_runtime(runtime, &p);
+	intel_device_info_print_topology(&runtime->sseu, &p);
 	intel_driver_caps_print(caps, &p);
-	intel_device_info_dump_topology(&runtime->sseu, &p);
 }
 
 static void err_print_params(struct drm_i915_error_state_buf *m,
@@ -625,18 +639,13 @@ static void err_print_pciid(struct drm_i915_error_state_buf *m,
 }
 
 static void err_print_uc(struct drm_i915_error_state_buf *m,
-			 const struct i915_error_uc *error_uc)
+			 const struct intel_uc_coredump *error_uc)
 {
 	struct drm_printer p = i915_error_printer(m);
-	const struct i915_gpu_state *error =
-		container_of(error_uc, typeof(*error), uc);
-
-	if (!error->device_info.has_gt_uc)
-		return;
 
 	intel_uc_fw_dump(&error_uc->guc_fw, &p);
 	intel_uc_fw_dump(&error_uc->huc_fw, &p);
-	print_error_obj(m, NULL, "GuC log buffer", error_uc->guc_log);
+	print_error_vma(m, NULL, error_uc->guc_log);
 }
 
 static void err_free_sgl(struct scatterlist *sgl)
@@ -656,12 +665,69 @@ static void err_free_sgl(struct scatterlist *sgl)
 	}
 }
 
+static void err_print_gt(struct drm_i915_error_state_buf *m,
+			 struct intel_gt_coredump *gt)
+{
+	const struct intel_engine_coredump *ee;
+	int i;
+
+	err_printf(m, "GT awake: %s\n", yesno(gt->awake));
+	err_printf(m, "EIR: 0x%08x\n", gt->eir);
+	err_printf(m, "IER: 0x%08x\n", gt->ier);
+	for (i = 0; i < gt->ngtier; i++)
+		err_printf(m, "GTIER[%d]: 0x%08x\n", i, gt->gtier[i]);
+	err_printf(m, "PGTBL_ER: 0x%08x\n", gt->pgtbl_er);
+	err_printf(m, "FORCEWAKE: 0x%08x\n", gt->forcewake);
+	err_printf(m, "DERRMR: 0x%08x\n", gt->derrmr);
+
+	for (i = 0; i < gt->nfence; i++)
+		err_printf(m, "  fence[%d] = %08llx\n", i, gt->fence[i]);
+
+	if (IS_GEN_RANGE(m->i915, 6, 11)) {
+		err_printf(m, "ERROR: 0x%08x\n", gt->error);
+		err_printf(m, "DONE_REG: 0x%08x\n", gt->done_reg);
+	}
+
+	if (INTEL_GEN(m->i915) >= 8)
+		err_printf(m, "FAULT_TLB_DATA: 0x%08x 0x%08x\n",
+			   gt->fault_data1, gt->fault_data0);
+
+	if (IS_GEN(m->i915, 7))
+		err_printf(m, "ERR_INT: 0x%08x\n", gt->err_int);
+
+	if (IS_GEN_RANGE(m->i915, 8, 11))
+		err_printf(m, "GTT_CACHE_EN: 0x%08x\n", gt->gtt_cache);
+
+	if (IS_GEN(m->i915, 12))
+		err_printf(m, "AUX_ERR_DBG: 0x%08x\n", gt->aux_err);
+
+	if (INTEL_GEN(m->i915) >= 12) {
+		int i;
+
+		for (i = 0; i < GEN12_SFC_DONE_MAX; i++)
+			err_printf(m, "  SFC_DONE[%d]: 0x%08x\n", i,
+				   gt->sfc_done[i]);
+
+		err_printf(m, "  GAM_DONE: 0x%08x\n", gt->gam_done);
+	}
+
+	for (ee = gt->engine; ee; ee = ee->next) {
+		const struct i915_vma_coredump *vma;
+
+		error_print_engine(m, ee);
+		for (vma = ee->vma; vma; vma = vma->next)
+			print_error_vma(m, ee->engine, vma);
+	}
+
+	if (gt->uc)
+		err_print_uc(m, gt->uc);
+}
+
 static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
-			       struct i915_gpu_state *error)
+			       struct i915_gpu_coredump *error)
 {
-	const struct drm_i915_error_engine *ee;
+	const struct intel_engine_coredump *ee;
 	struct timespec64 ts;
-	int i, j;
 
 	if (*error->error_msg)
 		err_printf(m, "%s\n", error->error_msg);
@@ -681,7 +747,7 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	err_printf(m, "Capture: %lu jiffies; %d ms ago\n",
 		   error->capture, jiffies_to_msecs(jiffies - error->capture));
 
-	for (ee = error->engine; ee; ee = ee->next)
+	for (ee = error->gt ? error->gt->engine : NULL; ee; ee = ee->next)
 		err_printf(m, "Active process (on ring %s): %s [%d]\n",
 			   ee->engine->name,
 			   ee->context.comm,
@@ -707,90 +773,11 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 			   CSR_VERSION_MINOR(csr->version));
 	}
 
-	err_printf(m, "GT awake: %s\n", yesno(error->awake));
 	err_printf(m, "RPM wakelock: %s\n", yesno(error->wakelock));
 	err_printf(m, "PM suspended: %s\n", yesno(error->suspended));
-	err_printf(m, "EIR: 0x%08x\n", error->eir);
-	err_printf(m, "IER: 0x%08x\n", error->ier);
-	for (i = 0; i < error->ngtier; i++)
-		err_printf(m, "GTIER[%d]: 0x%08x\n", i, error->gtier[i]);
-	err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
-	err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
-	err_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
-	err_printf(m, "CCID: 0x%08x\n", error->ccid);
-
-	for (i = 0; i < error->nfence; i++)
-		err_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
-
-	if (IS_GEN_RANGE(m->i915, 6, 11)) {
-		err_printf(m, "ERROR: 0x%08x\n", error->error);
-		err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
-	}
-
-	if (INTEL_GEN(m->i915) >= 8)
-		err_printf(m, "FAULT_TLB_DATA: 0x%08x 0x%08x\n",
-			   error->fault_data1, error->fault_data0);
-
-	if (IS_GEN(m->i915, 7))
-		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
-
-	if (IS_GEN_RANGE(m->i915, 8, 11))
-		err_printf(m, "GTT_CACHE_EN: 0x%08x\n", error->gtt_cache);
-
-	if (IS_GEN(m->i915, 12))
-		err_printf(m, "AUX_ERR_DBG: 0x%08x\n", error->aux_err);
-
-	if (INTEL_GEN(m->i915) >= 12) {
-		int i;
-
-		for (i = 0; i < GEN12_SFC_DONE_MAX; i++)
-			err_printf(m, "  SFC_DONE[%d]: 0x%08x\n", i,
-				   error->sfc_done[i]);
-
-		err_printf(m, "  GAM_DONE: 0x%08x\n", error->gam_done);
-	}
-
-	for (ee = error->engine; ee; ee = ee->next)
-		error_print_engine(m, ee, error->capture);
-
-	for (ee = error->engine; ee; ee = ee->next) {
-		const struct drm_i915_error_object *obj;
-
-		obj = ee->batchbuffer;
-		if (obj) {
-			err_puts(m, ee->engine->name);
-			if (ee->context.pid)
-				err_printf(m, " (submitted by %s [%d])",
-					   ee->context.comm,
-					   ee->context.pid);
-			err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
-				   upper_32_bits(obj->gtt_offset),
-				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, ee->engine, NULL, obj);
-		}
 
-		for (j = 0; j < ee->user_bo_count; j++)
-			print_error_obj(m, ee->engine, "user", ee->user_bo[j]);
-
-		if (ee->num_requests) {
-			err_printf(m, "%s --- %d requests\n",
-				   ee->engine->name,
-				   ee->num_requests);
-			for (j = 0; j < ee->num_requests; j++)
-				error_print_request(m, " ",
-						    &ee->requests[j],
-						    error->capture);
-		}
-
-		print_error_obj(m, ee->engine, "ringbuffer", ee->ringbuffer);
-		print_error_obj(m, ee->engine, "HW Status", ee->hws_page);
-		print_error_obj(m, ee->engine, "HW context", ee->ctx);
-		print_error_obj(m, ee->engine, "WA context", ee->wa_ctx);
-		print_error_obj(m, ee->engine,
-				"WA batchbuffer", ee->wa_batchbuffer);
-		print_error_obj(m, ee->engine,
-				"NULL context", ee->default_state);
-	}
+	if (error->gt)
+		err_print_gt(m, error->gt);
 
 	if (error->overlay)
 		intel_overlay_print_error_state(m, error->overlay);
@@ -801,10 +788,9 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	err_print_capabilities(m, &error->device_info, &error->runtime_info,
 			       &error->driver_caps);
 	err_print_params(m, &error->params);
-	err_print_uc(m, &error->uc);
 }
 
-static int err_print_to_sgl(struct i915_gpu_state *error)
+static int err_print_to_sgl(struct i915_gpu_coredump *error)
 {
 	struct drm_i915_error_state_buf m;
 
@@ -841,8 +827,8 @@ static int err_print_to_sgl(struct i915_gpu_state *error)
 	return 0;
 }
 
-ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error,
-				      char *buf, loff_t off, size_t rem)
+ssize_t i915_gpu_coredump_copy_to_buffer(struct i915_gpu_coredump *error,
+					 char *buf, loff_t off, size_t rem)
 {
 	struct scatterlist *sg;
 	size_t count;
@@ -905,85 +891,88 @@ ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error,
 	return count;
 }
 
-static void i915_error_object_free(struct drm_i915_error_object *obj)
+static void i915_vma_coredump_free(struct i915_vma_coredump *vma)
 {
-	int page;
+	while (vma) {
+		struct i915_vma_coredump *next = vma->next;
+		int page;
 
-	if (obj == NULL)
-		return;
-
-	for (page = 0; page < obj->page_count; page++)
-		free_page((unsigned long)obj->pages[page]);
+		for (page = 0; page < vma->page_count; page++)
+			free_page((unsigned long)vma->pages[page]);
 
-	kfree(obj);
+		kfree(vma);
+		vma = next;
+	}
 }
 
-
-static void cleanup_params(struct i915_gpu_state *error)
+static void cleanup_params(struct i915_gpu_coredump *error)
 {
 	i915_params_free(&error->params);
 }
 
-static void cleanup_uc_state(struct i915_gpu_state *error)
+static void cleanup_uc(struct intel_uc_coredump *uc)
 {
-	struct i915_error_uc *error_uc = &error->uc;
+	kfree(uc->guc_fw.path);
+	kfree(uc->huc_fw.path);
+	i915_vma_coredump_free(uc->guc_log);
 
-	kfree(error_uc->guc_fw.path);
-	kfree(error_uc->huc_fw.path);
-	i915_error_object_free(error_uc->guc_log);
+	kfree(uc);
 }
 
-void __i915_gpu_state_free(struct kref *error_ref)
+static void cleanup_gt(struct intel_gt_coredump *gt)
 {
-	struct i915_gpu_state *error =
-		container_of(error_ref, typeof(*error), ref);
-	long i;
+	while (gt->engine) {
+		struct intel_engine_coredump *ee = gt->engine;
 
-	while (error->engine) {
-		struct drm_i915_error_engine *ee = error->engine;
+		gt->engine = ee->next;
 
-		error->engine = ee->next;
+		i915_vma_coredump_free(ee->vma);
+		kfree(ee);
+	}
 
-		for (i = 0; i < ee->user_bo_count; i++)
-			i915_error_object_free(ee->user_bo[i]);
-		kfree(ee->user_bo);
+	if (gt->uc)
+		cleanup_uc(gt->uc);
 
-		i915_error_object_free(ee->batchbuffer);
-		i915_error_object_free(ee->wa_batchbuffer);
-		i915_error_object_free(ee->ringbuffer);
-		i915_error_object_free(ee->hws_page);
-		i915_error_object_free(ee->ctx);
-		i915_error_object_free(ee->wa_ctx);
+	kfree(gt);
+}
 
-		kfree(ee->requests);
-		kfree(ee);
+void __i915_gpu_coredump_free(struct kref *error_ref)
+{
+	struct i915_gpu_coredump *error =
+		container_of(error_ref, typeof(*error), ref);
+
+	while (error->gt) {
+		struct intel_gt_coredump *gt = error->gt;
+
+		error->gt = gt->next;
+		cleanup_gt(gt);
 	}
 
 	kfree(error->overlay);
 	kfree(error->display);
 
 	cleanup_params(error);
-	cleanup_uc_state(error);
 
 	err_free_sgl(error->sgl);
 	kfree(error);
 }
 
-static struct drm_i915_error_object *
-i915_error_object_create(struct drm_i915_private *i915,
-			 struct i915_vma *vma,
-			 struct compress *compress)
+static struct i915_vma_coredump *
+i915_vma_coredump_create(const struct intel_gt *gt,
+			 const struct i915_vma *vma,
+			 const char *name,
+			 struct i915_vma_compress *compress)
 {
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct i915_ggtt *ggtt = gt->ggtt;
 	const u64 slot = ggtt->error_capture.start;
-	struct drm_i915_error_object *dst;
+	struct i915_vma_coredump *dst;
 	unsigned long num_pages;
 	struct sgt_iter iter;
 	int ret;
 
 	might_sleep();
 
-	if (!vma || !vma->pages)
+	if (!vma || !vma->pages || !compress)
 		return NULL;
 
 	num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT;
@@ -997,6 +986,9 @@ i915_error_object_create(struct drm_i915_private *i915,
 		return NULL;
 	}
 
+	strcpy(dst->name, name);
+	dst->next = NULL;
+
 	dst->gtt_offset = vma->node.start;
 	dst->gtt_size = vma->node.size;
 	dst->gtt_page_sizes = vma->page_sizes.gtt;
@@ -1004,9 +996,6 @@ i915_error_object_create(struct drm_i915_private *i915,
 	dst->page_count = 0;
 	dst->unused = 0;
 
-	compress->wc = i915_gem_object_is_lmem(vma->obj) ||
-		       drm_mm_node_allocated(&ggtt->error_capture);
-
 	ret = -EINVAL;
 	if (drm_mm_node_allocated(&ggtt->error_capture)) {
 		void __iomem *s;
@@ -1015,9 +1004,12 @@ i915_error_object_create(struct drm_i915_private *i915,
 		for_each_sgt_daddr(dma, iter, vma->pages) {
 			ggtt->vm.insert_page(&ggtt->vm, dma, slot,
 					     I915_CACHE_NONE, 0);
+			mb();
 
 			s = io_mapping_map_wc(&ggtt->iomap, slot, PAGE_SIZE);
-			ret = compress_page(compress, (void  __force *)s, dst);
+			ret = compress_page(compress,
+					    (void  __force *)s, dst,
+					    true);
 			io_mapping_unmap(s);
 			if (ret)
 				break;
@@ -1030,7 +1022,9 @@ i915_error_object_create(struct drm_i915_private *i915,
 			void __iomem *s;
 
 			s = io_mapping_map_wc(&mem->iomap, dma, PAGE_SIZE);
-			ret = compress_page(compress, (void __force *)s, dst);
+			ret = compress_page(compress,
+					    (void __force *)s, dst,
+					    true);
 			io_mapping_unmap(s);
 			if (ret)
 				break;
@@ -1044,8 +1038,8 @@ i915_error_object_create(struct drm_i915_private *i915,
 			drm_clflush_pages(&page, 1);
 
 			s = kmap(page);
-			ret = compress_page(compress, s, dst);
-			kunmap(s);
+			ret = compress_page(compress, s, dst, false);
+			kunmap(page);
 
 			drm_clflush_pages(&page, 1);
 
@@ -1065,77 +1059,56 @@ i915_error_object_create(struct drm_i915_private *i915,
 	return dst;
 }
 
-/*
- * Generate a semi-unique error code. The code is not meant to have meaning, The
- * code's only purpose is to try to prevent false duplicated bug reports by
- * grossly estimating a GPU error state.
- *
- * TODO Ideally, hashing the batchbuffer would be a very nice way to determine
- * the hang if we could strip the GTT offset information from it.
- *
- * It's only a small step better than a random number in its current form.
- */
-static u32 i915_error_generate_code(struct i915_gpu_state *error)
+static void gt_record_fences(struct intel_gt_coredump *gt)
 {
-	const struct drm_i915_error_engine *ee = error->engine;
-
-	/*
-	 * IPEHR would be an ideal way to detect errors, as it's the gross
-	 * measure of "the command that hung." However, has some very common
-	 * synchronization commands which almost always appear in the case
-	 * strictly a client bug. Use instdone to differentiate those some.
-	 */
-	return ee ? ee->ipehr ^ ee->instdone.instdone : 0;
-}
-
-static void gem_record_fences(struct i915_gpu_state *error)
-{
-	struct drm_i915_private *dev_priv = error->i915;
-	struct intel_uncore *uncore = &dev_priv->uncore;
+	struct i915_ggtt *ggtt = gt->_gt->ggtt;
+	struct intel_uncore *uncore = gt->_gt->uncore;
 	int i;
 
-	if (INTEL_GEN(dev_priv) >= 6) {
-		for (i = 0; i < dev_priv->ggtt.num_fences; i++)
-			error->fence[i] =
+	if (INTEL_GEN(uncore->i915) >= 6) {
+		for (i = 0; i < ggtt->num_fences; i++)
+			gt->fence[i] =
 				intel_uncore_read64(uncore,
 						    FENCE_REG_GEN6_LO(i));
-	} else if (INTEL_GEN(dev_priv) >= 4) {
-		for (i = 0; i < dev_priv->ggtt.num_fences; i++)
-			error->fence[i] =
+	} else if (INTEL_GEN(uncore->i915) >= 4) {
+		for (i = 0; i < ggtt->num_fences; i++)
+			gt->fence[i] =
 				intel_uncore_read64(uncore,
 						    FENCE_REG_965_LO(i));
 	} else {
-		for (i = 0; i < dev_priv->ggtt.num_fences; i++)
-			error->fence[i] =
+		for (i = 0; i < ggtt->num_fences; i++)
+			gt->fence[i] =
 				intel_uncore_read(uncore, FENCE_REG(i));
 	}
-	error->nfence = i;
+	gt->nfence = i;
 }
 
-static void error_record_engine_registers(struct i915_gpu_state *error,
-					  struct intel_engine_cs *engine,
-					  struct drm_i915_error_engine *ee)
+static void engine_record_registers(struct intel_engine_coredump *ee)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
+	const struct intel_engine_cs *engine = ee->engine;
+	struct drm_i915_private *i915 = engine->i915;
 
-	if (INTEL_GEN(dev_priv) >= 6) {
+	if (INTEL_GEN(i915) >= 6) {
 		ee->rc_psmi = ENGINE_READ(engine, RING_PSMI_CTL);
 
-		if (INTEL_GEN(dev_priv) >= 12)
-			ee->fault_reg = I915_READ(GEN12_RING_FAULT_REG);
-		else if (INTEL_GEN(dev_priv) >= 8)
-			ee->fault_reg = I915_READ(GEN8_RING_FAULT_REG);
+		if (INTEL_GEN(i915) >= 12)
+			ee->fault_reg = intel_uncore_read(engine->uncore,
+							  GEN12_RING_FAULT_REG);
+		else if (INTEL_GEN(i915) >= 8)
+			ee->fault_reg = intel_uncore_read(engine->uncore,
+							  GEN8_RING_FAULT_REG);
 		else
 			ee->fault_reg = GEN6_RING_FAULT_REG_READ(engine);
 	}
 
-	if (INTEL_GEN(dev_priv) >= 4) {
+	if (INTEL_GEN(i915) >= 4) {
 		ee->faddr = ENGINE_READ(engine, RING_DMA_FADD);
 		ee->ipeir = ENGINE_READ(engine, RING_IPEIR);
 		ee->ipehr = ENGINE_READ(engine, RING_IPEHR);
 		ee->instps = ENGINE_READ(engine, RING_INSTPS);
 		ee->bbaddr = ENGINE_READ(engine, RING_BBADDR);
-		if (INTEL_GEN(dev_priv) >= 8) {
+		ee->ccid = ENGINE_READ(engine, CCID);
+		if (INTEL_GEN(i915) >= 8) {
 			ee->faddr |= (u64)ENGINE_READ(engine, RING_DMA_FADD_UDW) << 32;
 			ee->bbaddr |= (u64)ENGINE_READ(engine, RING_BBADDR_UDW) << 32;
 		}
@@ -1154,13 +1127,13 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
 	ee->head = ENGINE_READ(engine, RING_HEAD);
 	ee->tail = ENGINE_READ(engine, RING_TAIL);
 	ee->ctl = ENGINE_READ(engine, RING_CTL);
-	if (INTEL_GEN(dev_priv) > 2)
+	if (INTEL_GEN(i915) > 2)
 		ee->mode = ENGINE_READ(engine, RING_MI_MODE);
 
-	if (!HWS_NEEDS_PHYSICAL(dev_priv)) {
+	if (!HWS_NEEDS_PHYSICAL(i915)) {
 		i915_reg_t mmio;
 
-		if (IS_GEN(dev_priv, 7)) {
+		if (IS_GEN(i915, 7)) {
 			switch (engine->id) {
 			default:
 				MISSING_CASE(engine->id);
@@ -1185,110 +1158,63 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
 			mmio = RING_HWS_PGA(engine->mmio_base);
 		}
 
-		ee->hws = I915_READ(mmio);
+		ee->hws = intel_uncore_read(engine->uncore, mmio);
 	}
 
-	ee->idle = intel_engine_is_idle(engine);
-	ee->reset_count = i915_reset_engine_count(&dev_priv->gpu_error,
-						  engine);
+	ee->reset_count = i915_reset_engine_count(&i915->gpu_error, engine);
 
-	if (HAS_PPGTT(dev_priv)) {
+	if (HAS_PPGTT(i915)) {
 		int i;
 
 		ee->vm_info.gfx_mode = ENGINE_READ(engine, RING_MODE_GEN7);
 
-		if (IS_GEN(dev_priv, 6)) {
+		if (IS_GEN(i915, 6)) {
 			ee->vm_info.pp_dir_base =
 				ENGINE_READ(engine, RING_PP_DIR_BASE_READ);
-		} else if (IS_GEN(dev_priv, 7)) {
+		} else if (IS_GEN(i915, 7)) {
 			ee->vm_info.pp_dir_base =
 				ENGINE_READ(engine, RING_PP_DIR_BASE);
-		} else if (INTEL_GEN(dev_priv) >= 8) {
+		} else if (INTEL_GEN(i915) >= 8) {
 			u32 base = engine->mmio_base;
 
 			for (i = 0; i < 4; i++) {
 				ee->vm_info.pdp[i] =
-					I915_READ(GEN8_RING_PDP_UDW(base, i));
+					intel_uncore_read(engine->uncore,
+							  GEN8_RING_PDP_UDW(base, i));
 				ee->vm_info.pdp[i] <<= 32;
 				ee->vm_info.pdp[i] |=
-					I915_READ(GEN8_RING_PDP_LDW(base, i));
+					intel_uncore_read(engine->uncore,
+							  GEN8_RING_PDP_LDW(base, i));
 			}
 		}
 	}
 }
 
 static void record_request(const struct i915_request *request,
-			   struct drm_i915_error_request *erq)
+			   struct i915_request_coredump *erq)
 {
-	const struct i915_gem_context *ctx = request->gem_context;
+	const struct i915_gem_context *ctx;
 
 	erq->flags = request->fence.flags;
 	erq->context = request->fence.context;
 	erq->seqno = request->fence.seqno;
 	erq->sched_attr = request->sched.attr;
-	erq->jiffies = request->emitted_jiffies;
 	erq->start = i915_ggtt_offset(request->ring->vma);
 	erq->head = request->head;
 	erq->tail = request->tail;
 
+	erq->pid = 0;
 	rcu_read_lock();
-	erq->pid = ctx->pid ? pid_nr(ctx->pid) : 0;
+	ctx = rcu_dereference(request->context->gem_context);
+	if (ctx)
+		erq->pid = pid_nr(ctx->pid);
 	rcu_read_unlock();
 }
 
-static void engine_record_requests(struct intel_engine_cs *engine,
-				   struct i915_request *first,
-				   struct drm_i915_error_engine *ee)
+static void engine_record_execlists(struct intel_engine_coredump *ee)
 {
-	struct i915_request *request;
-	int count;
-
-	count = 0;
-	request = first;
-	list_for_each_entry_from(request, &engine->active.requests, sched.link)
-		count++;
-	if (!count)
-		return;
-
-	ee->requests = kcalloc(count, sizeof(*ee->requests), ATOMIC_MAYFAIL);
-	if (!ee->requests)
-		return;
-
-	ee->num_requests = count;
-
-	count = 0;
-	request = first;
-	list_for_each_entry_from(request,
-				 &engine->active.requests, sched.link) {
-		if (count >= ee->num_requests) {
-			/*
-			 * If the ring request list was changed in
-			 * between the point where the error request
-			 * list was created and dimensioned and this
-			 * point then just exit early to avoid crashes.
-			 *
-			 * We don't need to communicate that the
-			 * request list changed state during error
-			 * state capture and that the error state is
-			 * slightly incorrect as a consequence since we
-			 * are typically only interested in the request
-			 * list state at the point of error state
-			 * capture, not in any changes happening during
-			 * the capture.
-			 */
-			break;
-		}
-
-		record_request(request, &ee->requests[count++]);
-	}
-	ee->num_requests = count;
-}
-
-static void error_record_engine_execlists(const struct intel_engine_cs *engine,
-					  struct drm_i915_error_engine *ee)
-{
-	const struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct i915_request * const *port = execlists->active;
+	const struct intel_engine_execlists * const el = &ee->engine->execlists;
+	struct i915_request * const *port = el->active;
 	unsigned int n = 0;
 
 	while (*port)
@@ -1297,47 +1223,57 @@ static void error_record_engine_execlists(const struct intel_engine_cs *engine,
 	ee->num_ports = n;
 }
 
-static bool record_context(struct drm_i915_error_context *e,
+static bool record_context(struct i915_gem_context_coredump *e,
 			   const struct i915_request *rq)
 {
-	const struct i915_gem_context *ctx = rq->gem_context;
+	struct i915_gem_context *ctx;
+	struct task_struct *task;
+	bool capture;
 
-	if (ctx->pid) {
-		struct task_struct *task;
+	rcu_read_lock();
+	ctx = rcu_dereference(rq->context->gem_context);
+	if (ctx && !kref_get_unless_zero(&ctx->ref))
+		ctx = NULL;
+	rcu_read_unlock();
+	if (!ctx)
+		return false;
 
-		rcu_read_lock();
-		task = pid_task(ctx->pid, PIDTYPE_PID);
-		if (task) {
-			strcpy(e->comm, task->comm);
-			e->pid = task->pid;
-		}
-		rcu_read_unlock();
+	rcu_read_lock();
+	task = pid_task(ctx->pid, PIDTYPE_PID);
+	if (task) {
+		strcpy(e->comm, task->comm);
+		e->pid = task->pid;
 	}
+	rcu_read_unlock();
 
 	e->sched_attr = ctx->sched;
 	e->guilty = atomic_read(&ctx->guilty_count);
 	e->active = atomic_read(&ctx->active_count);
 
-	return i915_gem_context_no_error_capture(ctx);
+	capture = i915_gem_context_no_error_capture(ctx);
+
+	i915_gem_context_put(ctx);
+	return capture;
 }
 
-struct capture_vma {
-	struct capture_vma *next;
-	void **slot;
+struct intel_engine_capture_vma {
+	struct intel_engine_capture_vma *next;
+	struct i915_vma *vma;
+	char name[16];
 };
 
-static struct capture_vma *
-capture_vma(struct capture_vma *next,
+static struct intel_engine_capture_vma *
+capture_vma(struct intel_engine_capture_vma *next,
 	    struct i915_vma *vma,
-	    struct drm_i915_error_object **out)
+	    const char *name,
+	    gfp_t gfp)
 {
-	struct capture_vma *c;
+	struct intel_engine_capture_vma *c;
 
-	*out = NULL;
 	if (!vma)
 		return next;
 
-	c = kmalloc(sizeof(*c), ATOMIC_MAYFAIL);
+	c = kmalloc(sizeof(*c), gfp);
 	if (!c)
 		return next;
 
@@ -1346,54 +1282,31 @@ capture_vma(struct capture_vma *next,
 		return next;
 	}
 
-	c->slot = (void **)out;
-	*c->slot = i915_vma_get(vma);
+	strcpy(c->name, name);
+	c->vma = i915_vma_get(vma);
 
 	c->next = next;
 	return c;
 }
 
-static struct capture_vma *
-request_record_user_bo(struct i915_request *request,
-		       struct drm_i915_error_engine *ee,
-		       struct capture_vma *capture)
+static struct intel_engine_capture_vma *
+capture_user(struct intel_engine_capture_vma *capture,
+	     const struct i915_request *rq,
+	     gfp_t gfp)
 {
 	struct i915_capture_list *c;
-	struct drm_i915_error_object **bo;
-	long count, max;
-
-	max = 0;
-	for (c = request->capture_list; c; c = c->next)
-		max++;
-	if (!max)
-		return capture;
-
-	bo = kmalloc_array(max, sizeof(*bo), ATOMIC_MAYFAIL);
-	if (!bo) {
-		/* If we can't capture everything, try to capture something. */
-		max = min_t(long, max, PAGE_SIZE / sizeof(*bo));
-		bo = kmalloc_array(max, sizeof(*bo), ATOMIC_MAYFAIL);
-	}
-	if (!bo)
-		return capture;
 
-	count = 0;
-	for (c = request->capture_list; c; c = c->next) {
-		capture = capture_vma(capture, c->vma, &bo[count]);
-		if (++count == max)
-			break;
-	}
-
-	ee->user_bo = bo;
-	ee->user_bo_count = count;
+	for (c = rq->capture_list; c; c = c->next)
+		capture = capture_vma(capture, c->vma, "user", gfp);
 
 	return capture;
 }
 
-static struct drm_i915_error_object *
-capture_object(struct drm_i915_private *dev_priv,
+static struct i915_vma_coredump *
+capture_object(const struct intel_gt *gt,
 	       struct drm_i915_gem_object *obj,
-	       struct compress *compress)
+	       const char *name,
+	       struct i915_vma_compress *compress)
 {
 	if (obj && i915_gem_object_has_pages(obj)) {
 		struct i915_vma fake = {
@@ -1403,127 +1316,175 @@ capture_object(struct drm_i915_private *dev_priv,
 			.obj = obj,
 		};
 
-		return i915_error_object_create(dev_priv, &fake, compress);
+		return i915_vma_coredump_create(gt, &fake, name, compress);
 	} else {
 		return NULL;
 	}
 }
 
-static void
-gem_record_rings(struct i915_gpu_state *error, struct compress *compress)
+static void add_vma(struct intel_engine_coredump *ee,
+		    struct i915_vma_coredump *vma)
 {
-	struct drm_i915_private *i915 = error->i915;
-	struct intel_engine_cs *engine;
-	struct drm_i915_error_engine *ee;
+	if (vma) {
+		vma->next = ee->vma;
+		ee->vma = vma;
+	}
+}
+
+struct intel_engine_coredump *
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp)
+{
+	struct intel_engine_coredump *ee;
 
-	ee = kzalloc(sizeof(*ee), GFP_KERNEL);
+	ee = kzalloc(sizeof(*ee), gfp);
 	if (!ee)
-		return;
+		return NULL;
 
-	for_each_uabi_engine(engine, i915) {
-		struct capture_vma *capture = NULL;
-		struct i915_request *request;
-		unsigned long flags;
+	ee->engine = engine;
 
-		/* Refill our page pool before entering atomic section */
-		pool_refill(&compress->pool, ALLOW_FAIL);
+	engine_record_registers(ee);
+	engine_record_execlists(ee);
 
-		spin_lock_irqsave(&engine->active.lock, flags);
-		request = intel_engine_find_active_request(engine);
-		if (!request) {
-			spin_unlock_irqrestore(&engine->active.lock, flags);
-			continue;
-		}
+	return ee;
+}
 
-		error->simulated |= record_context(&ee->context, request);
+struct intel_engine_capture_vma *
+intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
+				  struct i915_request *rq,
+				  gfp_t gfp)
+{
+	struct intel_engine_capture_vma *vma = NULL;
 
-		/*
-		 * We need to copy these to an anonymous buffer
-		 * as the simplest method to avoid being overwritten
-		 * by userspace.
-		 */
-		capture = capture_vma(capture,
-				      request->batch,
-				      &ee->batchbuffer);
+	ee->simulated |= record_context(&ee->context, rq);
+	if (ee->simulated)
+		return NULL;
 
-		if (HAS_BROKEN_CS_TLB(i915))
-			capture = capture_vma(capture,
-					      engine->gt->scratch,
-					      &ee->wa_batchbuffer);
+	/*
+	 * We need to copy these to an anonymous buffer
+	 * as the simplest method to avoid being overwritten
+	 * by userspace.
+	 */
+	vma = capture_vma(vma, rq->batch, "batch", gfp);
+	vma = capture_user(vma, rq, gfp);
+	vma = capture_vma(vma, rq->ring->vma, "ring", gfp);
+	vma = capture_vma(vma, rq->context->state, "HW context", gfp);
+
+	ee->rq_head = rq->head;
+	ee->rq_post = rq->postfix;
+	ee->rq_tail = rq->tail;
+
+	return vma;
+}
 
-		capture = request_record_user_bo(request, ee, capture);
+void
+intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
+			      struct intel_engine_capture_vma *capture,
+			      struct i915_vma_compress *compress)
+{
+	const struct intel_engine_cs *engine = ee->engine;
 
-		capture = capture_vma(capture,
-				      request->hw_context->state,
-				      &ee->ctx);
+	while (capture) {
+		struct intel_engine_capture_vma *this = capture;
+		struct i915_vma *vma = this->vma;
 
-		capture = capture_vma(capture,
-				      request->ring->vma,
-				      &ee->ringbuffer);
+		add_vma(ee,
+			i915_vma_coredump_create(engine->gt,
+						 vma, this->name,
+						 compress));
 
-		ee->cpu_ring_head = request->ring->head;
-		ee->cpu_ring_tail = request->ring->tail;
+		i915_active_release(&vma->active);
+		i915_vma_put(vma);
 
-		ee->rq_head = request->head;
-		ee->rq_post = request->postfix;
-		ee->rq_tail = request->tail;
+		capture = this->next;
+		kfree(this);
+	}
 
-		engine_record_requests(engine, request, ee);
-		spin_unlock_irqrestore(&engine->active.lock, flags);
+	add_vma(ee,
+		i915_vma_coredump_create(engine->gt,
+					 engine->status_page.vma,
+					 "HW Status",
+					 compress));
 
-		error_record_engine_registers(error, engine, ee);
-		error_record_engine_execlists(engine, ee);
+	add_vma(ee,
+		i915_vma_coredump_create(engine->gt,
+					 engine->wa_ctx.vma,
+					 "WA context",
+					 compress));
 
-		while (capture) {
-			struct capture_vma *this = capture;
-			struct i915_vma *vma = *this->slot;
+	add_vma(ee,
+		capture_object(engine->gt,
+			       engine->default_state,
+			       "NULL context",
+			       compress));
+}
 
-			*this->slot =
-				i915_error_object_create(i915, vma, compress);
+static struct intel_engine_coredump *
+capture_engine(struct intel_engine_cs *engine,
+	       struct i915_vma_compress *compress)
+{
+	struct intel_engine_capture_vma *capture = NULL;
+	struct intel_engine_coredump *ee;
+	struct i915_request *rq;
+	unsigned long flags;
 
-			i915_active_release(&vma->active);
-			i915_vma_put(vma);
+	ee = intel_engine_coredump_alloc(engine, GFP_KERNEL);
+	if (!ee)
+		return NULL;
 
-			capture = this->next;
-			kfree(this);
-		}
+	spin_lock_irqsave(&engine->active.lock, flags);
+	rq = intel_engine_find_active_request(engine);
+	if (rq)
+		capture = intel_engine_coredump_add_request(ee, rq,
+							    ATOMIC_MAYFAIL);
+	spin_unlock_irqrestore(&engine->active.lock, flags);
+	if (!capture) {
+		kfree(ee);
+		return NULL;
+	}
 
-		ee->hws_page =
-			i915_error_object_create(i915,
-						 engine->status_page.vma,
-						 compress);
+	intel_engine_coredump_add_vma(ee, capture, compress);
 
-		ee->wa_ctx =
-			i915_error_object_create(i915,
-						 engine->wa_ctx.vma,
-						 compress);
+	return ee;
+}
 
-		ee->default_state =
-			capture_object(i915, engine->default_state, compress);
+static void
+gt_record_engines(struct intel_gt_coredump *gt,
+		  struct i915_vma_compress *compress)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-		ee->engine = engine;
+	for_each_engine(engine, gt->_gt, id) {
+		struct intel_engine_coredump *ee;
 
-		ee->next = error->engine;
-		error->engine = ee;
+		/* Refill our page pool before entering atomic section */
+		pool_refill(&compress->pool, ALLOW_FAIL);
 
-		ee = kzalloc(sizeof(*ee), GFP_KERNEL);
+		ee = capture_engine(engine, compress);
 		if (!ee)
-			return;
-	}
+			continue;
 
-	kfree(ee);
+		gt->simulated |= ee->simulated;
+		if (ee->simulated) {
+			kfree(ee);
+			continue;
+		}
+
+		ee->next = gt->engine;
+		gt->engine = ee;
+	}
 }
 
-static void
-capture_uc_state(struct i915_gpu_state *error, struct compress *compress)
+static struct intel_uc_coredump *
+gt_record_uc(struct intel_gt_coredump *gt,
+	     struct i915_vma_compress *compress)
 {
-	struct drm_i915_private *i915 = error->i915;
-	struct i915_error_uc *error_uc = &error->uc;
-	struct intel_uc *uc = &i915->gt.uc;
+	const struct intel_uc *uc = &gt->_gt->uc;
+	struct intel_uc_coredump *error_uc;
 
-	/* Capturing uC state won't be useful if there is no GuC */
-	if (!error->device_info.has_gt_uc)
-		return;
+	error_uc = kzalloc(sizeof(*error_uc), ALLOW_FAIL);
+	if (!error_uc)
+		return NULL;
 
 	memcpy(&error_uc->guc_fw, &uc->guc.fw, sizeof(uc->guc.fw));
 	memcpy(&error_uc->huc_fw, &uc->huc.fw, sizeof(uc->huc.fw));
@@ -1534,19 +1495,42 @@ capture_uc_state(struct i915_gpu_state *error, struct compress *compress)
 	 */
 	error_uc->guc_fw.path = kstrdup(uc->guc.fw.path, ALLOW_FAIL);
 	error_uc->huc_fw.path = kstrdup(uc->huc.fw.path, ALLOW_FAIL);
-	error_uc->guc_log = i915_error_object_create(i915,
-						     uc->guc.log.vma,
-						     compress);
+	error_uc->guc_log =
+		i915_vma_coredump_create(gt->_gt,
+					 uc->guc.log.vma, "GuC log buffer",
+					 compress);
+
+	return error_uc;
+}
+
+static void gt_capture_prepare(struct intel_gt_coredump *gt)
+{
+	struct i915_ggtt *ggtt = gt->_gt->ggtt;
+
+	mutex_lock(&ggtt->error_mutex);
+}
+
+static void gt_capture_finish(struct intel_gt_coredump *gt)
+{
+	struct i915_ggtt *ggtt = gt->_gt->ggtt;
+
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		ggtt->vm.clear_range(&ggtt->vm,
+				     ggtt->error_capture.start,
+				     PAGE_SIZE);
+
+	mutex_unlock(&ggtt->error_mutex);
 }
 
 /* Capture all registers which don't fit into another category. */
-static void capture_reg_state(struct i915_gpu_state *error)
+static void gt_record_regs(struct intel_gt_coredump *gt)
 {
-	struct drm_i915_private *i915 = error->i915;
-	struct intel_uncore *uncore = &i915->uncore;
+	struct intel_uncore *uncore = gt->_gt->uncore;
+	struct drm_i915_private *i915 = uncore->i915;
 	int i;
 
-	/* General organization
+	/*
+	 * General organization
 	 * 1. Registers specific to a single generation
 	 * 2. Registers which belong to multiple generations
 	 * 3. Feature specific registers.
@@ -1556,138 +1540,162 @@ static void capture_reg_state(struct i915_gpu_state *error)
 
 	/* 1: Registers specific to a single generation */
 	if (IS_VALLEYVIEW(i915)) {
-		error->gtier[0] = intel_uncore_read(uncore, GTIER);
-		error->ier = intel_uncore_read(uncore, VLV_IER);
-		error->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_VLV);
+		gt->gtier[0] = intel_uncore_read(uncore, GTIER);
+		gt->ier = intel_uncore_read(uncore, VLV_IER);
+		gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_VLV);
 	}
 
 	if (IS_GEN(i915, 7))
-		error->err_int = intel_uncore_read(uncore, GEN7_ERR_INT);
+		gt->err_int = intel_uncore_read(uncore, GEN7_ERR_INT);
 
 	if (INTEL_GEN(i915) >= 12) {
-		error->fault_data0 = intel_uncore_read(uncore,
-						       GEN12_FAULT_TLB_DATA0);
-		error->fault_data1 = intel_uncore_read(uncore,
-						       GEN12_FAULT_TLB_DATA1);
+		gt->fault_data0 = intel_uncore_read(uncore,
+						    GEN12_FAULT_TLB_DATA0);
+		gt->fault_data1 = intel_uncore_read(uncore,
+						    GEN12_FAULT_TLB_DATA1);
 	} else if (INTEL_GEN(i915) >= 8) {
-		error->fault_data0 = intel_uncore_read(uncore,
-						       GEN8_FAULT_TLB_DATA0);
-		error->fault_data1 = intel_uncore_read(uncore,
-						       GEN8_FAULT_TLB_DATA1);
+		gt->fault_data0 = intel_uncore_read(uncore,
+						    GEN8_FAULT_TLB_DATA0);
+		gt->fault_data1 = intel_uncore_read(uncore,
+						    GEN8_FAULT_TLB_DATA1);
 	}
 
 	if (IS_GEN(i915, 6)) {
-		error->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE);
-		error->gab_ctl = intel_uncore_read(uncore, GAB_CTL);
-		error->gfx_mode = intel_uncore_read(uncore, GFX_MODE);
+		gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE);
+		gt->gab_ctl = intel_uncore_read(uncore, GAB_CTL);
+		gt->gfx_mode = intel_uncore_read(uncore, GFX_MODE);
 	}
 
 	/* 2: Registers which belong to multiple generations */
 	if (INTEL_GEN(i915) >= 7)
-		error->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_MT);
+		gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_MT);
 
 	if (INTEL_GEN(i915) >= 6) {
-		error->derrmr = intel_uncore_read(uncore, DERRMR);
+		gt->derrmr = intel_uncore_read(uncore, DERRMR);
 		if (INTEL_GEN(i915) < 12) {
-			error->error = intel_uncore_read(uncore, ERROR_GEN6);
-			error->done_reg = intel_uncore_read(uncore, DONE_REG);
+			gt->error = intel_uncore_read(uncore, ERROR_GEN6);
+			gt->done_reg = intel_uncore_read(uncore, DONE_REG);
 		}
 	}
 
-	if (INTEL_GEN(i915) >= 5)
-		error->ccid = intel_uncore_read(uncore, CCID(RENDER_RING_BASE));
-
 	/* 3: Feature specific registers */
 	if (IS_GEN_RANGE(i915, 6, 7)) {
-		error->gam_ecochk = intel_uncore_read(uncore, GAM_ECOCHK);
-		error->gac_eco = intel_uncore_read(uncore, GAC_ECO_BITS);
+		gt->gam_ecochk = intel_uncore_read(uncore, GAM_ECOCHK);
+		gt->gac_eco = intel_uncore_read(uncore, GAC_ECO_BITS);
 	}
 
 	if (IS_GEN_RANGE(i915, 8, 11))
-		error->gtt_cache = intel_uncore_read(uncore, HSW_GTT_CACHE_EN);
+		gt->gtt_cache = intel_uncore_read(uncore, HSW_GTT_CACHE_EN);
 
 	if (IS_GEN(i915, 12))
-		error->aux_err = intel_uncore_read(uncore, GEN12_AUX_ERR_DBG);
+		gt->aux_err = intel_uncore_read(uncore, GEN12_AUX_ERR_DBG);
 
 	if (INTEL_GEN(i915) >= 12) {
 		for (i = 0; i < GEN12_SFC_DONE_MAX; i++) {
-			error->sfc_done[i] =
+			gt->sfc_done[i] =
 				intel_uncore_read(uncore, GEN12_SFC_DONE(i));
 		}
 
-		error->gam_done = intel_uncore_read(uncore, GEN12_GAM_DONE);
+		gt->gam_done = intel_uncore_read(uncore, GEN12_GAM_DONE);
 	}
 
 	/* 4: Everything else */
 	if (INTEL_GEN(i915) >= 11) {
-		error->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
-		error->gtier[0] =
+		gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
+		gt->gtier[0] =
 			intel_uncore_read(uncore,
 					  GEN11_RENDER_COPY_INTR_ENABLE);
-		error->gtier[1] =
+		gt->gtier[1] =
 			intel_uncore_read(uncore, GEN11_VCS_VECS_INTR_ENABLE);
-		error->gtier[2] =
+		gt->gtier[2] =
 			intel_uncore_read(uncore, GEN11_GUC_SG_INTR_ENABLE);
-		error->gtier[3] =
+		gt->gtier[3] =
 			intel_uncore_read(uncore,
 					  GEN11_GPM_WGBOXPERF_INTR_ENABLE);
-		error->gtier[4] =
+		gt->gtier[4] =
 			intel_uncore_read(uncore,
 					  GEN11_CRYPTO_RSVD_INTR_ENABLE);
-		error->gtier[5] =
+		gt->gtier[5] =
 			intel_uncore_read(uncore,
 					  GEN11_GUNIT_CSME_INTR_ENABLE);
-		error->ngtier = 6;
+		gt->ngtier = 6;
 	} else if (INTEL_GEN(i915) >= 8) {
-		error->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
+		gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
 		for (i = 0; i < 4; i++)
-			error->gtier[i] = intel_uncore_read(uncore,
-							    GEN8_GT_IER(i));
-		error->ngtier = 4;
+			gt->gtier[i] =
+				intel_uncore_read(uncore, GEN8_GT_IER(i));
+		gt->ngtier = 4;
 	} else if (HAS_PCH_SPLIT(i915)) {
-		error->ier = intel_uncore_read(uncore, DEIER);
-		error->gtier[0] = intel_uncore_read(uncore, GTIER);
-		error->ngtier = 1;
+		gt->ier = intel_uncore_read(uncore, DEIER);
+		gt->gtier[0] = intel_uncore_read(uncore, GTIER);
+		gt->ngtier = 1;
 	} else if (IS_GEN(i915, 2)) {
-		error->ier = intel_uncore_read16(uncore, GEN2_IER);
+		gt->ier = intel_uncore_read16(uncore, GEN2_IER);
 	} else if (!IS_VALLEYVIEW(i915)) {
-		error->ier = intel_uncore_read(uncore, GEN2_IER);
+		gt->ier = intel_uncore_read(uncore, GEN2_IER);
 	}
-	error->eir = intel_uncore_read(uncore, EIR);
-	error->pgtbl_er = intel_uncore_read(uncore, PGTBL_ER);
+	gt->eir = intel_uncore_read(uncore, EIR);
+	gt->pgtbl_er = intel_uncore_read(uncore, PGTBL_ER);
+}
+
+/*
+ * Generate a semi-unique error code. The code is not meant to have meaning, The
+ * code's only purpose is to try to prevent false duplicated bug reports by
+ * grossly estimating a GPU error state.
+ *
+ * TODO Ideally, hashing the batchbuffer would be a very nice way to determine
+ * the hang if we could strip the GTT offset information from it.
+ *
+ * It's only a small step better than a random number in its current form.
+ */
+static u32 generate_ecode(const struct intel_engine_coredump *ee)
+{
+	/*
+	 * IPEHR would be an ideal way to detect errors, as it's the gross
+	 * measure of "the command that hung." However, has some very common
+	 * synchronization commands which almost always appear in the case
+	 * strictly a client bug. Use instdone to differentiate those some.
+	 */
+	return ee ? ee->ipehr ^ ee->instdone.instdone : 0;
 }
 
-static const char *
-error_msg(struct i915_gpu_state *error,
-	  intel_engine_mask_t engines, const char *msg)
+static const char *error_msg(struct i915_gpu_coredump *error)
 {
+	struct intel_engine_coredump *first = NULL;
+	struct intel_gt_coredump *gt;
+	intel_engine_mask_t engines;
 	int len;
 
+	engines = 0;
+	for (gt = error->gt; gt; gt = gt->next) {
+		struct intel_engine_coredump *cs;
+
+		if (gt->engine && !first)
+			first = gt->engine;
+
+		for (cs = gt->engine; cs; cs = cs->next)
+			engines |= cs->engine->mask;
+	}
+
 	len = scnprintf(error->error_msg, sizeof(error->error_msg),
-			"GPU HANG: ecode %d:%x:0x%08x",
+			"GPU HANG: ecode %d:%x:%08x",
 			INTEL_GEN(error->i915), engines,
-			i915_error_generate_code(error));
-	if (error->engine) {
+			generate_ecode(first));
+	if (first) {
 		/* Just show the first executing process, more is confusing */
 		len += scnprintf(error->error_msg + len,
 				 sizeof(error->error_msg) - len,
 				 ", in %s [%d]",
-				 error->engine->context.comm,
-				 error->engine->context.pid);
+				 first->context.comm, first->context.pid);
 	}
-	if (msg)
-		len += scnprintf(error->error_msg + len,
-				 sizeof(error->error_msg) - len,
-				 ", %s", msg);
 
 	return error->error_msg;
 }
 
-static void capture_gen_state(struct i915_gpu_state *error)
+static void capture_gen(struct i915_gpu_coredump *error)
 {
 	struct drm_i915_private *i915 = error->i915;
 
-	error->awake = i915->gt.awake;
 	error->wakelock = atomic_read(&i915->runtime_pm.wakeref_count);
 	error->suspended = i915->runtime_pm.suspended;
 
@@ -1698,6 +1706,7 @@ static void capture_gen_state(struct i915_gpu_state *error)
 	error->reset_count = i915_reset_count(&i915->gpu_error);
 	error->suspend_count = i915->suspend_count;
 
+	i915_params_copy(&error->params, &i915_modparams);
 	memcpy(&error->device_info,
 	       INTEL_INFO(i915),
 	       sizeof(error->device_info));
@@ -1707,115 +1716,138 @@ static void capture_gen_state(struct i915_gpu_state *error)
 	error->driver_caps = i915->caps;
 }
 
-static void capture_params(struct i915_gpu_state *error)
+struct i915_gpu_coredump *
+i915_gpu_coredump_alloc(struct drm_i915_private *i915, gfp_t gfp)
 {
-	i915_params_copy(&error->params, &i915_modparams);
+	struct i915_gpu_coredump *error;
+
+	if (!i915_modparams.error_capture)
+		return NULL;
+
+	error = kzalloc(sizeof(*error), gfp);
+	if (!error)
+		return NULL;
+
+	kref_init(&error->ref);
+	error->i915 = i915;
+
+	error->time = ktime_get_real();
+	error->boottime = ktime_get_boottime();
+	error->uptime = ktime_sub(ktime_get(), i915->gt.last_init_time);
+	error->capture = jiffies;
+
+	capture_gen(error);
+
+	return error;
 }
 
-static void capture_finish(struct i915_gpu_state *error)
+#define DAY_AS_SECONDS(x) (24 * 60 * 60 * (x))
+
+struct intel_gt_coredump *
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp)
 {
-	struct i915_ggtt *ggtt = &error->i915->ggtt;
+	struct intel_gt_coredump *gc;
 
-	if (drm_mm_node_allocated(&ggtt->error_capture)) {
-		const u64 slot = ggtt->error_capture.start;
+	gc = kzalloc(sizeof(*gc), gfp);
+	if (!gc)
+		return NULL;
+
+	gc->_gt = gt;
+	gc->awake = intel_gt_pm_is_awake(gt);
+
+	gt_record_regs(gc);
+	gt_record_fences(gc);
+
+	return gc;
+}
 
-		ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
+struct i915_vma_compress *
+i915_vma_capture_prepare(struct intel_gt_coredump *gt)
+{
+	struct i915_vma_compress *compress;
+
+	compress = kmalloc(sizeof(*compress), ALLOW_FAIL);
+	if (!compress)
+		return NULL;
+
+	if (!compress_init(compress)) {
+		kfree(compress);
+		return NULL;
 	}
+
+	gt_capture_prepare(gt);
+
+	return compress;
 }
 
-#define DAY_AS_SECONDS(x) (24 * 60 * 60 * (x))
+void i915_vma_capture_finish(struct intel_gt_coredump *gt,
+			     struct i915_vma_compress *compress)
+{
+	if (!compress)
+		return;
 
-struct i915_gpu_state *
-i915_capture_gpu_state(struct drm_i915_private *i915)
+	gt_capture_finish(gt);
+
+	compress_fini(compress);
+	kfree(compress);
+}
+
+struct i915_gpu_coredump *i915_gpu_coredump(struct drm_i915_private *i915)
 {
-	struct i915_gpu_state *error;
-	struct compress compress;
+	struct i915_gpu_coredump *error;
 
 	/* Check if GPU capture has been disabled */
 	error = READ_ONCE(i915->gpu_error.first_error);
 	if (IS_ERR(error))
 		return error;
 
-	error = kzalloc(sizeof(*error), ALLOW_FAIL);
-	if (!error) {
-		i915_disable_error_state(i915, -ENOMEM);
+	error = i915_gpu_coredump_alloc(i915, ALLOW_FAIL);
+	if (!error)
 		return ERR_PTR(-ENOMEM);
-	}
 
-	if (!compress_init(&compress)) {
-		kfree(error);
-		i915_disable_error_state(i915, -ENOMEM);
-		return ERR_PTR(-ENOMEM);
-	}
+	error->gt = intel_gt_coredump_alloc(&i915->gt, ALLOW_FAIL);
+	if (error->gt) {
+		struct i915_vma_compress *compress;
 
-	kref_init(&error->ref);
-	error->i915 = i915;
+		compress = i915_vma_capture_prepare(error->gt);
+		if (!compress) {
+			kfree(error->gt);
+			kfree(error);
+			return ERR_PTR(-ENOMEM);
+		}
 
-	error->time = ktime_get_real();
-	error->boottime = ktime_get_boottime();
-	error->uptime = ktime_sub(ktime_get(), i915->gt.last_init_time);
-	error->capture = jiffies;
+		gt_record_engines(error->gt, compress);
+
+		if (INTEL_INFO(i915)->has_gt_uc)
+			error->gt->uc = gt_record_uc(error->gt, compress);
 
-	capture_params(error);
-	capture_gen_state(error);
-	capture_uc_state(error, &compress);
-	capture_reg_state(error);
-	gem_record_fences(error);
-	gem_record_rings(error, &compress);
+		i915_vma_capture_finish(error->gt, compress);
+
+		error->simulated |= error->gt->simulated;
+	}
 
 	error->overlay = intel_overlay_capture_error_state(i915);
 	error->display = intel_display_capture_error_state(i915);
 
-	capture_finish(error);
-	compress_fini(&compress);
-
 	return error;
 }
 
-/**
- * i915_capture_error_state - capture an error record for later analysis
- * @i915: i915 device
- * @engine_mask: the mask of engines triggering the hang
- * @msg: a message to insert into the error capture header
- *
- * Should be called when an error is detected (either a hang or an error
- * interrupt) to capture error state from the time of the error.  Fills
- * out a structure which becomes available in debugfs for user level tools
- * to pick up.
- */
-void i915_capture_error_state(struct drm_i915_private *i915,
-			      intel_engine_mask_t engine_mask,
-			      const char *msg)
+void i915_error_state_store(struct i915_gpu_coredump *error)
 {
+	struct drm_i915_private *i915;
 	static bool warned;
-	struct i915_gpu_state *error;
-	unsigned long flags;
 
-	if (!i915_modparams.error_capture)
+	if (IS_ERR_OR_NULL(error))
 		return;
 
-	if (READ_ONCE(i915->gpu_error.first_error))
-		return;
+	i915 = error->i915;
+	dev_info(i915->drm.dev, "%s\n", error_msg(error));
 
-	error = i915_capture_gpu_state(i915);
-	if (IS_ERR(error))
+	if (error->simulated ||
+	    cmpxchg(&i915->gpu_error.first_error, NULL, error))
 		return;
 
-	dev_info(i915->drm.dev, "%s\n", error_msg(error, engine_mask, msg));
-
-	if (!error->simulated) {
-		spin_lock_irqsave(&i915->gpu_error.lock, flags);
-		if (!i915->gpu_error.first_error) {
-			i915->gpu_error.first_error = error;
-			error = NULL;
-		}
-		spin_unlock_irqrestore(&i915->gpu_error.lock, flags);
-	}
-
-	if (error) {
-		__i915_gpu_state_free(&error->ref);
-		return;
-	}
+	i915_gpu_coredump_get(error);
 
 	if (!xchg(&warned, true) &&
 	    ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) {
@@ -1828,15 +1860,38 @@ void i915_capture_error_state(struct drm_i915_private *i915,
 	}
 }
 
-struct i915_gpu_state *
+/**
+ * i915_capture_error_state - capture an error record for later analysis
+ * @i915: i915 device
+ *
+ * Should be called when an error is detected (either a hang or an error
+ * interrupt) to capture error state from the time of the error.  Fills
+ * out a structure which becomes available in debugfs for user level tools
+ * to pick up.
+ */
+void i915_capture_error_state(struct drm_i915_private *i915)
+{
+	struct i915_gpu_coredump *error;
+
+	error = i915_gpu_coredump(i915);
+	if (IS_ERR(error)) {
+		cmpxchg(&i915->gpu_error.first_error, NULL, error);
+		return;
+	}
+
+	i915_error_state_store(error);
+	i915_gpu_coredump_put(error);
+}
+
+struct i915_gpu_coredump *
 i915_first_error_state(struct drm_i915_private *i915)
 {
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 
 	spin_lock_irq(&i915->gpu_error.lock);
 	error = i915->gpu_error.first_error;
 	if (!IS_ERR_OR_NULL(error))
-		i915_gpu_state_get(error);
+		i915_gpu_coredump_get(error);
 	spin_unlock_irq(&i915->gpu_error.lock);
 
 	return error;
@@ -1844,7 +1899,7 @@ i915_first_error_state(struct drm_i915_private *i915)
 
 void i915_reset_error_state(struct drm_i915_private *i915)
 {
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 
 	spin_lock_irq(&i915->gpu_error.lock);
 	error = i915->gpu_error.first_error;
@@ -1853,7 +1908,7 @@ void i915_reset_error_state(struct drm_i915_private *i915)
 	spin_unlock_irq(&i915->gpu_error.lock);
 
 	if (!IS_ERR_OR_NULL(error))
-		i915_gpu_state_put(error);
+		i915_gpu_coredump_put(error);
 }
 
 void i915_disable_error_state(struct drm_i915_private *i915, int err)
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 5d2c3372ff99..9109004956bd 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -25,43 +25,100 @@
 #include "i915_scheduler.h"
 
 struct drm_i915_private;
+struct i915_vma_compress;
+struct intel_engine_capture_vma;
 struct intel_overlay_error_state;
 struct intel_display_error_state;
 
-struct i915_gpu_state {
-	struct kref ref;
-	ktime_t time;
-	ktime_t boottime;
-	ktime_t uptime;
-	unsigned long capture;
+struct i915_vma_coredump {
+	struct i915_vma_coredump *next;
 
-	struct drm_i915_private *i915;
+	char name[20];
+
+	u64 gtt_offset;
+	u64 gtt_size;
+	u32 gtt_page_sizes;
+
+	int num_pages;
+	int page_count;
+	int unused;
+	u32 *pages[0];
+};
+
+struct i915_request_coredump {
+	unsigned long flags;
+	pid_t pid;
+	u32 context;
+	u32 seqno;
+	u32 start;
+	u32 head;
+	u32 tail;
+	struct i915_sched_attr sched_attr;
+};
+
+struct intel_engine_coredump {
+	const struct intel_engine_cs *engine;
 
-	char error_msg[128];
 	bool simulated;
-	bool awake;
-	bool wakelock;
-	bool suspended;
-	int iommu;
 	u32 reset_count;
-	u32 suspend_count;
-	struct intel_device_info device_info;
-	struct intel_runtime_info runtime_info;
-	struct intel_driver_caps driver_caps;
-	struct i915_params params;
 
-	struct i915_error_uc {
-		struct intel_uc_fw guc_fw;
-		struct intel_uc_fw huc_fw;
-		struct drm_i915_error_object *guc_log;
-	} uc;
+	/* position of active request inside the ring */
+	u32 rq_head, rq_post, rq_tail;
+
+	/* Register state */
+	u32 ccid;
+	u32 start;
+	u32 tail;
+	u32 head;
+	u32 ctl;
+	u32 mode;
+	u32 hws;
+	u32 ipeir;
+	u32 ipehr;
+	u32 bbstate;
+	u32 instpm;
+	u32 instps;
+	u64 bbaddr;
+	u64 acthd;
+	u32 fault_reg;
+	u64 faddr;
+	u32 rc_psmi; /* sleep state */
+	struct intel_instdone instdone;
+
+	struct i915_gem_context_coredump {
+		char comm[TASK_COMM_LEN];
+		pid_t pid;
+		int active;
+		int guilty;
+		struct i915_sched_attr sched_attr;
+	} context;
+
+	struct i915_vma_coredump *vma;
+
+	struct i915_request_coredump execlist[EXECLIST_MAX_PORTS];
+	unsigned int num_ports;
+
+	struct {
+		u32 gfx_mode;
+		union {
+			u64 pdp[4];
+			u32 pp_dir_base;
+		};
+	} vm_info;
+
+	struct intel_engine_coredump *next;
+};
+
+struct intel_gt_coredump {
+	const struct intel_gt *_gt;
+	bool awake;
+	bool simulated;
 
 	/* Generic register state */
 	u32 eir;
 	u32 pgtbl_er;
 	u32 ier;
 	u32 gtier[6], ngtier;
-	u32 ccid;
 	u32 derrmr;
 	u32 forcewake;
 	u32 error; /* gen6+ */
@@ -80,91 +137,45 @@ struct i915_gpu_state {
 
 	u32 nfence;
 	u64 fence[I915_MAX_NUM_FENCES];
+
+	struct intel_engine_coredump *engine;
+
+	struct intel_uc_coredump {
+		struct intel_uc_fw guc_fw;
+		struct intel_uc_fw huc_fw;
+		struct i915_vma_coredump *guc_log;
+	} *uc;
+
+	struct intel_gt_coredump *next;
+};
+
+struct i915_gpu_coredump {
+	struct kref ref;
+	ktime_t time;
+	ktime_t boottime;
+	ktime_t uptime;
+	unsigned long capture;
+
+	struct drm_i915_private *i915;
+
+	struct intel_gt_coredump *gt;
+
+	char error_msg[128];
+	bool simulated;
+	bool wakelock;
+	bool suspended;
+	int iommu;
+	u32 reset_count;
+	u32 suspend_count;
+
+	struct intel_device_info device_info;
+	struct intel_runtime_info runtime_info;
+	struct intel_driver_caps driver_caps;
+	struct i915_params params;
+
 	struct intel_overlay_error_state *overlay;
 	struct intel_display_error_state *display;
 
-	struct drm_i915_error_engine {
-		const struct intel_engine_cs *engine;
-
-		/* Software tracked state */
-		bool idle;
-		int num_requests;
-		u32 reset_count;
-
-		/* position of active request inside the ring */
-		u32 rq_head, rq_post, rq_tail;
-
-		/* our own tracking of ring head and tail */
-		u32 cpu_ring_head;
-		u32 cpu_ring_tail;
-
-		/* Register state */
-		u32 start;
-		u32 tail;
-		u32 head;
-		u32 ctl;
-		u32 mode;
-		u32 hws;
-		u32 ipeir;
-		u32 ipehr;
-		u32 bbstate;
-		u32 instpm;
-		u32 instps;
-		u64 bbaddr;
-		u64 acthd;
-		u32 fault_reg;
-		u64 faddr;
-		u32 rc_psmi; /* sleep state */
-		struct intel_instdone instdone;
-
-		struct drm_i915_error_context {
-			char comm[TASK_COMM_LEN];
-			pid_t pid;
-			int active;
-			int guilty;
-			struct i915_sched_attr sched_attr;
-		} context;
-
-		struct drm_i915_error_object {
-			u64 gtt_offset;
-			u64 gtt_size;
-			u32 gtt_page_sizes;
-			int num_pages;
-			int page_count;
-			int unused;
-			u32 *pages[0];
-		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
-
-		struct drm_i915_error_object **user_bo;
-		long user_bo_count;
-
-		struct drm_i915_error_object *wa_ctx;
-		struct drm_i915_error_object *default_state;
-
-		struct drm_i915_error_request {
-			unsigned long flags;
-			long jiffies;
-			pid_t pid;
-			u32 context;
-			u32 seqno;
-			u32 start;
-			u32 head;
-			u32 tail;
-			struct i915_sched_attr sched_attr;
-		} *requests, execlist[EXECLIST_MAX_PORTS];
-		unsigned int num_ports;
-
-		struct {
-			u32 gfx_mode;
-			union {
-				u64 pdp[4];
-				u32 pp_dir_base;
-			};
-		} vm_info;
-
-		struct drm_i915_error_engine *next;
-	} *engine;
-
 	struct scatterlist *sgl, *fit;
 };
 
@@ -172,7 +183,7 @@ struct i915_gpu_error {
 	/* For reset and error_state handling. */
 	spinlock_t lock;
 	/* Protected by the above dev->gpu_error.lock. */
-	struct i915_gpu_state *first_error;
+	struct i915_gpu_coredump *first_error;
 
 	atomic_t pending_fb_pin;
 
@@ -200,41 +211,115 @@ struct drm_i915_error_state_buf {
 __printf(2, 3)
 void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
 
-struct i915_gpu_state *i915_capture_gpu_state(struct drm_i915_private *i915);
-void i915_capture_error_state(struct drm_i915_private *dev_priv,
-			      intel_engine_mask_t engine_mask,
-			      const char *error_msg);
+struct i915_gpu_coredump *i915_gpu_coredump(struct drm_i915_private *i915);
+void i915_capture_error_state(struct drm_i915_private *i915);
+
+struct i915_gpu_coredump *
+i915_gpu_coredump_alloc(struct drm_i915_private *i915, gfp_t gfp);
+
+struct intel_gt_coredump *
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp);
+
+struct intel_engine_coredump *
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp);
+
+struct intel_engine_capture_vma *
+intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
+				  struct i915_request *rq,
+				  gfp_t gfp);
 
-static inline struct i915_gpu_state *
-i915_gpu_state_get(struct i915_gpu_state *gpu)
+void intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
+				   struct intel_engine_capture_vma *capture,
+				   struct i915_vma_compress *compress);
+
+struct i915_vma_compress *
+i915_vma_capture_prepare(struct intel_gt_coredump *gt);
+
+void i915_vma_capture_finish(struct intel_gt_coredump *gt,
+			     struct i915_vma_compress *compress);
+
+void i915_error_state_store(struct i915_gpu_coredump *error);
+
+static inline struct i915_gpu_coredump *
+i915_gpu_coredump_get(struct i915_gpu_coredump *gpu)
 {
 	kref_get(&gpu->ref);
 	return gpu;
 }
 
-ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error,
-				      char *buf, loff_t offset, size_t count);
+ssize_t
+i915_gpu_coredump_copy_to_buffer(struct i915_gpu_coredump *error,
+				 char *buf, loff_t offset, size_t count);
 
-void __i915_gpu_state_free(struct kref *kref);
-static inline void i915_gpu_state_put(struct i915_gpu_state *gpu)
+void __i915_gpu_coredump_free(struct kref *kref);
+static inline void i915_gpu_coredump_put(struct i915_gpu_coredump *gpu)
 {
 	if (gpu)
-		kref_put(&gpu->ref, __i915_gpu_state_free);
+		kref_put(&gpu->ref, __i915_gpu_coredump_free);
 }
 
-struct i915_gpu_state *i915_first_error_state(struct drm_i915_private *i915);
+struct i915_gpu_coredump *i915_first_error_state(struct drm_i915_private *i915);
 void i915_reset_error_state(struct drm_i915_private *i915);
 void i915_disable_error_state(struct drm_i915_private *i915, int err);
 
 #else
 
-static inline void i915_capture_error_state(struct drm_i915_private *dev_priv,
-					    u32 engine_mask,
-					    const char *error_msg)
+static inline void i915_capture_error_state(struct drm_i915_private *i915)
+{
+}
+
+static inline struct i915_gpu_coredump *
+i915_gpu_coredump_alloc(struct drm_i915_private *i915, gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline struct intel_gt_coredump *
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline struct intel_engine_coredump *
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline struct intel_engine_capture_vma *
+intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
+				  struct i915_request *rq,
+				  gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline void
+intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
+			      struct intel_engine_capture_vma *capture,
+			      struct i915_vma_compress *compress)
+{
+}
+
+static inline struct i915_vma_compress *
+i915_vma_capture_prepare(struct intel_gt_coredump *gt)
+{
+	return NULL;
+}
+
+static inline void
+i915_vma_capture_finish(struct intel_gt_coredump *gt,
+			struct i915_vma_compress *compress)
+{
+}
+
+static inline void
+i915_error_state_store(struct drm_i915_private *i915,
+		       struct i915_gpu_coredump *error)
 {
 }
 
-static inline struct i915_gpu_state *
+static inline struct i915_gpu_coredump *
 i915_first_error_state(struct drm_i915_private *i915)
 {
 	return ERR_PTR(-ENODEV);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index dae00f7dd7df..afc6aad9bf8c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -893,7 +893,7 @@ int intel_get_crtc_scanline(struct intel_crtc *crtc)
 }
 
 /**
- * ivybridge_parity_work - Workqueue called when a parity error interrupt
+ * ivb_parity_work - Workqueue called when a parity error interrupt
  * occurred.
  * @work: workqueue struct
  *
@@ -901,7 +901,7 @@ int intel_get_crtc_scanline(struct intel_crtc *crtc)
  * this event, userspace should try to remap the bad rows since statistically
  * it is likely the same row is more likely to go bad again.
  */
-static void ivybridge_parity_work(struct work_struct *work)
+static void ivb_parity_work(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(work, typeof(*dev_priv), l3_parity.error_work);
@@ -2031,7 +2031,7 @@ static void ivb_display_irq_handler(struct drm_i915_private *dev_priv,
  * 4 - Process the interrupt(s) that had bits set in the IIRs.
  * 5 - Re-enable Master Interrupt Control.
  */
-static irqreturn_t ironlake_irq_handler(int irq, void *arg)
+static irqreturn_t ilk_irq_handler(int irq, void *arg)
 {
 	struct drm_i915_private *dev_priv = arg;
 	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
@@ -2453,6 +2453,25 @@ static inline void gen11_master_intr_enable(void __iomem * const regs)
 	raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ);
 }
 
+static void
+gen11_display_irq_handler(struct drm_i915_private *i915)
+{
+	void __iomem * const regs = i915->uncore.regs;
+	const u32 disp_ctl = raw_reg_read(regs, GEN11_DISPLAY_INT_CTL);
+
+	disable_rpm_wakeref_asserts(&i915->runtime_pm);
+	/*
+	 * GEN11_DISPLAY_INT_CTL has same format as GEN8_MASTER_IRQ
+	 * for the display related bits.
+	 */
+	raw_reg_write(regs, GEN11_DISPLAY_INT_CTL, 0x0);
+	gen8_de_irq_handler(i915, disp_ctl);
+	raw_reg_write(regs, GEN11_DISPLAY_INT_CTL,
+		      GEN11_DISPLAY_IRQ_ENABLE);
+
+	enable_rpm_wakeref_asserts(&i915->runtime_pm);
+}
+
 static __always_inline irqreturn_t
 __gen11_irq_handler(struct drm_i915_private * const i915,
 		    u32 (*intr_disable)(void __iomem * const regs),
@@ -2476,17 +2495,8 @@ __gen11_irq_handler(struct drm_i915_private * const i915,
 	gen11_gt_irq_handler(gt, master_ctl);
 
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
-	if (master_ctl & GEN11_DISPLAY_IRQ) {
-		const u32 disp_ctl = raw_reg_read(regs, GEN11_DISPLAY_INT_CTL);
-
-		disable_rpm_wakeref_asserts(&i915->runtime_pm);
-		/*
-		 * GEN11_DISPLAY_INT_CTL has same format as GEN8_MASTER_IRQ
-		 * for the display related bits.
-		 */
-		gen8_de_irq_handler(i915, disp_ctl);
-		enable_rpm_wakeref_asserts(&i915->runtime_pm);
-	}
+	if (master_ctl & GEN11_DISPLAY_IRQ)
+		gen11_display_irq_handler(i915);
 
 	gu_misc_iir = gen11_gu_misc_irq_ack(gt, master_ctl);
 
@@ -2732,7 +2742,7 @@ static void vlv_display_irq_postinstall(struct drm_i915_private *dev_priv)
 
 /* drm_dma.h hooks
 */
-static void ironlake_irq_reset(struct drm_i915_private *dev_priv)
+static void ilk_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 
@@ -2788,15 +2798,11 @@ static void gen8_irq_reset(struct drm_i915_private *dev_priv)
 		ibx_irq_reset(dev_priv);
 }
 
-static void gen11_irq_reset(struct drm_i915_private *dev_priv)
+static void gen11_display_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 	enum pipe pipe;
 
-	gen11_master_intr_disable(dev_priv->uncore.regs);
-
-	gen11_gt_irq_reset(&dev_priv->gt);
-
 	intel_uncore_write(uncore, GEN11_DISPLAY_INT_CTL, 0);
 
 	if (INTEL_GEN(dev_priv) >= 12) {
@@ -2825,13 +2831,24 @@ static void gen11_irq_reset(struct drm_i915_private *dev_priv)
 	GEN3_IRQ_RESET(uncore, GEN8_DE_PORT_);
 	GEN3_IRQ_RESET(uncore, GEN8_DE_MISC_);
 	GEN3_IRQ_RESET(uncore, GEN11_DE_HPD_);
-	GEN3_IRQ_RESET(uncore, GEN11_GU_MISC_);
-	GEN3_IRQ_RESET(uncore, GEN8_PCU_);
 
 	if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
 		GEN3_IRQ_RESET(uncore, SDE);
 }
 
+static void gen11_irq_reset(struct drm_i915_private *dev_priv)
+{
+	struct intel_uncore *uncore = &dev_priv->uncore;
+
+	gen11_master_intr_disable(dev_priv->uncore.regs);
+
+	gen11_gt_irq_reset(&dev_priv->gt);
+	gen11_display_irq_reset(dev_priv);
+
+	GEN3_IRQ_RESET(uncore, GEN11_GU_MISC_);
+	GEN3_IRQ_RESET(uncore, GEN8_PCU_);
+}
+
 void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv,
 				     u8 pipe_mask)
 {
@@ -2976,6 +2993,8 @@ static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv,
 	hotplug_irqs = sde_ddi_mask | sde_tc_mask;
 	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, pins);
 
+	I915_WRITE(SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ);
+
 	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
 
 	icp_hpd_detection_setup(dev_priv, ddi_enable_mask, tc_enable_mask);
@@ -3081,6 +3100,9 @@ static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug_irqs, enabled_irqs;
 
+	if (INTEL_PCH_TYPE(dev_priv) >= PCH_CNP)
+		I915_WRITE(SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ);
+
 	hotplug_irqs = SDE_HOTPLUG_MASK_SPT;
 	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_spt);
 
@@ -3203,7 +3225,7 @@ static void ibx_irq_postinstall(struct drm_i915_private *dev_priv)
 		spt_hpd_detection_setup(dev_priv);
 }
 
-static void ironlake_irq_postinstall(struct drm_i915_private *dev_priv)
+static void ilk_irq_postinstall(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 	u32 display_mask, extra_mask;
@@ -3597,7 +3619,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		intel_uncore_write16(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_breadcrumbs_irq(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i8xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3702,7 +3724,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		I915_WRITE(GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_breadcrumbs_irq(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3844,10 +3866,10 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		I915_WRITE(GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_breadcrumbs_irq(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
 
 		if (iir & I915_BSD_USER_INTERRUPT)
-			intel_engine_breadcrumbs_irq(dev_priv->engine[VCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->engine[VCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3877,7 +3899,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 
 	intel_hpd_init_work(dev_priv);
 
-	INIT_WORK(&dev_priv->l3_parity.error_work, ivybridge_parity_work);
+	INIT_WORK(&dev_priv->l3_parity.error_work, ivb_parity_work);
 	for (i = 0; i < MAX_L3_SLICES; ++i)
 		dev_priv->l3_parity.remap_info[i] = NULL;
 
@@ -3958,7 +3980,7 @@ static irq_handler_t intel_irq_handler(struct drm_i915_private *dev_priv)
 		else if (INTEL_GEN(dev_priv) >= 8)
 			return gen8_irq_handler;
 		else
-			return ironlake_irq_handler;
+			return ilk_irq_handler;
 	}
 }
 
@@ -3981,7 +4003,7 @@ static void intel_irq_reset(struct drm_i915_private *dev_priv)
 		else if (INTEL_GEN(dev_priv) >= 8)
 			gen8_irq_reset(dev_priv);
 		else
-			ironlake_irq_reset(dev_priv);
+			ilk_irq_reset(dev_priv);
 	}
 }
 
@@ -4004,7 +4026,7 @@ static void intel_irq_postinstall(struct drm_i915_private *dev_priv)
 		else if (INTEL_GEN(dev_priv) >= 8)
 			gen8_irq_postinstall(dev_priv);
 		else
-			ironlake_irq_postinstall(dev_priv);
+			ilk_irq_postinstall(dev_priv);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/i915_memcpy.c b/drivers/gpu/drm/i915/i915_memcpy.c
index 07b04b0acb77..fdd550405fd3 100644
--- a/drivers/gpu/drm/i915/i915_memcpy.c
+++ b/drivers/gpu/drm/i915/i915_memcpy.c
@@ -27,6 +27,12 @@
 
 #include "i915_memcpy.h"
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
+#define CI_BUG_ON(expr) BUG_ON(expr)
+#else
+#define CI_BUG_ON(expr) BUILD_BUG_ON_INVALID(expr)
+#endif
+
 static DEFINE_STATIC_KEY_FALSE(has_movntdqa);
 
 #ifdef CONFIG_AS_MOVNTDQA
@@ -34,7 +40,6 @@ static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len)
 {
 	kernel_fpu_begin();
 
-	len >>= 4;
 	while (len >= 4) {
 		asm("movntdqa   (%0), %%xmm0\n"
 		    "movntdqa 16(%0), %%xmm1\n"
@@ -59,6 +64,38 @@ static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len)
 
 	kernel_fpu_end();
 }
+
+static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len)
+{
+	kernel_fpu_begin();
+
+	while (len >= 4) {
+		asm("movntdqa   (%0), %%xmm0\n"
+		    "movntdqa 16(%0), %%xmm1\n"
+		    "movntdqa 32(%0), %%xmm2\n"
+		    "movntdqa 48(%0), %%xmm3\n"
+		    "movups %%xmm0,   (%1)\n"
+		    "movups %%xmm1, 16(%1)\n"
+		    "movups %%xmm2, 32(%1)\n"
+		    "movups %%xmm3, 48(%1)\n"
+		    :: "r" (src), "r" (dst) : "memory");
+		src += 64;
+		dst += 64;
+		len -= 4;
+	}
+	while (len--) {
+		asm("movntdqa (%0), %%xmm0\n"
+		    "movups %%xmm0, (%1)\n"
+		    :: "r" (src), "r" (dst) : "memory");
+		src += 16;
+		dst += 16;
+	}
+
+	kernel_fpu_end();
+}
+#else
+static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) {}
+static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) {}
 #endif
 
 /**
@@ -83,17 +120,47 @@ bool i915_memcpy_from_wc(void *dst, const void *src, unsigned long len)
 	if (unlikely(((unsigned long)dst | (unsigned long)src | len) & 15))
 		return false;
 
-#ifdef CONFIG_AS_MOVNTDQA
 	if (static_branch_likely(&has_movntdqa)) {
 		if (likely(len))
-			__memcpy_ntdqa(dst, src, len);
+			__memcpy_ntdqa(dst, src, len >> 4);
 		return true;
 	}
-#endif
 
 	return false;
 }
 
+/**
+ * i915_unaligned_memcpy_from_wc: perform a mostly accelerated read from WC
+ * @dst: destination pointer
+ * @src: source pointer
+ * @len: how many bytes to copy
+ *
+ * Like i915_memcpy_from_wc(), the unaligned variant copies @len bytes from
+ * @src to @dst using * non-temporal instructions where available, but
+ * accepts that its arguments may not be aligned, but are valid for the
+ * potential 16-byte read past the end.
+ */
+void i915_unaligned_memcpy_from_wc(void *dst, void *src, unsigned long len)
+{
+	unsigned long addr;
+
+	CI_BUG_ON(!i915_has_memcpy_from_wc());
+
+	addr = (unsigned long)src;
+	if (!IS_ALIGNED(addr, 16)) {
+		unsigned long x = min(ALIGN(addr, 16) - addr, len);
+
+		memcpy(dst, src, x);
+
+		len -= x;
+		dst += x;
+		src += x;
+	}
+
+	if (likely(len))
+		__memcpy_ntdqu(dst, src, DIV_ROUND_UP(len, 16));
+}
+
 void i915_memcpy_init_early(struct drm_i915_private *dev_priv)
 {
 	/*
diff --git a/drivers/gpu/drm/i915/i915_memcpy.h b/drivers/gpu/drm/i915/i915_memcpy.h
index 970d84b16987..e36d30edd987 100644
--- a/drivers/gpu/drm/i915/i915_memcpy.h
+++ b/drivers/gpu/drm/i915/i915_memcpy.h
@@ -11,7 +11,9 @@
 struct drm_i915_private;
 
 void i915_memcpy_init_early(struct drm_i915_private *i915);
+
 bool i915_memcpy_from_wc(void *dst, const void *src, unsigned long len);
+void i915_unaligned_memcpy_from_wc(void *dst, void *src, unsigned long len);
 
 /* The movntdqa instructions used for memcpy-from-wc require 16-byte alignment,
  * as well as SSE4.1 support. i915_memcpy_from_wc() will report if it cannot
diff --git a/drivers/gpu/drm/i915/i915_mm.c b/drivers/gpu/drm/i915/i915_mm.c
index 318562ce64c0..b6376b25ef63 100644
--- a/drivers/gpu/drm/i915/i915_mm.c
+++ b/drivers/gpu/drm/i915/i915_mm.c
@@ -33,6 +33,9 @@ struct remap_pfn {
 	struct mm_struct *mm;
 	unsigned long pfn;
 	pgprot_t prot;
+
+	struct sgt_iter sgt;
+	resource_size_t iobase;
 };
 
 static int remap_pfn(pte_t *pte, unsigned long addr, void *data)
@@ -46,6 +49,35 @@ static int remap_pfn(pte_t *pte, unsigned long addr, void *data)
 	return 0;
 }
 
+#define use_dma(io) ((io) != -1)
+
+static inline unsigned long sgt_pfn(const struct remap_pfn *r)
+{
+	if (use_dma(r->iobase))
+		return (r->sgt.dma + r->sgt.curr + r->iobase) >> PAGE_SHIFT;
+	else
+		return r->sgt.pfn + (r->sgt.curr >> PAGE_SHIFT);
+}
+
+static int remap_sg(pte_t *pte, unsigned long addr, void *data)
+{
+	struct remap_pfn *r = data;
+
+	if (GEM_WARN_ON(!r->sgt.pfn))
+		return -EINVAL;
+
+	/* Special PTE are not associated with any struct page */
+	set_pte_at(r->mm, addr, pte,
+		   pte_mkspecial(pfn_pte(sgt_pfn(r), r->prot)));
+	r->pfn++; /* track insertions in case we need to unwind later */
+
+	r->sgt.curr += PAGE_SIZE;
+	if (r->sgt.curr >= r->sgt.max)
+		r->sgt = __sgt_iter(__sg_next(r->sgt.sgp), use_dma(r->iobase));
+
+	return 0;
+}
+
 /**
  * remap_io_mapping - remap an IO mapping to userspace
  * @vma: user vma to map to
@@ -80,3 +112,40 @@ int remap_io_mapping(struct vm_area_struct *vma,
 
 	return 0;
 }
+
+/**
+ * remap_io_sg - remap an IO mapping to userspace
+ * @vma: user vma to map to
+ * @addr: target user address to start at
+ * @size: size of map area
+ * @sgl: Start sg entry
+ * @iobase: Use stored dma address offset by this address or pfn if -1
+ *
+ *  Note: this is only safe if the mm semaphore is held when called.
+ */
+int remap_io_sg(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long size,
+		struct scatterlist *sgl, resource_size_t iobase)
+{
+	struct remap_pfn r = {
+		.mm = vma->vm_mm,
+		.prot = vma->vm_page_prot,
+		.sgt = __sgt_iter(sgl, use_dma(iobase)),
+		.iobase = iobase,
+	};
+	int err;
+
+	/* We rely on prevalidation of the io-mapping to skip track_pfn(). */
+	GEM_BUG_ON((vma->vm_flags & EXPECTED_FLAGS) != EXPECTED_FLAGS);
+
+	if (!use_dma(iobase))
+		flush_cache_range(vma, addr, size);
+
+	err = apply_to_page_range(r.mm, addr, size, remap_sg, &r);
+	if (unlikely(err)) {
+		zap_vma_ptes(vma, addr, r.pfn << PAGE_SHIFT);
+		return err;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 1bb701d32a5d..83f01401b8b5 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -30,6 +30,7 @@
 #include "display/intel_fbdev.h"
 
 #include "i915_drv.h"
+#include "i915_perf.h"
 #include "i915_globals.h"
 #include "i915_selftest.h"
 
@@ -192,23 +193,23 @@
 	GEN_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_i830_info = {
+static const struct intel_device_info i830_info = {
 	I830_FEATURES,
 	PLATFORM(INTEL_I830),
 };
 
-static const struct intel_device_info intel_i845g_info = {
+static const struct intel_device_info i845g_info = {
 	I845_FEATURES,
 	PLATFORM(INTEL_I845G),
 };
 
-static const struct intel_device_info intel_i85x_info = {
+static const struct intel_device_info i85x_info = {
 	I830_FEATURES,
 	PLATFORM(INTEL_I85X),
 	.display.has_fbc = 1,
 };
 
-static const struct intel_device_info intel_i865g_info = {
+static const struct intel_device_info i865g_info = {
 	I845_FEATURES,
 	PLATFORM(INTEL_I865G),
 };
@@ -227,7 +228,7 @@ static const struct intel_device_info intel_i865g_info = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_i915g_info = {
+static const struct intel_device_info i915g_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_I915G),
 	.has_coherent_ggtt = false,
@@ -238,7 +239,7 @@ static const struct intel_device_info intel_i915g_info = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i915gm_info = {
+static const struct intel_device_info i915gm_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_I915GM),
 	.is_mobile = 1,
@@ -251,7 +252,7 @@ static const struct intel_device_info intel_i915gm_info = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i945g_info = {
+static const struct intel_device_info i945g_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_I945G),
 	.display.has_hotplug = 1,
@@ -262,7 +263,7 @@ static const struct intel_device_info intel_i945g_info = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i945gm_info = {
+static const struct intel_device_info i945gm_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_I945GM),
 	.is_mobile = 1,
@@ -276,21 +277,21 @@ static const struct intel_device_info intel_i945gm_info = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_g33_info = {
+static const struct intel_device_info g33_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_G33),
 	.display.has_hotplug = 1,
 	.display.has_overlay = 1,
 };
 
-static const struct intel_device_info intel_pineview_g_info = {
+static const struct intel_device_info pnv_g_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_PINEVIEW),
 	.display.has_hotplug = 1,
 	.display.has_overlay = 1,
 };
 
-static const struct intel_device_info intel_pineview_m_info = {
+static const struct intel_device_info pnv_m_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_PINEVIEW),
 	.is_mobile = 1,
@@ -313,7 +314,7 @@ static const struct intel_device_info intel_pineview_m_info = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_i965g_info = {
+static const struct intel_device_info i965g_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_I965G),
 	.display.has_overlay = 1,
@@ -321,7 +322,7 @@ static const struct intel_device_info intel_i965g_info = {
 	.has_snoop = false,
 };
 
-static const struct intel_device_info intel_i965gm_info = {
+static const struct intel_device_info i965gm_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_I965GM),
 	.is_mobile = 1,
@@ -332,14 +333,14 @@ static const struct intel_device_info intel_i965gm_info = {
 	.has_snoop = false,
 };
 
-static const struct intel_device_info intel_g45_info = {
+static const struct intel_device_info g45_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_G45),
 	.engine_mask = BIT(RCS0) | BIT(VCS0),
 	.gpu_reset_clobbers_display = false,
 };
 
-static const struct intel_device_info intel_gm45_info = {
+static const struct intel_device_info gm45_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_GM45),
 	.is_mobile = 1,
@@ -364,12 +365,12 @@ static const struct intel_device_info intel_gm45_info = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_ironlake_d_info = {
+static const struct intel_device_info ilk_d_info = {
 	GEN5_FEATURES,
 	PLATFORM(INTEL_IRONLAKE),
 };
 
-static const struct intel_device_info intel_ironlake_m_info = {
+static const struct intel_device_info ilk_m_info = {
 	GEN5_FEATURES,
 	PLATFORM(INTEL_IRONLAKE),
 	.is_mobile = 1,
@@ -399,12 +400,12 @@ static const struct intel_device_info intel_ironlake_m_info = {
 	GEN6_FEATURES, \
 	PLATFORM(INTEL_SANDYBRIDGE)
 
-static const struct intel_device_info intel_sandybridge_d_gt1_info = {
+static const struct intel_device_info snb_d_gt1_info = {
 	SNB_D_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_sandybridge_d_gt2_info = {
+static const struct intel_device_info snb_d_gt2_info = {
 	SNB_D_PLATFORM,
 	.gt = 2,
 };
@@ -415,12 +416,12 @@ static const struct intel_device_info intel_sandybridge_d_gt2_info = {
 	.is_mobile = 1
 
 
-static const struct intel_device_info intel_sandybridge_m_gt1_info = {
+static const struct intel_device_info snb_m_gt1_info = {
 	SNB_M_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_sandybridge_m_gt2_info = {
+static const struct intel_device_info snb_m_gt2_info = {
 	SNB_M_PLATFORM,
 	.gt = 2,
 };
@@ -436,7 +437,7 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 	.has_rc6 = 1, \
 	.has_rc6p = 1, \
 	.has_rps = true, \
-	.ppgtt_type = INTEL_PPGTT_ALIASING, \
+	.ppgtt_type = INTEL_PPGTT_FULL, \
 	.ppgtt_size = 31, \
 	IVB_PIPE_OFFSETS, \
 	IVB_CURSOR_OFFSETS, \
@@ -449,12 +450,12 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 	PLATFORM(INTEL_IVYBRIDGE), \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_ivybridge_d_gt1_info = {
+static const struct intel_device_info ivb_d_gt1_info = {
 	IVB_D_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_ivybridge_d_gt2_info = {
+static const struct intel_device_info ivb_d_gt2_info = {
 	IVB_D_PLATFORM,
 	.gt = 2,
 };
@@ -465,17 +466,17 @@ static const struct intel_device_info intel_ivybridge_d_gt2_info = {
 	.is_mobile = 1, \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_ivybridge_m_gt1_info = {
+static const struct intel_device_info ivb_m_gt1_info = {
 	IVB_M_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_ivybridge_m_gt2_info = {
+static const struct intel_device_info ivb_m_gt2_info = {
 	IVB_M_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_ivybridge_q_info = {
+static const struct intel_device_info ivb_q_info = {
 	GEN7_FEATURES,
 	PLATFORM(INTEL_IVYBRIDGE),
 	.gt = 2,
@@ -483,7 +484,7 @@ static const struct intel_device_info intel_ivybridge_q_info = {
 	.has_l3_dpf = 1,
 };
 
-static const struct intel_device_info intel_valleyview_info = {
+static const struct intel_device_info vlv_info = {
 	PLATFORM(INTEL_VALLEYVIEW),
 	GEN(7),
 	.is_lp = 1,
@@ -493,7 +494,7 @@ static const struct intel_device_info intel_valleyview_info = {
 	.has_rps = true,
 	.display.has_gmch = 1,
 	.display.has_hotplug = 1,
-	.ppgtt_type = INTEL_PPGTT_ALIASING,
+	.ppgtt_type = INTEL_PPGTT_FULL,
 	.ppgtt_size = 31,
 	.has_snoop = true,
 	.has_coherent_ggtt = false,
@@ -522,17 +523,17 @@ static const struct intel_device_info intel_valleyview_info = {
 	PLATFORM(INTEL_HASWELL), \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_haswell_gt1_info = {
+static const struct intel_device_info hsw_gt1_info = {
 	HSW_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_haswell_gt2_info = {
+static const struct intel_device_info hsw_gt2_info = {
 	HSW_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_haswell_gt3_info = {
+static const struct intel_device_info hsw_gt3_info = {
 	HSW_PLATFORM,
 	.gt = 3,
 };
@@ -550,17 +551,17 @@ static const struct intel_device_info intel_haswell_gt3_info = {
 	GEN8_FEATURES, \
 	PLATFORM(INTEL_BROADWELL)
 
-static const struct intel_device_info intel_broadwell_gt1_info = {
+static const struct intel_device_info bdw_gt1_info = {
 	BDW_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_broadwell_gt2_info = {
+static const struct intel_device_info bdw_gt2_info = {
 	BDW_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_broadwell_rsvd_info = {
+static const struct intel_device_info bdw_rsvd_info = {
 	BDW_PLATFORM,
 	.gt = 3,
 	/* According to the device ID those devices are GT3, they were
@@ -568,14 +569,14 @@ static const struct intel_device_info intel_broadwell_rsvd_info = {
 	 */
 };
 
-static const struct intel_device_info intel_broadwell_gt3_info = {
+static const struct intel_device_info bdw_gt3_info = {
 	BDW_PLATFORM,
 	.gt = 3,
 	.engine_mask =
 		BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS1),
 };
 
-static const struct intel_device_info intel_cherryview_info = {
+static const struct intel_device_info chv_info = {
 	PLATFORM(INTEL_CHERRYVIEW),
 	GEN(8),
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C),
@@ -620,12 +621,12 @@ static const struct intel_device_info intel_cherryview_info = {
 	GEN9_FEATURES, \
 	PLATFORM(INTEL_SKYLAKE)
 
-static const struct intel_device_info intel_skylake_gt1_info = {
+static const struct intel_device_info skl_gt1_info = {
 	SKL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_skylake_gt2_info = {
+static const struct intel_device_info skl_gt2_info = {
 	SKL_PLATFORM,
 	.gt = 2,
 };
@@ -636,12 +637,12 @@ static const struct intel_device_info intel_skylake_gt2_info = {
 		BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS1)
 
 
-static const struct intel_device_info intel_skylake_gt3_info = {
+static const struct intel_device_info skl_gt3_info = {
 	SKL_GT3_PLUS_PLATFORM,
 	.gt = 3,
 };
 
-static const struct intel_device_info intel_skylake_gt4_info = {
+static const struct intel_device_info skl_gt4_info = {
 	SKL_GT3_PLUS_PLATFORM,
 	.gt = 4,
 };
@@ -678,13 +679,13 @@ static const struct intel_device_info intel_skylake_gt4_info = {
 	GEN9_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_broxton_info = {
+static const struct intel_device_info bxt_info = {
 	GEN9_LP_FEATURES,
 	PLATFORM(INTEL_BROXTON),
 	.ddb_size = 512,
 };
 
-static const struct intel_device_info intel_geminilake_info = {
+static const struct intel_device_info glk_info = {
 	GEN9_LP_FEATURES,
 	PLATFORM(INTEL_GEMINILAKE),
 	.ddb_size = 1024,
@@ -695,17 +696,17 @@ static const struct intel_device_info intel_geminilake_info = {
 	GEN9_FEATURES, \
 	PLATFORM(INTEL_KABYLAKE)
 
-static const struct intel_device_info intel_kabylake_gt1_info = {
+static const struct intel_device_info kbl_gt1_info = {
 	KBL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_kabylake_gt2_info = {
+static const struct intel_device_info kbl_gt2_info = {
 	KBL_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_kabylake_gt3_info = {
+static const struct intel_device_info kbl_gt3_info = {
 	KBL_PLATFORM,
 	.gt = 3,
 	.engine_mask =
@@ -716,17 +717,17 @@ static const struct intel_device_info intel_kabylake_gt3_info = {
 	GEN9_FEATURES, \
 	PLATFORM(INTEL_COFFEELAKE)
 
-static const struct intel_device_info intel_coffeelake_gt1_info = {
+static const struct intel_device_info cfl_gt1_info = {
 	CFL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_coffeelake_gt2_info = {
+static const struct intel_device_info cfl_gt2_info = {
 	CFL_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_coffeelake_gt3_info = {
+static const struct intel_device_info cfl_gt3_info = {
 	CFL_PLATFORM,
 	.gt = 3,
 	.engine_mask =
@@ -741,7 +742,7 @@ static const struct intel_device_info intel_coffeelake_gt3_info = {
 	.has_coherent_ggtt = false, \
 	GLK_COLORS
 
-static const struct intel_device_info intel_cannonlake_info = {
+static const struct intel_device_info cnl_info = {
 	GEN10_FEATURES,
 	PLATFORM(INTEL_CANNONLAKE),
 	.gt = 2,
@@ -776,14 +777,14 @@ static const struct intel_device_info intel_cannonlake_info = {
 	.has_logical_ring_elsq = 1, \
 	.color = { .degamma_lut_size = 33, .gamma_lut_size = 262145 }
 
-static const struct intel_device_info intel_icelake_11_info = {
+static const struct intel_device_info icl_info = {
 	GEN11_FEATURES,
 	PLATFORM(INTEL_ICELAKE),
 	.engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
 };
 
-static const struct intel_device_info intel_elkhartlake_info = {
+static const struct intel_device_info ehl_info = {
 	GEN11_FEATURES,
 	PLATFORM(INTEL_ELKHARTLAKE),
 	.require_force_probe = 1,
@@ -814,7 +815,7 @@ static const struct intel_device_info intel_elkhartlake_info = {
 	.has_global_mocs = 1, \
 	.display.has_dsb = 1
 
-static const struct intel_device_info intel_tigerlake_12_info = {
+static const struct intel_device_info tgl_info = {
 	GEN12_FEATURES,
 	PLATFORM(INTEL_TIGERLAKE),
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
@@ -839,68 +840,70 @@ static const struct intel_device_info intel_tigerlake_12_info = {
  * PCI ID matches, otherwise we'll use the wrong info struct above.
  */
 static const struct pci_device_id pciidlist[] = {
-	INTEL_I830_IDS(&intel_i830_info),
-	INTEL_I845G_IDS(&intel_i845g_info),
-	INTEL_I85X_IDS(&intel_i85x_info),
-	INTEL_I865G_IDS(&intel_i865g_info),
-	INTEL_I915G_IDS(&intel_i915g_info),
-	INTEL_I915GM_IDS(&intel_i915gm_info),
-	INTEL_I945G_IDS(&intel_i945g_info),
-	INTEL_I945GM_IDS(&intel_i945gm_info),
-	INTEL_I965G_IDS(&intel_i965g_info),
-	INTEL_G33_IDS(&intel_g33_info),
-	INTEL_I965GM_IDS(&intel_i965gm_info),
-	INTEL_GM45_IDS(&intel_gm45_info),
-	INTEL_G45_IDS(&intel_g45_info),
-	INTEL_PINEVIEW_G_IDS(&intel_pineview_g_info),
-	INTEL_PINEVIEW_M_IDS(&intel_pineview_m_info),
-	INTEL_IRONLAKE_D_IDS(&intel_ironlake_d_info),
-	INTEL_IRONLAKE_M_IDS(&intel_ironlake_m_info),
-	INTEL_SNB_D_GT1_IDS(&intel_sandybridge_d_gt1_info),
-	INTEL_SNB_D_GT2_IDS(&intel_sandybridge_d_gt2_info),
-	INTEL_SNB_M_GT1_IDS(&intel_sandybridge_m_gt1_info),
-	INTEL_SNB_M_GT2_IDS(&intel_sandybridge_m_gt2_info),
-	INTEL_IVB_Q_IDS(&intel_ivybridge_q_info), /* must be first IVB */
-	INTEL_IVB_M_GT1_IDS(&intel_ivybridge_m_gt1_info),
-	INTEL_IVB_M_GT2_IDS(&intel_ivybridge_m_gt2_info),
-	INTEL_IVB_D_GT1_IDS(&intel_ivybridge_d_gt1_info),
-	INTEL_IVB_D_GT2_IDS(&intel_ivybridge_d_gt2_info),
-	INTEL_HSW_GT1_IDS(&intel_haswell_gt1_info),
-	INTEL_HSW_GT2_IDS(&intel_haswell_gt2_info),
-	INTEL_HSW_GT3_IDS(&intel_haswell_gt3_info),
-	INTEL_VLV_IDS(&intel_valleyview_info),
-	INTEL_BDW_GT1_IDS(&intel_broadwell_gt1_info),
-	INTEL_BDW_GT2_IDS(&intel_broadwell_gt2_info),
-	INTEL_BDW_GT3_IDS(&intel_broadwell_gt3_info),
-	INTEL_BDW_RSVD_IDS(&intel_broadwell_rsvd_info),
-	INTEL_CHV_IDS(&intel_cherryview_info),
-	INTEL_SKL_GT1_IDS(&intel_skylake_gt1_info),
-	INTEL_SKL_GT2_IDS(&intel_skylake_gt2_info),
-	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info),
-	INTEL_SKL_GT4_IDS(&intel_skylake_gt4_info),
-	INTEL_BXT_IDS(&intel_broxton_info),
-	INTEL_GLK_IDS(&intel_geminilake_info),
-	INTEL_KBL_GT1_IDS(&intel_kabylake_gt1_info),
-	INTEL_KBL_GT2_IDS(&intel_kabylake_gt2_info),
-	INTEL_KBL_GT3_IDS(&intel_kabylake_gt3_info),
-	INTEL_KBL_GT4_IDS(&intel_kabylake_gt3_info),
-	INTEL_AML_KBL_GT2_IDS(&intel_kabylake_gt2_info),
-	INTEL_CFL_S_GT1_IDS(&intel_coffeelake_gt1_info),
-	INTEL_CFL_S_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CFL_H_GT1_IDS(&intel_coffeelake_gt1_info),
-	INTEL_CFL_H_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CFL_U_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CFL_U_GT3_IDS(&intel_coffeelake_gt3_info),
-	INTEL_WHL_U_GT1_IDS(&intel_coffeelake_gt1_info),
-	INTEL_WHL_U_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_AML_CFL_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_WHL_U_GT3_IDS(&intel_coffeelake_gt3_info),
-	INTEL_CML_GT1_IDS(&intel_coffeelake_gt1_info),
-	INTEL_CML_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CNL_IDS(&intel_cannonlake_info),
-	INTEL_ICL_11_IDS(&intel_icelake_11_info),
-	INTEL_EHL_IDS(&intel_elkhartlake_info),
-	INTEL_TGL_12_IDS(&intel_tigerlake_12_info),
+	INTEL_I830_IDS(&i830_info),
+	INTEL_I845G_IDS(&i845g_info),
+	INTEL_I85X_IDS(&i85x_info),
+	INTEL_I865G_IDS(&i865g_info),
+	INTEL_I915G_IDS(&i915g_info),
+	INTEL_I915GM_IDS(&i915gm_info),
+	INTEL_I945G_IDS(&i945g_info),
+	INTEL_I945GM_IDS(&i945gm_info),
+	INTEL_I965G_IDS(&i965g_info),
+	INTEL_G33_IDS(&g33_info),
+	INTEL_I965GM_IDS(&i965gm_info),
+	INTEL_GM45_IDS(&gm45_info),
+	INTEL_G45_IDS(&g45_info),
+	INTEL_PINEVIEW_G_IDS(&pnv_g_info),
+	INTEL_PINEVIEW_M_IDS(&pnv_m_info),
+	INTEL_IRONLAKE_D_IDS(&ilk_d_info),
+	INTEL_IRONLAKE_M_IDS(&ilk_m_info),
+	INTEL_SNB_D_GT1_IDS(&snb_d_gt1_info),
+	INTEL_SNB_D_GT2_IDS(&snb_d_gt2_info),
+	INTEL_SNB_M_GT1_IDS(&snb_m_gt1_info),
+	INTEL_SNB_M_GT2_IDS(&snb_m_gt2_info),
+	INTEL_IVB_Q_IDS(&ivb_q_info), /* must be first IVB */
+	INTEL_IVB_M_GT1_IDS(&ivb_m_gt1_info),
+	INTEL_IVB_M_GT2_IDS(&ivb_m_gt2_info),
+	INTEL_IVB_D_GT1_IDS(&ivb_d_gt1_info),
+	INTEL_IVB_D_GT2_IDS(&ivb_d_gt2_info),
+	INTEL_HSW_GT1_IDS(&hsw_gt1_info),
+	INTEL_HSW_GT2_IDS(&hsw_gt2_info),
+	INTEL_HSW_GT3_IDS(&hsw_gt3_info),
+	INTEL_VLV_IDS(&vlv_info),
+	INTEL_BDW_GT1_IDS(&bdw_gt1_info),
+	INTEL_BDW_GT2_IDS(&bdw_gt2_info),
+	INTEL_BDW_GT3_IDS(&bdw_gt3_info),
+	INTEL_BDW_RSVD_IDS(&bdw_rsvd_info),
+	INTEL_CHV_IDS(&chv_info),
+	INTEL_SKL_GT1_IDS(&skl_gt1_info),
+	INTEL_SKL_GT2_IDS(&skl_gt2_info),
+	INTEL_SKL_GT3_IDS(&skl_gt3_info),
+	INTEL_SKL_GT4_IDS(&skl_gt4_info),
+	INTEL_BXT_IDS(&bxt_info),
+	INTEL_GLK_IDS(&glk_info),
+	INTEL_KBL_GT1_IDS(&kbl_gt1_info),
+	INTEL_KBL_GT2_IDS(&kbl_gt2_info),
+	INTEL_KBL_GT3_IDS(&kbl_gt3_info),
+	INTEL_KBL_GT4_IDS(&kbl_gt3_info),
+	INTEL_AML_KBL_GT2_IDS(&kbl_gt2_info),
+	INTEL_CFL_S_GT1_IDS(&cfl_gt1_info),
+	INTEL_CFL_S_GT2_IDS(&cfl_gt2_info),
+	INTEL_CFL_H_GT1_IDS(&cfl_gt1_info),
+	INTEL_CFL_H_GT2_IDS(&cfl_gt2_info),
+	INTEL_CFL_U_GT2_IDS(&cfl_gt2_info),
+	INTEL_CFL_U_GT3_IDS(&cfl_gt3_info),
+	INTEL_WHL_U_GT1_IDS(&cfl_gt1_info),
+	INTEL_WHL_U_GT2_IDS(&cfl_gt2_info),
+	INTEL_AML_CFL_GT2_IDS(&cfl_gt2_info),
+	INTEL_WHL_U_GT3_IDS(&cfl_gt3_info),
+	INTEL_CML_GT1_IDS(&cfl_gt1_info),
+	INTEL_CML_GT2_IDS(&cfl_gt2_info),
+	INTEL_CML_U_GT1_IDS(&cfl_gt1_info),
+	INTEL_CML_U_GT2_IDS(&cfl_gt2_info),
+	INTEL_CNL_IDS(&cnl_info),
+	INTEL_ICL_11_IDS(&icl_info),
+	INTEL_EHL_IDS(&ehl_info),
+	INTEL_TGL_12_IDS(&tgl_info),
 	{0, 0, 0}
 };
 MODULE_DEVICE_TABLE(pci, pciidlist);
@@ -1003,6 +1006,12 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return err > 0 ? -ENOTTY : err;
 	}
 
+	err = i915_perf_selftests(pdev);
+	if (err) {
+		i915_pci_remove(pdev);
+		return err > 0 ? -ENOTTY : err;
+	}
+
 	return 0;
 }
 
@@ -1045,7 +1054,12 @@ static int __init i915_init(void)
 		return 0;
 	}
 
-	return pci_register_driver(&i915_pci_driver);
+	err = pci_register_driver(&i915_pci_driver);
+	if (err)
+		return err;
+
+	i915_perf_sysctl_register();
+	return 0;
 }
 
 static void __exit i915_exit(void)
@@ -1053,6 +1067,7 @@ static void __exit i915_exit(void)
 	if (!i915_pci_driver.driver.owner)
 		return;
 
+	i915_perf_sysctl_unregister();
 	pci_unregister_driver(&i915_pci_driver);
 	i915_globals_exit();
 }
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2ae14bc14931..0f556d80ba36 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -387,6 +387,8 @@ struct i915_oa_config_bo {
 	struct i915_vma *vma;
 };
 
+static struct ctl_table_header *sysctl_header;
+
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
 
 void i915_oa_config_release(struct kref *ref)
@@ -1777,6 +1779,8 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 	*cs++ = MI_MATH_ADD;
 	*cs++ = MI_MATH_STOREINV(MI_MATH_REG(JUMP_PREDICATE), MI_MATH_REG_CF);
 
+	*cs++ = MI_ARB_CHECK;
+
 	/*
 	 * Transfer the result into the predicate register to be used for the
 	 * predicated jump.
@@ -1966,7 +1970,9 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 	if (err)
 		goto err_vma_put;
 
+	intel_engine_pm_get(ce->engine);
 	rq = i915_request_create(ce);
+	intel_engine_pm_put(ce->engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_vma_unpin;
@@ -2153,9 +2159,7 @@ static int gen8_modify_context(struct intel_context *ce,
 	struct i915_request *rq;
 	int err;
 
-	lockdep_assert_held(&ce->pin_mutex);
-
-	rq = i915_request_create(ce->engine->kernel_context);
+	rq = intel_engine_create_kernel_request(ce->engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -2197,17 +2201,14 @@ static int gen8_configure_context(struct i915_gem_context *ctx,
 		if (ce->engine->class != RENDER_CLASS)
 			continue;
 
-		err = intel_context_lock_pinned(ce);
-		if (err)
-			break;
+		/* Otherwise OA settings will be set upon first use */
+		if (!intel_context_pin_if_active(ce))
+			continue;
 
 		flex->value = intel_sseu_make_rpcs(ctx->i915, &ce->sseu);
+		err = gen8_modify_context(ce, flex, count);
 
-		/* Otherwise OA settings will be set upon first use */
-		if (intel_context_is_pinned(ce))
-			err = gen8_modify_context(ce, flex, count);
-
-		intel_context_unlock_pinned(ce);
+		intel_context_unpin(ce);
 		if (err)
 			break;
 	}
@@ -2317,9 +2318,6 @@ static int oa_configure_all_contexts(struct i915_perf_stream *stream,
 	 */
 	spin_lock(&i915->gem.contexts.lock);
 	list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) {
-		if (ctx == i915->kernel_context)
-			continue;
-
 		if (!kref_get_unless_zero(&ctx->ref))
 			continue;
 
@@ -2455,6 +2453,13 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
 
+static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
+{
+	return _MASKED_FIELD(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS,
+			     (stream->sample_flags & SAMPLE_OA_REPORT) ?
+			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
+}
+
 static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
@@ -2468,12 +2473,10 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
 					      GEN12_OAG_OA_DEBUG_INCLUDE_CLK_RATIO) |
 			   /*
-			    * If the user didn't require OA reports, instruct the
-			    * hardware not to emit ctx switch reports.
+			    * If the user didn't require OA reports, instruct
+			    * the hardware not to emit ctx switch reports.
 			    */
-			   !(stream->sample_flags & SAMPLE_OA_REPORT) ?
-			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS) :
-			   _MASKED_BIT_DISABLE(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS));
+			   oag_report_ctx_switches(stream));
 
 	intel_uncore_write(uncore, GEN12_OAG_OAGLBCTXCTRL, periodic ?
 			   (GEN12_OAG_OAGLBCTXCTRL_COUNTER_RESUME |
@@ -3101,7 +3104,7 @@ static void i915_perf_enable_locked(struct i915_perf_stream *stream)
 		stream->ops->enable(stream);
 
 	if (stream->hold_preemption)
-		i915_gem_context_set_nopreempt(stream->ctx);
+		intel_context_set_nopreempt(stream->pinned_ctx);
 }
 
 /**
@@ -3127,7 +3130,7 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream)
 	stream->enabled = false;
 
 	if (stream->hold_preemption)
-		i915_gem_context_clear_nopreempt(stream->ctx);
+		intel_context_clear_nopreempt(stream->pinned_ctx);
 
 	if (stream->ops->disable)
 		stream->ops->disable(stream);
@@ -3981,7 +3984,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 	struct i915_perf *perf = &to_i915(dev)->perf;
 	struct drm_i915_perf_oa_config *args = data;
 	struct i915_oa_config *oa_config, *tmp;
-	static struct i915_oa_reg *regs;
+	struct i915_oa_reg *regs;
 	int err, id;
 
 	if (!perf->i915) {
@@ -4219,7 +4222,7 @@ static struct ctl_table dev_root[] = {
 };
 
 /**
- * i915_perf_init - initialize i915-perf state on module load
+ * i915_perf_init - initialize i915-perf state on module bind
  * @i915: i915 device instance
  *
  * Initializes i915-perf state without exposing anything to userspace.
@@ -4336,7 +4339,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 
 		oa_sample_rate_hard_limit = 1000 *
 			(RUNTIME_INFO(i915)->cs_timestamp_frequency_khz / 2);
-		perf->sysctl_header = register_sysctl_table(dev_root);
 
 		mutex_init(&perf->metrics_lock);
 		idr_init(&perf->metrics_idr);
@@ -4372,6 +4374,16 @@ static int destroy_config(int id, void *p, void *data)
 	return 0;
 }
 
+void i915_perf_sysctl_register(void)
+{
+	sysctl_header = register_sysctl_table(dev_root);
+}
+
+void i915_perf_sysctl_unregister(void)
+{
+	unregister_sysctl_table(sysctl_header);
+}
+
 /**
  * i915_perf_fini - Counter part to i915_perf_init()
  * @i915: i915 device instance
@@ -4386,8 +4398,6 @@ void i915_perf_fini(struct drm_i915_private *i915)
 	idr_for_each(&perf->metrics_idr, destroy_config, perf);
 	idr_destroy(&perf->metrics_idr);
 
-	unregister_sysctl_table(perf->sysctl_header);
-
 	memset(&perf->ops, 0, sizeof(perf->ops));
 	perf->i915 = NULL;
 }
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 4ceebce72060..882fdd0a7680 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -23,6 +23,8 @@ void i915_perf_fini(struct drm_i915_private *i915);
 void i915_perf_register(struct drm_i915_private *i915);
 void i915_perf_unregister(struct drm_i915_private *i915);
 int i915_perf_ioctl_version(void);
+void i915_perf_sysctl_register(void);
+void i915_perf_sysctl_unregister(void);
 
 int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file);
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 74ddc20a0d37..45e581455f5d 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -380,7 +380,6 @@ struct i915_perf {
 	struct drm_i915_private *i915;
 
 	struct kobject *metrics_kobj;
-	struct ctl_table_header *sysctl_header;
 
 	/*
 	 * Lock associated with adding/modifying/removing OA configs
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index d6d2e6fb8674..28a82c849bac 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -259,6 +259,16 @@ add_sample(struct i915_pmu_sample *sample, u32 val)
 	sample->cur += val;
 }
 
+static bool exclusive_mmio_access(const struct drm_i915_private *i915)
+{
+	/*
+	 * We have to avoid concurrent mmio cache line access on gen7 or
+	 * risk a machine hang. For a fun history lesson dig out the old
+	 * userspace intel_gpu_top and run it on Ivybridge or Haswell!
+	 */
+	return IS_GEN(i915, 7);
+}
+
 static void
 engines_sample(struct intel_gt *gt, unsigned int period_ns)
 {
@@ -269,8 +279,12 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 	if ((i915->pmu.enable & ENGINE_SAMPLE_MASK) == 0)
 		return;
 
+	if (!intel_gt_pm_is_awake(gt))
+		return;
+
 	for_each_engine(engine, gt, id) {
 		struct intel_engine_pmu *pmu = &engine->pmu;
+		spinlock_t *mmio_lock;
 		unsigned long flags;
 		bool busy;
 		u32 val;
@@ -278,7 +292,12 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 		if (!intel_engine_pm_get_if_awake(engine))
 			continue;
 
-		spin_lock_irqsave(&engine->uncore->lock, flags);
+		mmio_lock = NULL;
+		if (exclusive_mmio_access(i915))
+			mmio_lock = &engine->uncore->lock;
+
+		if (unlikely(mmio_lock))
+			spin_lock_irqsave(mmio_lock, flags);
 
 		val = ENGINE_READ_FW(engine, RING_CTL);
 		if (val == 0) /* powerwell off => engine idle */
@@ -309,7 +328,8 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 			add_sample(&pmu->sample[I915_SAMPLE_BUSY], period_ns);
 
 skip:
-		spin_unlock_irqrestore(&engine->uncore->lock, flags);
+		if (unlikely(mmio_lock))
+			spin_unlock_irqrestore(mmio_lock, flags);
 		intel_engine_pm_put_async(engine);
 	}
 }
@@ -320,6 +340,13 @@ add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul)
 	sample->cur += mul_u32_u32(val, mul);
 }
 
+static bool frequency_sampling_enabled(struct i915_pmu *pmu)
+{
+	return pmu->enable &
+	       (config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY) |
+		config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY));
+}
+
 static void
 frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 {
@@ -328,19 +355,33 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 	struct i915_pmu *pmu = &i915->pmu;
 	struct intel_rps *rps = &gt->rps;
 
+	if (!frequency_sampling_enabled(pmu))
+		return;
+
+	/* Report 0/0 (actual/requested) frequency while parked. */
+	if (!intel_gt_pm_get_if_awake(gt))
+		return;
+
 	if (pmu->enable & config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY)) {
 		u32 val;
 
-		val = rps->cur_freq;
-		if (intel_gt_pm_get_if_awake(gt)) {
-			val = intel_uncore_read_notrace(uncore, GEN6_RPSTAT1);
-			val = intel_get_cagf(rps, val);
-			intel_gt_pm_put_async(gt);
-		}
+		/*
+		 * We take a quick peek here without using forcewake
+		 * so that we don't perturb the system under observation
+		 * (forcewake => !rc6 => increased power use). We expect
+		 * that if the read fails because it is outside of the
+		 * mmio power well, then it will return 0 -- in which
+		 * case we assume the system is running at the intended
+		 * frequency. Fortunately, the read should rarely fail!
+		 */
+		val = intel_uncore_read_fw(uncore, GEN6_RPSTAT1);
+		if (val)
+			val = intel_rps_get_cagf(rps, val);
+		else
+			val = rps->cur_freq;
 
 		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT],
-				intel_gpu_freq(rps, val),
-				period_ns / 1000);
+				intel_gpu_freq(rps, val), period_ns / 1000);
 	}
 
 	if (pmu->enable & config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY)) {
@@ -348,6 +389,8 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 				intel_gpu_freq(rps, rps->cur_freq),
 				period_ns / 1000);
 	}
+
+	intel_gt_pm_put_async(gt);
 }
 
 static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 094011b8f64d..6cc55c103f67 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2244,26 +2244,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 				    MG_DP_MODE_LN1_ACU_PORT1)
 #define   MG_DP_MODE_CFG_DP_X2_MODE			(1 << 7)
 #define   MG_DP_MODE_CFG_DP_X1_MODE			(1 << 6)
-#define   MG_DP_MODE_CFG_TR2PWR_GATING			(1 << 5)
-#define   MG_DP_MODE_CFG_TRPWR_GATING			(1 << 4)
-#define   MG_DP_MODE_CFG_CLNPWR_GATING			(1 << 3)
-#define   MG_DP_MODE_CFG_DIGPWR_GATING			(1 << 2)
-#define   MG_DP_MODE_CFG_GAONPWR_GATING			(1 << 1)
-
-#define MG_MISC_SUS0_PORT1				0x168814
-#define MG_MISC_SUS0_PORT2				0x169814
-#define MG_MISC_SUS0_PORT3				0x16A814
-#define MG_MISC_SUS0_PORT4				0x16B814
-#define MG_MISC_SUS0(tc_port) \
-	_MMIO(_PORT(tc_port, MG_MISC_SUS0_PORT1, MG_MISC_SUS0_PORT2))
-#define   MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE_MASK	(3 << 14)
-#define   MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE(x)	((x) << 14)
-#define   MG_MISC_SUS0_CFG_TR2PWR_GATING		(1 << 12)
-#define   MG_MISC_SUS0_CFG_CL2PWR_GATING		(1 << 11)
-#define   MG_MISC_SUS0_CFG_GAONPWR_GATING		(1 << 10)
-#define   MG_MISC_SUS0_CFG_TRPWR_GATING			(1 << 7)
-#define   MG_MISC_SUS0_CFG_CL1PWR_GATING		(1 << 6)
-#define   MG_MISC_SUS0_CFG_DGPWR_GATING			(1 << 5)
 
 /* The spec defines this only for BXT PHY0, but lets assume that this
  * would exist for PHY1 too if it had a second channel.
@@ -5048,14 +5028,20 @@ enum {
 #define   BLM_PCH_POLARITY			(1 << 29)
 #define BLC_PWM_PCH_CTL2	_MMIO(0xc8254)
 
-#define UTIL_PIN_CTL		_MMIO(0x48400)
-#define   UTIL_PIN_ENABLE	(1 << 31)
-
-#define   UTIL_PIN_PIPE(x)     ((x) << 29)
-#define   UTIL_PIN_PIPE_MASK   (3 << 29)
-#define   UTIL_PIN_MODE_PWM    (1 << 24)
-#define   UTIL_PIN_MODE_MASK   (0xf << 24)
-#define   UTIL_PIN_POLARITY    (1 << 22)
+#define UTIL_PIN_CTL			_MMIO(0x48400)
+#define   UTIL_PIN_ENABLE		(1 << 31)
+#define   UTIL_PIN_PIPE_MASK		(3 << 29)
+#define   UTIL_PIN_PIPE(x)		((x) << 29)
+#define   UTIL_PIN_MODE_MASK		(0xf << 24)
+#define   UTIL_PIN_MODE_DATA		(0 << 24)
+#define   UTIL_PIN_MODE_PWM		(1 << 24)
+#define   UTIL_PIN_MODE_VBLANK		(4 << 24)
+#define   UTIL_PIN_MODE_VSYNC		(5 << 24)
+#define   UTIL_PIN_MODE_EYE_LEVEL	(8 << 24)
+#define   UTIL_PIN_OUTPUT_DATA		(1 << 23)
+#define   UTIL_PIN_POLARITY		(1 << 22)
+#define   UTIL_PIN_DIRECTION_INPUT	(1 << 19)
+#define   UTIL_PIN_INPUT_DATA		(1 << 16)
 
 /* BXT backlight register definition. */
 #define _BXT_BLC_PWM_CTL1			0xC8250
@@ -5757,7 +5743,8 @@ enum {
 #define   PIPECONF_DOUBLE_WIDE	(1 << 30)
 #define   I965_PIPECONF_ACTIVE	(1 << 30)
 #define   PIPECONF_DSI_PLL_LOCKED	(1 << 29) /* vlv & pipe A only */
-#define   PIPECONF_FRAME_START_DELAY_MASK (3 << 27)
+#define   PIPECONF_FRAME_START_DELAY_MASK	(3 << 27) /* pre-hsw */
+#define   PIPECONF_FRAME_START_DELAY(x)		((x) << 27) /* pre-hsw: 0-3 */
 #define   PIPECONF_SINGLE_WIDE	0
 #define   PIPECONF_PIPE_UNLOCKED 0
 #define   PIPECONF_PIPE_LOCKED	(1 << 25)
@@ -6365,6 +6352,7 @@ enum {
 #define   DISPPLANE_RGBX101010			(0x8 << 26)
 #define   DISPPLANE_RGBA101010			(0x9 << 26)
 #define   DISPPLANE_BGRX101010			(0xa << 26)
+#define   DISPPLANE_BGRA101010			(0xb << 26)
 #define   DISPPLANE_RGBX161616			(0xc << 26)
 #define   DISPPLANE_RGBX888			(0xe << 26)
 #define   DISPPLANE_RGBA888			(0xf << 26)
@@ -6639,12 +6627,15 @@ enum {
 #define   SP_ENABLE			(1 << 31)
 #define   SP_GAMMA_ENABLE		(1 << 30)
 #define   SP_PIXFORMAT_MASK		(0xf << 26)
-#define   SP_FORMAT_YUV422		(0 << 26)
-#define   SP_FORMAT_BGR565		(5 << 26)
-#define   SP_FORMAT_BGRX8888		(6 << 26)
-#define   SP_FORMAT_BGRA8888		(7 << 26)
-#define   SP_FORMAT_RGBX1010102		(8 << 26)
-#define   SP_FORMAT_RGBA1010102		(9 << 26)
+#define   SP_FORMAT_YUV422		(0x0 << 26)
+#define   SP_FORMAT_8BPP		(0x2 << 26)
+#define   SP_FORMAT_BGR565		(0x5 << 26)
+#define   SP_FORMAT_BGRX8888		(0x6 << 26)
+#define   SP_FORMAT_BGRA8888		(0x7 << 26)
+#define   SP_FORMAT_RGBX1010102		(0x8 << 26)
+#define   SP_FORMAT_RGBA1010102		(0x9 << 26)
+#define   SP_FORMAT_BGRX1010102		(0xa << 26) /* CHV pipe B */
+#define   SP_FORMAT_BGRA1010102		(0xb << 26) /* CHV pipe B */
 #define   SP_FORMAT_RGBX8888		(0xe << 26)
 #define   SP_FORMAT_RGBA8888		(0xf << 26)
 #define   SP_ALPHA_PREMULTIPLY		(1 << 23) /* CHV pipe B */
@@ -6795,6 +6786,7 @@ enum {
 #define   PLANE_CTL_YUV422_VYUY			(3 << 16)
 #define   PLANE_CTL_RENDER_DECOMPRESSION_ENABLE	(1 << 15)
 #define   PLANE_CTL_TRICKLE_FEED_DISABLE	(1 << 14)
+#define   PLANE_CTL_CLEAR_COLOR_DISABLE		(1 << 13) /* TGL+ */
 #define   PLANE_CTL_PLANE_GAMMA_DISABLE		(1 << 13) /* Pre-GLK */
 #define   PLANE_CTL_TILED_MASK			(0x7 << 10)
 #define   PLANE_CTL_TILED_LINEAR		(0 << 10)
@@ -6802,6 +6794,7 @@ enum {
 #define   PLANE_CTL_TILED_Y			(4 << 10)
 #define   PLANE_CTL_TILED_YF			(5 << 10)
 #define   PLANE_CTL_FLIP_HORIZONTAL		(1 << 8)
+#define   PLANE_CTL_MEDIA_DECOMPRESSION_ENABLE	(1 << 4) /* TGL+ */
 #define   PLANE_CTL_ALPHA_MASK			(0x3 << 4) /* Pre-GLK */
 #define   PLANE_CTL_ALPHA_DISABLE		(0 << 4)
 #define   PLANE_CTL_ALPHA_SW_PREMULTIPLY	(2 << 4)
@@ -7512,11 +7505,15 @@ enum {
 #define GEN8_DE_PORT_IMR _MMIO(0x44444)
 #define GEN8_DE_PORT_IIR _MMIO(0x44448)
 #define GEN8_DE_PORT_IER _MMIO(0x4444c)
+#define  DSI1_NON_TE			(1 << 31)
+#define  DSI0_NON_TE			(1 << 30)
 #define  ICL_AUX_CHANNEL_E		(1 << 29)
 #define  CNL_AUX_CHANNEL_F		(1 << 28)
 #define  GEN9_AUX_CHANNEL_D		(1 << 27)
 #define  GEN9_AUX_CHANNEL_C		(1 << 26)
 #define  GEN9_AUX_CHANNEL_B		(1 << 25)
+#define  DSI1_TE			(1 << 24)
+#define  DSI0_TE			(1 << 23)
 #define  BXT_DE_PORT_HP_DDIC		(1 << 5)
 #define  BXT_DE_PORT_HP_DDIB		(1 << 4)
 #define  BXT_DE_PORT_HP_DDIA		(1 << 3)
@@ -7731,6 +7728,8 @@ enum {
 					    [TRANSCODER_B] = _CHICKEN_TRANS_B, \
 					    [TRANSCODER_C] = _CHICKEN_TRANS_C, \
 					    [TRANSCODER_D] = _CHICKEN_TRANS_D))
+#define  HSW_FRAME_START_DELAY_MASK	(3 << 27)
+#define  HSW_FRAME_START_DELAY(x)	((x) << 27) /* 0-3 */
 #define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1 << 25) /* GLK and CNL+ */
 #define  DDI_TRAINING_OVERRIDE_ENABLE	(1 << 19)
 #define  DDI_TRAINING_OVERRIDE_VALUE	(1 << 18)
@@ -7754,6 +7753,14 @@ enum {
 #define GEN7_MSG_CTL	_MMIO(0x45010)
 #define  WAIT_FOR_PCH_RESET_ACK		(1 << 1)
 #define  WAIT_FOR_PCH_FLR_ACK		(1 << 0)
+
+#define BW_BUDDY1_CTL			_MMIO(0x45140)
+#define BW_BUDDY2_CTL			_MMIO(0x45150)
+#define   BW_BUDDY_DISABLE		REG_BIT(31)
+
+#define BW_BUDDY1_PAGE_MASK		_MMIO(0x45144)
+#define BW_BUDDY2_PAGE_MASK		_MMIO(0x45154)
+
 #define HSW_NDE_RSTWRN_OPT	_MMIO(0x46408)
 #define  RESET_PCH_HANDSHAKE_ENABLE	(1 << 4)
 
@@ -7911,6 +7918,10 @@ enum {
 #define   PIXEL_ROUNDING_TRUNC_FB_PASSTHRU 	(1 << 15)
 #define   PER_PIXEL_ALPHA_BYPASS_EN		(1 << 7)
 
+#define FF_MODE2			_MMIO(0x6604)
+#define   FF_MODE2_TDS_TIMER_MASK	REG_GENMASK(23, 16)
+#define   FF_MODE2_TDS_TIMER_128	REG_FIELD_PREP(FF_MODE2_TDS_TIMER_MASK, 4)
+
 /* PCH */
 
 #define PCH_DISPLAY_BASE	0xc0000u
@@ -8099,6 +8110,10 @@ enum {
 
 #define SHOTPLUG_CTL_TC				_MMIO(0xc4034)
 #define   ICP_TC_HPD_ENABLE(tc_port)		(8 << (tc_port) * 4)
+
+#define SHPD_FILTER_CNT				_MMIO(0xc4038)
+#define   SHPD_FILTER_CNT_500_ADJ		0x001D9
+
 /* Icelake DSC Rate Control Range Parameter Registers */
 #define DSCA_RC_RANGE_PARAMETERS_0		_MMIO(0x6B240)
 #define DSCA_RC_RANGE_PARAMETERS_0_UDW		_MMIO(0x6B240 + 4)
@@ -8449,10 +8464,8 @@ enum {
 #define  TRANS_STATE_MASK       (1 << 30)
 #define  TRANS_STATE_DISABLE    (0 << 30)
 #define  TRANS_STATE_ENABLE     (1 << 30)
-#define  TRANS_FSYNC_DELAY_HB1  (0 << 27)
-#define  TRANS_FSYNC_DELAY_HB2  (1 << 27)
-#define  TRANS_FSYNC_DELAY_HB3  (2 << 27)
-#define  TRANS_FSYNC_DELAY_HB4  (3 << 27)
+#define  TRANS_FRAME_START_DELAY_MASK	(3 << 27) /* ibx */
+#define  TRANS_FRAME_START_DELAY(x)	((x) << 27) /* ibx: 0-3 */
 #define  TRANS_INTERLACE_MASK   (7 << 21)
 #define  TRANS_PROGRESSIVE      (0 << 21)
 #define  TRANS_INTERLACED       (3 << 21)
@@ -8473,6 +8486,7 @@ enum {
 #define  TRANS_CHICKEN2_TIMING_OVERRIDE			(1 << 31)
 #define  TRANS_CHICKEN2_FDI_POLARITY_REVERSED		(1 << 29)
 #define  TRANS_CHICKEN2_FRAME_START_DELAY_MASK		(3 << 27)
+#define  TRANS_CHICKEN2_FRAME_START_DELAY(x)		((x) << 27) /* 0-3 */
 #define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER	(1 << 26)
 #define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH	(1 << 25)
 
@@ -9675,6 +9689,7 @@ enum skl_power_gate {
 #define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4 << 12)
 #define  TRANS_DDI_EDP_INPUT_B_ONOFF	(5 << 12)
 #define  TRANS_DDI_EDP_INPUT_C_ONOFF	(6 << 12)
+#define  TRANS_DDI_EDP_INPUT_D_ONOFF	(7 << 12)
 #define  TRANS_DDI_MST_TRANSPORT_SELECT_MASK	REG_GENMASK(11, 10)
 #define  TRANS_DDI_MST_TRANSPORT_SELECT(trans)	\
 	REG_FIELD_PREP(TRANS_DDI_MST_TRANSPORT_SELECT_MASK, trans)
@@ -10780,6 +10795,57 @@ enum skl_power_gate {
 #define  ICL_ESC_CLK_DIV_SHIFT			0
 #define DSI_MAX_ESC_CLK			20000		/* in KHz */
 
+#define _DSI_CMD_FRMCTL_0		0x6b034
+#define _DSI_CMD_FRMCTL_1		0x6b834
+#define DSI_CMD_FRMCTL(port)		_MMIO_PORT(port,	\
+						   _DSI_CMD_FRMCTL_0,\
+						   _DSI_CMD_FRMCTL_1)
+#define   DSI_FRAME_UPDATE_REQUEST		(1 << 31)
+#define   DSI_PERIODIC_FRAME_UPDATE_ENABLE	(1 << 29)
+#define   DSI_NULL_PACKET_ENABLE		(1 << 28)
+#define   DSI_FRAME_IN_PROGRESS			(1 << 0)
+
+#define _DSI_INTR_MASK_REG_0		0x6b070
+#define _DSI_INTR_MASK_REG_1		0x6b870
+#define DSI_INTR_MASK_REG(port)		_MMIO_PORT(port,	\
+						   _DSI_INTR_MASK_REG_0,\
+						   _DSI_INTR_MASK_REG_1)
+
+#define _DSI_INTR_IDENT_REG_0		0x6b074
+#define _DSI_INTR_IDENT_REG_1		0x6b874
+#define DSI_INTR_IDENT_REG(port)	_MMIO_PORT(port,	\
+						   _DSI_INTR_IDENT_REG_0,\
+						   _DSI_INTR_IDENT_REG_1)
+#define   DSI_TE_EVENT				(1 << 31)
+#define   DSI_RX_DATA_OR_BTA_TERMINATED		(1 << 30)
+#define   DSI_TX_DATA				(1 << 29)
+#define   DSI_ULPS_ENTRY_DONE			(1 << 28)
+#define   DSI_NON_TE_TRIGGER_RECEIVED		(1 << 27)
+#define   DSI_HOST_CHKSUM_ERROR			(1 << 26)
+#define   DSI_HOST_MULTI_ECC_ERROR		(1 << 25)
+#define   DSI_HOST_SINGL_ECC_ERROR		(1 << 24)
+#define   DSI_HOST_CONTENTION_DETECTED		(1 << 23)
+#define   DSI_HOST_FALSE_CONTROL_ERROR		(1 << 22)
+#define   DSI_HOST_TIMEOUT_ERROR		(1 << 21)
+#define   DSI_HOST_LOW_POWER_TX_SYNC_ERROR	(1 << 20)
+#define   DSI_HOST_ESCAPE_MODE_ENTRY_ERROR	(1 << 19)
+#define   DSI_FRAME_UPDATE_DONE			(1 << 16)
+#define   DSI_PROTOCOL_VIOLATION_REPORTED	(1 << 15)
+#define   DSI_INVALID_TX_LENGTH			(1 << 13)
+#define   DSI_INVALID_VC			(1 << 12)
+#define   DSI_INVALID_DATA_TYPE			(1 << 11)
+#define   DSI_PERIPHERAL_CHKSUM_ERROR		(1 << 10)
+#define   DSI_PERIPHERAL_MULTI_ECC_ERROR	(1 << 9)
+#define   DSI_PERIPHERAL_SINGLE_ECC_ERROR	(1 << 8)
+#define   DSI_PERIPHERAL_CONTENTION_DETECTED	(1 << 7)
+#define   DSI_PERIPHERAL_FALSE_CTRL_ERROR	(1 << 6)
+#define   DSI_PERIPHERAL_TIMEOUT_ERROR		(1 << 5)
+#define   DSI_PERIPHERAL_LP_TX_SYNC_ERROR	(1 << 4)
+#define   DSI_PERIPHERAL_ESC_MODE_ENTRY_CMD_ERR	(1 << 3)
+#define   DSI_EOT_SYNC_ERROR			(1 << 2)
+#define   DSI_SOT_SYNC_ERROR			(1 << 1)
+#define   DSI_SOT_ERROR				(1 << 0)
+
 /* Gen4+ Timestamp and Pipe Frame time stamp registers */
 #define GEN4_TIMESTAMP		_MMIO(0x2358)
 #define ILK_TIMESTAMP_HI	_MMIO(0x70070)
@@ -11384,6 +11450,7 @@ enum skl_power_gate {
 #define  CMD_MODE_TE_GATE		(0x1 << 28)
 #define  VIDEO_MODE_SYNC_EVENT		(0x2 << 28)
 #define  VIDEO_MODE_SYNC_PULSE		(0x3 << 28)
+#define  TE_SOURCE_GPIO			(1 << 27)
 #define  LINK_READY			(1 << 20)
 #define  PIX_FMT_MASK			(0x3 << 16)
 #define  PIX_FMT_SHIFT			16
@@ -11636,13 +11703,18 @@ enum skl_power_gate {
 /* MOCS (Memory Object Control State) registers */
 #define GEN9_LNCFCMOCS(i)	_MMIO(0xb020 + (i) * 4)	/* L3 Cache Control */
 
-#define GEN9_GFX_MOCS(i)	_MMIO(0xc800 + (i) * 4)	/* Graphics MOCS registers */
-#define GEN9_MFX0_MOCS(i)	_MMIO(0xc900 + (i) * 4)	/* Media 0 MOCS registers */
-#define GEN9_MFX1_MOCS(i)	_MMIO(0xca00 + (i) * 4)	/* Media 1 MOCS registers */
-#define GEN9_VEBOX_MOCS(i)	_MMIO(0xcb00 + (i) * 4)	/* Video MOCS registers */
-#define GEN9_BLT_MOCS(i)	_MMIO(0xcc00 + (i) * 4)	/* Blitter MOCS registers */
-/* Media decoder 2 MOCS registers */
-#define GEN11_MFX2_MOCS(i)	_MMIO(0x10000 + (i) * 4)
+#define __GEN9_RCS0_MOCS0	0xc800
+#define GEN9_GFX_MOCS(i)	_MMIO(__GEN9_RCS0_MOCS0 + (i) * 4)
+#define __GEN9_VCS0_MOCS0	0xc900
+#define GEN9_MFX0_MOCS(i)	_MMIO(__GEN9_VCS0_MOCS0 + (i) * 4)
+#define __GEN9_VCS1_MOCS0	0xca00
+#define GEN9_MFX1_MOCS(i)	_MMIO(__GEN9_VCS1_MOCS0 + (i) * 4)
+#define __GEN9_VECS0_MOCS0	0xcb00
+#define GEN9_VEBOX_MOCS(i)	_MMIO(__GEN9_VECS0_MOCS0 + (i) * 4)
+#define __GEN9_BCS0_MOCS0	0xcc00
+#define GEN9_BLT_MOCS(i)	_MMIO(__GEN9_BCS0_MOCS0 + (i) * 4)
+#define __GEN11_VCS2_MOCS0	0x10000
+#define GEN11_MFX2_MOCS(i)	_MMIO(__GEN11_VCS2_MOCS0 + (i) * 4)
 
 #define GEN10_SCRATCH_LNCF2		_MMIO(0xb0a0)
 #define   PMFLUSHDONE_LNICRSDROP	(1 << 20)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 765bec89fc0d..be185886e4fc 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -57,11 +57,13 @@ static struct i915_global_request {
 
 static const char *i915_fence_get_driver_name(struct dma_fence *fence)
 {
-	return "i915";
+	return dev_name(to_request(fence)->i915->drm.dev);
 }
 
 static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
 {
+	const struct i915_gem_context *ctx;
+
 	/*
 	 * The timeline struct (as part of the ppgtt underneath a context)
 	 * may be freed when the request is no longer in use by the GPU.
@@ -74,7 +76,11 @@ static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 		return "signaled";
 
-	return to_request(fence)->gem_context->name ?: "[i915]";
+	ctx = i915_request_gem_context(to_request(fence));
+	if (!ctx)
+		return "[" DRIVER_NAME "]";
+
+	return ctx->name;
 }
 
 static bool i915_fence_signaled(struct dma_fence *fence)
@@ -188,7 +194,7 @@ static void free_capture_list(struct i915_request *request)
 {
 	struct i915_capture_list *capture;
 
-	capture = request->capture_list;
+	capture = fetch_and_zero(&request->capture_list);
 	while (capture) {
 		struct i915_capture_list *next = capture->next;
 
@@ -214,7 +220,7 @@ static void remove_from_engine(struct i915_request *rq)
 		spin_lock(&engine->active.lock);
 		locked = engine;
 	}
-	list_del(&rq->sched.link);
+	list_del_init(&rq->sched.link);
 	spin_unlock_irq(&locked->active.lock);
 }
 
@@ -223,10 +229,7 @@ bool i915_request_retire(struct i915_request *rq)
 	if (!i915_request_completed(rq))
 		return false;
 
-	GEM_TRACE("%s fence %llx:%lld, current %d\n",
-		  rq->engine->name,
-		  rq->fence.context, rq->fence.seqno,
-		  hwsp_seqno(rq));
+	RQ_TRACE(rq, "\n");
 
 	GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit));
 	trace_i915_request_retire(rq);
@@ -272,8 +275,8 @@ bool i915_request_retire(struct i915_request *rq)
 	remove_from_client(rq);
 	list_del(&rq->link);
 
-	intel_context_exit(rq->hw_context);
-	intel_context_unpin(rq->hw_context);
+	intel_context_exit(rq->context);
+	intel_context_unpin(rq->context);
 
 	free_capture_list(rq);
 	i915_sched_node_fini(&rq->sched);
@@ -287,10 +290,7 @@ void i915_request_retire_upto(struct i915_request *rq)
 	struct intel_timeline * const tl = i915_request_timeline(rq);
 	struct i915_request *tmp;
 
-	GEM_TRACE("%s fence %llx:%lld, current %d\n",
-		  rq->engine->name,
-		  rq->fence.context, rq->fence.seqno,
-		  hwsp_seqno(rq));
+	RQ_TRACE(rq, "\n");
 
 	GEM_BUG_ON(!i915_request_completed(rq));
 
@@ -351,10 +351,7 @@ bool __i915_request_submit(struct i915_request *request)
 	struct intel_engine_cs *engine = request->engine;
 	bool result = false;
 
-	GEM_TRACE("%s fence %llx:%lld, current %d\n",
-		  engine->name,
-		  request->fence.context, request->fence.seqno,
-		  hwsp_seqno(request));
+	RQ_TRACE(request, "\n");
 
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
@@ -378,7 +375,7 @@ bool __i915_request_submit(struct i915_request *request)
 	if (i915_request_completed(request))
 		goto xfer;
 
-	if (i915_gem_context_is_banned(request->gem_context))
+	if (intel_context_is_banned(request->context))
 		i915_request_skip(request, -EIO);
 
 	/*
@@ -417,7 +414,7 @@ xfer:	/* We may be recursing from the signal callback of another i915 fence */
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
 	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
 	    !i915_request_enable_breadcrumb(request))
-		intel_engine_queue_breadcrumbs(engine);
+		intel_engine_signal_breadcrumbs(engine);
 
 	__notify_execute_cb(request);
 
@@ -443,10 +440,7 @@ void __i915_request_unsubmit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
 
-	GEM_TRACE("%s fence %llx:%lld, current %d\n",
-		  engine->name,
-		  request->fence.context, request->fence.seqno,
-		  hwsp_seqno(request));
+	RQ_TRACE(request, "\n");
 
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
@@ -588,6 +582,21 @@ out:
 	return kmem_cache_alloc(global.slab_requests, gfp);
 }
 
+static void __i915_request_ctor(void *arg)
+{
+	struct i915_request *rq = arg;
+
+	spin_lock_init(&rq->lock);
+	i915_sched_node_init(&rq->sched);
+	i915_sw_fence_init(&rq->submit, submit_notify);
+	i915_sw_fence_init(&rq->semaphore, semaphore_notify);
+
+	rq->file_priv = NULL;
+	rq->capture_list = NULL;
+
+	INIT_LIST_HEAD(&rq->execute_cb);
+}
+
 struct i915_request *
 __i915_request_create(struct intel_context *ce, gfp_t gfp)
 {
@@ -645,35 +654,31 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 		goto err_free;
 
 	rq->i915 = ce->engine->i915;
-	rq->hw_context = ce;
-	rq->gem_context = ce->gem_context;
+	rq->context = ce;
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
 
-	rcu_assign_pointer(rq->timeline, tl);
+	RCU_INIT_POINTER(rq->timeline, tl);
+	RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline);
 	rq->hwsp_seqno = tl->hwsp_seqno;
-	rq->hwsp_cacheline = tl->hwsp_cacheline;
 
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
-	spin_lock_init(&rq->lock);
 	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
 		       tl->fence_context, seqno);
 
 	/* We bump the ref for the fence chain */
-	i915_sw_fence_init(&i915_request_get(rq)->submit, submit_notify);
-	i915_sw_fence_init(&i915_request_get(rq)->semaphore, semaphore_notify);
+	i915_sw_fence_reinit(&i915_request_get(rq)->submit);
+	i915_sw_fence_reinit(&i915_request_get(rq)->semaphore);
 
-	i915_sched_node_init(&rq->sched);
+	i915_sched_node_reinit(&rq->sched);
 
-	/* No zalloc, must clear what we need by hand */
-	rq->file_priv = NULL;
+	/* No zalloc, everything must be cleared after use */
 	rq->batch = NULL;
-	rq->capture_list = NULL;
-	rq->flags = 0;
-
-	INIT_LIST_HEAD(&rq->execute_cb);
+	GEM_BUG_ON(rq->file_priv);
+	GEM_BUG_ON(rq->capture_list);
+	GEM_BUG_ON(!list_empty(&rq->execute_cb));
 
 	/*
 	 * Reserve space in the ring buffer for all the commands required to
@@ -755,34 +760,37 @@ err_unlock:
 static int
 i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 {
-	struct intel_timeline *tl;
 	struct dma_fence *fence;
 	int err;
 
 	GEM_BUG_ON(i915_request_timeline(rq) ==
 		   rcu_access_pointer(signal->timeline));
 
+	fence = NULL;
 	rcu_read_lock();
-	tl = rcu_dereference(signal->timeline);
-	if (i915_request_started(signal) || !kref_get_unless_zero(&tl->kref))
-		tl = NULL;
-	rcu_read_unlock();
-	if (!tl) /* already started or maybe even completed */
-		return 0;
+	spin_lock_irq(&signal->lock);
+	if (!i915_request_started(signal) &&
+	    !list_is_first(&signal->link,
+			   &rcu_dereference(signal->timeline)->requests)) {
+		struct i915_request *prev = list_prev_entry(signal, link);
 
-	fence = ERR_PTR(-EBUSY);
-	if (mutex_trylock(&tl->mutex)) {
-		fence = NULL;
-		if (!i915_request_started(signal) &&
-		    !list_is_first(&signal->link, &tl->requests)) {
-			signal = list_prev_entry(signal, link);
-			fence = dma_fence_get(&signal->fence);
+		/*
+		 * Peek at the request before us in the timeline. That
+		 * request will only be valid before it is retired, so
+		 * after acquiring a reference to it, confirm that it is
+		 * still part of the signaler's timeline.
+		 */
+		if (i915_request_get_rcu(prev)) {
+			if (list_next_entry(prev, link) == signal)
+				fence = &prev->fence;
+			else
+				i915_request_put(prev);
 		}
-		mutex_unlock(&tl->mutex);
 	}
-	intel_timeline_put(tl);
-	if (IS_ERR_OR_NULL(fence))
-		return PTR_ERR_OR_ZERO(fence);
+	spin_unlock_irq(&signal->lock);
+	rcu_read_unlock();
+	if (!fence)
+		return 0;
 
 	err = 0;
 	if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
@@ -908,18 +916,16 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 			return ret;
 	}
 
-	if (to->engine == from->engine) {
+	if (to->engine == from->engine)
 		ret = i915_sw_fence_await_sw_fence_gfp(&to->submit,
 						       &from->submit,
 						       I915_FENCE_GFP);
-	} else if (intel_engine_has_semaphores(to->engine) &&
-		   to->gem_context->sched.priority >= I915_PRIORITY_NORMAL) {
+	else if (intel_context_use_semaphores(to->context))
 		ret = emit_semaphore_wait(to, from, I915_FENCE_GFP);
-	} else {
+	else
 		ret = i915_sw_fence_await_dma_fence(&to->submit,
 						    &from->fence, 0,
 						    I915_FENCE_GFP);
-	}
 	if (ret < 0)
 		return ret;
 
@@ -959,8 +965,10 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 	do {
 		fence = *child++;
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			i915_sw_fence_set_error_once(&rq->submit, fence->error);
 			continue;
+		}
 
 		/*
 		 * Requests on the same timeline are explicitly ordered, along
@@ -1067,8 +1075,10 @@ i915_request_await_execution(struct i915_request *rq,
 
 	do {
 		fence = *child++;
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			i915_sw_fence_set_error_once(&rq->submit, fence->error);
 			continue;
+		}
 
 		/*
 		 * We don't squash repeated fence dependencies here as we
@@ -1244,8 +1254,7 @@ struct i915_request *__i915_request_commit(struct i915_request *rq)
 	struct intel_ring *ring = rq->ring;
 	u32 *cs;
 
-	GEM_TRACE("%s fence %llx:%lld\n",
-		  engine->name, rq->fence.context, rq->fence.seqno);
+	RQ_TRACE(rq, "\n");
 
 	/*
 	 * To ensure that this call will not fail, space for its emissions
@@ -1291,8 +1300,8 @@ void __i915_request_queue(struct i915_request *rq,
 
 void i915_request_add(struct i915_request *rq)
 {
-	struct i915_sched_attr attr = rq->gem_context->sched;
 	struct intel_timeline * const tl = i915_request_timeline(rq);
+	struct i915_sched_attr attr = {};
 	struct i915_request *prev;
 
 	lockdep_assert_held(&tl->mutex);
@@ -1302,6 +1311,9 @@ void i915_request_add(struct i915_request *rq)
 
 	prev = __i915_request_commit(rq);
 
+	if (rcu_access_pointer(rq->context->gem_context))
+		attr = i915_request_gem_context(rq)->sched;
+
 	/*
 	 * Boost actual workloads past semaphores!
 	 *
@@ -1597,10 +1609,14 @@ static struct i915_global_request global = { {
 
 int __init i915_global_request_init(void)
 {
-	global.slab_requests = KMEM_CACHE(i915_request,
-					  SLAB_HWCACHE_ALIGN |
-					  SLAB_RECLAIM_ACCOUNT |
-					  SLAB_TYPESAFE_BY_RCU);
+	global.slab_requests =
+		kmem_cache_create("i915_request",
+				  sizeof(struct i915_request),
+				  __alignof__(struct i915_request),
+				  SLAB_HWCACHE_ALIGN |
+				  SLAB_RECLAIM_ACCOUNT |
+				  SLAB_TYPESAFE_BY_RCU,
+				  __i915_request_ctor);
 	if (!global.slab_requests)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 96991d64759c..031433691a06 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -28,8 +28,10 @@
 #include <linux/dma-fence.h>
 #include <linux/lockdep.h>
 
+#include "gem/i915_gem_context_types.h"
 #include "gt/intel_context_types.h"
 #include "gt/intel_engine_types.h"
+#include "gt/intel_timeline_types.h"
 
 #include "i915_gem.h"
 #include "i915_scheduler.h"
@@ -41,14 +43,19 @@
 struct drm_file;
 struct drm_i915_gem_object;
 struct i915_request;
-struct intel_timeline;
-struct intel_timeline_cacheline;
 
 struct i915_capture_list {
 	struct i915_capture_list *next;
 	struct i915_vma *vma;
 };
 
+#define RQ_TRACE(rq, fmt, ...) do {					\
+	const struct i915_request *rq__ = (rq);				\
+	ENGINE_TRACE(rq__->engine, "fence %llx:%lld, current %d " fmt,	\
+		     rq__->fence.context, rq__->fence.seqno,		\
+		     hwsp_seqno(rq__), ##__VA_ARGS__);			\
+} while (0)
+
 enum {
 	/*
 	 * I915_FENCE_FLAG_ACTIVE - this request is currently submitted to HW.
@@ -70,6 +77,38 @@ enum {
 	 * a request is on the various signal_list.
 	 */
 	I915_FENCE_FLAG_SIGNAL,
+
+	/*
+	 * I915_FENCE_FLAG_NOPREEMPT - this request should not be preempted
+	 *
+	 * The execution of some requests should not be interrupted. This is
+	 * a sensitive operation as it makes the request super important,
+	 * blocking other higher priority work. Abuse of this flag will
+	 * lead to quality of service issues.
+	 */
+	I915_FENCE_FLAG_NOPREEMPT,
+
+	/*
+	 * I915_FENCE_FLAG_SENTINEL - this request should be last in the queue
+	 *
+	 * A high priority sentinel request may be submitted to clear the
+	 * submission queue. As it will be the only request in-flight, upon
+	 * execution all other active requests will have been preempted and
+	 * unsubmitted. This preemptive pulse is used to re-evaluate the
+	 * in-flight requests, particularly in cases where an active context
+	 * is banned and those active requests need to be cancelled.
+	 */
+	I915_FENCE_FLAG_SENTINEL,
+
+	/*
+	 * I915_FENCE_FLAG_BOOST - upclock the gpu for this request
+	 *
+	 * Some requests are more important than others! In particular, a
+	 * request that the user is waiting on is typically required for
+	 * interactive latency, for which we want to minimise by upclocking
+	 * the GPU. Here we track such boost requests on a per-request basis.
+	 */
+	I915_FENCE_FLAG_BOOST,
 };
 
 /**
@@ -109,9 +148,8 @@ struct i915_request {
 	 * i915_request_free() will then decrement the refcount on the
 	 * context.
 	 */
-	struct i915_gem_context *gem_context;
 	struct intel_engine_cs *engine;
-	struct intel_context *hw_context;
+	struct intel_context *context;
 	struct intel_ring *ring;
 	struct intel_timeline __rcu *timeline;
 	struct list_head signal_link;
@@ -144,6 +182,10 @@ struct i915_request {
 	union {
 		wait_queue_entry_t submitq;
 		struct i915_sw_dma_fence_cb dmaq;
+		struct i915_request_duration_cb {
+			struct dma_fence_cb cb;
+			ktime_t emitted;
+		} duration;
 	};
 	struct list_head execute_cb;
 	struct i915_sw_fence semaphore;
@@ -176,7 +218,7 @@ struct i915_request {
 	 * inside the timeline's HWSP vma, but it is only valid while this
 	 * request has not completed and guarded by the timeline mutex.
 	 */
-	struct intel_timeline_cacheline *hwsp_cacheline;
+	struct intel_timeline_cacheline __rcu *hwsp_cacheline;
 
 	/** Position in the ring of the start of the request */
 	u32 head;
@@ -215,11 +257,6 @@ struct i915_request {
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;
 
-	unsigned long flags;
-#define I915_REQUEST_WAITBOOST	BIT(0)
-#define I915_REQUEST_NOPREEMPT	BIT(1)
-#define I915_REQUEST_SENTINEL	BIT(2)
-
 	/** timeline->request entry for this request */
 	struct list_head link;
 
@@ -432,18 +469,18 @@ static inline void i915_request_mark_complete(struct i915_request *rq)
 
 static inline bool i915_request_has_waitboost(const struct i915_request *rq)
 {
-	return rq->flags & I915_REQUEST_WAITBOOST;
+	return test_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags);
 }
 
 static inline bool i915_request_has_nopreempt(const struct i915_request *rq)
 {
 	/* Preemption should only be disabled very rarely */
-	return unlikely(rq->flags & I915_REQUEST_NOPREEMPT);
+	return unlikely(test_bit(I915_FENCE_FLAG_NOPREEMPT, &rq->fence.flags));
 }
 
 static inline bool i915_request_has_sentinel(const struct i915_request *rq)
 {
-	return unlikely(rq->flags & I915_REQUEST_SENTINEL);
+	return unlikely(test_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags));
 }
 
 static inline struct intel_timeline *
@@ -454,6 +491,13 @@ i915_request_timeline(struct i915_request *rq)
 					 lockdep_is_held(&rcu_access_pointer(rq->timeline)->mutex));
 }
 
+static inline struct i915_gem_context *
+i915_request_gem_context(struct i915_request *rq)
+{
+	/* Valid only while the request is being constructed (or retired). */
+	return rcu_dereference_protected(rq->context->gem_context, true);
+}
+
 static inline struct intel_timeline *
 i915_request_active_timeline(struct i915_request *rq)
 {
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 247a9671bca5..bf87c70bfdd9 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -213,7 +213,7 @@ static void kick_submission(struct intel_engine_cs *engine,
 	 * If we are already the currently executing context, don't
 	 * bother evaluating if we should preempt ourselves.
 	 */
-	if (inflight->hw_context == rq->hw_context)
+	if (inflight->context == rq->context)
 		goto unlock;
 
 	engine->execlists.queue_priority_hint = prio;
@@ -387,9 +387,19 @@ void i915_sched_node_init(struct i915_sched_node *node)
 	INIT_LIST_HEAD(&node->signalers_list);
 	INIT_LIST_HEAD(&node->waiters_list);
 	INIT_LIST_HEAD(&node->link);
+
+	i915_sched_node_reinit(node);
+}
+
+void i915_sched_node_reinit(struct i915_sched_node *node)
+{
 	node->attr.priority = I915_PRIORITY_INVALID;
 	node->semaphores = 0;
 	node->flags = 0;
+
+	GEM_BUG_ON(!list_empty(&node->signalers_list));
+	GEM_BUG_ON(!list_empty(&node->waiters_list));
+	GEM_BUG_ON(!list_empty(&node->link));
 }
 
 static struct i915_dependency *
@@ -480,6 +490,7 @@ void i915_sched_node_fini(struct i915_sched_node *node)
 		if (dep->flags & I915_DEPENDENCY_ALLOC)
 			i915_dependency_free(dep);
 	}
+	INIT_LIST_HEAD(&node->signalers_list);
 
 	/* Remove ourselves from everyone who depends upon us */
 	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
@@ -490,6 +501,7 @@ void i915_sched_node_fini(struct i915_sched_node *node)
 		if (dep->flags & I915_DEPENDENCY_ALLOC)
 			i915_dependency_free(dep);
 	}
+	INIT_LIST_HEAD(&node->waiters_list);
 
 	spin_unlock_irq(&schedule_lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 07d243acf553..d1dc4efef77b 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -26,6 +26,7 @@
 					 sched.link)
 
 void i915_sched_node_init(struct i915_sched_node *node);
+void i915_sched_node_reinit(struct i915_sched_node *node);
 
 bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 				      struct i915_sched_node *signal,
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index 4d88205de51b..98bcb6fa0ab4 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -36,6 +36,7 @@ struct i915_selftest {
 	char *filter;
 	int mock;
 	int live;
+	int perf;
 };
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
@@ -45,6 +46,7 @@ extern struct i915_selftest i915_selftest;
 
 int i915_mock_selftests(void);
 int i915_live_selftests(struct pci_dev *pdev);
+int i915_perf_selftests(struct pci_dev *pdev);
 
 /* We extract the function declarations from i915_mock_selftests.h and
  * i915_live_selftests.h Add your unit test declarations there!
@@ -61,6 +63,7 @@ int i915_live_selftests(struct pci_dev *pdev);
 #undef selftest
 #define selftest(name, func) int func(struct drm_i915_private *i915);
 #include "selftests/i915_live_selftests.h"
+#include "selftests/i915_perf_selftests.h"
 #undef selftest
 
 struct i915_subtest {
@@ -109,6 +112,7 @@ int __i915_subtests(const char *caller,
 
 static inline int i915_mock_selftests(void) { return 0; }
 static inline int i915_live_selftests(struct pci_dev *pdev) { return 0; }
+static inline int i915_perf_selftests(struct pci_dev *pdev) { return 0; }
 
 #define I915_SELFTEST_DECLARE(x)
 #define I915_SELFTEST_ONLY(x) 0
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 6a88db291252..51ba97daf2a0 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -12,6 +12,12 @@
 #include "i915_sw_fence.h"
 #include "i915_selftest.h"
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
+#define I915_SW_FENCE_BUG_ON(expr) BUG_ON(expr)
+#else
+#define I915_SW_FENCE_BUG_ON(expr) BUILD_BUG_ON_INVALID(expr)
+#endif
+
 #define I915_SW_FENCE_FLAG_ALLOC BIT(3) /* after WQ_FLAG_* for safety */
 
 static DEFINE_SPINLOCK(i915_sw_fence_lock);
@@ -218,13 +224,21 @@ void __i915_sw_fence_init(struct i915_sw_fence *fence,
 {
 	BUG_ON(!fn || (unsigned long)fn & ~I915_SW_FENCE_MASK);
 
+	__init_waitqueue_head(&fence->wait, name, key);
+	fence->flags = (unsigned long)fn;
+
+	i915_sw_fence_reinit(fence);
+}
+
+void i915_sw_fence_reinit(struct i915_sw_fence *fence)
+{
 	debug_fence_init(fence);
 
-	__init_waitqueue_head(&fence->wait, name, key);
 	atomic_set(&fence->pending, 1);
 	fence->error = 0;
 
-	fence->flags = (unsigned long)fn;
+	I915_SW_FENCE_BUG_ON(!fence->flags);
+	I915_SW_FENCE_BUG_ON(!list_empty(&fence->wait.head));
 }
 
 void i915_sw_fence_commit(struct i915_sw_fence *fence)
@@ -414,8 +428,10 @@ static void dma_i915_sw_fence_wake_timer(struct dma_fence *dma,
 	struct i915_sw_fence *fence;
 
 	fence = xchg(&cb->base.fence, NULL);
-	if (fence)
+	if (fence) {
+		i915_sw_fence_set_error_once(fence, dma->error);
 		i915_sw_fence_complete(fence);
+	}
 
 	irq_work_queue(&cb->work);
 }
@@ -443,8 +459,10 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 	debug_fence_assert(fence);
 	might_sleep_if(gfpflags_allow_blocking(gfp));
 
-	if (dma_fence_is_signaled(dma))
+	if (dma_fence_is_signaled(dma)) {
+		i915_sw_fence_set_error_once(fence, dma->error);
 		return 0;
+	}
 
 	cb = kmalloc(timeout ?
 		     sizeof(struct i915_sw_dma_fence_cb_timer) :
@@ -454,7 +472,12 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 		if (!gfpflags_allow_blocking(gfp))
 			return -ENOMEM;
 
-		return dma_fence_wait(dma, false);
+		ret = dma_fence_wait(dma, false);
+		if (ret)
+			return ret;
+
+		i915_sw_fence_set_error_once(fence, dma->error);
+		return 0;
 	}
 
 	cb->fence = fence;
@@ -504,8 +527,10 @@ int __i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 
 	debug_fence_assert(fence);
 
-	if (dma_fence_is_signaled(dma))
+	if (dma_fence_is_signaled(dma)) {
+		i915_sw_fence_set_error_once(fence, dma->error);
 		return 0;
+	}
 
 	cb->fence = fence;
 	i915_sw_fence_await(fence);
@@ -539,8 +564,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence,
 		struct dma_fence **shared;
 		unsigned int count, i;
 
-		ret = dma_resv_get_fences_rcu(resv,
-							&excl, &count, &shared);
+		ret = dma_resv_get_fences_rcu(resv, &excl, &count, &shared);
 		if (ret)
 			return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h
index ab7d58bd0b9d..19e806ce43bc 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.h
+++ b/drivers/gpu/drm/i915/i915_sw_fence.h
@@ -54,6 +54,8 @@ do {								\
 	__i915_sw_fence_init((fence), (fn), NULL, NULL)
 #endif
 
+void i915_sw_fence_reinit(struct i915_sw_fence *fence);
+
 #ifdef CONFIG_DRM_I915_SW_FENCE_DEBUG_OBJECTS
 void i915_sw_fence_fini(struct i915_sw_fence *fence);
 #else
@@ -110,7 +112,8 @@ static inline void i915_sw_fence_wait(struct i915_sw_fence *fence)
 static inline void
 i915_sw_fence_set_error_once(struct i915_sw_fence *fence, int error)
 {
-	cmpxchg(&fence->error, 0, error);
+	if (unlikely(error))
+		cmpxchg(&fence->error, 0, error);
 }
 
 #endif /* _I915_SW_FENCE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.c b/drivers/gpu/drm/i915/i915_sw_fence_work.c
index 8538ee7a521d..997b2998f1f2 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence_work.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence_work.c
@@ -6,6 +6,13 @@
 
 #include "i915_sw_fence_work.h"
 
+static void fence_complete(struct dma_fence_work *f)
+{
+	if (f->ops->release)
+		f->ops->release(f);
+	dma_fence_signal(&f->dma);
+}
+
 static void fence_work(struct work_struct *work)
 {
 	struct dma_fence_work *f = container_of(work, typeof(*f), work);
@@ -14,7 +21,8 @@ static void fence_work(struct work_struct *work)
 	err = f->ops->work(f);
 	if (err)
 		dma_fence_set_error(&f->dma, err);
-	dma_fence_signal(&f->dma);
+
+	fence_complete(f);
 	dma_fence_put(&f->dma);
 }
 
@@ -32,7 +40,7 @@ fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 			dma_fence_get(&f->dma);
 			queue_work(system_unbound_wq, &f->work);
 		} else {
-			dma_fence_signal(&f->dma);
+			fence_complete(f);
 		}
 		break;
 
@@ -60,9 +68,6 @@ static void fence_release(struct dma_fence *fence)
 {
 	struct dma_fence_work *f = container_of(fence, typeof(*f), dma);
 
-	if (f->ops->release)
-		f->ops->release(f);
-
 	i915_sw_fence_fini(&f->chain);
 
 	BUILD_BUG_ON(offsetof(typeof(*f), dma));
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 65476909d1bf..0cef3130db05 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -259,33 +259,18 @@ static const struct bin_attribute dpf_attrs_1 = {
 static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 				    struct device_attribute *attr, char *buf)
 {
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
-	intel_wakeref_t wakeref;
-	u32 freq;
-
-	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		vlv_punit_get(dev_priv);
-		freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-		vlv_punit_put(dev_priv);
-
-		freq = (freq >> 8) & 0xff;
-	} else {
-		freq = intel_get_cagf(rps, I915_READ(GEN6_RPSTAT1));
-	}
-
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &i915->gt.rps;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", intel_gpu_freq(rps, freq));
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			intel_rps_read_actual_frequency(rps));
 }
 
 static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 				    struct device_attribute *attr, char *buf)
 {
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &i915->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
 			intel_gpu_freq(rps, rps->cur_freq));
@@ -293,8 +278,8 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 
 static ssize_t gt_boost_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &i915->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
 			intel_gpu_freq(rps, rps->boost_freq));
@@ -513,15 +498,15 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 
 	struct device *kdev = kobj_to_dev(kobj);
 	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
-	struct i915_gpu_state *gpu;
+	struct i915_gpu_coredump *gpu;
 	ssize_t ret;
 
 	gpu = i915_first_error_state(i915);
 	if (IS_ERR(gpu)) {
 		ret = PTR_ERR(gpu);
 	} else if (gpu) {
-		ret = i915_gpu_state_copy_to_buffer(gpu, buf, off, count);
-		i915_gpu_state_put(gpu);
+		ret = i915_gpu_coredump_copy_to_buffer(gpu, buf, off, count);
+		i915_gpu_coredump_put(gpu);
 	} else {
 		const char *str = "No error state collected\n";
 		size_t len = strlen(str);
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 7ef7a1e1664c..233a97a2c276 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -341,7 +341,7 @@ TRACE_EVENT(intel_disable_plane,
 
 /* pipe updates */
 
-TRACE_EVENT(i915_pipe_update_start,
+TRACE_EVENT(intel_pipe_update_start,
 	    TP_PROTO(struct intel_crtc *crtc),
 	    TP_ARGS(crtc),
 
@@ -366,7 +366,7 @@ TRACE_EVENT(i915_pipe_update_start,
 		       __entry->scanline, __entry->min, __entry->max)
 );
 
-TRACE_EVENT(i915_pipe_update_vblank_evaded,
+TRACE_EVENT(intel_pipe_update_vblank_evaded,
 	    TP_PROTO(struct intel_crtc *crtc),
 	    TP_ARGS(crtc),
 
@@ -391,7 +391,7 @@ TRACE_EVENT(i915_pipe_update_vblank_evaded,
 		       __entry->scanline, __entry->min, __entry->max)
 );
 
-TRACE_EVENT(i915_pipe_update_end,
+TRACE_EVENT(intel_pipe_update_end,
 	    TP_PROTO(struct intel_crtc *crtc, u32 frame, int scanline_end),
 	    TP_ARGS(crtc, frame, scanline_end),
 
diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c
index 0348c6d0ef5f..c47261ae86ea 100644
--- a/drivers/gpu/drm/i915/i915_utils.c
+++ b/drivers/gpu/drm/i915/i915_utils.c
@@ -23,7 +23,7 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 	struct va_format vaf;
 	va_list args;
 
-	if (is_debug && !(drm_debug & DRM_UT_DRIVER))
+	if (is_debug && !drm_debug_enabled(DRM_UT_DRIVER))
 		return;
 
 	va_start(args, fmt);
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 04139ba1191e..b0ade76bec90 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -69,7 +69,7 @@ bool i915_error_injected(void);
 
 #else
 
-#define i915_inject_probe_error(_i915, _err) 0
+#define i915_inject_probe_error(i915, e) ({ BUILD_BUG_ON_INVALID(i915); 0; })
 #define i915_error_injected() false
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 01c822256b39..17d7c525ea5c 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -28,7 +28,9 @@
 #include "display/intel_frontbuffer.h"
 
 #include "gt/intel_engine.h"
+#include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
 #include "i915_globals.h"
@@ -112,6 +114,7 @@ vma_create(struct drm_i915_gem_object *obj,
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	kref_init(&vma->ref);
 	mutex_init(&vma->pages_mutex);
 	vma->vm = i915_vm_get(vm);
 	vma->ops = &vm->vma_ops;
@@ -290,6 +293,7 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 struct i915_vma_work {
 	struct dma_fence_work base;
 	struct i915_vma *vma;
+	struct drm_i915_gem_object *pinned;
 	enum i915_cache_level cache_level;
 	unsigned int flags;
 };
@@ -304,15 +308,21 @@ static int __vma_bind(struct dma_fence_work *work)
 	if (err)
 		atomic_or(I915_VMA_ERROR, &vma->flags);
 
-	if (vma->obj)
-		__i915_gem_object_unpin_pages(vma->obj);
-
 	return err;
 }
 
+static void __vma_release(struct dma_fence_work *work)
+{
+	struct i915_vma_work *vw = container_of(work, typeof(*vw), base);
+
+	if (vw->pinned)
+		__i915_gem_object_unpin_pages(vw->pinned);
+}
+
 static const struct dma_fence_work_ops bind_ops = {
 	.name = "bind",
 	.work = __vma_bind,
+	.release = __vma_release,
 };
 
 struct i915_vma_work *i915_vma_work(void)
@@ -393,8 +403,10 @@ int i915_vma_bind(struct i915_vma *vma,
 		i915_active_set_exclusive(&vma->active, &work->base.dma);
 		work->base.dma.error = 0; /* enable the queue_work() */
 
-		if (vma->obj)
+		if (vma->obj) {
 			__i915_gem_object_pin_pages(vma->obj);
+			work->pinned = vma->obj;
+		}
 	} else {
 		GEM_BUG_ON((bind_flags & ~vma_flags) & vma->vm->bind_async_flags);
 		ret = vma->ops->bind_vma(vma, cache_level, bind_flags);
@@ -411,8 +423,6 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	void __iomem *ptr;
 	int err;
 
-	/* Access through the GTT requires the device to be awake. */
-	assert_rpm_wakelock_held(vma->vm->gt->uncore->rpm);
 	if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
 		err = -ENODEV;
 		goto err;
@@ -444,6 +454,8 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 		goto err_unpin;
 
 	i915_vma_set_ggtt_write(vma);
+
+	/* NB Access through the GTT requires the device to be awake. */
 	return ptr;
 
 err_unpin:
@@ -846,6 +858,7 @@ static void vma_unbind_pages(struct i915_vma *vma)
 int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 {
 	struct i915_vma_work *work = NULL;
+	intel_wakeref_t wakeref = 0;
 	unsigned int bound;
 	int err;
 
@@ -871,6 +884,9 @@ int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		}
 	}
 
+	if (flags & PIN_GLOBAL)
+		wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
+
 	/* No more allocations allowed once we hold vm->mutex */
 	err = mutex_lock_interruptible(&vma->vm->mutex);
 	if (err)
@@ -934,11 +950,45 @@ err_unlock:
 err_fence:
 	if (work)
 		dma_fence_work_commit(&work->base);
+	if (wakeref)
+		intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
 err_pages:
 	vma_put_pages(vma);
 	return err;
 }
 
+static void flush_idle_contexts(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id)
+		intel_engine_flush_barriers(engine);
+
+	intel_gt_wait_for_idle(gt, MAX_SCHEDULE_TIMEOUT);
+}
+
+int i915_ggtt_pin(struct i915_vma *vma, u32 align, unsigned int flags)
+{
+	struct i915_address_space *vm = vma->vm;
+	int err;
+
+	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
+
+	do {
+		err = i915_vma_pin(vma, 0, align, flags | PIN_GLOBAL);
+		if (err != -ENOSPC)
+			return err;
+
+		/* Unlike i915_vma_pin, we don't take no for an answer! */
+		flush_idle_contexts(vm->gt);
+		if (mutex_lock_interruptible(&vm->mutex) == 0) {
+			i915_gem_evict_vm(vm);
+			mutex_unlock(&vm->mutex);
+		}
+	} while (1);
+}
+
 void i915_vma_close(struct i915_vma *vma)
 {
 	struct intel_gt *gt = vma->vm->gt;
@@ -978,8 +1028,10 @@ void i915_vma_reopen(struct i915_vma *vma)
 		__i915_vma_remove_closed(vma);
 }
 
-void i915_vma_destroy(struct i915_vma *vma)
+void i915_vma_release(struct kref *ref)
 {
+	struct i915_vma *vma = container_of(ref, typeof(*vma), ref);
+
 	if (drm_mm_node_allocated(&vma->node)) {
 		mutex_lock(&vma->vm->mutex);
 		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
@@ -1019,7 +1071,9 @@ void i915_vma_parked(struct intel_gt *gt)
 		if (!kref_get_unless_zero(&obj->base.refcount))
 			continue;
 
-		if (!i915_vm_tryopen(vm)) {
+		if (i915_vm_tryopen(vm)) {
+			list_del_init(&vma->closed_link);
+		} else {
 			i915_gem_object_put(obj);
 			obj = NULL;
 		}
@@ -1027,7 +1081,7 @@ void i915_vma_parked(struct intel_gt *gt)
 		spin_unlock_irq(&gt->closed_lock);
 
 		if (obj) {
-			i915_vma_destroy(vma);
+			__i915_vma_put(vma);
 			i915_gem_object_put(obj);
 		}
 
@@ -1054,17 +1108,16 @@ static void __i915_vma_iounmap(struct i915_vma *vma)
 
 void i915_vma_revoke_mmap(struct i915_vma *vma)
 {
-	struct drm_vma_offset_node *node = &vma->obj->base.vma_node;
+	struct drm_vma_offset_node *node;
 	u64 vma_offset;
 
-	lockdep_assert_held(&vma->vm->mutex);
-
 	if (!i915_vma_has_userfault(vma))
 		return;
 
 	GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma));
 	GEM_BUG_ON(!vma->obj->userfault_count);
 
+	node = &vma->mmo->vma_node;
 	vma_offset = vma->ggtt_view.partial.offset << PAGE_SHIFT;
 	unmap_mapping_range(vma->vm->i915->drm.anon_inode->i_mapping,
 			    drm_vma_node_offset_addr(node) + vma_offset,
@@ -1152,7 +1205,7 @@ int __i915_vma_unbind(struct i915_vma *vma)
 	GEM_BUG_ON(i915_vma_is_active(vma));
 	if (i915_vma_is_pinned(vma)) {
 		vma_print_allocator(vma, "is pinned");
-		return -EBUSY;
+		return -EAGAIN;
 	}
 
 	GEM_BUG_ON(i915_vma_is_active(vma));
@@ -1192,15 +1245,23 @@ int __i915_vma_unbind(struct i915_vma *vma)
 	i915_vma_detach(vma);
 	vma_unbind_pages(vma);
 
-	drm_mm_remove_node(&vma->node); /* pairs with i915_vma_destroy() */
+	drm_mm_remove_node(&vma->node); /* pairs with i915_vma_release() */
 	return 0;
 }
 
 int i915_vma_unbind(struct i915_vma *vma)
 {
 	struct i915_address_space *vm = vma->vm;
+	intel_wakeref_t wakeref = 0;
 	int err;
 
+	if (!drm_mm_node_allocated(&vma->node))
+		return 0;
+
+	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
+		/* XXX not always required: nop_clear_range */
+		wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
+
 	err = mutex_lock_interruptible(&vm->mutex);
 	if (err)
 		return err;
@@ -1208,6 +1269,9 @@ int i915_vma_unbind(struct i915_vma *vma)
 	err = __i915_vma_unbind(vma);
 	mutex_unlock(&vm->mutex);
 
+	if (wakeref)
+		intel_runtime_pm_put(&vm->i915->runtime_pm, wakeref);
+
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 465932813bc5..02b31a62951e 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -30,139 +30,14 @@
 
 #include <drm/drm_mm.h>
 
+#include "gem/i915_gem_object.h"
+
 #include "i915_gem_gtt.h"
 #include "i915_gem_fence_reg.h"
-#include "gem/i915_gem_object.h"
 
 #include "i915_active.h"
 #include "i915_request.h"
-
-enum i915_cache_level;
-
-/**
- * DOC: Virtual Memory Address
- *
- * A VMA represents a GEM BO that is bound into an address space. Therefore, a
- * VMA's presence cannot be guaranteed before binding, or after unbinding the
- * object into/from the address space.
- *
- * To make things as simple as possible (ie. no refcounting), a VMA's lifetime
- * will always be <= an objects lifetime. So object refcounting should cover us.
- */
-struct i915_vma {
-	struct drm_mm_node node;
-	struct drm_i915_gem_object *obj;
-	struct i915_address_space *vm;
-	const struct i915_vma_ops *ops;
-	struct i915_fence_reg *fence;
-	struct dma_resv *resv; /** Alias of obj->resv */
-	struct sg_table *pages;
-	void __iomem *iomap;
-	void *private; /* owned by creator */
-	u64 size;
-	u64 display_alignment;
-	struct i915_page_sizes page_sizes;
-
-	u32 fence_size;
-	u32 fence_alignment;
-
-	/**
-	 * Count of the number of times this vma has been opened by different
-	 * handles (but same file) for execbuf, i.e. the number of aliases
-	 * that exist in the ctx->handle_vmas LUT for this vma.
-	 */
-	atomic_t open_count;
-	atomic_t flags;
-	/**
-	 * How many users have pinned this object in GTT space.
-	 *
-	 * This is a tightly bound, fairly small number of users, so we
-	 * stuff inside the flags field so that we can both check for overflow
-	 * and detect a no-op i915_vma_pin() in a single check, while also
-	 * pinning the vma.
-	 *
-	 * The worst case display setup would have the same vma pinned for
-	 * use on each plane on each crtc, while also building the next atomic
-	 * state and holding a pin for the length of the cleanup queue. In the
-	 * future, the flip queue may be increased from 1.
-	 * Estimated worst case: 3 [qlen] * 4 [max crtcs] * 7 [max planes] = 84
-	 *
-	 * For GEM, the number of concurrent users for pwrite/pread is
-	 * unbounded. For execbuffer, it is currently one but will in future
-	 * be extended to allow multiple clients to pin vma concurrently.
-	 *
-	 * We also use suballocated pages, with each suballocation claiming
-	 * its own pin on the shared vma. At present, this is limited to
-	 * exclusive cachelines of a single page, so a maximum of 64 possible
-	 * users.
-	 */
-#define I915_VMA_PIN_MASK 0x3ff
-#define I915_VMA_OVERFLOW 0x200
-
-	/** Flags and address space this VMA is bound to */
-#define I915_VMA_GLOBAL_BIND_BIT 10
-#define I915_VMA_LOCAL_BIND_BIT  11
-
-#define I915_VMA_GLOBAL_BIND	((int)BIT(I915_VMA_GLOBAL_BIND_BIT))
-#define I915_VMA_LOCAL_BIND	((int)BIT(I915_VMA_LOCAL_BIND_BIT))
-
-#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND)
-
-#define I915_VMA_ALLOC_BIT	12
-#define I915_VMA_ALLOC		((int)BIT(I915_VMA_ALLOC_BIT))
-
-#define I915_VMA_ERROR_BIT	13
-#define I915_VMA_ERROR		((int)BIT(I915_VMA_ERROR_BIT))
-
-#define I915_VMA_GGTT_BIT	14
-#define I915_VMA_CAN_FENCE_BIT	15
-#define I915_VMA_USERFAULT_BIT	16
-#define I915_VMA_GGTT_WRITE_BIT	17
-
-#define I915_VMA_GGTT		((int)BIT(I915_VMA_GGTT_BIT))
-#define I915_VMA_CAN_FENCE	((int)BIT(I915_VMA_CAN_FENCE_BIT))
-#define I915_VMA_USERFAULT	((int)BIT(I915_VMA_USERFAULT_BIT))
-#define I915_VMA_GGTT_WRITE	((int)BIT(I915_VMA_GGTT_WRITE_BIT))
-
-	struct i915_active active;
-
-#define I915_VMA_PAGES_BIAS 24
-#define I915_VMA_PAGES_ACTIVE (BIT(24) | 1)
-	atomic_t pages_count; /* number of active binds to the pages */
-	struct mutex pages_mutex; /* protect acquire/release of backing pages */
-
-	/**
-	 * Support different GGTT views into the same object.
-	 * This means there can be multiple VMA mappings per object and per VM.
-	 * i915_ggtt_view_type is used to distinguish between those entries.
-	 * The default one of zero (I915_GGTT_VIEW_NORMAL) is default and also
-	 * assumed in GEM functions which take no ggtt view parameter.
-	 */
-	struct i915_ggtt_view ggtt_view;
-
-	/** This object's place on the active/inactive lists */
-	struct list_head vm_link;
-
-	struct list_head obj_link; /* Link in the object's VMA list */
-	struct rb_node obj_node;
-	struct hlist_node obj_hash;
-
-	/** This vma's place in the execbuf reservation list */
-	struct list_head exec_link;
-	struct list_head reloc_link;
-
-	/** This vma's place in the eviction list */
-	struct list_head evict_link;
-
-	struct list_head closed_link;
-
-	/**
-	 * Used for performing relocations during execbuffer insertion.
-	 */
-	unsigned int *exec_flags;
-	struct hlist_node exec_node;
-	u32 exec_handle;
-};
+#include "i915_vma_types.h"
 
 struct i915_vma *
 i915_vma_instance(struct drm_i915_gem_object *obj,
@@ -333,7 +208,20 @@ int __must_check i915_vma_unbind(struct i915_vma *vma);
 void i915_vma_unlink_ctx(struct i915_vma *vma);
 void i915_vma_close(struct i915_vma *vma);
 void i915_vma_reopen(struct i915_vma *vma);
-void i915_vma_destroy(struct i915_vma *vma);
+
+static inline struct i915_vma *__i915_vma_get(struct i915_vma *vma)
+{
+	if (kref_get_unless_zero(&vma->ref))
+		return vma;
+
+	return NULL;
+}
+
+void i915_vma_release(struct kref *ref);
+static inline void __i915_vma_put(struct i915_vma *vma)
+{
+	kref_put(&vma->ref, i915_vma_release);
+}
 
 #define assert_vma_held(vma) dma_resv_assert_held((vma)->resv)
 
@@ -349,6 +237,7 @@ static inline void i915_vma_unlock(struct i915_vma *vma)
 
 int __must_check
 i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags);
+int i915_ggtt_pin(struct i915_vma *vma, u32 align, unsigned int flags);
 
 static inline int i915_vma_pin_count(const struct i915_vma *vma)
 {
diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h
new file mode 100644
index 000000000000..e0942efd5236
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_vma_types.h
@@ -0,0 +1,294 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __I915_VMA_TYPES_H__
+#define __I915_VMA_TYPES_H__
+
+#include <linux/rbtree.h>
+
+#include <drm/drm_mm.h>
+
+#include "gem/i915_gem_object_types.h"
+
+enum i915_cache_level;
+
+/**
+ * DOC: Global GTT views
+ *
+ * Background and previous state
+ *
+ * Historically objects could exists (be bound) in global GTT space only as
+ * singular instances with a view representing all of the object's backing pages
+ * in a linear fashion. This view will be called a normal view.
+ *
+ * To support multiple views of the same object, where the number of mapped
+ * pages is not equal to the backing store, or where the layout of the pages
+ * is not linear, concept of a GGTT view was added.
+ *
+ * One example of an alternative view is a stereo display driven by a single
+ * image. In this case we would have a framebuffer looking like this
+ * (2x2 pages):
+ *
+ *    12
+ *    34
+ *
+ * Above would represent a normal GGTT view as normally mapped for GPU or CPU
+ * rendering. In contrast, fed to the display engine would be an alternative
+ * view which could look something like this:
+ *
+ *   1212
+ *   3434
+ *
+ * In this example both the size and layout of pages in the alternative view is
+ * different from the normal view.
+ *
+ * Implementation and usage
+ *
+ * GGTT views are implemented using VMAs and are distinguished via enum
+ * i915_ggtt_view_type and struct i915_ggtt_view.
+ *
+ * A new flavour of core GEM functions which work with GGTT bound objects were
+ * added with the _ggtt_ infix, and sometimes with _view postfix to avoid
+ * renaming  in large amounts of code. They take the struct i915_ggtt_view
+ * parameter encapsulating all metadata required to implement a view.
+ *
+ * As a helper for callers which are only interested in the normal view,
+ * globally const i915_ggtt_view_normal singleton instance exists. All old core
+ * GEM API functions, the ones not taking the view parameter, are operating on,
+ * or with the normal GGTT view.
+ *
+ * Code wanting to add or use a new GGTT view needs to:
+ *
+ * 1. Add a new enum with a suitable name.
+ * 2. Extend the metadata in the i915_ggtt_view structure if required.
+ * 3. Add support to i915_get_vma_pages().
+ *
+ * New views are required to build a scatter-gather table from within the
+ * i915_get_vma_pages function. This table is stored in the vma.ggtt_view and
+ * exists for the lifetime of an VMA.
+ *
+ * Core API is designed to have copy semantics which means that passed in
+ * struct i915_ggtt_view does not need to be persistent (left around after
+ * calling the core API functions).
+ *
+ */
+
+struct intel_remapped_plane_info {
+	/* in gtt pages */
+	unsigned int width, height, stride, offset;
+} __packed;
+
+struct intel_remapped_info {
+	struct intel_remapped_plane_info plane[2];
+	unsigned int unused_mbz;
+} __packed;
+
+struct intel_rotation_info {
+	struct intel_remapped_plane_info plane[2];
+} __packed;
+
+struct intel_partial_info {
+	u64 offset;
+	unsigned int size;
+} __packed;
+
+enum i915_ggtt_view_type {
+	I915_GGTT_VIEW_NORMAL = 0,
+	I915_GGTT_VIEW_ROTATED = sizeof(struct intel_rotation_info),
+	I915_GGTT_VIEW_PARTIAL = sizeof(struct intel_partial_info),
+	I915_GGTT_VIEW_REMAPPED = sizeof(struct intel_remapped_info),
+};
+
+static inline void assert_i915_gem_gtt_types(void)
+{
+	BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 8*sizeof(unsigned int));
+	BUILD_BUG_ON(sizeof(struct intel_partial_info) != sizeof(u64) + sizeof(unsigned int));
+	BUILD_BUG_ON(sizeof(struct intel_remapped_info) != 9*sizeof(unsigned int));
+
+	/* Check that rotation/remapped shares offsets for simplicity */
+	BUILD_BUG_ON(offsetof(struct intel_remapped_info, plane[0]) !=
+		     offsetof(struct intel_rotation_info, plane[0]));
+	BUILD_BUG_ON(offsetofend(struct intel_remapped_info, plane[1]) !=
+		     offsetofend(struct intel_rotation_info, plane[1]));
+
+	/* As we encode the size of each branch inside the union into its type,
+	 * we have to be careful that each branch has a unique size.
+	 */
+	switch ((enum i915_ggtt_view_type)0) {
+	case I915_GGTT_VIEW_NORMAL:
+	case I915_GGTT_VIEW_PARTIAL:
+	case I915_GGTT_VIEW_ROTATED:
+	case I915_GGTT_VIEW_REMAPPED:
+		/* gcc complains if these are identical cases */
+		break;
+	}
+}
+
+struct i915_ggtt_view {
+	enum i915_ggtt_view_type type;
+	union {
+		/* Members need to contain no holes/padding */
+		struct intel_partial_info partial;
+		struct intel_rotation_info rotated;
+		struct intel_remapped_info remapped;
+	};
+};
+
+/**
+ * DOC: Virtual Memory Address
+ *
+ * A VMA represents a GEM BO that is bound into an address space. Therefore, a
+ * VMA's presence cannot be guaranteed before binding, or after unbinding the
+ * object into/from the address space.
+ *
+ * To make things as simple as possible (ie. no refcounting), a VMA's lifetime
+ * will always be <= an objects lifetime. So object refcounting should cover us.
+ */
+struct i915_vma {
+	struct drm_mm_node node;
+
+	struct i915_address_space *vm;
+	const struct i915_vma_ops *ops;
+
+	struct drm_i915_gem_object *obj;
+	struct dma_resv *resv; /** Alias of obj->resv */
+
+	struct sg_table *pages;
+	void __iomem *iomap;
+	void *private; /* owned by creator */
+
+	struct i915_fence_reg *fence;
+
+	u64 size;
+	u64 display_alignment;
+	struct i915_page_sizes page_sizes;
+
+	/* mmap-offset associated with fencing for this vma */
+	struct i915_mmap_offset	*mmo;
+
+	u32 fence_size;
+	u32 fence_alignment;
+
+	/**
+	 * Count of the number of times this vma has been opened by different
+	 * handles (but same file) for execbuf, i.e. the number of aliases
+	 * that exist in the ctx->handle_vmas LUT for this vma.
+	 */
+	struct kref ref;
+	atomic_t open_count;
+	atomic_t flags;
+	/**
+	 * How many users have pinned this object in GTT space.
+	 *
+	 * This is a tightly bound, fairly small number of users, so we
+	 * stuff inside the flags field so that we can both check for overflow
+	 * and detect a no-op i915_vma_pin() in a single check, while also
+	 * pinning the vma.
+	 *
+	 * The worst case display setup would have the same vma pinned for
+	 * use on each plane on each crtc, while also building the next atomic
+	 * state and holding a pin for the length of the cleanup queue. In the
+	 * future, the flip queue may be increased from 1.
+	 * Estimated worst case: 3 [qlen] * 4 [max crtcs] * 7 [max planes] = 84
+	 *
+	 * For GEM, the number of concurrent users for pwrite/pread is
+	 * unbounded. For execbuffer, it is currently one but will in future
+	 * be extended to allow multiple clients to pin vma concurrently.
+	 *
+	 * We also use suballocated pages, with each suballocation claiming
+	 * its own pin on the shared vma. At present, this is limited to
+	 * exclusive cachelines of a single page, so a maximum of 64 possible
+	 * users.
+	 */
+#define I915_VMA_PIN_MASK 0x3ff
+#define I915_VMA_OVERFLOW 0x200
+
+	/** Flags and address space this VMA is bound to */
+#define I915_VMA_GLOBAL_BIND_BIT 10
+#define I915_VMA_LOCAL_BIND_BIT  11
+
+#define I915_VMA_GLOBAL_BIND	((int)BIT(I915_VMA_GLOBAL_BIND_BIT))
+#define I915_VMA_LOCAL_BIND	((int)BIT(I915_VMA_LOCAL_BIND_BIT))
+
+#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND)
+
+#define I915_VMA_ALLOC_BIT	12
+#define I915_VMA_ALLOC		((int)BIT(I915_VMA_ALLOC_BIT))
+
+#define I915_VMA_ERROR_BIT	13
+#define I915_VMA_ERROR		((int)BIT(I915_VMA_ERROR_BIT))
+
+#define I915_VMA_GGTT_BIT	14
+#define I915_VMA_CAN_FENCE_BIT	15
+#define I915_VMA_USERFAULT_BIT	16
+#define I915_VMA_GGTT_WRITE_BIT	17
+
+#define I915_VMA_GGTT		((int)BIT(I915_VMA_GGTT_BIT))
+#define I915_VMA_CAN_FENCE	((int)BIT(I915_VMA_CAN_FENCE_BIT))
+#define I915_VMA_USERFAULT	((int)BIT(I915_VMA_USERFAULT_BIT))
+#define I915_VMA_GGTT_WRITE	((int)BIT(I915_VMA_GGTT_WRITE_BIT))
+
+	struct i915_active active;
+
+#define I915_VMA_PAGES_BIAS 24
+#define I915_VMA_PAGES_ACTIVE (BIT(24) | 1)
+	atomic_t pages_count; /* number of active binds to the pages */
+	struct mutex pages_mutex; /* protect acquire/release of backing pages */
+
+	/**
+	 * Support different GGTT views into the same object.
+	 * This means there can be multiple VMA mappings per object and per VM.
+	 * i915_ggtt_view_type is used to distinguish between those entries.
+	 * The default one of zero (I915_GGTT_VIEW_NORMAL) is default and also
+	 * assumed in GEM functions which take no ggtt view parameter.
+	 */
+	struct i915_ggtt_view ggtt_view;
+
+	/** This object's place on the active/inactive lists */
+	struct list_head vm_link;
+
+	struct list_head obj_link; /* Link in the object's VMA list */
+	struct rb_node obj_node;
+	struct hlist_node obj_hash;
+
+	/** This vma's place in the execbuf reservation list */
+	struct list_head exec_link;
+	struct list_head reloc_link;
+
+	/** This vma's place in the eviction list */
+	struct list_head evict_link;
+
+	struct list_head closed_link;
+
+	/**
+	 * Used for performing relocations during execbuffer insertion.
+	 */
+	unsigned int *exec_flags;
+	struct hlist_node exec_node;
+	u32 exec_handle;
+};
+
+#endif
+
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index a5b571364cf6..6670a0763be2 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -73,9 +73,30 @@ const char *intel_platform_name(enum intel_platform platform)
 	return platform_names[platform];
 }
 
-void intel_device_info_dump_flags(const struct intel_device_info *info,
-				  struct drm_printer *p)
+static const char *iommu_name(void)
 {
+	const char *msg = "n/a";
+
+#ifdef CONFIG_INTEL_IOMMU
+	msg = enableddisabled(intel_iommu_gfx_mapped);
+#endif
+
+	return msg;
+}
+
+void intel_device_info_print_static(const struct intel_device_info *info,
+				    struct drm_printer *p)
+{
+	drm_printf(p, "engines: %x\n", info->engine_mask);
+	drm_printf(p, "gen: %d\n", info->gen);
+	drm_printf(p, "gt: %d\n", info->gt);
+	drm_printf(p, "iommu: %s\n", iommu_name());
+	drm_printf(p, "memory-regions: %x\n", info->memory_regions);
+	drm_printf(p, "page-sizes: %x\n", info->page_sizes);
+	drm_printf(p, "platform: %s\n", intel_platform_name(info->platform));
+	drm_printf(p, "ppgtt-size: %d\n", info->ppgtt_size);
+	drm_printf(p, "ppgtt-type: %d\n", info->ppgtt_type);
+
 #define PRINT_FLAG(name) drm_printf(p, "%s: %s\n", #name, yesno(info->name));
 	DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG);
 #undef PRINT_FLAG
@@ -106,8 +127,8 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 	drm_printf(p, "has EU power gating: %s\n", yesno(sseu->has_eu_pg));
 }
 
-void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
-				    struct drm_printer *p)
+void intel_device_info_print_runtime(const struct intel_runtime_info *info,
+				     struct drm_printer *p)
 {
 	sseu_dump(&info->sseu, p);
 
@@ -148,8 +169,8 @@ static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
 	}
 }
 
-void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
-				     struct drm_printer *p)
+void intel_device_info_print_topology(const struct sseu_dev_info *sseu,
+				      struct drm_printer *p)
 {
 	int s, ss;
 
@@ -498,7 +519,7 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
+static void bdw_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	int s, ss;
@@ -579,7 +600,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 	sseu->has_eu_pg = 0;
 }
 
-static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
+static void hsw_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 fuse1;
@@ -808,6 +829,8 @@ static const u16 subplatform_ult_ids[] = {
 	INTEL_WHL_U_GT1_IDS(0),
 	INTEL_WHL_U_GT2_IDS(0),
 	INTEL_WHL_U_GT3_IDS(0),
+	INTEL_CML_U_GT1_IDS(0),
+	INTEL_CML_U_GT2_IDS(0),
 };
 
 static const u16 subplatform_ulx_ids[] = {
@@ -998,11 +1021,11 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 
 	/* Initialize slice/subslice/EU info */
 	if (IS_HASWELL(dev_priv))
-		haswell_sseu_info_init(dev_priv);
+		hsw_sseu_info_init(dev_priv);
 	else if (IS_CHERRYVIEW(dev_priv))
 		cherryview_sseu_info_init(dev_priv);
 	else if (IS_BROADWELL(dev_priv))
-		broadwell_sseu_info_init(dev_priv);
+		bdw_sseu_info_init(dev_priv);
 	else if (IS_GEN(dev_priv, 9))
 		gen9_sseu_info_init(dev_priv);
 	else if (IS_GEN(dev_priv, 10))
@@ -1070,7 +1093,7 @@ void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
 		 * hooked up to an SFC (Scaler & Format Converter) unit.
 		 * In TGL each VDBOX has access to an SFC.
 		 */
-		if (IS_TIGERLAKE(dev_priv) || logical_vdbox++ % 2 == 0)
+		if (INTEL_GEN(dev_priv) >= 12 || logical_vdbox++ % 2 == 0)
 			RUNTIME_INFO(dev_priv)->vdbox_sfc_access |= BIT(i);
 	}
 	DRM_DEBUG_DRIVER("vdbox enable: %04x, instances: %04lx\n",
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 4bdf8a6cfb47..2725cb7fc169 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -230,12 +230,13 @@ const char *intel_platform_name(enum intel_platform platform);
 
 void intel_device_info_subplatform_init(struct drm_i915_private *dev_priv);
 void intel_device_info_runtime_init(struct drm_i915_private *dev_priv);
-void intel_device_info_dump_flags(const struct intel_device_info *info,
-				  struct drm_printer *p);
-void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
+
+void intel_device_info_print_static(const struct intel_device_info *info,
 				    struct drm_printer *p);
-void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
+void intel_device_info_print_runtime(const struct intel_runtime_info *info,
 				     struct drm_printer *p);
+void intel_device_info_print_topology(const struct sseu_dev_info *sseu,
+				      struct drm_printer *p);
 
 void intel_device_info_init_mmio(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index baaeaecc64af..d0d038b3cd79 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -16,6 +16,20 @@ const u32 intel_region_map[] = {
 	[INTEL_REGION_STOLEN] = REGION_MAP(INTEL_MEMORY_STOLEN, 0),
 };
 
+struct intel_memory_region *
+intel_memory_region_by_type(struct drm_i915_private *i915,
+			    enum intel_memory_type mem_type)
+{
+	struct intel_memory_region *mr;
+	int id;
+
+	for_each_memory_region(mr, i915, id)
+		if (mr->type == mem_type)
+			return mr;
+
+	return NULL;
+}
+
 static u64
 intel_memory_region_free_pages(struct intel_memory_region *mem,
 			       struct list_head *blocks)
@@ -37,7 +51,7 @@ __intel_memory_region_put_pages_buddy(struct intel_memory_region *mem,
 				      struct list_head *blocks)
 {
 	mutex_lock(&mem->mm_lock);
-	intel_memory_region_free_pages(mem, blocks);
+	mem->avail += intel_memory_region_free_pages(mem, blocks);
 	mutex_unlock(&mem->mm_lock);
 }
 
@@ -73,6 +87,9 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
 		min_order = ilog2(size) - ilog2(mem->mm.chunk_size);
 	}
 
+	if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
+		return -E2BIG;
+
 	n_pages = size >> ilog2(mem->mm.chunk_size);
 
 	mutex_lock(&mem->mm_lock);
@@ -103,6 +120,7 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
 			break;
 	} while (1);
 
+	mem->avail -= size;
 	mutex_unlock(&mem->mm_lock);
 	return 0;
 
@@ -161,6 +179,8 @@ intel_memory_region_create(struct drm_i915_private *i915,
 	mem->io_start = io_start;
 	mem->min_page_size = min_page_size;
 	mem->ops = ops;
+	mem->total = size;
+	mem->avail = mem->total;
 
 	mutex_init(&mem->objects.lock);
 	INIT_LIST_HEAD(&mem->objects.list);
@@ -182,6 +202,16 @@ err_free:
 	return ERR_PTR(err);
 }
 
+void intel_memory_region_set_name(struct intel_memory_region *mem,
+				  const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vsnprintf(mem->name, sizeof(mem->name), fmt, ap);
+	va_end(ap);
+}
+
 static void __intel_memory_region_destroy(struct kref *kref)
 {
 	struct intel_memory_region *mem =
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 238722009677..232490d89a83 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -47,6 +47,10 @@ enum intel_region_id {
 #define I915_ALLOC_MIN_PAGE_SIZE  BIT(0)
 #define I915_ALLOC_CONTIGUOUS     BIT(1)
 
+#define for_each_memory_region(mr, i915, id) \
+	for (id = 0; id < ARRAY_SIZE((i915)->mm.regions); id++) \
+		for_each_if((mr) = (i915)->mm.regions[id])
+
 /**
  * Memory regions encoded as type | instance
  */
@@ -82,10 +86,13 @@ struct intel_memory_region {
 
 	resource_size_t io_start;
 	resource_size_t min_page_size;
+	resource_size_t total;
+	resource_size_t avail;
 
 	unsigned int type;
 	unsigned int instance;
 	unsigned int id;
+	char name[8];
 
 	dma_addr_t remap_addr;
 
@@ -125,5 +132,12 @@ void intel_memory_region_put(struct intel_memory_region *mem);
 
 int intel_memory_regions_hw_probe(struct drm_i915_private *i915);
 void intel_memory_regions_driver_release(struct drm_i915_private *i915);
+struct intel_memory_region *
+intel_memory_region_by_type(struct drm_i915_private *i915,
+			    enum intel_memory_type mem_type);
+
+__printf(2, 3) void
+intel_memory_region_set_name(struct intel_memory_region *mem,
+			     const char *fmt, ...);
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index 8fd92b9130a7..4ed60e1f01db 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -12,89 +12,91 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 {
 	switch (id) {
 	case INTEL_PCH_IBX_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Ibex Peak PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Ibex Peak PCH\n");
 		WARN_ON(!IS_GEN(dev_priv, 5));
 		return PCH_IBX;
 	case INTEL_PCH_CPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found CougarPoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found CougarPoint PCH\n");
 		WARN_ON(!IS_GEN(dev_priv, 6) && !IS_IVYBRIDGE(dev_priv));
 		return PCH_CPT;
 	case INTEL_PCH_PPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found PantherPoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found PantherPoint PCH\n");
 		WARN_ON(!IS_GEN(dev_priv, 6) && !IS_IVYBRIDGE(dev_priv));
 		/* PantherPoint is CPT compatible */
 		return PCH_CPT;
 	case INTEL_PCH_LPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found LynxPoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found LynxPoint PCH\n");
 		WARN_ON(!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv));
 		WARN_ON(IS_HSW_ULT(dev_priv) || IS_BDW_ULT(dev_priv));
 		return PCH_LPT;
 	case INTEL_PCH_LPT_LP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found LynxPoint LP PCH\n");
 		WARN_ON(!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv));
 		WARN_ON(!IS_HSW_ULT(dev_priv) && !IS_BDW_ULT(dev_priv));
 		return PCH_LPT;
 	case INTEL_PCH_WPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found WildcatPoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found WildcatPoint PCH\n");
 		WARN_ON(!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv));
 		WARN_ON(IS_HSW_ULT(dev_priv) || IS_BDW_ULT(dev_priv));
 		/* WildcatPoint is LPT compatible */
 		return PCH_LPT;
 	case INTEL_PCH_WPT_LP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found WildcatPoint LP PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found WildcatPoint LP PCH\n");
 		WARN_ON(!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv));
 		WARN_ON(!IS_HSW_ULT(dev_priv) && !IS_BDW_ULT(dev_priv));
 		/* WildcatPoint is LPT compatible */
 		return PCH_LPT;
 	case INTEL_PCH_SPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found SunrisePoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found SunrisePoint PCH\n");
 		WARN_ON(!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv));
 		return PCH_SPT;
 	case INTEL_PCH_SPT_LP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found SunrisePoint LP PCH\n");
 		WARN_ON(!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv) &&
 			!IS_COFFEELAKE(dev_priv));
 		return PCH_SPT;
 	case INTEL_PCH_KBP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Kaby Lake PCH (KBP)\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Kaby Lake PCH (KBP)\n");
 		WARN_ON(!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv) &&
 			!IS_COFFEELAKE(dev_priv));
 		/* KBP is SPT compatible */
 		return PCH_SPT;
 	case INTEL_PCH_CNP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Cannon Lake PCH (CNP)\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Cannon Lake PCH (CNP)\n");
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CNP_LP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Cannon Lake LP PCH (CNP-LP)\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Found Cannon Lake LP PCH (CNP-LP)\n");
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CMP_DEVICE_ID_TYPE:
 	case INTEL_PCH_CMP2_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Comet Lake PCH (CMP)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* CometPoint is CNP Compatible */
 		return PCH_CNP;
 	case INTEL_PCH_CMP_V_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Comet Lake V PCH (CMP-V)\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Comet Lake V PCH (CMP-V)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* Comet Lake V PCH is based on KBP, which is SPT compatible */
 		return PCH_SPT;
 	case INTEL_PCH_ICP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Ice Lake PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Ice Lake PCH\n");
 		WARN_ON(!IS_ICELAKE(dev_priv));
 		return PCH_ICP;
 	case INTEL_PCH_MCC_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Mule Creek Canyon PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Mule Creek Canyon PCH\n");
 		WARN_ON(!IS_ELKHARTLAKE(dev_priv));
 		return PCH_MCC;
 	case INTEL_PCH_TGP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Tiger Lake LP PCH\n");
+	case INTEL_PCH_TGP2_DEVICE_ID_TYPE:
+		drm_dbg_kms(&dev_priv->drm, "Found Tiger Lake LP PCH\n");
 		WARN_ON(!IS_TIGERLAKE(dev_priv));
 		return PCH_TGP;
 	case INTEL_PCH_JSP_DEVICE_ID_TYPE:
 	case INTEL_PCH_JSP2_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Jasper Lake PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Jasper Lake PCH\n");
 		WARN_ON(!IS_ELKHARTLAKE(dev_priv));
 		return PCH_JSP;
 	default:
@@ -144,9 +146,9 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv)
 		id = INTEL_PCH_IBX_DEVICE_ID_TYPE;
 
 	if (id)
-		DRM_DEBUG_KMS("Assuming PCH ID %04x\n", id);
+		drm_dbg_kms(&dev_priv->drm, "Assuming PCH ID %04x\n", id);
 	else
-		DRM_DEBUG_KMS("Assuming no PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Assuming no PCH\n");
 
 	return id;
 }
@@ -200,13 +202,14 @@ void intel_detect_pch(struct drm_i915_private *dev_priv)
 	 * display.
 	 */
 	if (pch && !HAS_DISPLAY(dev_priv)) {
-		DRM_DEBUG_KMS("Display disabled, reverting to NOP PCH\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Display disabled, reverting to NOP PCH\n");
 		dev_priv->pch_type = PCH_NOP;
 		dev_priv->pch_id = 0;
 	}
 
 	if (!pch)
-		DRM_DEBUG_KMS("No PCH found.\n");
+		drm_dbg_kms(&dev_priv->drm, "No PCH found.\n");
 
 	pci_dev_put(pch);
 }
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index d26c25dd8d54..3053d1ce398b 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -47,6 +47,7 @@ enum intel_pch {
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_MCC_DEVICE_ID_TYPE		0x4B00
 #define INTEL_PCH_TGP_DEVICE_ID_TYPE		0xA080
+#define INTEL_PCH_TGP2_DEVICE_ID_TYPE		0x4380
 #define INTEL_PCH_JSP_DEVICE_ID_TYPE		0x4D80
 #define INTEL_PCH_JSP2_DEVICE_ID_TYPE		0x3880
 #define INTEL_PCH_P2X_DEVICE_ID_TYPE		0x7100
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 86379eddc908..bd2d30ecc030 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -140,7 +140,7 @@ static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
 
 }
 
-static void i915_pineview_get_mem_freq(struct drm_i915_private *dev_priv)
+static void pnv_get_mem_freq(struct drm_i915_private *dev_priv)
 {
 	u32 tmp;
 
@@ -178,7 +178,7 @@ static void i915_pineview_get_mem_freq(struct drm_i915_private *dev_priv)
 	dev_priv->is_ddr3 = (tmp & CSHRDDR3CTL_DDR3) ? 1 : 0;
 }
 
-static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
+static void ilk_get_mem_freq(struct drm_i915_private *dev_priv)
 {
 	u16 ddrpll, csipll;
 
@@ -199,8 +199,8 @@ static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
 		dev_priv->mem_freq = 1600;
 		break;
 	default:
-		DRM_DEBUG_DRIVER("unknown memory frequency 0x%02x\n",
-				 ddrpll & 0xff);
+		drm_dbg(&dev_priv->drm, "unknown memory frequency 0x%02x\n",
+			ddrpll & 0xff);
 		dev_priv->mem_freq = 0;
 		break;
 	}
@@ -228,8 +228,8 @@ static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
 		dev_priv->fsb_freq = 6400;
 		break;
 	default:
-		DRM_DEBUG_DRIVER("unknown fsb frequency 0x%04x\n",
-				 csipll & 0x3ff);
+		drm_dbg(&dev_priv->drm, "unknown fsb frequency 0x%04x\n",
+			csipll & 0x3ff);
 		dev_priv->fsb_freq = 0;
 		break;
 	}
@@ -314,7 +314,8 @@ static void chv_set_memory_dvfs(struct drm_i915_private *dev_priv, bool enable)
 
 	if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2) &
 		      FORCE_DDR_FREQ_REQ_ACK) == 0, 3))
-		DRM_ERROR("timed out waiting for Punit DDR DVFS request\n");
+		drm_err(&dev_priv->drm,
+			"timed out waiting for Punit DDR DVFS request\n");
 
 	vlv_punit_put(dev_priv);
 }
@@ -383,9 +384,9 @@ static bool _intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enabl
 
 	trace_intel_memory_cxsr(dev_priv, was_enabled, enable);
 
-	DRM_DEBUG_KMS("memory self-refresh is %s (was %s)\n",
-		      enableddisabled(enable),
-		      enableddisabled(was_enabled));
+	drm_dbg_kms(&dev_priv->drm, "memory self-refresh is %s (was %s)\n",
+		    enableddisabled(enable),
+		    enableddisabled(was_enabled));
 
 	return was_enabled;
 }
@@ -463,7 +464,7 @@ static const int pessimal_latency_ns = 5000;
 
 static void vlv_get_fifo_size(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
 	enum pipe pipe = crtc->pipe;
@@ -510,8 +511,8 @@ static int i9xx_get_fifo_size(struct drm_i915_private *dev_priv,
 	if (i9xx_plane == PLANE_B)
 		size = ((dsparb >> DSPARB_CSTART_SHIFT) & 0x7f) - size;
 
-	DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
-		      dsparb, plane_name(i9xx_plane), size);
+	drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+		    dsparb, plane_name(i9xx_plane), size);
 
 	return size;
 }
@@ -527,8 +528,8 @@ static int i830_get_fifo_size(struct drm_i915_private *dev_priv,
 		size = ((dsparb >> DSPARB_BEND_SHIFT) & 0x1ff) - size;
 	size >>= 1; /* Convert to cachelines */
 
-	DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
-		      dsparb, plane_name(i9xx_plane), size);
+	drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+		    dsparb, plane_name(i9xx_plane), size);
 
 	return size;
 }
@@ -542,41 +543,45 @@ static int i845_get_fifo_size(struct drm_i915_private *dev_priv,
 	size = dsparb & 0x7f;
 	size >>= 2; /* Convert to cachelines */
 
-	DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
-		      dsparb, plane_name(i9xx_plane), size);
+	drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+		    dsparb, plane_name(i9xx_plane), size);
 
 	return size;
 }
 
 /* Pineview has different values for various configs */
-static const struct intel_watermark_params pineview_display_wm = {
+static const struct intel_watermark_params pnv_display_wm = {
 	.fifo_size = PINEVIEW_DISPLAY_FIFO,
 	.max_wm = PINEVIEW_MAX_WM,
 	.default_wm = PINEVIEW_DFT_WM,
 	.guard_size = PINEVIEW_GUARD_WM,
 	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params pineview_display_hplloff_wm = {
+
+static const struct intel_watermark_params pnv_display_hplloff_wm = {
 	.fifo_size = PINEVIEW_DISPLAY_FIFO,
 	.max_wm = PINEVIEW_MAX_WM,
 	.default_wm = PINEVIEW_DFT_HPLLOFF_WM,
 	.guard_size = PINEVIEW_GUARD_WM,
 	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params pineview_cursor_wm = {
+
+static const struct intel_watermark_params pnv_cursor_wm = {
 	.fifo_size = PINEVIEW_CURSOR_FIFO,
 	.max_wm = PINEVIEW_CURSOR_MAX_WM,
 	.default_wm = PINEVIEW_CURSOR_DFT_WM,
 	.guard_size = PINEVIEW_CURSOR_GUARD_WM,
 	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params pineview_cursor_hplloff_wm = {
+
+static const struct intel_watermark_params pnv_cursor_hplloff_wm = {
 	.fifo_size = PINEVIEW_CURSOR_FIFO,
 	.max_wm = PINEVIEW_CURSOR_MAX_WM,
 	.default_wm = PINEVIEW_CURSOR_DFT_WM,
 	.guard_size = PINEVIEW_CURSOR_GUARD_WM,
 	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i965_cursor_wm_info = {
 	.fifo_size = I965_CURSOR_FIFO,
 	.max_wm = I965_CURSOR_MAX_WM,
@@ -584,6 +589,7 @@ static const struct intel_watermark_params i965_cursor_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i945_wm_info = {
 	.fifo_size = I945_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -591,6 +597,7 @@ static const struct intel_watermark_params i945_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i915_wm_info = {
 	.fifo_size = I915_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -598,6 +605,7 @@ static const struct intel_watermark_params i915_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i830_a_wm_info = {
 	.fifo_size = I855GM_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -605,6 +613,7 @@ static const struct intel_watermark_params i830_a_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I830_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i830_bc_wm_info = {
 	.fifo_size = I855GM_FIFO_SIZE,
 	.max_wm = I915_MAX_WM/2,
@@ -612,6 +621,7 @@ static const struct intel_watermark_params i830_bc_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I830_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i845_wm_info = {
 	.fifo_size = I830_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -794,10 +804,10 @@ static int intel_wm_num_levels(struct drm_i915_private *dev_priv)
 static bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state,
 				   const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 
 	/* FIXME check the 'enable' instead */
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return false;
 
 	/*
@@ -809,9 +819,28 @@ static bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state,
 	 * around this problem with the watermark code.
 	 */
 	if (plane->id == PLANE_CURSOR)
-		return plane_state->base.fb != NULL;
+		return plane_state->hw.fb != NULL;
 	else
-		return plane_state->base.visible;
+		return plane_state->uapi.visible;
+}
+
+static bool intel_crtc_active(struct intel_crtc *crtc)
+{
+	/* Be paranoid as we can arrive here with only partial
+	 * state retrieved from the hardware during setup.
+	 *
+	 * We can ditch the adjusted_mode.crtc_clock check as soon
+	 * as Haswell has gained clock readout/fastboot support.
+	 *
+	 * We can ditch the crtc->primary->state->fb check as soon as we can
+	 * properly reconstruct framebuffers.
+	 *
+	 * FIXME: The intel_crtc->active here should be switched to
+	 * crtc->state->active once we have proper CRTC states wired up
+	 * for atomic.
+	 */
+	return crtc->active && crtc->base.primary->state->fb &&
+		crtc->config->hw.adjusted_mode.crtc_clock;
 }
 
 static struct intel_crtc *single_enabled_crtc(struct drm_i915_private *dev_priv)
@@ -829,7 +858,7 @@ static struct intel_crtc *single_enabled_crtc(struct drm_i915_private *dev_priv)
 	return enabled;
 }
 
-static void pineview_update_wm(struct intel_crtc *unused_crtc)
+static void pnv_update_wm(struct intel_crtc *unused_crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
 	struct intel_crtc *crtc;
@@ -842,7 +871,8 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc)
 					 dev_priv->fsb_freq,
 					 dev_priv->mem_freq);
 	if (!latency) {
-		DRM_DEBUG_KMS("Unknown FSB/MEM found, disable CxSR\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Unknown FSB/MEM found, disable CxSR\n");
 		intel_set_memory_cxsr(dev_priv, false);
 		return;
 	}
@@ -850,25 +880,25 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc)
 	crtc = single_enabled_crtc(dev_priv);
 	if (crtc) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->base.adjusted_mode;
+			&crtc->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp = fb->format->cpp[0];
 		int clock = adjusted_mode->crtc_clock;
 
 		/* Display SR */
-		wm = intel_calculate_wm(clock, &pineview_display_wm,
-					pineview_display_wm.fifo_size,
+		wm = intel_calculate_wm(clock, &pnv_display_wm,
+					pnv_display_wm.fifo_size,
 					cpp, latency->display_sr);
 		reg = I915_READ(DSPFW1);
 		reg &= ~DSPFW_SR_MASK;
 		reg |= FW_WM(wm, SR);
 		I915_WRITE(DSPFW1, reg);
-		DRM_DEBUG_KMS("DSPFW1 register is %x\n", reg);
+		drm_dbg_kms(&dev_priv->drm, "DSPFW1 register is %x\n", reg);
 
 		/* cursor SR */
-		wm = intel_calculate_wm(clock, &pineview_cursor_wm,
-					pineview_display_wm.fifo_size,
+		wm = intel_calculate_wm(clock, &pnv_cursor_wm,
+					pnv_display_wm.fifo_size,
 					4, latency->cursor_sr);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_CURSOR_SR_MASK;
@@ -876,8 +906,8 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc)
 		I915_WRITE(DSPFW3, reg);
 
 		/* Display HPLL off SR */
-		wm = intel_calculate_wm(clock, &pineview_display_hplloff_wm,
-					pineview_display_hplloff_wm.fifo_size,
+		wm = intel_calculate_wm(clock, &pnv_display_hplloff_wm,
+					pnv_display_hplloff_wm.fifo_size,
 					cpp, latency->display_hpll_disable);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_HPLL_SR_MASK;
@@ -885,14 +915,14 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc)
 		I915_WRITE(DSPFW3, reg);
 
 		/* cursor HPLL off SR */
-		wm = intel_calculate_wm(clock, &pineview_cursor_hplloff_wm,
-					pineview_display_hplloff_wm.fifo_size,
+		wm = intel_calculate_wm(clock, &pnv_cursor_hplloff_wm,
+					pnv_display_hplloff_wm.fifo_size,
 					4, latency->cursor_hpll_disable);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_HPLL_CURSOR_MASK;
 		reg |= FW_WM(wm, HPLL_CURSOR);
 		I915_WRITE(DSPFW3, reg);
-		DRM_DEBUG_KMS("DSPFW3 register is %x\n", reg);
+		drm_dbg_kms(&dev_priv->drm, "DSPFW3 register is %x\n", reg);
 
 		intel_set_memory_cxsr(dev_priv, true);
 	} else {
@@ -1083,10 +1113,10 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state,
 			  int level)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	unsigned int latency = dev_priv->wm.pri_latency[level] * 10;
 	unsigned int clock, htotal, cpp, width, wm;
 
@@ -1096,7 +1126,7 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
 	/*
 	 * Not 100% sure which way ELK should go here as the
@@ -1116,7 +1146,7 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 	clock = adjusted_mode->crtc_clock;
 	htotal = adjusted_mode->crtc_htotal;
 
-	width = drm_rect_width(&plane_state->base.dst);
+	width = drm_rect_width(&plane_state->uapi.dst);
 
 	if (plane->id == PLANE_CURSOR) {
 		wm = intel_wm_method2(clock, htotal, width, cpp, latency);
@@ -1143,7 +1173,7 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 static bool g4x_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
 				 int level, enum plane_id plane_id, u16 value)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	bool dirty = false;
 
 	for (; level < intel_wm_num_levels(dev_priv); level++) {
@@ -1159,7 +1189,7 @@ static bool g4x_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
 static bool g4x_raw_fbc_wm_set(struct intel_crtc_state *crtc_state,
 			       int level, u16 value)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	bool dirty = false;
 
 	/* NORMAL level doesn't have an FBC watermark */
@@ -1182,7 +1212,8 @@ static u32 ilk_compute_fbc_wm(const struct intel_crtc_state *crtc_state,
 static bool g4x_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
 				     const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int num_levels = intel_wm_num_levels(to_i915(plane->base.dev));
 	enum plane_id plane_id = plane->id;
 	bool dirty = false;
@@ -1235,16 +1266,18 @@ static bool g4x_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
 
  out:
 	if (dirty) {
-		DRM_DEBUG_KMS("%s watermarks: normal=%d, SR=%d, HPLL=%d\n",
-			      plane->base.name,
-			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_NORMAL].plane[plane_id],
-			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].plane[plane_id],
-			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].plane[plane_id]);
+		drm_dbg_kms(&dev_priv->drm,
+			    "%s watermarks: normal=%d, SR=%d, HPLL=%d\n",
+			    plane->base.name,
+			    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_NORMAL].plane[plane_id],
+			    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].plane[plane_id],
+			    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].plane[plane_id]);
 
 		if (plane_id == PLANE_PRIMARY)
-			DRM_DEBUG_KMS("FBC watermarks: SR=%d, HPLL=%d\n",
-				      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].fbc,
-				      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].fbc);
+			drm_dbg_kms(&dev_priv->drm,
+				    "FBC watermarks: SR=%d, HPLL=%d\n",
+				    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].fbc,
+				    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].fbc);
 	}
 
 	return dirty;
@@ -1261,7 +1294,7 @@ static bool g4x_raw_plane_wm_is_valid(const struct intel_crtc_state *crtc_state,
 static bool g4x_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state,
 				     int level)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (level > dev_priv->wm.max_level)
 		return false;
@@ -1299,9 +1332,9 @@ static void g4x_invalidate_wms(struct intel_crtc *crtc,
 
 static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 	struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal;
 	int num_active_planes = hweight8(crtc_state->active_planes &
 					 ~BIT(PLANE_CURSOR));
@@ -1316,8 +1349,8 @@ static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	for_each_oldnew_intel_plane_in_state(state, plane,
 					     old_plane_state,
 					     new_plane_state, i) {
-		if (new_plane_state->base.crtc != &crtc->base &&
-		    old_plane_state->base.crtc != &crtc->base)
+		if (new_plane_state->hw.crtc != &crtc->base &&
+		    old_plane_state->hw.crtc != &crtc->base)
 			continue;
 
 		if (g4x_raw_plane_wm_compute(crtc_state, new_plane_state))
@@ -1388,17 +1421,17 @@ static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 
 static int g4x_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct g4x_wm_state *intermediate = &new_crtc_state->wm.g4x.intermediate;
 	const struct g4x_wm_state *optimal = &new_crtc_state->wm.g4x.optimal;
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(intel_state, crtc);
 	const struct g4x_wm_state *active = &old_crtc_state->wm.g4x.optimal;
 	enum plane_id plane_id;
 
-	if (!new_crtc_state->base.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->base)) {
+	if (!new_crtc_state->hw.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
 		*intermediate = *optimal;
 
 		intermediate->cxsr = false;
@@ -1528,10 +1561,11 @@ static void g4x_program_watermarks(struct drm_i915_private *dev_priv)
 }
 
 static void g4x_initial_watermarks(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state)
+				   struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 	crtc->wm.active.g4x = crtc_state->wm.g4x.intermediate;
@@ -1540,10 +1574,11 @@ static void g4x_initial_watermarks(struct intel_atomic_state *state,
 }
 
 static void g4x_optimize_watermarks(struct intel_atomic_state *state,
-				    struct intel_crtc_state *crtc_state)
+				    struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	if (!crtc_state->wm.need_postvbl_update)
 		return;
@@ -1589,10 +1624,10 @@ static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
 				const struct intel_plane_state *plane_state,
 				int level)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	unsigned int clock, htotal, cpp, width, wm;
 
 	if (dev_priv->wm.pri_latency[level] == 0)
@@ -1601,7 +1636,7 @@ static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 	clock = adjusted_mode->crtc_clock;
 	htotal = adjusted_mode->crtc_htotal;
 	width = crtc_state->pipe_src_w;
@@ -1630,7 +1665,7 @@ static bool vlv_need_sprite0_fifo_workaround(unsigned int active_planes)
 
 static int vlv_compute_fifo(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	const struct g4x_pipe_wm *raw =
 		&crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2];
 	struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
@@ -1742,7 +1777,7 @@ static u16 vlv_invert_wm_value(u16 wm, u16 fifo_size)
 static bool vlv_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
 				 int level, enum plane_id plane_id, u16 value)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int num_levels = intel_wm_num_levels(dev_priv);
 	bool dirty = false;
 
@@ -1759,7 +1794,8 @@ static bool vlv_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
 static bool vlv_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
 				     const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	enum plane_id plane_id = plane->id;
 	int num_levels = intel_wm_num_levels(to_i915(plane->base.dev));
 	int level;
@@ -1787,11 +1823,12 @@ static bool vlv_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
 
 out:
 	if (dirty)
-		DRM_DEBUG_KMS("%s watermarks: PM2=%d, PM5=%d, DDR DVFS=%d\n",
-			      plane->base.name,
-			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2].plane[plane_id],
-			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM5].plane[plane_id],
-			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_DDR_DVFS].plane[plane_id]);
+		drm_dbg_kms(&dev_priv->drm,
+			    "%s watermarks: PM2=%d, PM5=%d, DDR DVFS=%d\n",
+			    plane->base.name,
+			    crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2].plane[plane_id],
+			    crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM5].plane[plane_id],
+			    crtc_state->wm.vlv.raw[VLV_WM_LEVEL_DDR_DVFS].plane[plane_id]);
 
 	return dirty;
 }
@@ -1817,16 +1854,16 @@ static bool vlv_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state,
 
 static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 	struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal;
 	const struct vlv_fifo_state *fifo_state =
 		&crtc_state->wm.vlv.fifo_state;
 	int num_active_planes = hweight8(crtc_state->active_planes &
 					 ~BIT(PLANE_CURSOR));
-	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->base);
+	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->uapi);
 	const struct intel_plane_state *old_plane_state;
 	const struct intel_plane_state *new_plane_state;
 	struct intel_plane *plane;
@@ -1837,8 +1874,8 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	for_each_oldnew_intel_plane_in_state(state, plane,
 					     old_plane_state,
 					     new_plane_state, i) {
-		if (new_plane_state->base.crtc != &crtc->base &&
-		    old_plane_state->base.crtc != &crtc->base)
+		if (new_plane_state->hw.crtc != &crtc->base &&
+		    old_plane_state->hw.crtc != &crtc->base)
 			continue;
 
 		if (vlv_raw_plane_wm_compute(crtc_state, new_plane_state))
@@ -1923,11 +1960,12 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	(((value) << DSPARB_ ## plane ## _SHIFT_VLV) & DSPARB_ ## plane ## _MASK_VLV)
 
 static void vlv_atomic_update_fifo(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state)
+				   struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_uncore *uncore = &dev_priv->uncore;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	const struct vlv_fifo_state *fifo_state =
 		&crtc_state->wm.vlv.fifo_state;
 	int sprite0_start, sprite1_start, fifo_size;
@@ -2021,17 +2059,17 @@ static void vlv_atomic_update_fifo(struct intel_atomic_state *state,
 
 static int vlv_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct vlv_wm_state *intermediate = &new_crtc_state->wm.vlv.intermediate;
 	const struct vlv_wm_state *optimal = &new_crtc_state->wm.vlv.optimal;
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(intel_state, crtc);
 	const struct vlv_wm_state *active = &old_crtc_state->wm.vlv.optimal;
 	int level;
 
-	if (!new_crtc_state->base.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->base)) {
+	if (!new_crtc_state->hw.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
 		*intermediate = *optimal;
 
 		intermediate->cxsr = false;
@@ -2147,10 +2185,11 @@ static void vlv_program_watermarks(struct drm_i915_private *dev_priv)
 }
 
 static void vlv_initial_watermarks(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state)
+				   struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 	crtc->wm.active.vlv = crtc_state->wm.vlv.intermediate;
@@ -2159,10 +2198,11 @@ static void vlv_initial_watermarks(struct intel_atomic_state *state,
 }
 
 static void vlv_optimize_watermarks(struct intel_atomic_state *state,
-				    struct intel_crtc_state *crtc_state)
+				    struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	if (!crtc_state->wm.need_postvbl_update)
 		return;
@@ -2187,7 +2227,7 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 		/* self-refresh has much higher latency */
 		static const int sr_latency_ns = 12000;
 		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->base.adjusted_mode;
+			&crtc->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int clock = adjusted_mode->crtc_clock;
@@ -2203,8 +2243,9 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 		if (srwm < 0)
 			srwm = 1;
 		srwm &= 0x1ff;
-		DRM_DEBUG_KMS("self-refresh entries: %d, wm: %d\n",
-			      entries, srwm);
+		drm_dbg_kms(&dev_priv->drm,
+			    "self-refresh entries: %d, wm: %d\n",
+			    entries, srwm);
 
 		entries = intel_wm_method2(clock, htotal,
 					   crtc->base.cursor->state->crtc_w, 4,
@@ -2217,8 +2258,9 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 		if (cursor_sr > i965_cursor_wm_info.max_wm)
 			cursor_sr = i965_cursor_wm_info.max_wm;
 
-		DRM_DEBUG_KMS("self-refresh watermark: display plane %d "
-			      "cursor %d\n", srwm, cursor_sr);
+		drm_dbg_kms(&dev_priv->drm,
+			    "self-refresh watermark: display plane %d "
+			    "cursor %d\n", srwm, cursor_sr);
 
 		cxsr_enabled = true;
 	} else {
@@ -2227,8 +2269,9 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 		intel_set_memory_cxsr(dev_priv, false);
 	}
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: 8, B: 8, C: 8, SR %d\n",
-		      srwm);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Setting FIFO watermarks - A: 8, B: 8, C: 8, SR %d\n",
+		    srwm);
 
 	/* 965 has limitations... */
 	I915_WRITE(DSPFW1, FW_WM(srwm, SR) |
@@ -2268,7 +2311,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 	crtc = intel_get_crtc_for_plane(dev_priv, PLANE_A);
 	if (intel_crtc_active(crtc)) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->base.adjusted_mode;
+			&crtc->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp;
@@ -2295,7 +2338,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 	crtc = intel_get_crtc_for_plane(dev_priv, PLANE_B);
 	if (intel_crtc_active(crtc)) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->base.adjusted_mode;
+			&crtc->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp;
@@ -2318,7 +2361,8 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 			planeb_wm = wm_info->max_wm;
 	}
 
-	DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
+	drm_dbg_kms(&dev_priv->drm,
+		    "FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
 
 	if (IS_I915GM(dev_priv) && enabled) {
 		struct drm_i915_gem_object *obj;
@@ -2343,7 +2387,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 		/* self-refresh has much higher latency */
 		static const int sr_latency_ns = 6000;
 		const struct drm_display_mode *adjusted_mode =
-			&enabled->config->base.adjusted_mode;
+			&enabled->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			enabled->base.primary->state->fb;
 		int clock = adjusted_mode->crtc_clock;
@@ -2360,7 +2404,8 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 		entries = intel_wm_method2(clock, htotal, hdisplay, cpp,
 					   sr_latency_ns / 100);
 		entries = DIV_ROUND_UP(entries, wm_info->cacheline_size);
-		DRM_DEBUG_KMS("self-refresh entries: %d\n", entries);
+		drm_dbg_kms(&dev_priv->drm,
+			    "self-refresh entries: %d\n", entries);
 		srwm = wm_info->fifo_size - entries;
 		if (srwm < 0)
 			srwm = 1;
@@ -2372,8 +2417,9 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 			I915_WRITE(FW_BLC_SELF, srwm & 0x3f);
 	}
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n",
-		      planea_wm, planeb_wm, cwm, srwm);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n",
+		     planea_wm, planeb_wm, cwm, srwm);
 
 	fwater_lo = ((planeb_wm & 0x3f) << 16) | (planea_wm & 0x3f);
 	fwater_hi = (cwm & 0x1f);
@@ -2401,7 +2447,7 @@ static void i845_update_wm(struct intel_crtc *unused_crtc)
 	if (crtc == NULL)
 		return;
 
-	adjusted_mode = &crtc->config->base.adjusted_mode;
+	adjusted_mode = &crtc->config->hw.adjusted_mode;
 	planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
 				       &i845_wm_info,
 				       dev_priv->display.get_fifo_size(dev_priv, PLANE_A),
@@ -2409,7 +2455,8 @@ static void i845_update_wm(struct intel_crtc *unused_crtc)
 	fwater_lo = I915_READ(FW_BLC) & ~0xfff;
 	fwater_lo |= (3<<8) | planea_wm;
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: %d\n", planea_wm);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Setting FIFO watermarks - A: %d\n", planea_wm);
 
 	I915_WRITE(FW_BLC, fwater_lo);
 }
@@ -2483,7 +2530,7 @@ static u32 ilk_compute_pri_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
 	method1 = ilk_wm_method1(crtc_state->pixel_rate, cpp, mem_value);
 
@@ -2491,8 +2538,8 @@ static u32 ilk_compute_pri_wm(const struct intel_crtc_state *crtc_state,
 		return method1;
 
 	method2 = ilk_wm_method2(crtc_state->pixel_rate,
-				 crtc_state->base.adjusted_mode.crtc_htotal,
-				 drm_rect_width(&plane_state->base.dst),
+				 crtc_state->hw.adjusted_mode.crtc_htotal,
+				 drm_rect_width(&plane_state->uapi.dst),
 				 cpp, mem_value);
 
 	return min(method1, method2);
@@ -2515,12 +2562,12 @@ static u32 ilk_compute_spr_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
 	method1 = ilk_wm_method1(crtc_state->pixel_rate, cpp, mem_value);
 	method2 = ilk_wm_method2(crtc_state->pixel_rate,
-				 crtc_state->base.adjusted_mode.crtc_htotal,
-				 drm_rect_width(&plane_state->base.dst),
+				 crtc_state->hw.adjusted_mode.crtc_htotal,
+				 drm_rect_width(&plane_state->uapi.dst),
 				 cpp, mem_value);
 	return min(method1, method2);
 }
@@ -2541,11 +2588,11 @@ static u32 ilk_compute_cur_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
 	return ilk_wm_method2(crtc_state->pixel_rate,
-			      crtc_state->base.adjusted_mode.crtc_htotal,
-			      drm_rect_width(&plane_state->base.dst),
+			      crtc_state->hw.adjusted_mode.crtc_htotal,
+			      drm_rect_width(&plane_state->uapi.dst),
 			      cpp, mem_value);
 }
 
@@ -2559,9 +2606,10 @@ static u32 ilk_compute_fbc_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
-	return ilk_wm_fbc(pri_val, drm_rect_width(&plane_state->base.dst), cpp);
+	return ilk_wm_fbc(pri_val, drm_rect_width(&plane_state->uapi.dst),
+			  cpp);
 }
 
 static unsigned int
@@ -2766,12 +2814,12 @@ static u32
 hsw_compute_linetime_wm(const struct intel_crtc_state *crtc_state)
 {
 	const struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	u32 linetime, ips_linetime;
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return 0;
 	if (WARN_ON(adjusted_mode->crtc_clock == 0))
 		return 0;
@@ -2807,7 +2855,8 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 					     &val, NULL);
 
 		if (ret) {
-			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
+			drm_err(&dev_priv->drm,
+				"SKL Mailbox read error = %d\n", ret);
 			return;
 		}
 
@@ -2825,7 +2874,8 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 					     GEN9_PCODE_READ_MEM_LATENCY,
 					     &val, NULL);
 		if (ret) {
-			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
+			drm_err(&dev_priv->drm,
+				"SKL Mailbox read error = %d\n", ret);
 			return;
 		}
 
@@ -2943,8 +2993,9 @@ static void intel_print_wm_latency(struct drm_i915_private *dev_priv,
 		unsigned int latency = wm[level];
 
 		if (latency == 0) {
-			DRM_DEBUG_KMS("%s WM%d latency not provided\n",
-				      name, level);
+			drm_dbg_kms(&dev_priv->drm,
+				    "%s WM%d latency not provided\n",
+				    name, level);
 			continue;
 		}
 
@@ -2957,9 +3008,9 @@ static void intel_print_wm_latency(struct drm_i915_private *dev_priv,
 		else if (level > 0)
 			latency *= 5;
 
-		DRM_DEBUG_KMS("%s WM%d latency %u (%u.%u usec)\n",
-			      name, level, wm[level],
-			      latency / 10, latency % 10);
+		drm_dbg_kms(&dev_priv->drm,
+			    "%s WM%d latency %u (%u.%u usec)\n", name, level,
+			    wm[level], latency / 10, latency % 10);
 	}
 }
 
@@ -2993,7 +3044,8 @@ static void snb_wm_latency_quirk(struct drm_i915_private *dev_priv)
 	if (!changed)
 		return;
 
-	DRM_DEBUG_KMS("WM latency values increased to avoid potential underruns\n");
+	drm_dbg_kms(&dev_priv->drm,
+		    "WM latency values increased to avoid potential underruns\n");
 	intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency);
 	intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
 	intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);
@@ -3021,7 +3073,8 @@ static void snb_wm_lp3_irq_quirk(struct drm_i915_private *dev_priv)
 	dev_priv->wm.spr_latency[3] = 0;
 	dev_priv->wm.cur_latency[3] = 0;
 
-	DRM_DEBUG_KMS("LP3 watermarks disabled due to potential for lost interrupts\n");
+	drm_dbg_kms(&dev_priv->drm,
+		    "LP3 watermarks disabled due to potential for lost interrupts\n");
 	intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency);
 	intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
 	intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);
@@ -3071,7 +3124,7 @@ static bool ilk_validate_pipe_wm(const struct drm_i915_private *dev_priv,
 
 	/* At least LP0 must be valid */
 	if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) {
-		DRM_DEBUG_KMS("LP0 watermark invalid\n");
+		drm_dbg_kms(&dev_priv->drm, "LP0 watermark invalid\n");
 		return false;
 	}
 
@@ -3081,11 +3134,9 @@ static bool ilk_validate_pipe_wm(const struct drm_i915_private *dev_priv,
 /* Compute new watermarks for the pipe */
 static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_pipe_wm *pipe_wm;
-	struct drm_device *dev = state->dev;
-	const struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *plane;
 	const struct intel_plane_state *plane_state;
 	const struct intel_plane_state *pristate = NULL;
@@ -3105,12 +3156,12 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 			curstate = plane_state;
 	}
 
-	pipe_wm->pipe_enabled = crtc_state->base.active;
+	pipe_wm->pipe_enabled = crtc_state->hw.active;
 	if (sprstate) {
-		pipe_wm->sprites_enabled = sprstate->base.visible;
-		pipe_wm->sprites_scaled = sprstate->base.visible &&
-			(drm_rect_width(&sprstate->base.dst) != drm_rect_width(&sprstate->base.src) >> 16 ||
-			 drm_rect_height(&sprstate->base.dst) != drm_rect_height(&sprstate->base.src) >> 16);
+		pipe_wm->sprites_enabled = sprstate->uapi.visible;
+		pipe_wm->sprites_scaled = sprstate->uapi.visible &&
+			(drm_rect_width(&sprstate->uapi.dst) != drm_rect_width(&sprstate->uapi.src) >> 16 ||
+			 drm_rect_height(&sprstate->uapi.dst) != drm_rect_height(&sprstate->uapi.src) >> 16);
 	}
 
 	usable_level = max_level;
@@ -3162,11 +3213,11 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
  */
 static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(newstate->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(newstate->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	struct intel_pipe_wm *a = &newstate->wm.ilk.intermediate;
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(newstate->base.state);
+		to_intel_atomic_state(newstate->uapi.state);
 	const struct intel_crtc_state *oldstate =
 		intel_atomic_get_old_crtc_state(intel_state, intel_crtc);
 	const struct intel_pipe_wm *b = &oldstate->wm.ilk.optimal;
@@ -3178,7 +3229,7 @@ static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate)
 	 * and after the vblank.
 	 */
 	*a = newstate->wm.ilk.optimal;
-	if (!newstate->base.active || drm_atomic_crtc_needs_modeset(&newstate->base) ||
+	if (!newstate->hw.active || drm_atomic_crtc_needs_modeset(&newstate->uapi) ||
 	    intel_state->skip_intermediate_wm)
 		return 0;
 
@@ -3588,10 +3639,8 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 	dev_priv->wm.hw = *results;
 }
 
-bool ilk_disable_lp_wm(struct drm_device *dev)
+bool ilk_disable_lp_wm(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
 	return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL);
 }
 
@@ -3652,7 +3701,7 @@ skl_setup_sagv_block_time(struct drm_i915_private *dev_priv)
 			return;
 		}
 
-		DRM_DEBUG_DRIVER("Couldn't read SAGV block time!\n");
+		drm_dbg(&dev_priv->drm, "Couldn't read SAGV block time!\n");
 	} else if (IS_GEN(dev_priv, 11)) {
 		dev_priv->sagv_block_time_us = 10;
 		return;
@@ -3692,7 +3741,7 @@ intel_enable_sagv(struct drm_i915_private *dev_priv)
 	if (dev_priv->sagv_status == I915_SAGV_ENABLED)
 		return 0;
 
-	DRM_DEBUG_KMS("Enabling SAGV\n");
+	drm_dbg_kms(&dev_priv->drm, "Enabling SAGV\n");
 	ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
 				      GEN9_SAGV_ENABLE);
 
@@ -3703,11 +3752,11 @@ intel_enable_sagv(struct drm_i915_private *dev_priv)
 	 * don't actually have SAGV.
 	 */
 	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
-		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+		drm_dbg(&dev_priv->drm, "No SAGV found on system, ignoring\n");
 		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
 		return 0;
 	} else if (ret < 0) {
-		DRM_ERROR("Failed to enable SAGV\n");
+		drm_err(&dev_priv->drm, "Failed to enable SAGV\n");
 		return ret;
 	}
 
@@ -3726,7 +3775,7 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 	if (dev_priv->sagv_status == I915_SAGV_DISABLED)
 		return 0;
 
-	DRM_DEBUG_KMS("Disabling SAGV\n");
+	drm_dbg_kms(&dev_priv->drm, "Disabling SAGV\n");
 	/* bspec says to keep retrying for at least 1 ms */
 	ret = skl_pcode_request(dev_priv, GEN9_PCODE_SAGV_CONTROL,
 				GEN9_SAGV_DISABLE,
@@ -3737,11 +3786,11 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 	 * don't actually have SAGV.
 	 */
 	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
-		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+		drm_dbg(&dev_priv->drm, "No SAGV found on system, ignoring\n");
 		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
 		return 0;
 	} else if (ret < 0) {
-		DRM_ERROR("Failed to disable SAGV (%d)\n", ret);
+		drm_err(&dev_priv->drm, "Failed to disable SAGV (%d)\n", ret);
 		return ret;
 	}
 
@@ -3780,7 +3829,7 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 	crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 	crtc_state = to_intel_crtc_state(crtc->base.state);
 
-	if (crtc->base.state->adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
 		return false;
 
 	for_each_intel_plane_on_crtc(dev, crtc, plane) {
@@ -3830,7 +3879,7 @@ static u16 intel_get_ddb_size(struct drm_i915_private *dev_priv,
 	if (INTEL_GEN(dev_priv) < 11)
 		return ddb_size - 4; /* 4 blocks for bypass path allocation */
 
-	adjusted_mode = &crtc_state->base.adjusted_mode;
+	adjusted_mode = &crtc_state->hw.adjusted_mode;
 	total_data_bw = total_data_rate * drm_mode_vrefresh(adjusted_mode);
 
 	/*
@@ -3859,16 +3908,16 @@ skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
 				   struct skl_ddb_entry *alloc, /* out */
 				   int *num_active /* out */)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct drm_crtc *for_crtc = crtc_state->base.crtc;
+	struct drm_crtc *for_crtc = crtc_state->uapi.crtc;
 	const struct intel_crtc *crtc;
 	u32 pipe_width = 0, total_width = 0, width_before_pipe = 0;
 	enum pipe for_pipe = to_intel_crtc(for_crtc)->pipe;
 	u16 ddb_size;
 	u32 i;
 
-	if (WARN_ON(!state) || !crtc_state->base.active) {
+	if (WARN_ON(!state) || !crtc_state->hw.active) {
 		alloc->start = 0;
 		alloc->end = 0;
 		*num_active = hweight8(dev_priv->active_pipes);
@@ -3907,11 +3956,11 @@ skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
 	 */
 	for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc_state->base.adjusted_mode;
+			&crtc_state->hw.adjusted_mode;
 		enum pipe pipe = crtc->pipe;
 		int hdisplay, vdisplay;
 
-		if (!crtc_state->base.enable)
+		if (!crtc_state->hw.enable)
 			continue;
 
 		drm_mode_get_hv_timing(adjusted_mode, &hdisplay, &vdisplay);
@@ -3942,7 +3991,7 @@ static unsigned int
 skl_cursor_allocation(const struct intel_crtc_state *crtc_state,
 		      int num_active)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int level, max_level = ilk_wm_max_level(dev_priv);
 	struct skl_wm_level wm = {};
 	int ret, min_ddb_alloc = 0;
@@ -4082,10 +4131,10 @@ skl_plane_downscale_amount(const struct intel_crtc_state *crtc_state,
 	 *
 	 * n.b., src is 16.16 fixed point, dst is whole integer.
 	 */
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	dst_w = drm_rect_width(&plane_state->base.dst);
-	dst_h = drm_rect_height(&plane_state->base.dst);
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->uapi.dst);
+	dst_h = drm_rect_height(&plane_state->uapi.dst);
 
 	fp_w_ratio = div_fixed16(src_w, dst_w);
 	fp_h_ratio = div_fixed16(src_h, dst_h);
@@ -4100,21 +4149,21 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state,
 			     int color_plane)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	u32 data_rate;
 	u32 width = 0, height = 0;
 	uint_fixed_16_16_t down_scale_amount;
 	u64 rate;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	if (plane->id == PLANE_CURSOR)
 		return 0;
 
 	if (color_plane == 1 &&
-	    !drm_format_info_is_yuv_semiplanar(fb->format))
+	    !intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		return 0;
 
 	/*
@@ -4122,8 +4171,8 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 	 * the 90/270 degree plane rotation cases (to match the
 	 * GTT mapping), hence no need to account for rotation here.
 	 */
-	width = drm_rect_width(&plane_state->base.src) >> 16;
-	height = drm_rect_height(&plane_state->base.src) >> 16;
+	width = drm_rect_width(&plane_state->uapi.src) >> 16;
+	height = drm_rect_height(&plane_state->uapi.src) >> 16;
 
 	/* UV plane does 1/2 pixel sub-sampling */
 	if (color_plane == 1) {
@@ -4146,7 +4195,7 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 				 u64 *plane_data_rate,
 				 u64 *uv_plane_data_rate)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
 	struct intel_plane *plane;
 	const struct intel_plane_state *plane_state;
 	u64 total_data_rate = 0;
@@ -4181,7 +4230,7 @@ icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 	const struct intel_plane_state *plane_state;
 	u64 total_data_rate = 0;
 
-	if (WARN_ON(!crtc_state->base.state))
+	if (WARN_ON(!crtc_state->uapi.state))
 		return 0;
 
 	/* Calculate and cache data rate for each plane */
@@ -4225,8 +4274,8 @@ static int
 skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state,
 		      struct skl_ddb_allocation *ddb /* out */)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
-	struct drm_crtc *crtc = crtc_state->base.crtc;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
+	struct drm_crtc *crtc = crtc_state->uapi.crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct skl_ddb_entry *alloc = &crtc_state->wm.skl.ddb;
@@ -4248,7 +4297,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state,
 	if (WARN_ON(!state))
 		return 0;
 
-	if (!crtc_state->base.active) {
+	if (!crtc_state->hw.active) {
 		alloc->start = alloc->end = 0;
 		return 0;
 	}
@@ -4310,9 +4359,10 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state,
 	}
 
 	if (level < 0) {
-		DRM_DEBUG_KMS("Requested display configuration exceeds system DDB limitations");
-		DRM_DEBUG_KMS("minimum required %d/%d\n", blocks,
-			      alloc_size);
+		drm_dbg_kms(&dev_priv->drm,
+			    "Requested display configuration exceeds system DDB limitations");
+		drm_dbg_kms(&dev_priv->drm, "minimum required %d/%d\n",
+			    blocks, alloc_size);
 		return -EINVAL;
 	}
 
@@ -4490,7 +4540,7 @@ intel_get_linetime_us(const struct intel_crtc_state *crtc_state)
 	u32 crtc_htotal;
 	uint_fixed_16_16_t linetime_us;
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return u32_to_fixed16(0);
 
 	pixel_rate = crtc_state->pixel_rate;
@@ -4498,7 +4548,7 @@ intel_get_linetime_us(const struct intel_crtc_state *crtc_state)
 	if (WARN_ON(pixel_rate == 0))
 		return u32_to_fixed16(0);
 
-	crtc_htotal = crtc_state->base.adjusted_mode.crtc_htotal;
+	crtc_htotal = crtc_state->hw.adjusted_mode.crtc_htotal;
 	linetime_us = div_fixed16(crtc_htotal * 1000, pixel_rate);
 
 	return linetime_us;
@@ -4533,13 +4583,15 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 		      u32 plane_pixel_rate, struct skl_wm_params *wp,
 		      int color_plane)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 interm_pbpl;
 
 	/* only planar format has two planes */
-	if (color_plane == 1 && !drm_format_info_is_yuv_semiplanar(format)) {
-		DRM_DEBUG_KMS("Non planar format have single plane\n");
+	if (color_plane == 1 &&
+	    !intel_format_info_is_yuv_semiplanar(format, modifier)) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "Non planar format have single plane\n");
 		return -EINVAL;
 	}
 
@@ -4550,7 +4602,7 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
-	wp->is_planar = drm_format_info_is_yuv_semiplanar(format);
+	wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
 
 	wp->width = width;
 	if (color_plane == 1 && wp->is_planar)
@@ -4622,7 +4674,7 @@ skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state,
 			    const struct intel_plane_state *plane_state,
 			    struct skl_wm_params *wp, int color_plane)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int width;
 
 	/*
@@ -4630,11 +4682,11 @@ skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state,
 	 * the 90/270 degree plane rotation cases (to match the
 	 * GTT mapping), hence no need to account for rotation here.
 	 */
-	width = drm_rect_width(&plane_state->base.src) >> 16;
+	width = drm_rect_width(&plane_state->uapi.src) >> 16;
 
 	return skl_compute_wm_params(crtc_state, width,
 				     fb->format, fb->modifier,
-				     plane_state->base.rotation,
+				     plane_state->hw.rotation,
 				     skl_adjusted_plane_pixel_rate(crtc_state, plane_state),
 				     wp, color_plane);
 }
@@ -4654,7 +4706,7 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 				 const struct skl_wm_level *result_prev,
 				 struct skl_wm_level *result /* out */)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 latency = dev_priv->wm.skl_latency[level];
 	uint_fixed_16_16_t method1, method2;
 	uint_fixed_16_16_t selected_result;
@@ -4680,14 +4732,14 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 	method1 = skl_wm_method1(dev_priv, wp->plane_pixel_rate,
 				 wp->cpp, latency, wp->dbuf_block_size);
 	method2 = skl_wm_method2(wp->plane_pixel_rate,
-				 crtc_state->base.adjusted_mode.crtc_htotal,
+				 crtc_state->hw.adjusted_mode.crtc_htotal,
 				 latency,
 				 wp->plane_blocks_per_line);
 
 	if (wp->y_tiled) {
 		selected_result = max_fixed16(method2, wp->y_tile_minimum);
 	} else {
-		if ((wp->cpp * crtc_state->base.adjusted_mode.crtc_htotal /
+		if ((wp->cpp * crtc_state->hw.adjusted_mode.crtc_htotal /
 		     wp->dbuf_block_size < 1) &&
 		     (wp->plane_bytes_per_line / wp->dbuf_block_size < 1)) {
 			selected_result = method2;
@@ -4778,7 +4830,7 @@ skl_compute_wm_levels(const struct intel_crtc_state *crtc_state,
 		      const struct skl_wm_params *wm_params,
 		      struct skl_wm_level *levels)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int level, max_level = ilk_wm_max_level(dev_priv);
 	struct skl_wm_level *result_prev = &levels[0];
 
@@ -4795,7 +4847,7 @@ skl_compute_wm_levels(const struct intel_crtc_state *crtc_state,
 static u32
 skl_compute_linetime_wm(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
 	struct drm_i915_private *dev_priv = to_i915(state->dev);
 	uint_fixed_16_16_t linetime_us;
 	u32 linetime_wm;
@@ -4814,7 +4866,7 @@ static void skl_compute_transition_wm(const struct intel_crtc_state *crtc_state,
 				      const struct skl_wm_params *wp,
 				      struct skl_plane_wm *wm)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_device *dev = crtc_state->uapi.crtc->dev;
 	const struct drm_i915_private *dev_priv = to_i915(dev);
 	u16 trans_min, trans_y_tile_min;
 	const u16 trans_amount = 10; /* This is configurable amount */
@@ -4912,8 +4964,8 @@ static int skl_build_plane_wm_uv(struct intel_crtc_state *crtc_state,
 static int skl_build_plane_wm(struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum plane_id plane_id = plane->id;
 	int ret;
 
@@ -4938,7 +4990,7 @@ static int skl_build_plane_wm(struct intel_crtc_state *crtc_state,
 static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state)
 {
-	enum plane_id plane_id = to_intel_plane(plane_state->base.plane)->id;
+	enum plane_id plane_id = to_intel_plane(plane_state->uapi.plane)->id;
 	int ret;
 
 	/* Watermarks calculated in master */
@@ -4946,7 +4998,7 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 		return 0;
 
 	if (plane_state->planar_linked_plane) {
-		const struct drm_framebuffer *fb = plane_state->base.fb;
+		const struct drm_framebuffer *fb = plane_state->hw.fb;
 		enum plane_id y_plane_id = plane_state->planar_linked_plane->id;
 
 		WARN_ON(!intel_wm_plane_visible(crtc_state, plane_state));
@@ -4974,7 +5026,7 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 
 static int skl_build_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
 	struct intel_plane *plane;
 	const struct intel_plane_state *plane_state;
@@ -5151,8 +5203,8 @@ static int
 skl_ddb_add_affected_planes(const struct intel_crtc_state *old_crtc_state,
 			    struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->base.state);
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->uapi.state);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_plane *plane;
 
@@ -5218,7 +5270,7 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 	struct intel_crtc *crtc;
 	int i;
 
-	if ((drm_debug & DRM_UT_KMS) == 0)
+	if (!drm_debug_enabled(DRM_UT_KMS))
 		return;
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
@@ -5238,10 +5290,11 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 			if (skl_ddb_entry_equal(old, new))
 				continue;
 
-			DRM_DEBUG_KMS("[PLANE:%d:%s] ddb (%4d - %4d) -> (%4d - %4d), size %4d -> %4d\n",
-				      plane->base.base.id, plane->base.name,
-				      old->start, old->end, new->start, new->end,
-				      skl_ddb_entry_size(old), skl_ddb_entry_size(new));
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s] ddb (%4d - %4d) -> (%4d - %4d), size %4d -> %4d\n",
+				    plane->base.base.id, plane->base.name,
+				    old->start, old->end, new->start, new->end,
+				    skl_ddb_entry_size(old), skl_ddb_entry_size(new));
 		}
 
 		for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
@@ -5254,70 +5307,74 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 			if (skl_plane_wm_equals(dev_priv, old_wm, new_wm))
 				continue;
 
-			DRM_DEBUG_KMS("[PLANE:%d:%s]   level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm"
-				      " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm\n",
-				      plane->base.base.id, plane->base.name,
-				      enast(old_wm->wm[0].plane_en), enast(old_wm->wm[1].plane_en),
-				      enast(old_wm->wm[2].plane_en), enast(old_wm->wm[3].plane_en),
-				      enast(old_wm->wm[4].plane_en), enast(old_wm->wm[5].plane_en),
-				      enast(old_wm->wm[6].plane_en), enast(old_wm->wm[7].plane_en),
-				      enast(old_wm->trans_wm.plane_en),
-				      enast(new_wm->wm[0].plane_en), enast(new_wm->wm[1].plane_en),
-				      enast(new_wm->wm[2].plane_en), enast(new_wm->wm[3].plane_en),
-				      enast(new_wm->wm[4].plane_en), enast(new_wm->wm[5].plane_en),
-				      enast(new_wm->wm[6].plane_en), enast(new_wm->wm[7].plane_en),
-				      enast(new_wm->trans_wm.plane_en));
-
-			DRM_DEBUG_KMS("[PLANE:%d:%s]   lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d"
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s]   level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm"
+				    " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm\n",
+				    plane->base.base.id, plane->base.name,
+				    enast(old_wm->wm[0].plane_en), enast(old_wm->wm[1].plane_en),
+				    enast(old_wm->wm[2].plane_en), enast(old_wm->wm[3].plane_en),
+				    enast(old_wm->wm[4].plane_en), enast(old_wm->wm[5].plane_en),
+				    enast(old_wm->wm[6].plane_en), enast(old_wm->wm[7].plane_en),
+				    enast(old_wm->trans_wm.plane_en),
+				    enast(new_wm->wm[0].plane_en), enast(new_wm->wm[1].plane_en),
+				    enast(new_wm->wm[2].plane_en), enast(new_wm->wm[3].plane_en),
+				    enast(new_wm->wm[4].plane_en), enast(new_wm->wm[5].plane_en),
+				    enast(new_wm->wm[6].plane_en), enast(new_wm->wm[7].plane_en),
+				    enast(new_wm->trans_wm.plane_en));
+
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s]   lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d"
 				      " -> %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d\n",
-				      plane->base.base.id, plane->base.name,
-				      enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].plane_res_l,
-				      enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].plane_res_l,
-				      enast(old_wm->wm[2].ignore_lines), old_wm->wm[2].plane_res_l,
-				      enast(old_wm->wm[3].ignore_lines), old_wm->wm[3].plane_res_l,
-				      enast(old_wm->wm[4].ignore_lines), old_wm->wm[4].plane_res_l,
-				      enast(old_wm->wm[5].ignore_lines), old_wm->wm[5].plane_res_l,
-				      enast(old_wm->wm[6].ignore_lines), old_wm->wm[6].plane_res_l,
-				      enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].plane_res_l,
-				      enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.plane_res_l,
-
-				      enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].plane_res_l,
-				      enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].plane_res_l,
-				      enast(new_wm->wm[2].ignore_lines), new_wm->wm[2].plane_res_l,
-				      enast(new_wm->wm[3].ignore_lines), new_wm->wm[3].plane_res_l,
-				      enast(new_wm->wm[4].ignore_lines), new_wm->wm[4].plane_res_l,
-				      enast(new_wm->wm[5].ignore_lines), new_wm->wm[5].plane_res_l,
-				      enast(new_wm->wm[6].ignore_lines), new_wm->wm[6].plane_res_l,
-				      enast(new_wm->wm[7].ignore_lines), new_wm->wm[7].plane_res_l,
-				      enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.plane_res_l);
-
-			DRM_DEBUG_KMS("[PLANE:%d:%s]  blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
-				      " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
-				      plane->base.base.id, plane->base.name,
-				      old_wm->wm[0].plane_res_b, old_wm->wm[1].plane_res_b,
-				      old_wm->wm[2].plane_res_b, old_wm->wm[3].plane_res_b,
-				      old_wm->wm[4].plane_res_b, old_wm->wm[5].plane_res_b,
-				      old_wm->wm[6].plane_res_b, old_wm->wm[7].plane_res_b,
-				      old_wm->trans_wm.plane_res_b,
-				      new_wm->wm[0].plane_res_b, new_wm->wm[1].plane_res_b,
-				      new_wm->wm[2].plane_res_b, new_wm->wm[3].plane_res_b,
-				      new_wm->wm[4].plane_res_b, new_wm->wm[5].plane_res_b,
-				      new_wm->wm[6].plane_res_b, new_wm->wm[7].plane_res_b,
-				      new_wm->trans_wm.plane_res_b);
-
-			DRM_DEBUG_KMS("[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
-				      " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
-				      plane->base.base.id, plane->base.name,
-				      old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc,
-				      old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc,
-				      old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc,
-				      old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc,
-				      old_wm->trans_wm.min_ddb_alloc,
-				      new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc,
-				      new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc,
-				      new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc,
-				      new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc,
-				      new_wm->trans_wm.min_ddb_alloc);
+				    plane->base.base.id, plane->base.name,
+				    enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].plane_res_l,
+				    enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].plane_res_l,
+				    enast(old_wm->wm[2].ignore_lines), old_wm->wm[2].plane_res_l,
+				    enast(old_wm->wm[3].ignore_lines), old_wm->wm[3].plane_res_l,
+				    enast(old_wm->wm[4].ignore_lines), old_wm->wm[4].plane_res_l,
+				    enast(old_wm->wm[5].ignore_lines), old_wm->wm[5].plane_res_l,
+				    enast(old_wm->wm[6].ignore_lines), old_wm->wm[6].plane_res_l,
+				    enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].plane_res_l,
+				    enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.plane_res_l,
+
+				    enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].plane_res_l,
+				    enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].plane_res_l,
+				    enast(new_wm->wm[2].ignore_lines), new_wm->wm[2].plane_res_l,
+				    enast(new_wm->wm[3].ignore_lines), new_wm->wm[3].plane_res_l,
+				    enast(new_wm->wm[4].ignore_lines), new_wm->wm[4].plane_res_l,
+				    enast(new_wm->wm[5].ignore_lines), new_wm->wm[5].plane_res_l,
+				    enast(new_wm->wm[6].ignore_lines), new_wm->wm[6].plane_res_l,
+				    enast(new_wm->wm[7].ignore_lines), new_wm->wm[7].plane_res_l,
+				    enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.plane_res_l);
+
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s]  blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
+				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
+				    plane->base.base.id, plane->base.name,
+				    old_wm->wm[0].plane_res_b, old_wm->wm[1].plane_res_b,
+				    old_wm->wm[2].plane_res_b, old_wm->wm[3].plane_res_b,
+				    old_wm->wm[4].plane_res_b, old_wm->wm[5].plane_res_b,
+				    old_wm->wm[6].plane_res_b, old_wm->wm[7].plane_res_b,
+				    old_wm->trans_wm.plane_res_b,
+				    new_wm->wm[0].plane_res_b, new_wm->wm[1].plane_res_b,
+				    new_wm->wm[2].plane_res_b, new_wm->wm[3].plane_res_b,
+				    new_wm->wm[4].plane_res_b, new_wm->wm[5].plane_res_b,
+				    new_wm->wm[6].plane_res_b, new_wm->wm[7].plane_res_b,
+				    new_wm->trans_wm.plane_res_b);
+
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
+				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
+				    plane->base.base.id, plane->base.name,
+				    old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc,
+				    old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc,
+				    old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc,
+				    old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc,
+				    old_wm->trans_wm.min_ddb_alloc,
+				    new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc,
+				    new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc,
+				    new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc,
+				    new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc,
+				    new_wm->trans_wm.min_ddb_alloc);
 		}
 	}
 }
@@ -5356,7 +5413,7 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
 		if (ret)
 			return ret;
 
-		state->active_pipe_changes = ~0;
+		state->active_pipe_changes = INTEL_INFO(dev_priv)->pipe_mask;
 
 		/*
 		 * We usually only initialize state->active_pipes if we
@@ -5382,7 +5439,7 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
 	 * to grab the lock on *all* CRTC's.
 	 */
 	if (state->active_pipe_changes || state->modeset) {
-		state->wm_results.dirty_pipes = ~0;
+		state->wm_results.dirty_pipes = INTEL_INFO(dev_priv)->pipe_mask;
 
 		ret = intel_add_all_pipes(state);
 		if (ret)
@@ -5436,7 +5493,7 @@ static int skl_wm_add_affected_planes(struct intel_atomic_state *state,
 		 * power well the hardware state will go out of sync
 		 * with the software state.
 		 */
-		if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->base) &&
+		if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi) &&
 		    skl_plane_wm_equals(dev_priv,
 					&old_crtc_state->wm.skl.optimal.planes[plane_id],
 					&new_crtc_state->wm.skl.optimal.planes[plane_id]))
@@ -5500,11 +5557,12 @@ skl_compute_wm(struct intel_atomic_state *state)
 }
 
 static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state,
-				      struct intel_crtc_state *crtc_state)
+				      struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
 	enum pipe pipe = crtc->pipe;
 
 	if ((state->wm_results.dirty_pipes & BIT(crtc->pipe)) == 0)
@@ -5514,10 +5572,11 @@ static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state,
 }
 
 static void skl_initial_wm(struct intel_atomic_state *state,
-			   struct intel_crtc_state *crtc_state)
+			   struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	struct skl_ddb_values *results = &state->wm_results;
 
 	if ((results->dirty_pipes & BIT(crtc->pipe)) == 0)
@@ -5525,8 +5584,8 @@ static void skl_initial_wm(struct intel_atomic_state *state,
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 
-	if (crtc_state->base.active_changed)
-		skl_atomic_update_crtc_wm(state, crtc_state);
+	if (crtc_state->uapi.active_changed)
+		skl_atomic_update_crtc_wm(state, crtc);
 
 	mutex_unlock(&dev_priv->wm.wm_mutex);
 }
@@ -5582,10 +5641,11 @@ static void ilk_program_watermarks(struct drm_i915_private *dev_priv)
 }
 
 static void ilk_initial_watermarks(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state)
+				   struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 	crtc->wm.active.ilk = crtc_state->wm.ilk.intermediate;
@@ -5594,10 +5654,11 @@ static void ilk_initial_watermarks(struct intel_atomic_state *state,
 }
 
 static void ilk_optimize_watermarks(struct intel_atomic_state *state,
-				    struct intel_crtc_state *crtc_state)
+				    struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	if (!crtc_state->wm.need_postvbl_update)
 		return;
@@ -5905,19 +5966,22 @@ void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		crtc_state->wm.g4x.optimal = *active;
 		crtc_state->wm.g4x.intermediate = *active;
 
-		DRM_DEBUG_KMS("Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite=%d\n",
-			      pipe_name(pipe),
-			      wm->pipe[pipe].plane[PLANE_PRIMARY],
-			      wm->pipe[pipe].plane[PLANE_CURSOR],
-			      wm->pipe[pipe].plane[PLANE_SPRITE0]);
+		drm_dbg_kms(&dev_priv->drm,
+			    "Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite=%d\n",
+			    pipe_name(pipe),
+			    wm->pipe[pipe].plane[PLANE_PRIMARY],
+			    wm->pipe[pipe].plane[PLANE_CURSOR],
+			    wm->pipe[pipe].plane[PLANE_SPRITE0]);
 	}
 
-	DRM_DEBUG_KMS("Initial SR watermarks: plane=%d, cursor=%d fbc=%d\n",
-		      wm->sr.plane, wm->sr.cursor, wm->sr.fbc);
-	DRM_DEBUG_KMS("Initial HPLL watermarks: plane=%d, SR cursor=%d fbc=%d\n",
-		      wm->hpll.plane, wm->hpll.cursor, wm->hpll.fbc);
-	DRM_DEBUG_KMS("Initial SR=%s HPLL=%s FBC=%s\n",
-		      yesno(wm->cxsr), yesno(wm->hpll_en), yesno(wm->fbc_en));
+	drm_dbg_kms(&dev_priv->drm,
+		    "Initial SR watermarks: plane=%d, cursor=%d fbc=%d\n",
+		    wm->sr.plane, wm->sr.cursor, wm->sr.fbc);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Initial HPLL watermarks: plane=%d, SR cursor=%d fbc=%d\n",
+		    wm->hpll.plane, wm->hpll.cursor, wm->hpll.fbc);
+	drm_dbg_kms(&dev_priv->drm, "Initial SR=%s HPLL=%s FBC=%s\n",
+		    yesno(wm->cxsr), yesno(wm->hpll_en), yesno(wm->fbc_en));
 }
 
 void g4x_wm_sanitize(struct drm_i915_private *dev_priv)
@@ -5938,7 +6002,7 @@ void g4x_wm_sanitize(struct drm_i915_private *dev_priv)
 		enum plane_id plane_id = plane->id;
 		int level;
 
-		if (plane_state->base.visible)
+		if (plane_state->uapi.visible)
 			continue;
 
 		for (level = 0; level < 3; level++) {
@@ -6009,8 +6073,9 @@ void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv)
 
 		if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2) &
 			      FORCE_DDR_FREQ_REQ_ACK) == 0, 3)) {
-			DRM_DEBUG_KMS("Punit not acking DDR DVFS request, "
-				      "assuming DDR DVFS is disabled\n");
+			drm_dbg_kms(&dev_priv->drm,
+				    "Punit not acking DDR DVFS request, "
+				    "assuming DDR DVFS is disabled\n");
 			dev_priv->wm.max_level = VLV_WM_LEVEL_PM5;
 		} else {
 			val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2);
@@ -6061,16 +6126,18 @@ void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		crtc_state->wm.vlv.optimal = *active;
 		crtc_state->wm.vlv.intermediate = *active;
 
-		DRM_DEBUG_KMS("Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite0=%d, sprite1=%d\n",
-			      pipe_name(pipe),
-			      wm->pipe[pipe].plane[PLANE_PRIMARY],
-			      wm->pipe[pipe].plane[PLANE_CURSOR],
-			      wm->pipe[pipe].plane[PLANE_SPRITE0],
-			      wm->pipe[pipe].plane[PLANE_SPRITE1]);
+		drm_dbg_kms(&dev_priv->drm,
+			    "Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite0=%d, sprite1=%d\n",
+			    pipe_name(pipe),
+			    wm->pipe[pipe].plane[PLANE_PRIMARY],
+			    wm->pipe[pipe].plane[PLANE_CURSOR],
+			    wm->pipe[pipe].plane[PLANE_SPRITE0],
+			    wm->pipe[pipe].plane[PLANE_SPRITE1]);
 	}
 
-	DRM_DEBUG_KMS("Initial watermarks: SR plane=%d, SR cursor=%d level=%d cxsr=%d\n",
-		      wm->sr.plane, wm->sr.cursor, wm->level, wm->cxsr);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Initial watermarks: SR plane=%d, SR cursor=%d level=%d cxsr=%d\n",
+		    wm->sr.plane, wm->sr.cursor, wm->level, wm->cxsr);
 }
 
 void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
@@ -6093,7 +6160,7 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
 		enum plane_id plane_id = plane->id;
 		int level;
 
-		if (plane_state->base.visible)
+		if (plane_state->uapi.visible)
 			continue;
 
 		for (level = 0; level < wm_state->num_levels; level++) {
@@ -6369,7 +6436,6 @@ static void cpt_init_clock_gating(struct drm_i915_private *dev_priv)
 		val &= ~TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
 		if (dev_priv->vbt.fdi_rx_polarity_inverted)
 			val |= TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
-		val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
 		val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER;
 		val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH;
 		I915_WRITE(TRANS_CHICKEN2(pipe), val);
@@ -6387,8 +6453,9 @@ static void gen6_check_mch_setup(struct drm_i915_private *dev_priv)
 
 	tmp = I915_READ(MCH_SSKPD);
 	if ((tmp & MCH_SSKPD_WM0_MASK) != MCH_SSKPD_WM0_VAL)
-		DRM_DEBUG_KMS("Wrong MCH_SSKPD value: 0x%08x This can cause underruns.\n",
-			      tmp);
+		drm_dbg_kms(&dev_priv->drm,
+			    "Wrong MCH_SSKPD value: 0x%08x This can cause underruns.\n",
+			    tmp);
 }
 
 static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -6583,6 +6650,10 @@ static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
 	u32 vd_pg_enable = 0;
 	unsigned int i;
 
+	/* Wa_1408615072:tgl */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE2,
+			 0, VSUNIT_CLKGATE_DIS_TGL);
+
 	/* This is not a WA. Enable VD HCP & MFX_ENC powergate */
 	for (i = 0; i < I915_MAX_VCS; i++) {
 		if (HAS_ENGINE(dev_priv, _VCS(i)))
@@ -7099,7 +7170,8 @@ void intel_suspend_hw(struct drm_i915_private *dev_priv)
 
 static void nop_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	DRM_DEBUG_KMS("No clock gating settings or workarounds applied.\n");
+	drm_dbg_kms(&dev_priv->drm,
+		    "No clock gating settings or workarounds applied.\n");
 }
 
 /**
@@ -7166,9 +7238,9 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 {
 	/* For cxsr */
 	if (IS_PINEVIEW(dev_priv))
-		i915_pineview_get_mem_freq(dev_priv);
+		pnv_get_mem_freq(dev_priv);
 	else if (IS_GEN(dev_priv, 5))
-		i915_ironlake_get_mem_freq(dev_priv);
+		ilk_get_mem_freq(dev_priv);
 
 	if (intel_has_sagv(dev_priv))
 		skl_setup_sagv_block_time(dev_priv);
@@ -7194,8 +7266,9 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 			dev_priv->display.optimize_watermarks =
 				ilk_optimize_watermarks;
 		} else {
-			DRM_DEBUG_KMS("Failed to read display plane latency. "
-				      "Disable CxSR\n");
+			drm_dbg_kms(&dev_priv->drm,
+				    "Failed to read display plane latency. "
+				    "Disable CxSR\n");
 		}
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		vlv_setup_wm_latency(dev_priv);
@@ -7215,7 +7288,8 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 					    dev_priv->is_ddr3,
 					    dev_priv->fsb_freq,
 					    dev_priv->mem_freq)) {
-			DRM_INFO("failed to find known CxSR latency "
+			drm_info(&dev_priv->drm,
+				 "failed to find known CxSR latency "
 				 "(found ddr%s fsb freq %d, mem freq %d), "
 				 "disabling CxSR\n",
 				 (dev_priv->is_ddr3 == 1) ? "3" : "2",
@@ -7224,7 +7298,7 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 			intel_set_memory_cxsr(dev_priv, false);
 			dev_priv->display.update_wm = NULL;
 		} else
-			dev_priv->display.update_wm = pineview_update_wm;
+			dev_priv->display.update_wm = pnv_update_wm;
 	} else if (IS_GEN(dev_priv, 4)) {
 		dev_priv->display.update_wm = i965_update_wm;
 	} else if (IS_GEN(dev_priv, 3)) {
@@ -7239,7 +7313,8 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 			dev_priv->display.get_fifo_size = i830_get_fifo_size;
 		}
 	} else {
-		DRM_ERROR("unexpected fall-through in intel_init_pm\n");
+		drm_err(&dev_priv->drm,
+			"unexpected fall-through in %s\n", __func__);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h
index b579c724b915..c06c6a846d9a 100644
--- a/drivers/gpu/drm/i915/intel_pm.h
+++ b/drivers/gpu/drm/i915/intel_pm.h
@@ -54,7 +54,7 @@ void skl_write_plane_wm(struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state);
 void skl_write_cursor_wm(struct intel_plane *plane,
 			 const struct intel_crtc_state *crtc_state);
-bool ilk_disable_lp_wm(struct drm_device *dev);
+bool ilk_disable_lp_wm(struct drm_i915_private *dev_priv);
 void intel_init_ipc(struct drm_i915_private *dev_priv);
 void intel_enable_ipc(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_region_lmem.c b/drivers/gpu/drm/i915/intel_region_lmem.c
index 583118095635..14b59b899c9b 100644
--- a/drivers/gpu/drm/i915/intel_region_lmem.c
+++ b/drivers/gpu/drm/i915/intel_region_lmem.c
@@ -51,8 +51,10 @@ static int init_fake_lmem_bar(struct intel_memory_region *mem)
 
 static void release_fake_lmem_bar(struct intel_memory_region *mem)
 {
-	if (drm_mm_node_allocated(&mem->fake_mappable))
-		drm_mm_remove_node(&mem->fake_mappable);
+	if (!drm_mm_node_allocated(&mem->fake_mappable))
+		return;
+
+	drm_mm_remove_node(&mem->fake_mappable);
 
 	dma_unmap_resource(&mem->i915->drm.pdev->dev,
 			   mem->remap_addr,
@@ -88,6 +90,8 @@ region_lmem_init(struct intel_memory_region *mem)
 	if (ret)
 		io_mapping_fini(&mem->iomap);
 
+	intel_memory_region_set_name(mem, "local");
+
 	return ret;
 }
 
@@ -121,10 +125,12 @@ intel_setup_fake_lmem(struct drm_i915_private *i915)
 					 io_start,
 					 &intel_region_lmem_ops);
 	if (!IS_ERR(mem)) {
-		DRM_INFO("Intel graphics fake LMEM: %pR\n", &mem->region);
-		DRM_INFO("Intel graphics fake LMEM IO start: %llx\n",
-			 (u64)mem->io_start);
-		DRM_INFO("Intel graphics fake LMEM size: %llx\n",
+		drm_info(&i915->drm, "Intel graphics fake LMEM: %pR\n",
+			 &mem->region);
+		drm_info(&i915->drm,
+			 "Intel graphics fake LMEM IO start: %llx\n",
+			(u64)mem->io_start);
+		drm_info(&i915->drm, "Intel graphics fake LMEM size: %llx\n",
 			 (u64)resource_size(&mem->region));
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index e06b35b844a0..cbfb7171d62d 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -105,8 +105,8 @@ static int vlv_sideband_rw(struct drm_i915_private *i915,
 	if (intel_wait_for_register(uncore,
 				    VLV_IOSF_DOORBELL_REQ, IOSF_SB_BUSY, 0,
 				    5)) {
-		DRM_DEBUG_DRIVER("IOSF sideband idle wait (%s) timed out\n",
-				 is_read ? "read" : "write");
+		drm_dbg(&i915->drm, "IOSF sideband idle wait (%s) timed out\n",
+			is_read ? "read" : "write");
 		return -EAGAIN;
 	}
 
@@ -129,8 +129,8 @@ static int vlv_sideband_rw(struct drm_i915_private *i915,
 			*val = intel_uncore_read_fw(uncore, VLV_IOSF_DATA);
 		err = 0;
 	} else {
-		DRM_DEBUG_DRIVER("IOSF sideband finish wait (%s) timed out\n",
-				 is_read ? "read" : "write");
+		drm_dbg(&i915->drm, "IOSF sideband finish wait (%s) timed out\n",
+			is_read ? "read" : "write");
 		err = -ETIMEDOUT;
 	}
 
@@ -283,7 +283,8 @@ static int intel_sbi_rw(struct drm_i915_private *i915, u16 reg,
 	if (intel_wait_for_register_fw(uncore,
 				       SBI_CTL_STAT, SBI_BUSY, 0,
 				       100)) {
-		DRM_ERROR("timeout waiting for SBI to become ready\n");
+		drm_err(&i915->drm,
+			"timeout waiting for SBI to become ready\n");
 		return -EBUSY;
 	}
 
@@ -301,12 +302,13 @@ static int intel_sbi_rw(struct drm_i915_private *i915, u16 reg,
 	if (__intel_wait_for_register_fw(uncore,
 					 SBI_CTL_STAT, SBI_BUSY, 0,
 					 100, 100, &cmd)) {
-		DRM_ERROR("timeout waiting for SBI to complete read\n");
+		drm_err(&i915->drm,
+			"timeout waiting for SBI to complete read\n");
 		return -ETIMEDOUT;
 	}
 
 	if (cmd & SBI_RESPONSE_FAIL) {
-		DRM_ERROR("error during SBI read of reg %x\n", reg);
+		drm_err(&i915->drm, "error during SBI read of reg %x\n", reg);
 		return -ENXIO;
 	}
 
@@ -426,8 +428,9 @@ int sandybridge_pcode_read(struct drm_i915_private *i915, u32 mbox,
 	mutex_unlock(&i915->sb_lock);
 
 	if (err) {
-		DRM_DEBUG_DRIVER("warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n",
-				 mbox, __builtin_return_address(0), err);
+		drm_dbg(&i915->drm,
+			"warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n",
+			mbox, __builtin_return_address(0), err);
 	}
 
 	return err;
@@ -447,8 +450,9 @@ int sandybridge_pcode_write_timeout(struct drm_i915_private *i915,
 	mutex_unlock(&i915->sb_lock);
 
 	if (err) {
-		DRM_DEBUG_DRIVER("warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n",
-				 val, mbox, __builtin_return_address(0), err);
+		drm_dbg(&i915->drm,
+			"warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n",
+			val, mbox, __builtin_return_address(0), err);
 	}
 
 	return err;
@@ -519,7 +523,8 @@ int skl_pcode_request(struct drm_i915_private *i915, u32 mbox, u32 request,
 	 * requests, and for any quirks of the PCODE firmware that delays
 	 * the request completion.
 	 */
-	DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
+	drm_dbg_kms(&i915->drm,
+		    "PCODE timeout, retrying with preemption disabled\n");
 	WARN_ON_ONCE(timeout_base_ms > 3);
 	preempt_disable();
 	ret = wait_for_atomic(COND, 50);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 94a97bf8c021..5f2cf6f43b8b 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -359,7 +359,8 @@ static void __gen6_gt_wait_for_fifo(struct intel_uncore *uncore)
 		if (wait_for_atomic((n = fifo_free_entries(uncore)) >
 				    GT_FIFO_NUM_RESERVED_ENTRIES,
 				    GT_FIFO_TIMEOUT_MS)) {
-			DRM_DEBUG("GT_FIFO timeout, entries: %u\n", n);
+			drm_dbg(&uncore->i915->drm,
+				"GT_FIFO timeout, entries: %u\n", n);
 			return;
 		}
 	}
@@ -432,7 +433,7 @@ intel_uncore_forcewake_reset(struct intel_uncore *uncore)
 			break;
 
 		if (--retry_count == 0) {
-			DRM_ERROR("Timed out waiting for forcewake timers to finish\n");
+			drm_err(&uncore->i915->drm, "Timed out waiting for forcewake timers to finish\n");
 			break;
 		}
 
@@ -490,7 +491,7 @@ gen6_check_for_fifo_debug(struct intel_uncore *uncore)
 	fifodbg = __raw_uncore_read32(uncore, GTFIFODBG);
 
 	if (unlikely(fifodbg)) {
-		DRM_DEBUG_DRIVER("GTFIFODBG = 0x08%x\n", fifodbg);
+		drm_dbg(&uncore->i915->drm, "GTFIFODBG = 0x08%x\n", fifodbg);
 		__raw_uncore_write32(uncore, GTFIFODBG, fifodbg);
 	}
 
@@ -562,7 +563,7 @@ void intel_uncore_resume_early(struct intel_uncore *uncore)
 	unsigned int restore_forcewake;
 
 	if (intel_uncore_unclaimed_mmio(uncore))
-		DRM_DEBUG("unclaimed mmio detected on resume, clearing\n");
+		drm_dbg(&uncore->i915->drm, "unclaimed mmio detected on resume, clearing\n");
 
 	if (!intel_uncore_has_forcewake(uncore))
 		return;
@@ -1595,8 +1596,8 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore)
 		spin_unlock_irq(&uncore->lock);
 
 		if (!(ecobus & FORCEWAKE_MT_ENABLE)) {
-			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
-			DRM_INFO("when using vblank-synced partial screen updates.\n");
+			drm_info(&i915->drm, "No MT forcewake available on Ivybridge, this can result in issues\n");
+			drm_info(&i915->drm, "when using vblank-synced partial screen updates.\n");
 			fw_domain_fini(uncore, FW_DOMAIN_ID_RENDER);
 			fw_domain_init(uncore, FW_DOMAIN_ID_RENDER,
 				       FORCEWAKE, FORCEWAKE_ACK);
@@ -1683,8 +1684,7 @@ static int uncore_mmio_setup(struct intel_uncore *uncore)
 		mmio_size = 2 * 1024 * 1024;
 	uncore->regs = pci_iomap(pdev, mmio_bar, mmio_size);
 	if (uncore->regs == NULL) {
-		DRM_ERROR("failed to map registers\n");
-
+		drm_err(&i915->drm, "failed to map registers\n");
 		return -EIO;
 	}
 
@@ -1807,7 +1807,7 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore)
 
 	/* clear out unclaimed reg detection bit */
 	if (intel_uncore_unclaimed_mmio(uncore))
-		DRM_DEBUG("unclaimed mmio detected on uncore init, clearing\n");
+		drm_dbg(&i915->drm, "unclaimed mmio detected on uncore init, clearing\n");
 
 	return 0;
 
@@ -2072,9 +2072,10 @@ intel_uncore_arm_unclaimed_mmio_detection(struct intel_uncore *uncore)
 
 	if (unlikely(check_for_unclaimed_mmio(uncore))) {
 		if (!i915_modparams.mmio_debug) {
-			DRM_DEBUG("Unclaimed register detected, "
-				  "enabling oneshot unclaimed register reporting. "
-				  "Please use i915.mmio_debug=N for more information.\n");
+			drm_dbg(&uncore->i915->drm,
+				"Unclaimed register detected, "
+				"enabling oneshot unclaimed register reporting. "
+				"Please use i915.mmio_debug=N for more information.\n");
 			i915_modparams.mmio_debug++;
 		}
 		uncore->debug->unclaimed_mmio_check--;
diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c
index 59aa1b6f1827..8fbf6f4d3f26 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.c
+++ b/drivers/gpu/drm/i915/intel_wakeref.c
@@ -95,16 +95,17 @@ static void __intel_wakeref_put_work(struct work_struct *wrk)
 void __intel_wakeref_init(struct intel_wakeref *wf,
 			  struct intel_runtime_pm *rpm,
 			  const struct intel_wakeref_ops *ops,
-			  struct lock_class_key *key)
+			  struct intel_wakeref_lockclass *key)
 {
 	wf->rpm = rpm;
 	wf->ops = ops;
 
-	__mutex_init(&wf->mutex, "wakeref", key);
+	__mutex_init(&wf->mutex, "wakeref.mutex", &key->mutex);
 	atomic_set(&wf->count, 0);
 	wf->wakeref = 0;
 
 	INIT_WORK(&wf->work, __intel_wakeref_put_work);
+	lockdep_init_map(&wf->work.lockdep_map, "wakeref.work", &key->work, 0);
 }
 
 int intel_wakeref_wait_for_idle(struct intel_wakeref *wf)
diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h
index da6e8fd506e6..7d1e676b71ef 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.h
+++ b/drivers/gpu/drm/i915/intel_wakeref.h
@@ -44,12 +44,17 @@ struct intel_wakeref {
 	struct work_struct work;
 };
 
+struct intel_wakeref_lockclass {
+	struct lock_class_key mutex;
+	struct lock_class_key work;
+};
+
 void __intel_wakeref_init(struct intel_wakeref *wf,
 			  struct intel_runtime_pm *rpm,
 			  const struct intel_wakeref_ops *ops,
-			  struct lock_class_key *key);
+			  struct intel_wakeref_lockclass *key);
 #define intel_wakeref_init(wf, rpm, ops) do {				\
-	static struct lock_class_key __key;				\
+	static struct intel_wakeref_lockclass __key;			\
 									\
 	__intel_wakeref_init((wf), (rpm), (ops), &__key);		\
 } while (0)
@@ -59,9 +64,7 @@ void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags);
 
 /**
  * intel_wakeref_get: Acquire the wakeref
- * @i915: the drm_i915_private device
  * @wf: the wakeref
- * @fn: callback for acquired the wakeref, called only on first acquire.
  *
  * Acquire a hold on the wakeref. The first user to do so, will acquire
  * the runtime pm wakeref and then call the @fn underneath the wakeref
@@ -76,6 +79,7 @@ void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags);
 static inline int
 intel_wakeref_get(struct intel_wakeref *wf)
 {
+	might_sleep();
 	if (unlikely(!atomic_inc_not_zero(&wf->count)))
 		return __intel_wakeref_get_first(wf);
 
@@ -83,6 +87,22 @@ intel_wakeref_get(struct intel_wakeref *wf)
 }
 
 /**
+ * __intel_wakeref_get: Acquire the wakeref, again
+ * @wf: the wakeref
+ *
+ * Increment the wakeref counter, only valid if it is already held by
+ * the caller.
+ *
+ * See intel_wakeref_get().
+ */
+static inline void
+__intel_wakeref_get(struct intel_wakeref *wf)
+{
+	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
+	atomic_inc(&wf->count);
+}
+
+/**
  * intel_wakeref_get_if_in_use: Acquire the wakeref
  * @wf: the wakeref
  *
diff --git a/drivers/gpu/drm/i915/oa/Makefile b/drivers/gpu/drm/i915/oa/Makefile
deleted file mode 100644
index df028e2b0d64..000000000000
--- a/drivers/gpu/drm/i915/oa/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: MIT
-
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 260b0ee5d1e3..ef572a0c2566 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -99,7 +99,7 @@ __live_active_setup(struct drm_i915_private *i915)
 	for_each_uabi_engine(engine, i915) {
 		struct i915_request *rq;
 
-		rq = i915_request_create(engine->kernel_context);
+		rq = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			break;
@@ -155,7 +155,11 @@ static int live_active_wait(void *arg)
 
 	i915_active_wait(&active->base);
 	if (!READ_ONCE(active->retired)) {
+		struct drm_printer p = drm_err_printer(__func__);
+
 		pr_err("i915_active not retired after waiting!\n");
+		i915_active_print(&active->base, &p);
+
 		err = -EINVAL;
 	}
 
@@ -184,7 +188,11 @@ static int live_active_retire(void *arg)
 		err = -EIO;
 
 	if (!READ_ONCE(active->retired)) {
+		struct drm_printer p = drm_err_printer(__func__);
+
 		pr_err("i915_active not retired after flushing!\n");
+		i915_active_print(&active->base, &p);
+
 		err = -EINVAL;
 	}
 
@@ -250,3 +258,36 @@ void i915_active_print(struct i915_active *ref, struct drm_printer *m)
 		i915_active_release(ref);
 	}
 }
+
+static void spin_unlock_wait(spinlock_t *lock)
+{
+	spin_lock_irq(lock);
+	spin_unlock_irq(lock);
+}
+
+void i915_active_unlock_wait(struct i915_active *ref)
+{
+	if (i915_active_acquire_if_busy(ref)) {
+		struct active_node *it, *n;
+
+		rcu_read_lock();
+		rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
+			struct dma_fence *f;
+
+			/* Wait for all active callbacks */
+			f = rcu_dereference(it->base.fence);
+			if (f)
+				spin_unlock_wait(f->lock);
+		}
+		rcu_read_unlock();
+
+		i915_active_release(ref);
+	}
+
+	/* And wait for the retire callback */
+	spin_lock_irq(&ref->tree_lock);
+	spin_unlock_irq(&ref->tree_lock);
+
+	/* ... which may have been on a thread instead */
+	flush_work(&ref->work);
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index d83f6bf6d9d4..78f36faf2bbe 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -9,6 +9,7 @@
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_pm.h"
 
 #include "i915_selftest.h"
 
@@ -123,8 +124,6 @@ static void pm_resume(struct drm_i915_private *i915)
 	 * that runtime-pm just works.
 	 */
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
-		intel_gt_sanitize(&i915->gt, false);
-
 		i915_gem_restore_gtt_mappings(i915);
 		i915_gem_restore_fences(&i915->ggtt);
 
@@ -136,7 +135,7 @@ static int igt_gem_suspend(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_gem_context *ctx;
-	struct drm_file *file;
+	struct file *file;
 	int err;
 
 	file = mock_file(i915);
@@ -163,7 +162,7 @@ static int igt_gem_suspend(void *arg)
 
 	err = switch_to_context(ctx);
 out:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -171,7 +170,7 @@ static int igt_gem_hibernate(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_gem_context *ctx;
-	struct drm_file *file;
+	struct file *file;
 	int err;
 
 	file = mock_file(i915);
@@ -198,7 +197,7 @@ static int igt_gem_hibernate(void *arg)
 
 	err = switch_to_context(ctx);
 out:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 42e948144f1b..06ef88510209 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -198,8 +198,8 @@ static int igt_overcommit(void *arg)
 	quirk_add(obj, &objects);
 
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
-	if (!IS_ERR(vma) || PTR_ERR(vma) != -ENOSPC) {
-		pr_err("Failed to evict+insert, i915_gem_object_ggtt_pin returned err=%d\n", (int)PTR_ERR(vma));
+	if (vma != ERR_PTR(-ENOSPC)) {
+		pr_err("Failed to evict+insert, i915_gem_object_ggtt_pin returned err=%d\n", (int)PTR_ERR_OR_ZERO(vma));
 		err = -EINVAL;
 		goto cleanup;
 	}
@@ -466,7 +466,7 @@ static int igt_evict_contexts(void *arg)
 	/* Overfill the GGTT with context objects and so try to evict one. */
 	for_each_engine(engine, gt, id) {
 		struct i915_sw_fence fence;
-		struct drm_file *file;
+		struct file *file;
 
 		file = mock_file(i915);
 		if (IS_ERR(file)) {
@@ -515,7 +515,7 @@ static int igt_evict_contexts(void *arg)
 		pr_info("Submitted %lu contexts/requests on %s\n",
 			count, engine->name);
 
-		mock_file_free(i915, file);
+		fput(file);
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 3f7e80fb3bbd..b342bef5e7c9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -34,6 +34,7 @@
 
 #include "mock_drm.h"
 #include "mock_gem_device.h"
+#include "mock_gtt.h"
 #include "igt_flush_test.h"
 
 static void cleanup_freed_objects(struct drm_i915_private *i915)
@@ -151,7 +152,7 @@ static int igt_ppgtt_alloc(void *arg)
 	if (!HAS_PPGTT(dev_priv))
 		return 0;
 
-	ppgtt = __ppgtt_create(dev_priv);
+	ppgtt = i915_ppgtt_create(&dev_priv->gt);
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
@@ -206,16 +207,17 @@ err_ppgtt_cleanup:
 	return err;
 }
 
-static int lowlevel_hole(struct drm_i915_private *i915,
-			 struct i915_address_space *vm,
+static int lowlevel_hole(struct i915_address_space *vm,
 			 u64 hole_start, u64 hole_end,
 			 unsigned long end_time)
 {
 	I915_RND_STATE(seed_prng);
+	struct i915_vma *mock_vma;
 	unsigned int size;
-	struct i915_vma mock_vma;
 
-	memset(&mock_vma, 0, sizeof(struct i915_vma));
+	mock_vma = kzalloc(sizeof(*mock_vma), GFP_KERNEL);
+	if (!mock_vma)
+		return -ENOMEM;
 
 	/* Keep creating larger objects until one cannot fit into the hole */
 	for (size = 12; (hole_end - hole_start) >> size; size++) {
@@ -239,8 +241,10 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			if (order)
 				break;
 		} while (count >>= 1);
-		if (!count)
+		if (!count) {
+			kfree(mock_vma);
 			return -ENOMEM;
+		}
 		GEM_BUG_ON(!order);
 
 		GEM_BUG_ON(count * BIT_ULL(size) > vm->total);
@@ -252,7 +256,7 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 		 * memory. We expect to hit -ENOMEM.
 		 */
 
-		obj = fake_dma_object(i915, BIT_ULL(size));
+		obj = fake_dma_object(vm->i915, BIT_ULL(size));
 		if (IS_ERR(obj)) {
 			kfree(order);
 			break;
@@ -283,12 +287,12 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			    vm->allocate_va_range(vm, addr, BIT_ULL(size)))
 				break;
 
-			mock_vma.pages = obj->mm.pages;
-			mock_vma.node.size = BIT_ULL(size);
-			mock_vma.node.start = addr;
+			mock_vma->pages = obj->mm.pages;
+			mock_vma->node.size = BIT_ULL(size);
+			mock_vma->node.start = addr;
 
-			with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-				vm->insert_entries(vm, &mock_vma,
+			with_intel_runtime_pm(vm->gt->uncore->rpm, wakeref)
+				vm->insert_entries(vm, mock_vma,
 						   I915_CACHE_NONE, 0);
 		}
 		count = n;
@@ -299,7 +303,7 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			intel_wakeref_t wakeref;
 
 			GEM_BUG_ON(addr + BIT_ULL(size) > vm->total);
-			with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+			with_intel_runtime_pm(vm->gt->uncore->rpm, wakeref)
 				vm->clear_range(vm, addr, BIT_ULL(size));
 		}
 
@@ -308,9 +312,10 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 
 		kfree(order);
 
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
+	kfree(mock_vma);
 	return 0;
 }
 
@@ -335,8 +340,7 @@ static void close_object_list(struct list_head *objects,
 	}
 }
 
-static int fill_hole(struct drm_i915_private *i915,
-		     struct i915_address_space *vm,
+static int fill_hole(struct i915_address_space *vm,
 		     u64 hole_start, u64 hole_end,
 		     unsigned long end_time)
 {
@@ -369,7 +373,7 @@ static int fill_hole(struct drm_i915_private *i915,
 				{ }
 			}, *p;
 
-			obj = fake_dma_object(i915, full_size);
+			obj = fake_dma_object(vm->i915, full_size);
 			if (IS_ERR(obj))
 				break;
 
@@ -537,7 +541,7 @@ static int fill_hole(struct drm_i915_private *i915,
 		}
 
 		close_object_list(&objects, vm);
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
 	return 0;
@@ -547,8 +551,7 @@ err:
 	return err;
 }
 
-static int walk_hole(struct drm_i915_private *i915,
-		     struct i915_address_space *vm,
+static int walk_hole(struct i915_address_space *vm,
 		     u64 hole_start, u64 hole_end,
 		     unsigned long end_time)
 {
@@ -570,7 +573,7 @@ static int walk_hole(struct drm_i915_private *i915,
 		u64 addr;
 		int err = 0;
 
-		obj = fake_dma_object(i915, size << PAGE_SHIFT);
+		obj = fake_dma_object(vm->i915, size << PAGE_SHIFT);
 		if (IS_ERR(obj))
 			break;
 
@@ -625,14 +628,13 @@ err_put:
 		if (err)
 			return err;
 
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
 	return 0;
 }
 
-static int pot_hole(struct drm_i915_private *i915,
-		    struct i915_address_space *vm,
+static int pot_hole(struct i915_address_space *vm,
 		    u64 hole_start, u64 hole_end,
 		    unsigned long end_time)
 {
@@ -646,7 +648,7 @@ static int pot_hole(struct drm_i915_private *i915,
 	if (i915_is_ggtt(vm))
 		flags |= PIN_GLOBAL;
 
-	obj = i915_gem_object_create_internal(i915, 2 * I915_GTT_PAGE_SIZE);
+	obj = i915_gem_object_create_internal(vm->i915, 2 * I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -707,8 +709,7 @@ err_obj:
 	return err;
 }
 
-static int drunk_hole(struct drm_i915_private *i915,
-		      struct i915_address_space *vm,
+static int drunk_hole(struct i915_address_space *vm,
 		      u64 hole_start, u64 hole_end,
 		      unsigned long end_time)
 {
@@ -753,7 +754,7 @@ static int drunk_hole(struct drm_i915_private *i915,
 		 * memory. We expect to hit -ENOMEM.
 		 */
 
-		obj = fake_dma_object(i915, BIT_ULL(size));
+		obj = fake_dma_object(vm->i915, BIT_ULL(size));
 		if (IS_ERR(obj)) {
 			kfree(order);
 			break;
@@ -811,14 +812,13 @@ err_obj:
 		if (err)
 			return err;
 
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
 	return 0;
 }
 
-static int __shrink_hole(struct drm_i915_private *i915,
-			 struct i915_address_space *vm,
+static int __shrink_hole(struct i915_address_space *vm,
 			 u64 hole_start, u64 hole_end,
 			 unsigned long end_time)
 {
@@ -835,7 +835,7 @@ static int __shrink_hole(struct drm_i915_private *i915,
 		u64 size = BIT_ULL(order++);
 
 		size = min(size, hole_end - addr);
-		obj = fake_dma_object(i915, size);
+		obj = fake_dma_object(vm->i915, size);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
 			break;
@@ -889,12 +889,11 @@ static int __shrink_hole(struct drm_i915_private *i915,
 	}
 
 	close_object_list(&objects, vm);
-	cleanup_freed_objects(i915);
+	cleanup_freed_objects(vm->i915);
 	return err;
 }
 
-static int shrink_hole(struct drm_i915_private *i915,
-		       struct i915_address_space *vm,
+static int shrink_hole(struct i915_address_space *vm,
 		       u64 hole_start, u64 hole_end,
 		       unsigned long end_time)
 {
@@ -906,7 +905,7 @@ static int shrink_hole(struct drm_i915_private *i915,
 
 	for_each_prime_number_from(prime, 0, ULONG_MAX - 1) {
 		vm->fault_attr.interval = prime;
-		err = __shrink_hole(i915, vm, hole_start, hole_end, end_time);
+		err = __shrink_hole(vm, hole_start, hole_end, end_time);
 		if (err)
 			break;
 	}
@@ -916,8 +915,7 @@ static int shrink_hole(struct drm_i915_private *i915,
 	return err;
 }
 
-static int shrink_boom(struct drm_i915_private *i915,
-		       struct i915_address_space *vm,
+static int shrink_boom(struct i915_address_space *vm,
 		       u64 hole_start, u64 hole_end,
 		       unsigned long end_time)
 {
@@ -939,7 +937,7 @@ static int shrink_boom(struct drm_i915_private *i915,
 		unsigned int size = sizes[i];
 		struct i915_vma *vma;
 
-		purge = fake_dma_object(i915, size);
+		purge = fake_dma_object(vm->i915, size);
 		if (IS_ERR(purge))
 			return PTR_ERR(purge);
 
@@ -956,7 +954,7 @@ static int shrink_boom(struct drm_i915_private *i915,
 		/* Should now be ripe for purging */
 		i915_vma_unpin(vma);
 
-		explode = fake_dma_object(i915, size);
+		explode = fake_dma_object(vm->i915, size);
 		if (IS_ERR(explode)) {
 			err = PTR_ERR(explode);
 			goto err_purge;
@@ -982,7 +980,7 @@ static int shrink_boom(struct drm_i915_private *i915,
 		i915_gem_object_put(explode);
 
 		memset(&vm->fault_attr, 0, sizeof(vm->fault_attr));
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
 	return 0;
@@ -996,14 +994,13 @@ err_purge:
 }
 
 static int exercise_ppgtt(struct drm_i915_private *dev_priv,
-			  int (*func)(struct drm_i915_private *i915,
-				      struct i915_address_space *vm,
+			  int (*func)(struct i915_address_space *vm,
 				      u64 hole_start, u64 hole_end,
 				      unsigned long end_time))
 {
-	struct drm_file *file;
 	struct i915_ppgtt *ppgtt;
 	IGT_TIMEOUT(end_time);
+	struct file *file;
 	int err;
 
 	if (!HAS_FULL_PPGTT(dev_priv))
@@ -1013,7 +1010,7 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ppgtt = i915_ppgtt_create(dev_priv);
+	ppgtt = i915_ppgtt_create(&dev_priv->gt);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_free;
@@ -1021,12 +1018,12 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 	GEM_BUG_ON(offset_in_page(ppgtt->vm.total));
 	GEM_BUG_ON(!atomic_read(&ppgtt->vm.open));
 
-	err = func(dev_priv, &ppgtt->vm, 0, ppgtt->vm.total, end_time);
+	err = func(&ppgtt->vm, 0, ppgtt->vm.total, end_time);
 
 	i915_vm_put(&ppgtt->vm);
 
 out_free:
-	mock_file_free(dev_priv, file);
+	fput(file);
 	return err;
 }
 
@@ -1077,8 +1074,7 @@ static int sort_holes(void *priv, struct list_head *A, struct list_head *B)
 }
 
 static int exercise_ggtt(struct drm_i915_private *i915,
-			 int (*func)(struct drm_i915_private *i915,
-				     struct i915_address_space *vm,
+			 int (*func)(struct i915_address_space *vm,
 				     u64 hole_start, u64 hole_end,
 				     unsigned long end_time))
 {
@@ -1100,7 +1096,7 @@ restart:
 		if (hole_start >= hole_end)
 			continue;
 
-		err = func(i915, &ggtt->vm, hole_start, hole_end, end_time);
+		err = func(&ggtt->vm, hole_start, hole_end, end_time);
 		if (err)
 			break;
 
@@ -1161,11 +1157,13 @@ static int igt_ggtt_page(void *arg)
 		goto out_free;
 
 	memset(&tmp, 0, sizeof(tmp));
+	mutex_lock(&ggtt->vm.mutex);
 	err = drm_mm_insert_node_in_range(&ggtt->vm.mm, &tmp,
 					  count * PAGE_SIZE, 0,
 					  I915_COLOR_UNEVICTABLE,
 					  0, ggtt->mappable_end,
 					  DRM_MM_INSERT_LOW);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err)
 		goto out_unpin;
 
@@ -1217,7 +1215,9 @@ static int igt_ggtt_page(void *arg)
 out_remove:
 	ggtt->vm.clear_range(&ggtt->vm, tmp.start, tmp.size);
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	mutex_lock(&ggtt->vm.mutex);
 	drm_mm_remove_node(&tmp);
+	mutex_unlock(&ggtt->vm.mutex);
 out_unpin:
 	i915_gem_object_unpin_pages(obj);
 out_free:
@@ -1243,8 +1243,7 @@ static void track_vma_bind(struct i915_vma *vma)
 }
 
 static int exercise_mock(struct drm_i915_private *i915,
-			 int (*func)(struct drm_i915_private *i915,
-				     struct i915_address_space *vm,
+			 int (*func)(struct i915_address_space *vm,
 				     u64 hole_start, u64 hole_end,
 				     unsigned long end_time))
 {
@@ -1259,7 +1258,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 		return -ENOMEM;
 
 	vm = i915_gem_context_get_vm_rcu(ctx);
-	err = func(i915, vm, 0, min(vm->total, limit), end_time);
+	err = func(vm, 0, min(vm->total, limit), end_time);
 	i915_vm_put(vm);
 
 	mock_context_close(ctx);
@@ -1782,9 +1781,9 @@ static int igt_cs_tlb(void *arg)
 	struct i915_address_space *vm;
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
-	struct drm_file *file;
 	struct i915_vma *vma;
 	I915_RND_STATE(prng);
+	struct file *file;
 	unsigned int i;
 	u32 *result;
 	u32 *batch;
@@ -2022,7 +2021,7 @@ out_put_bbe:
 out_vm:
 	i915_vm_put(vm);
 out_unlock:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 4b3cac73e291..34138c7bdd15 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -1,5 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* List each unit test as selftest(name, function)
+
+#ifndef selftest
+#define selftest(x, y)
+#endif
+
+/*
+ * List each unit test as selftest(name, function)
  *
  * The name is used as both an enum and expanded as subtest__name to create
  * a module parameter. It must be unique and legal for a C identifier.
@@ -16,6 +22,7 @@ selftest(gt_engines, intel_engine_live_selftests)
 selftest(gt_timelines, intel_timeline_live_selftests)
 selftest(gt_contexts, intel_context_live_selftests)
 selftest(gt_lrc, intel_lrc_live_selftests)
+selftest(gt_mocs, intel_mocs_live_selftests)
 selftest(gt_pm, intel_gt_pm_live_selftests)
 selftest(gt_heartbeat, intel_heartbeat_live_selftests)
 selftest(requests, i915_request_live_selftests)
@@ -36,5 +43,6 @@ selftest(reset, intel_reset_live_selftests)
 selftest(memory_region, intel_memory_region_live_selftests)
 selftest(hangcheck, intel_hangcheck_live_selftests)
 selftest(execlists, intel_execlists_live_selftests)
-selftest(guc, intel_guc_live_selftest)
 selftest(perf, i915_perf_live_selftests)
+/* Here be dragons: keep last to run last! */
+selftest(late_gt_pm, intel_gt_pm_late_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index aa5a0e7f5d9e..5b39bab4da1d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -1,5 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* List each unit test as selftest(name, function)
+
+#ifndef selftest
+#define selftest(x, y)
+#endif
+
+/*
+ * List each unit test as selftest(name, function)
  *
  * The name is used as both an enum and expanded as subtest__name to create
  * a module parameter. It must be unique and legal for a C identifier.
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index aabd07f67e49..d1a1568c47ba 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -132,7 +132,7 @@ static int live_noa_delay(void *arg)
 	for (i = 0; i < 4; i++)
 		intel_write_status_page(stream->engine, 0x100 + i, 0);
 
-	rq = i915_request_create(stream->engine->kernel_context);
+	rq = intel_engine_create_kernel_request(stream->engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto out;
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
new file mode 100644
index 000000000000..5a577a1332f5
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef selftest
+#define selftest(x, y)
+#endif
+
+/*
+ * List each unit test as selftest(name, function)
+ *
+ * The name is used as both an enum and expanded as subtest__name to create
+ * a module parameter. It must be unique and legal for a C identifier.
+ *
+ * The function should be of type int function(void). It may be conditionally
+ * compiled using #if IS_ENABLED(DRM_I915_SELFTEST).
+ *
+ * Tests are executed in order by igt/i915_selftest
+ */
+selftest(engine_cs, intel_engine_cs_perf_selftests)
+selftest(blt, i915_gem_object_blt_perf_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 8618a4dc0701..f89d9c42f1fa 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -27,11 +27,13 @@
 #include "gem/i915_gem_pm.h"
 #include "gem/selftests/mock_context.h"
 
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 
 #include "i915_random.h"
 #include "i915_selftest.h"
 #include "igt_live_test.h"
+#include "igt_spinner.h"
 #include "lib_sw_fence.h"
 
 #include "mock_drm.h"
@@ -540,6 +542,7 @@ static int live_nop_request(void *arg)
 		if (err)
 			return err;
 
+		intel_engine_pm_get(engine);
 		for_each_prime_number_from(prime, 1, 8192) {
 			struct i915_request *request = NULL;
 
@@ -578,6 +581,7 @@ static int live_nop_request(void *arg)
 			if (__igt_timeout(end_time, NULL))
 				break;
 		}
+		intel_engine_pm_put(engine);
 
 		err = igt_live_test_end(&t);
 		if (err)
@@ -692,10 +696,13 @@ static int live_empty_request(void *arg)
 		if (err)
 			goto out_batch;
 
+		intel_engine_pm_get(engine);
+
 		/* Warmup / preload */
 		request = empty_request(engine, batch);
 		if (IS_ERR(request)) {
 			err = PTR_ERR(request);
+			intel_engine_pm_put(engine);
 			goto out_batch;
 		}
 		i915_request_wait(request, 0, MAX_SCHEDULE_TIMEOUT);
@@ -708,6 +715,7 @@ static int live_empty_request(void *arg)
 				request = empty_request(engine, batch);
 				if (IS_ERR(request)) {
 					err = PTR_ERR(request);
+					intel_engine_pm_put(engine);
 					goto out_batch;
 				}
 			}
@@ -721,6 +729,7 @@ static int live_empty_request(void *arg)
 				break;
 		}
 		i915_request_put(request);
+		intel_engine_pm_put(engine);
 
 		err = igt_live_test_end(&t);
 		if (err)
@@ -740,10 +749,8 @@ out_batch:
 
 static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 {
-	struct i915_gem_context *ctx = i915->kernel_context;
 	struct drm_i915_gem_object *obj;
 	const int gen = INTEL_GEN(i915);
-	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	u32 *cmd;
 	int err;
@@ -752,9 +759,7 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
-	vma = i915_vma_instance(obj, vm, NULL);
-	i915_vm_put(vm);
+	vma = i915_vma_instance(obj, i915->gt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err;
@@ -845,7 +850,7 @@ static int live_all_engines(void *arg)
 
 	idx = 0;
 	for_each_uabi_engine(engine, i915) {
-		request[idx] = i915_request_create(engine->kernel_context);
+		request[idx] = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(request[idx])) {
 			err = PTR_ERR(request[idx]);
 			pr_err("%s: Request allocation failed with err=%d\n",
@@ -962,7 +967,7 @@ static int live_sequential_engines(void *arg)
 			goto out_free;
 		}
 
-		request[idx] = i915_request_create(engine->kernel_context);
+		request[idx] = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(request[idx])) {
 			err = PTR_ERR(request[idx]);
 			pr_err("%s: Request allocation failed for %s with err=%d\n",
@@ -1067,15 +1072,18 @@ static int __live_parallel_engine1(void *arg)
 	struct intel_engine_cs *engine = arg;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
+	int err = 0;
 
 	count = 0;
+	intel_engine_pm_get(engine);
 	do {
 		struct i915_request *rq;
-		int err;
 
 		rq = i915_request_create(engine->kernel_context);
-		if (IS_ERR(rq))
-			return PTR_ERR(rq);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
 
 		i915_request_get(rq);
 		i915_request_add(rq);
@@ -1085,13 +1093,14 @@ static int __live_parallel_engine1(void *arg)
 			err = -ETIME;
 		i915_request_put(rq);
 		if (err)
-			return err;
+			break;
 
 		count++;
 	} while (!__igt_timeout(end_time, NULL));
+	intel_engine_pm_put(engine);
 
 	pr_info("%s: %lu request + sync\n", engine->name, count);
-	return 0;
+	return err;
 }
 
 static int __live_parallel_engineN(void *arg)
@@ -1099,21 +1108,100 @@ static int __live_parallel_engineN(void *arg)
 	struct intel_engine_cs *engine = arg;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
+	int err = 0;
 
 	count = 0;
+	intel_engine_pm_get(engine);
 	do {
 		struct i915_request *rq;
 
 		rq = i915_request_create(engine->kernel_context);
-		if (IS_ERR(rq))
-			return PTR_ERR(rq);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
 
 		i915_request_add(rq);
 		count++;
 	} while (!__igt_timeout(end_time, NULL));
+	intel_engine_pm_put(engine);
 
 	pr_info("%s: %lu requests\n", engine->name, count);
-	return 0;
+	return err;
+}
+
+static bool wake_all(struct drm_i915_private *i915)
+{
+	if (atomic_dec_and_test(&i915->selftest.counter)) {
+		wake_up_var(&i915->selftest.counter);
+		return true;
+	}
+
+	return false;
+}
+
+static int wait_for_all(struct drm_i915_private *i915)
+{
+	if (wake_all(i915))
+		return 0;
+
+	if (wait_var_event_timeout(&i915->selftest.counter,
+				   !atomic_read(&i915->selftest.counter),
+				   i915_selftest.timeout_jiffies))
+		return 0;
+
+	return -ETIME;
+}
+
+static int __live_parallel_spin(void *arg)
+{
+	struct intel_engine_cs *engine = arg;
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	int err = 0;
+
+	/*
+	 * Create a spinner running for eternity on each engine. If a second
+	 * spinner is incorrectly placed on the same engine, it will not be
+	 * able to start in time.
+	 */
+
+	if (igt_spinner_init(&spin, engine->gt)) {
+		wake_all(engine->i915);
+		return -ENOMEM;
+	}
+
+	intel_engine_pm_get(engine);
+	rq = igt_spinner_create_request(&spin,
+					engine->kernel_context,
+					MI_NOOP); /* no preemption */
+	intel_engine_pm_put(engine);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		if (err == -ENODEV)
+			err = 0;
+		wake_all(engine->i915);
+		goto out_spin;
+	}
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (igt_wait_for_spinner(&spin, rq)) {
+		/* Occupy this engine for the whole test */
+		err = wait_for_all(engine->i915);
+	} else {
+		pr_err("Failed to start spinner on %s\n", engine->name);
+		err = -EINVAL;
+	}
+	igt_spinner_end(&spin);
+
+	if (err == 0 && i915_request_wait(rq, 0, HZ / 5) < 0)
+		err = -EIO;
+	i915_request_put(rq);
+
+out_spin:
+	igt_spinner_fini(&spin);
+	return err;
 }
 
 static int live_parallel_engines(void *arg)
@@ -1122,6 +1210,7 @@ static int live_parallel_engines(void *arg)
 	static int (* const func[])(void *arg) = {
 		__live_parallel_engine1,
 		__live_parallel_engineN,
+		__live_parallel_spin,
 		NULL,
 	};
 	const unsigned int nengines = num_uabi_engines(i915);
@@ -1140,13 +1229,17 @@ static int live_parallel_engines(void *arg)
 		return -ENOMEM;
 
 	for (fn = func; !err && *fn; fn++) {
+		char name[KSYM_NAME_LEN];
 		struct igt_live_test t;
 		unsigned int idx;
 
-		err = igt_live_test_begin(&t, i915, __func__, "");
+		snprintf(name, sizeof(name), "%pS", fn);
+		err = igt_live_test_begin(&t, i915, __func__, name);
 		if (err)
 			break;
 
+		atomic_set(&i915->selftest.counter, nengines);
+
 		idx = 0;
 		for_each_uabi_engine(engine, i915) {
 			tsk[idx] = kthread_run(*fn, engine,
@@ -1230,9 +1323,9 @@ static int live_breadcrumbs_smoketest(void *arg)
 	struct task_struct **threads;
 	struct igt_live_test live;
 	intel_wakeref_t wakeref;
-	struct drm_file *file;
 	struct smoketest *smoke;
 	unsigned int n, idx;
+	struct file *file;
 	int ret = 0;
 
 	/*
@@ -1354,7 +1447,7 @@ out_threads:
 out_smoke:
 	kfree(smoke);
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 out_rpm:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index a6cca4ad96f6..d3bf9eefb682 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -57,6 +57,12 @@ enum {
 #undef selftest
 };
 
+enum {
+#define selftest(name, func) perf_##name,
+#include "i915_perf_selftests.h"
+#undef selftest
+};
+
 struct selftest {
 	bool enabled;
 	const char *name;
@@ -78,6 +84,12 @@ static struct selftest live_selftests[] = {
 };
 #undef selftest
 
+#define selftest(n, f) [perf_##n] = { .name = #n, { .live = f } },
+static struct selftest perf_selftests[] = {
+#include "i915_perf_selftests.h"
+};
+#undef selftest
+
 /* Embed the line number into the parameter name so that we can order tests */
 #define selftest(n, func) selftest_0(n, func, param(n))
 #define param(n) __PASTE(igt__, __PASTE(__LINE__, __mock_##n))
@@ -93,6 +105,13 @@ module_param_named(id, live_selftests[live_##n].enabled, bool, 0400);
 #include "i915_live_selftests.h"
 #undef selftest_0
 #undef param
+
+#define param(n) __PASTE(igt__, __PASTE(__LINE__, __perf_##n))
+#define selftest_0(n, func, id) \
+module_param_named(id, perf_selftests[perf_##n].enabled, bool, 0400);
+#include "i915_perf_selftests.h"
+#undef selftest_0
+#undef param
 #undef selftest
 
 static void set_default_test_all(struct selftest *st, unsigned int count)
@@ -200,6 +219,27 @@ int i915_live_selftests(struct pci_dev *pdev)
 	return 0;
 }
 
+int i915_perf_selftests(struct pci_dev *pdev)
+{
+	int err;
+
+	if (!i915_selftest.perf)
+		return 0;
+
+	err = run_selftests(perf, pdev_to_i915(pdev));
+	if (err) {
+		i915_selftest.perf = err;
+		return err;
+	}
+
+	if (i915_selftest.perf < 0) {
+		i915_selftest.perf = -ENOTTY;
+		return 1;
+	}
+
+	return 0;
+}
+
 static bool apply_subtest_filter(const char *caller, const char *name)
 {
 	char *filter, *sep, *tok;
@@ -365,3 +405,6 @@ MODULE_PARM_DESC(mock_selftests, "Run selftests before loading, using mock hardw
 
 module_param_named_unsafe(live_selftests, i915_selftest.live, int, 0400);
 MODULE_PARM_DESC(live_selftests, "Run selftests after driver initialisation on the live system (0:disabled [default], 1:run tests then continue, -1:run tests then exit module)");
+
+module_param_named_unsafe(perf_selftests, i915_selftest.perf, int, 0400);
+MODULE_PARM_DESC(perf_selftests, "Run performance orientated selftests after driver initialisation on the live system (0:disabled [default], 1:run tests then continue, -1:run tests then exit module)");
diff --git a/drivers/gpu/drm/i915/selftests/igt_atomic.c b/drivers/gpu/drm/i915/selftests/igt_atomic.c
new file mode 100644
index 000000000000..fb506b699095
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_atomic.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include <linux/preempt.h>
+#include <linux/bottom_half.h>
+#include <linux/irqflags.h>
+
+#include "igt_atomic.h"
+
+static void __preempt_begin(void)
+{
+	preempt_disable();
+}
+
+static void __preempt_end(void)
+{
+	preempt_enable();
+}
+
+static void __softirq_begin(void)
+{
+	local_bh_disable();
+}
+
+static void __softirq_end(void)
+{
+	local_bh_enable();
+}
+
+static void __hardirq_begin(void)
+{
+	local_irq_disable();
+}
+
+static void __hardirq_end(void)
+{
+	local_irq_enable();
+}
+
+const struct igt_atomic_section igt_atomic_phases[] = {
+	{ "preempt", __preempt_begin, __preempt_end },
+	{ "softirq", __softirq_begin, __softirq_end },
+	{ "hardirq", __hardirq_begin, __hardirq_end },
+	{ }
+};
diff --git a/drivers/gpu/drm/i915/selftests/igt_atomic.h b/drivers/gpu/drm/i915/selftests/igt_atomic.h
index 93ec89f487ec..1991798abf4b 100644
--- a/drivers/gpu/drm/i915/selftests/igt_atomic.h
+++ b/drivers/gpu/drm/i915/selftests/igt_atomic.h
@@ -6,51 +6,12 @@
 #ifndef IGT_ATOMIC_H
 #define IGT_ATOMIC_H
 
-#include <linux/preempt.h>
-#include <linux/bottom_half.h>
-#include <linux/irqflags.h>
-
-static void __preempt_begin(void)
-{
-	preempt_disable();
-}
-
-static void __preempt_end(void)
-{
-	preempt_enable();
-}
-
-static void __softirq_begin(void)
-{
-	local_bh_disable();
-}
-
-static void __softirq_end(void)
-{
-	local_bh_enable();
-}
-
-static void __hardirq_begin(void)
-{
-	local_irq_disable();
-}
-
-static void __hardirq_end(void)
-{
-	local_irq_enable();
-}
-
 struct igt_atomic_section {
 	const char *name;
 	void (*critical_section_begin)(void);
 	void (*critical_section_end)(void);
 };
 
-static const struct igt_atomic_section igt_atomic_phases[] = {
-	{ "preempt", __preempt_begin, __preempt_end },
-	{ "softirq", __softirq_begin, __softirq_end },
-	{ "hardirq", __hardirq_begin, __hardirq_end },
-	{ }
-};
+extern const struct igt_atomic_section igt_atomic_phases[];
 
 #endif /* IGT_ATOMIC_H */
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h
index c0e9f99d50de..36ed42736c52 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.h
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h
@@ -7,7 +7,7 @@
 #ifndef IGT_LIVE_TEST_H
 #define IGT_LIVE_TEST_H
 
-#include "../i915_gem.h"
+#include "gt/intel_engine.h" /* for I915_NUM_ENGINES */
 
 struct drm_i915_private;
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_mmap.c b/drivers/gpu/drm/i915/selftests/igt_mmap.c
new file mode 100644
index 000000000000..583a4ff8b8c9
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_mmap.c
@@ -0,0 +1,39 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <drm/drm_file.h>
+
+#include "i915_drv.h"
+#include "igt_mmap.h"
+
+unsigned long igt_mmap_node(struct drm_i915_private *i915,
+			    struct drm_vma_offset_node *node,
+			    unsigned long addr,
+			    unsigned long prot,
+			    unsigned long flags)
+{
+	struct file *file;
+	int err;
+
+	/* Pretend to open("/dev/dri/card0") */
+	file = mock_drm_getfile(i915->drm.primary, O_RDWR);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	err = drm_vma_node_allow(node, file->private_data);
+	if (err) {
+		addr = err;
+		goto out_file;
+	}
+
+	addr = vm_mmap(file, addr, drm_vma_node_size(node) << PAGE_SHIFT,
+		       prot, flags, drm_vma_node_offset_addr(node));
+
+	drm_vma_node_revoke(node, file->private_data);
+out_file:
+	fput(file);
+	return addr;
+}
diff --git a/drivers/gpu/drm/i915/selftests/igt_mmap.h b/drivers/gpu/drm/i915/selftests/igt_mmap.h
new file mode 100644
index 000000000000..6e716cb59d7e
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_mmap.h
@@ -0,0 +1,19 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef IGT_MMAP_H
+#define IGT_MMAP_H
+
+struct drm_i915_private;
+struct drm_vma_offset_node;
+
+unsigned long igt_mmap_node(struct drm_i915_private *i915,
+			    struct drm_vma_offset_node *node,
+			    unsigned long addr,
+			    unsigned long prot,
+			    unsigned long flags);
+
+#endif /* IGT_MMAP_H */
diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c
index ee8450b871da..e8a58fe49c39 100644
--- a/drivers/gpu/drm/i915/selftests/igt_spinner.c
+++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c
@@ -15,8 +15,6 @@ int igt_spinner_init(struct igt_spinner *spin, struct intel_gt *gt)
 	void *vaddr;
 	int err;
 
-	GEM_BUG_ON(INTEL_GEN(gt->i915) < 8);
-
 	memset(spin, 0, sizeof(*spin));
 	spin->gt = gt;
 
@@ -95,11 +93,15 @@ igt_spinner_create_request(struct igt_spinner *spin,
 	struct intel_engine_cs *engine = ce->engine;
 	struct i915_request *rq = NULL;
 	struct i915_vma *hws, *vma;
+	unsigned int flags;
 	u32 *batch;
 	int err;
 
 	GEM_BUG_ON(spin->gt != ce->vm->gt);
 
+	if (!intel_engine_can_store_dword(ce->engine))
+		return ERR_PTR(-ENODEV);
+
 	vma = i915_vma_instance(spin->obj, ce->vm, NULL);
 	if (IS_ERR(vma))
 		return ERR_CAST(vma);
@@ -132,16 +134,37 @@ igt_spinner_create_request(struct igt_spinner *spin,
 
 	batch = spin->batch;
 
-	*batch++ = MI_STORE_DWORD_IMM_GEN4;
-	*batch++ = lower_32_bits(hws_address(hws, rq));
-	*batch++ = upper_32_bits(hws_address(hws, rq));
+	if (INTEL_GEN(rq->i915) >= 8) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4;
+		*batch++ = lower_32_bits(hws_address(hws, rq));
+		*batch++ = upper_32_bits(hws_address(hws, rq));
+	} else if (INTEL_GEN(rq->i915) >= 6) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4;
+		*batch++ = 0;
+		*batch++ = hws_address(hws, rq);
+	} else if (INTEL_GEN(rq->i915) >= 4) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+		*batch++ = 0;
+		*batch++ = hws_address(hws, rq);
+	} else {
+		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
+		*batch++ = hws_address(hws, rq);
+	}
 	*batch++ = rq->fence.seqno;
 
 	*batch++ = arbitration_command;
 
-	*batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1;
+	if (INTEL_GEN(rq->i915) >= 8)
+		*batch++ = MI_BATCH_BUFFER_START | BIT(8) | 1;
+	else if (IS_HASWELL(rq->i915))
+		*batch++ = MI_BATCH_BUFFER_START | MI_BATCH_PPGTT_HSW;
+	else if (INTEL_GEN(rq->i915) >= 6)
+		*batch++ = MI_BATCH_BUFFER_START;
+	else
+		*batch++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
 	*batch++ = lower_32_bits(vma->node.start);
 	*batch++ = upper_32_bits(vma->node.start);
+
 	*batch++ = MI_BATCH_BUFFER_END; /* not reached */
 
 	intel_gt_chipset_flush(engine->gt);
@@ -153,7 +176,10 @@ igt_spinner_create_request(struct igt_spinner *spin,
 			goto cancel_rq;
 	}
 
-	err = engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0);
+	flags = 0;
+	if (INTEL_GEN(rq->i915) <= 5)
+		flags |= I915_DISPATCH_SECURE;
+	err = engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
 
 cancel_rq:
 	if (err) {
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 19e1cca8f143..3ef3620e0da5 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -32,7 +32,7 @@ static void close_objects(struct intel_memory_region *mem,
 		if (i915_gem_object_has_pinned_pages(obj))
 			i915_gem_object_unpin_pages(obj);
 		/* No polluting the memory region between tests */
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 		list_del(&obj->st_link);
 		i915_gem_object_put(obj);
 	}
@@ -122,7 +122,7 @@ put:
 static void igt_object_release(struct drm_i915_gem_object *obj)
 {
 	i915_gem_object_unpin_pages(obj);
-	__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+	__i915_gem_object_put_pages(obj);
 	list_del(&obj->st_link);
 	i915_gem_object_put(obj);
 }
@@ -270,36 +270,31 @@ static int igt_gpu_write_dw(struct intel_context *ce,
 
 static int igt_cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 {
-	unsigned long n;
+	unsigned long n = obj->base.size >> PAGE_SHIFT;
+	u32 *ptr;
 	int err;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_wc_domain(obj, false);
-	i915_gem_object_unlock(obj);
-	if (err)
-		return err;
-
-	err = i915_gem_object_pin_pages(obj);
+	err = i915_gem_object_wait(obj, 0, MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
-	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
-		u32 __iomem *base;
-		u32 read_val;
-
-		base = i915_gem_object_lmem_io_map_page_atomic(obj, n);
+	ptr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
 
-		read_val = ioread32(base + dword);
-		io_mapping_unmap_atomic(base);
-		if (read_val != val) {
-			pr_err("n=%lu base[%u]=%u, val=%u\n",
-			       n, dword, read_val, val);
+	ptr += dword;
+	while (n--) {
+		if (*ptr != val) {
+			pr_err("base[%u]=%08x, val=%08x\n",
+			       dword, *ptr, val);
 			err = -EINVAL;
 			break;
 		}
+
+		ptr += PAGE_SIZE / sizeof(*ptr);
 	}
 
-	i915_gem_object_unpin_pages(obj);
+	i915_gem_object_unpin_map(obj);
 	return err;
 }
 
@@ -404,7 +399,7 @@ static int igt_lmem_write_gpu(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj;
 	struct i915_gem_context *ctx;
-	struct drm_file *file;
+	struct file *file;
 	I915_RND_STATE(prng);
 	u32 sz;
 	int err;
@@ -439,7 +434,7 @@ static int igt_lmem_write_gpu(void *arg)
 out_put:
 	i915_gem_object_put(obj);
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -506,7 +501,9 @@ static int igt_lmem_write_cpu(void *arg)
 	}
 
 	/* Put the pages into a known state -- from the gpu for added fun */
+	intel_engine_pm_get(engine);
 	err = i915_gem_object_fill_blt(obj, engine->kernel_context, 0xdeadbeaf);
+	intel_engine_pm_put(engine);
 	if (err)
 		goto out_unpin;
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_drm.c b/drivers/gpu/drm/i915/selftests/mock_drm.c
deleted file mode 100644
index 09c704153456..000000000000
--- a/drivers/gpu/drm/i915/selftests/mock_drm.c
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * Copyright © 2017 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- */
-
-#include "mock_drm.h"
-
-struct drm_file *mock_file(struct drm_i915_private *i915)
-{
-	struct file *filp;
-	struct inode *inode;
-	struct drm_file *file;
-	int err;
-
-	inode = kzalloc(sizeof(*inode), GFP_KERNEL);
-	if (!inode) {
-		err = -ENOMEM;
-		goto err;
-	}
-
-	inode->i_rdev = i915->drm.primary->index;
-
-	filp = kzalloc(sizeof(*filp), GFP_KERNEL);
-	if (!filp) {
-		err = -ENOMEM;
-		goto err_inode;
-	}
-
-	err = drm_open(inode, filp);
-	if (err)
-		goto err_filp;
-
-	file = filp->private_data;
-	memset(&file->filp, POISON_INUSE, sizeof(file->filp));
-	file->authenticated = true;
-
-	kfree(filp);
-	kfree(inode);
-	return file;
-
-err_filp:
-	kfree(filp);
-err_inode:
-	kfree(inode);
-err:
-	return ERR_PTR(err);
-}
-
-void mock_file_free(struct drm_i915_private *i915, struct drm_file *file)
-{
-	struct file filp = { .private_data = file };
-
-	drm_release(NULL, &filp);
-}
diff --git a/drivers/gpu/drm/i915/selftests/mock_drm.h b/drivers/gpu/drm/i915/selftests/mock_drm.h
index b39beee9f8f6..9916b6f95526 100644
--- a/drivers/gpu/drm/i915/selftests/mock_drm.h
+++ b/drivers/gpu/drm/i915/selftests/mock_drm.h
@@ -25,7 +25,21 @@
 #ifndef __MOCK_DRM_H
 #define __MOCK_DRM_H
 
-struct drm_file *mock_file(struct drm_i915_private *i915);
-void mock_file_free(struct drm_i915_private *i915, struct drm_file *file);
+#include <drm/drm_file.h>
+
+#include "i915_drv.h"
+
+struct drm_file;
+struct file;
+
+static inline struct file *mock_file(struct drm_i915_private *i915)
+{
+	return mock_drm_getfile(i915->drm.primary, O_RDWR);
+}
+
+static inline struct drm_file *to_drm_file(struct file *f)
+{
+	return f->private_data;
+}
 
 #endif /* !__MOCK_DRM_H */
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 27ed3cee6a9b..3b8986983afc 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -54,25 +54,19 @@ void mock_device_flush(struct drm_i915_private *i915)
 static void mock_device_release(struct drm_device *dev)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 
 	mock_device_flush(i915);
+	intel_gt_driver_remove(&i915->gt);
 
-	i915_gem_drain_workqueue(i915);
-
-	for_each_engine(engine, &i915->gt, id)
-		mock_engine_free(engine);
 	i915_gem_driver_release__contexts(i915);
 
-	intel_timelines_fini(i915);
-
-	drain_workqueue(i915->wq);
+	i915_gem_drain_workqueue(i915);
 	i915_gem_drain_freed_objects(i915);
 
 	mock_fini_ggtt(&i915->ggtt);
 	destroy_workqueue(i915->wq);
 
+	intel_gt_driver_late_release(&i915->gt);
 	intel_memory_regions_driver_release(i915);
 
 	drm_mode_config_cleanup(&i915->drm);
@@ -180,9 +174,8 @@ struct drm_i915_private *mock_gem_device(void)
 
 	mock_init_contexts(i915);
 
-	intel_timelines_init(i915);
-
 	mock_init_ggtt(i915, &i915->ggtt);
+	i915->gt.vm = i915_vm_get(&i915->ggtt.vm);
 
 	mkwrite_device_info(i915)->engine_mask = BIT(0);
 
@@ -190,25 +183,20 @@ struct drm_i915_private *mock_gem_device(void)
 	if (!i915->engine[RCS0])
 		goto err_unlock;
 
-	i915->kernel_context = mock_context(i915, NULL);
-	if (!i915->kernel_context)
-		goto err_engine;
-
 	if (mock_engine_init(i915->engine[RCS0]))
 		goto err_context;
 
+	__clear_bit(I915_WEDGED, &i915->gt.reset.flags);
 	intel_engines_driver_register(i915);
 
 	return i915;
 
 err_context:
-	i915_gem_driver_release__contexts(i915);
-err_engine:
-	mock_engine_free(i915->engine[RCS0]);
+	intel_gt_driver_remove(&i915->gt);
 err_unlock:
-	intel_timelines_fini(i915);
 	destroy_workqueue(i915->wq);
 err_drv:
+	intel_gt_driver_late_release(&i915->gt);
 	intel_memory_regions_driver_release(i915);
 	drm_mode_config_cleanup(&i915->drm);
 	drm_dev_fini(&i915->drm);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 20ac3844edec..edc5e3dda8ca 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -55,6 +55,11 @@ static void mock_cleanup(struct i915_address_space *vm)
 {
 }
 
+static void mock_clear_range(struct i915_address_space *vm,
+			     u64 start, u64 length)
+{
+}
+
 struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 {
 	struct i915_ppgtt *ppgtt;
@@ -70,7 +75,7 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 
 	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
 
-	ppgtt->vm.clear_range = nop_clear_range;
+	ppgtt->vm.clear_range = mock_clear_range;
 	ppgtt->vm.insert_page = mock_insert_page;
 	ppgtt->vm.insert_entries = mock_insert_entries;
 	ppgtt->vm.cleanup = mock_cleanup;
@@ -107,7 +112,7 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt)
 	ggtt->mappable_end = resource_size(&ggtt->gmadr);
 	ggtt->vm.total = 4096 * PAGE_SIZE;
 
-	ggtt->vm.clear_range = nop_clear_range;
+	ggtt->vm.clear_range = mock_clear_range;
 	ggtt->vm.insert_page = mock_insert_page;
 	ggtt->vm.insert_entries = mock_insert_entries;
 	ggtt->vm.cleanup = mock_cleanup;
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.h b/drivers/gpu/drm/i915/selftests/mock_gtt.h
index 3387393286de..e3f224f43beb 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.h
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.h
@@ -25,6 +25,9 @@
 #ifndef __MOCK_GTT_H
 #define __MOCK_GTT_H
 
+struct drm_i915_private;
+struct i915_ggtt;
+
 void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt);
 void mock_fini_ggtt(struct i915_ggtt *ggtt);
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.h b/drivers/gpu/drm/i915/selftests/mock_region.h
index 24608089d833..329bf74dfaca 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.h
+++ b/drivers/gpu/drm/i915/selftests/mock_region.h
@@ -6,6 +6,11 @@
 #ifndef __MOCK_REGION_H
 #define __MOCK_REGION_H
 
+#include <linux/types.h>
+
+struct drm_i915_private;
+struct intel_memory_region;
+
 struct intel_memory_region *
 mock_region_create(struct drm_i915_private *i915,
 		   resource_size_t start,
diff --git a/drivers/gpu/drm/i915/selftests/mock_uncore.h b/drivers/gpu/drm/i915/selftests/mock_uncore.h
index 8a2cc553f466..7acf1ef4d488 100644
--- a/drivers/gpu/drm/i915/selftests/mock_uncore.h
+++ b/drivers/gpu/drm/i915/selftests/mock_uncore.h
@@ -25,6 +25,9 @@
 #ifndef __MOCK_UNCORE_H
 #define __MOCK_UNCORE_H
 
+struct drm_i915_private;
+struct intel_uncore;
+
 void mock_uncore_init(struct intel_uncore *uncore,
 		      struct drm_i915_private *i915);
 
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 208069faf183..8cb2665b2c74 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -127,7 +127,7 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector)
 	struct imx_ldb_channel *imx_ldb_ch = con_to_imx_ldb_ch(connector);
 	int num_modes;
 
-	num_modes = drm_panel_get_modes(imx_ldb_ch->panel);
+	num_modes = drm_panel_get_modes(imx_ldb_ch->panel, connector);
 	if (num_modes > 0)
 		return num_modes;
 
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 35518e5de356..3dca424059f7 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -50,7 +50,7 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 	struct device_node *np = imxpd->dev->of_node;
 	int num_modes;
 
-	num_modes = drm_panel_get_modes(imxpd->panel);
+	num_modes = drm_panel_get_modes(imxpd->panel, connector);
 	if (num_modes > 0)
 		return num_modes;
 
diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c
index ec32e1c67335..6d47ef7b148c 100644
--- a/drivers/gpu/drm/ingenic/ingenic-drm.c
+++ b/drivers/gpu/drm/ingenic/ingenic-drm.c
@@ -153,6 +153,7 @@ struct ingenic_dma_hwdesc {
 
 struct jz_soc_info {
 	bool needs_dev_clk;
+	unsigned int max_width, max_height;
 };
 
 struct ingenic_drm {
@@ -164,6 +165,7 @@ struct ingenic_drm {
 	struct device *dev;
 	struct regmap *map;
 	struct clk *lcd_clk, *pix_clk;
+	const struct jz_soc_info *soc_info;
 
 	struct ingenic_dma_hwdesc *dma_hwdesc;
 	dma_addr_t dma_hwdesc_phys;
@@ -326,6 +328,10 @@ static int ingenic_drm_crtc_atomic_check(struct drm_crtc *crtc,
 	if (!drm_atomic_crtc_needs_modeset(state))
 		return 0;
 
+	if (state->mode.hdisplay > priv->soc_info->max_height ||
+	    state->mode.vdisplay > priv->soc_info->max_width)
+		return -EINVAL;
+
 	rate = clk_round_rate(priv->pix_clk,
 			      state->adjusted_mode.clock * 1000);
 	if (rate < 0)
@@ -372,14 +378,18 @@ static void ingenic_drm_plane_atomic_update(struct drm_plane *plane,
 	struct ingenic_drm *priv = drm_plane_get_priv(plane);
 	struct drm_plane_state *state = plane->state;
 	unsigned int width, height, cpp;
+	dma_addr_t addr;
 
-	width = state->crtc->state->adjusted_mode.hdisplay;
-	height = state->crtc->state->adjusted_mode.vdisplay;
-	cpp = state->fb->format->cpp[plane->index];
+	if (state && state->fb) {
+		addr = drm_fb_cma_get_gem_addr(state->fb, state, 0);
+		width = state->src_w >> 16;
+		height = state->src_h >> 16;
+		cpp = state->fb->format->cpp[plane->index];
 
-	priv->dma_hwdesc->addr = drm_fb_cma_get_gem_addr(state->fb, state, 0);
-	priv->dma_hwdesc->cmd = width * height * cpp / 4;
-	priv->dma_hwdesc->cmd |= JZ_LCD_CMD_EOF_IRQ;
+		priv->dma_hwdesc->addr = addr;
+		priv->dma_hwdesc->cmd = width * height * cpp / 4;
+		priv->dma_hwdesc->cmd |= JZ_LCD_CMD_EOF_IRQ;
+	}
 }
 
 static void ingenic_drm_encoder_atomic_mode_set(struct drm_encoder *encoder,
@@ -617,6 +627,7 @@ static int ingenic_drm_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
+	priv->soc_info = soc_info;
 	priv->dev = dev;
 	drm = &priv->drm;
 	drm->dev_private = priv;
@@ -632,8 +643,8 @@ static int ingenic_drm_probe(struct platform_device *pdev)
 	drm_mode_config_init(drm);
 	drm->mode_config.min_width = 0;
 	drm->mode_config.min_height = 0;
-	drm->mode_config.max_width = 800;
-	drm->mode_config.max_height = 600;
+	drm->mode_config.max_width = soc_info->max_width;
+	drm->mode_config.max_height = 4095;
 	drm->mode_config.funcs = &ingenic_drm_mode_config_funcs;
 
 	base = devm_platform_ioremap_resource(pdev, 0);
@@ -810,15 +821,26 @@ static int ingenic_drm_remove(struct platform_device *pdev)
 
 static const struct jz_soc_info jz4740_soc_info = {
 	.needs_dev_clk = true,
+	.max_width = 800,
+	.max_height = 600,
 };
 
 static const struct jz_soc_info jz4725b_soc_info = {
 	.needs_dev_clk = false,
+	.max_width = 800,
+	.max_height = 600,
+};
+
+static const struct jz_soc_info jz4770_soc_info = {
+	.needs_dev_clk = false,
+	.max_width = 1280,
+	.max_height = 720,
 };
 
 static const struct of_device_id ingenic_drm_of_match[] = {
 	{ .compatible = "ingenic,jz4740-lcd", .data = &jz4740_soc_info },
 	{ .compatible = "ingenic,jz4725b-lcd", .data = &jz4725b_soc_info },
+	{ .compatible = "ingenic,jz4770-lcd", .data = &jz4770_soc_info },
 	{ /* sentinel */ },
 };
 
diff --git a/drivers/gpu/drm/lima/Kconfig b/drivers/gpu/drm/lima/Kconfig
index 571dc369a7e9..d589f09d04d9 100644
--- a/drivers/gpu/drm/lima/Kconfig
+++ b/drivers/gpu/drm/lima/Kconfig
@@ -11,4 +11,4 @@ config DRM_LIMA
        select DRM_SCHED
        select DRM_GEM_SHMEM_HELPER
        help
-         DRM driver for ARM Mali 400/450 GPUs.
+	 DRM driver for ARM Mali 400/450 GPUs.
diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
index f522c5f99729..b561dd05bd62 100644
--- a/drivers/gpu/drm/lima/lima_sched.c
+++ b/drivers/gpu/drm/lima/lima_sched.c
@@ -159,9 +159,10 @@ int lima_sched_context_init(struct lima_sched_pipe *pipe,
 			    struct lima_sched_context *context,
 			    atomic_t *guilty)
 {
-	struct drm_sched_rq *rq = pipe->base.sched_rq + DRM_SCHED_PRIORITY_NORMAL;
+	struct drm_gpu_scheduler *sched = &pipe->base;
 
-	return drm_sched_entity_init(&context->base, &rq, 1, guilty);
+	return drm_sched_entity_init(&context->base, DRM_SCHED_PRIORITY_NORMAL,
+				     &sched, 1, guilty);
 }
 
 void lima_sched_context_fini(struct lima_sched_pipe *pipe,
@@ -255,13 +256,17 @@ static struct dma_fence *lima_sched_run_job(struct drm_sched_job *job)
 	return task->fence;
 }
 
-static void lima_sched_handle_error_task(struct lima_sched_pipe *pipe,
-					 struct lima_sched_task *task)
+static void lima_sched_timedout_job(struct drm_sched_job *job)
 {
+	struct lima_sched_pipe *pipe = to_lima_pipe(job->sched);
+	struct lima_sched_task *task = to_lima_task(job);
+
+	if (!pipe->error)
+		DRM_ERROR("lima job timeout\n");
+
 	drm_sched_stop(&pipe->base, &task->base);
 
-	if (task)
-		drm_sched_increase_karma(&task->base);
+	drm_sched_increase_karma(&task->base);
 
 	pipe->task_error(pipe);
 
@@ -284,16 +289,6 @@ static void lima_sched_handle_error_task(struct lima_sched_pipe *pipe,
 	drm_sched_start(&pipe->base, true);
 }
 
-static void lima_sched_timedout_job(struct drm_sched_job *job)
-{
-	struct lima_sched_pipe *pipe = to_lima_pipe(job->sched);
-	struct lima_sched_task *task = to_lima_task(job);
-
-	DRM_ERROR("lima job timeout\n");
-
-	lima_sched_handle_error_task(pipe, task);
-}
-
 static void lima_sched_free_job(struct drm_sched_job *job)
 {
 	struct lima_sched_task *task = to_lima_task(job);
@@ -318,15 +313,6 @@ static const struct drm_sched_backend_ops lima_sched_ops = {
 	.free_job = lima_sched_free_job,
 };
 
-static void lima_sched_error_work(struct work_struct *work)
-{
-	struct lima_sched_pipe *pipe =
-		container_of(work, struct lima_sched_pipe, error_work);
-	struct lima_sched_task *task = pipe->current_task;
-
-	lima_sched_handle_error_task(pipe, task);
-}
-
 int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
 {
 	unsigned int timeout = lima_sched_timeout_ms > 0 ?
@@ -335,8 +321,6 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
 	pipe->fence_context = dma_fence_context_alloc(1);
 	spin_lock_init(&pipe->fence_lock);
 
-	INIT_WORK(&pipe->error_work, lima_sched_error_work);
-
 	return drm_sched_init(&pipe->base, &lima_sched_ops, 1, 0,
 			      msecs_to_jiffies(timeout), name);
 }
@@ -349,7 +333,7 @@ void lima_sched_pipe_fini(struct lima_sched_pipe *pipe)
 void lima_sched_pipe_task_done(struct lima_sched_pipe *pipe)
 {
 	if (pipe->error)
-		schedule_work(&pipe->error_work);
+		drm_sched_fault(&pipe->base);
 	else {
 		struct lima_sched_task *task = pipe->current_task;
 
diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h
index 928af91c1118..1d814fecbcc0 100644
--- a/drivers/gpu/drm/lima/lima_sched.h
+++ b/drivers/gpu/drm/lima/lima_sched.h
@@ -68,8 +68,6 @@ struct lima_sched_pipe {
 	void (*task_fini)(struct lima_sched_pipe *pipe);
 	void (*task_error)(struct lima_sched_pipe *pipe);
 	void (*task_mmu_error)(struct lima_sched_pipe *pipe);
-
-	struct work_struct error_work;
 };
 
 int lima_sched_task_init(struct lima_sched_task *task,
diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c
index 751454ae3cd1..e59907e68854 100644
--- a/drivers/gpu/drm/mcde/mcde_display.c
+++ b/drivers/gpu/drm/mcde/mcde_display.c
@@ -498,24 +498,20 @@ static void mcde_configure_channel(struct mcde *mcde, enum mcde_channel ch,
 	}
 
 	/* Set up channel 0 sync (based on chnl_update_registers()) */
-	if (mcde->te_sync) {
-		/*
-		 * Turn on hardware TE0 synchronization
-		 */
+	if (mcde->video_mode || mcde->te_sync)
 		val = MCDE_CHNLXSYNCHMOD_SRC_SYNCH_HARDWARE
 			<< MCDE_CHNLXSYNCHMOD_SRC_SYNCH_SHIFT;
-		val |= MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_TE0
-			<< MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_SHIFT;
-	} else {
-		/*
-		 * Set up sync source to software, out sync formatter
-		 * Code mostly from mcde_hw.c chnl_update_registers()
-		 */
+	else
 		val = MCDE_CHNLXSYNCHMOD_SRC_SYNCH_SOFTWARE
 			<< MCDE_CHNLXSYNCHMOD_SRC_SYNCH_SHIFT;
+
+	if (mcde->te_sync)
+		val |= MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_TE0
+			<< MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_SHIFT;
+	else
 		val |= MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_FORMATTER
 			<< MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_SHIFT;
-	}
+
 	writel(val, mcde->regs + sync);
 
 	/* Set up pixels per line and lines per frame */
@@ -934,10 +930,17 @@ static void mcde_display_enable(struct drm_simple_display_pipe *pipe,
 		val = readl(mcde->regs + MCDE_CRC);
 		val |= MCDE_CRC_SYCEN0;
 		writel(val, mcde->regs + MCDE_CRC);
-
-		drm_crtc_vblank_on(crtc);
 	}
 
+	drm_crtc_vblank_on(crtc);
+
+	if (mcde->video_mode)
+		/*
+		 * Keep FIFO permanently enabled in video mode,
+		 * otherwise MCDE will stop feeding data to the panel.
+		 */
+		mcde_enable_fifo(mcde, MCDE_FIFO_A);
+
 	dev_info(drm->dev, "MCDE display is enabled\n");
 }
 
@@ -946,13 +949,22 @@ static void mcde_display_disable(struct drm_simple_display_pipe *pipe)
 	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_device *drm = crtc->dev;
 	struct mcde *mcde = drm->dev_private;
+	struct drm_pending_vblank_event *event;
 
-	if (mcde->te_sync)
-		drm_crtc_vblank_off(crtc);
+	drm_crtc_vblank_off(crtc);
 
 	/* Disable FIFO A flow */
 	mcde_disable_fifo(mcde, MCDE_FIFO_A, true);
 
+	event = crtc->state->event;
+	if (event) {
+		crtc->state->event = NULL;
+
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
+
 	dev_info(drm->dev, "MCDE display is disabled\n");
 }
 
@@ -1048,8 +1060,9 @@ static void mcde_display_update(struct drm_simple_display_pipe *pipe,
 	 */
 	if (fb) {
 		mcde_set_extsrc(mcde, drm_fb_cma_get_gem_addr(fb, pstate, 0));
-		/* Send a single frame using software sync */
-		mcde_display_send_one_frame(mcde);
+		if (!mcde->video_mode)
+			/* Send a single frame using software sync */
+			mcde_display_send_one_frame(mcde);
 		dev_info_once(mcde->dev, "sent first display update\n");
 	} else {
 		/*
@@ -1097,6 +1110,8 @@ static struct drm_simple_display_pipe_funcs mcde_display_funcs = {
 	.enable = mcde_display_enable,
 	.disable = mcde_display_disable,
 	.update = mcde_display_update,
+	.enable_vblank = mcde_display_enable_vblank,
+	.disable_vblank = mcde_display_disable_vblank,
 	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
 };
 
@@ -1123,12 +1138,6 @@ int mcde_display_init(struct drm_device *drm)
 		DRM_FORMAT_YUV422,
 	};
 
-	/* Provide vblank only when we have TE enabled */
-	if (mcde->te_sync) {
-		mcde_display_funcs.enable_vblank = mcde_display_enable_vblank;
-		mcde_display_funcs.disable_vblank = mcde_display_disable_vblank;
-	}
-
 	ret = drm_simple_display_pipe_init(drm, &mcde->pipe,
 					   &mcde_display_funcs,
 					   formats, ARRAY_SIZE(formats),
diff --git a/drivers/gpu/drm/mcde/mcde_drm.h b/drivers/gpu/drm/mcde/mcde_drm.h
index dab4db021231..80edd6628979 100644
--- a/drivers/gpu/drm/mcde/mcde_drm.h
+++ b/drivers/gpu/drm/mcde/mcde_drm.h
@@ -19,6 +19,7 @@ struct mcde {
 	struct mipi_dsi_device *mdsi;
 	s16 stride;
 	bool te_sync;
+	bool video_mode;
 	bool oneshot_mode;
 	unsigned int flow_active;
 	spinlock_t flow_lock; /* Locks the channel flow control */
diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c
index 5649887d2b90..9008ddcfc528 100644
--- a/drivers/gpu/drm/mcde/mcde_drv.c
+++ b/drivers/gpu/drm/mcde/mcde_drv.c
@@ -179,18 +179,10 @@ static int mcde_modeset_init(struct drm_device *drm)
 	mode_config->min_height = 1;
 	mode_config->max_height = 1080;
 
-	/*
-	 * Currently we only support vblank handling on the DSI bridge, using
-	 * TE synchronization. If TE sync is not set up, it is still possible
-	 * to push out a single update on demand, but this is hard for DRM to
-	 * exploit.
-	 */
-	if (mcde->te_sync) {
-		ret = drm_vblank_init(drm, 1);
-		if (ret) {
-			dev_err(drm->dev, "failed to init vblank\n");
-			goto out_config;
-		}
+	ret = drm_vblank_init(drm, 1);
+	if (ret) {
+		dev_err(drm->dev, "failed to init vblank\n");
+		goto out_config;
 	}
 
 	ret = mcde_display_init(drm);
@@ -339,8 +331,6 @@ static int mcde_probe(struct platform_device *pdev)
 	drm->dev_private = mcde;
 	platform_set_drvdata(pdev, drm);
 
-	/* Enable use of the TE signal and interrupt */
-	mcde->te_sync = true;
 	/* Enable continuous updates: this is what Linux' framebuffer expects */
 	mcde->oneshot_mode = false;
 	drm->dev_private = mcde;
diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c
index ef4c630afe3f..bb6528b01cd0 100644
--- a/drivers/gpu/drm/mcde/mcde_dsi.c
+++ b/drivers/gpu/drm/mcde/mcde_dsi.c
@@ -39,7 +39,6 @@ struct mcde_dsi {
 	struct device *dev;
 	struct mcde *mcde;
 	struct drm_bridge bridge;
-	struct drm_connector connector;
 	struct drm_panel *panel;
 	struct drm_bridge *bridge_out;
 	struct mipi_dsi_host dsi_host;
@@ -64,11 +63,6 @@ static inline struct mcde_dsi *host_to_mcde_dsi(struct mipi_dsi_host *h)
 	return container_of(h, struct mcde_dsi, dsi_host);
 }
 
-static inline struct mcde_dsi *connector_to_mcde_dsi(struct drm_connector *c)
-{
-	return container_of(c, struct mcde_dsi, connector);
-}
-
 bool mcde_dsi_irq(struct mipi_dsi_device *mdsi)
 {
 	struct mcde_dsi *d;
@@ -124,12 +118,41 @@ bool mcde_dsi_irq(struct mipi_dsi_device *mdsi)
 
 	val = readl(d->regs + DSI_VID_MODE_STS_FLAG);
 	if (val)
-		dev_err(d->dev, "some video mode error status\n");
+		dev_dbg(d->dev, "DSI_VID_MODE_STS_FLAG = %08x\n", val);
+	if (val & DSI_VID_MODE_STS_VSG_RUNNING)
+		dev_dbg(d->dev, "VID mode VSG running\n");
+	if (val & DSI_VID_MODE_STS_ERR_MISSING_DATA)
+		dev_err(d->dev, "VID mode missing data\n");
+	if (val & DSI_VID_MODE_STS_ERR_MISSING_HSYNC)
+		dev_err(d->dev, "VID mode missing HSYNC\n");
+	if (val & DSI_VID_MODE_STS_ERR_MISSING_VSYNC)
+		dev_err(d->dev, "VID mode missing VSYNC\n");
+	if (val & DSI_VID_MODE_STS_REG_ERR_SMALL_LENGTH)
+		dev_err(d->dev, "VID mode less bytes than expected between two HSYNC\n");
+	if (val & DSI_VID_MODE_STS_REG_ERR_SMALL_HEIGHT)
+		dev_err(d->dev, "VID mode less lines than expected between two VSYNC\n");
+	if (val & (DSI_VID_MODE_STS_ERR_BURSTWRITE |
+		   DSI_VID_MODE_STS_ERR_LINEWRITE |
+		   DSI_VID_MODE_STS_ERR_LONGREAD))
+		dev_err(d->dev, "VID mode read/write error\n");
+	if (val & DSI_VID_MODE_STS_ERR_VRS_WRONG_LENGTH)
+		dev_err(d->dev, "VID mode received packets differ from expected size\n");
+	if (val & DSI_VID_MODE_STS_VSG_RECOVERY)
+		dev_err(d->dev, "VID mode VSG in recovery mode\n");
 	writel(val, d->regs + DSI_VID_MODE_STS_CLR);
 
 	return te_received;
 }
 
+static void mcde_dsi_attach_to_mcde(struct mcde_dsi *d)
+{
+	d->mcde->mdsi = d->mdsi;
+
+	d->mcde->video_mode = !!(d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO);
+	/* Enable use of the TE signal for all command mode panels */
+	d->mcde->te_sync = !d->mcde->video_mode;
+}
+
 static int mcde_dsi_host_attach(struct mipi_dsi_host *host,
 				struct mipi_dsi_device *mdsi)
 {
@@ -148,7 +171,7 @@ static int mcde_dsi_host_attach(struct mipi_dsi_host *host,
 
 	d->mdsi = mdsi;
 	if (d->mcde)
-		d->mcde->mdsi = mdsi;
+		mcde_dsi_attach_to_mcde(d);
 
 	return 0;
 }
@@ -223,25 +246,25 @@ static ssize_t mcde_dsi_host_transfer(struct mipi_dsi_host *host,
 	if (txlen > 0) {
 		val = 0;
 		for (i = 0; i < 4 && i < txlen; i++)
-			val |= tx[i] << (i & 3) * 8;
+			val |= tx[i] << (i * 8);
 	}
 	writel(val, d->regs + DSI_DIRECT_CMD_WRDAT0);
 	if (txlen > 4) {
 		val = 0;
 		for (i = 0; i < 4 && (i + 4) < txlen; i++)
-			val |= tx[i + 4] << (i & 3) * 8;
+			val |= tx[i + 4] << (i * 8);
 		writel(val, d->regs + DSI_DIRECT_CMD_WRDAT1);
 	}
 	if (txlen > 8) {
 		val = 0;
 		for (i = 0; i < 4 && (i + 8) < txlen; i++)
-			val |= tx[i + 8] << (i & 3) * 8;
+			val |= tx[i + 8] << (i * 8);
 		writel(val, d->regs + DSI_DIRECT_CMD_WRDAT2);
 	}
 	if (txlen > 12) {
 		val = 0;
 		for (i = 0; i < 4 && (i + 12) < txlen; i++)
-			val |= tx[i + 12] << (i & 3) * 8;
+			val |= tx[i + 12] << (i * 8);
 		writel(val, d->regs + DSI_DIRECT_CMD_WRDAT3);
 	}
 
@@ -336,7 +359,7 @@ void mcde_dsi_te_request(struct mipi_dsi_device *mdsi)
 	val |= 0 << DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_ID_SHIFT;
 	val |= 2 << DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_SIZE_SHIFT;
 	val |= DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_LP_EN;
-	val |= DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_SHORT_WRITE_1 <<
+	val |= MIPI_DSI_GENERIC_SHORT_WRITE_1_PARAM <<
 		DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SHIFT;
 	writel(val, d->regs + DSI_DIRECT_CMD_MAIN_SETTINGS);
 
@@ -365,13 +388,14 @@ void mcde_dsi_te_request(struct mipi_dsi_device *mdsi)
 static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 				      const struct drm_display_mode *mode)
 {
-	u8 bpp = mipi_dsi_pixel_format_to_bpp(d->mdsi->format);
+	/* cpp, characters per pixel, number of bytes per pixel */
+	u8 cpp = mipi_dsi_pixel_format_to_bpp(d->mdsi->format) / 8;
+	u64 pclk;
 	u64 bpl;
-	u32 hfp;
-	u32 hbp;
-	u32 hsa;
+	int hfp;
+	int hbp;
+	int hsa;
 	u32 blkline_pck, line_duration;
-	u32 blkeol_pck, blkeol_duration;
 	u32 val;
 
 	val = 0;
@@ -408,11 +432,21 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 		return;
 	}
 
-	/* TODO: TVG could be enabled here */
+	/* TODO: TVG (test video generator) could be enabled here */
 
-	/* Send blanking packet */
+	/*
+	 * During vertical blanking: go to LP mode
+	 * Like with the EOL setting, if this is not set, the EOL area will be
+	 * filled with NULL or blanking packets in the vblank area.
+	 * FIXME: some Samsung phones and display panels such as s6e63m0 use
+	 * DSI_VID_MAIN_CTL_REG_BLKLINE_MODE_BLANKING here instead,
+	 * figure out how to properly configure that from the panel.
+	 */
 	val |= DSI_VID_MAIN_CTL_REG_BLKLINE_MODE_LP_0;
-	/* Send EOL packet */
+	/*
+	 * During EOL: go to LP mode. If this is not set, the EOL area will be
+	 * filled with NULL or blanking packets.
+	 */
 	val |= DSI_VID_MAIN_CTL_REG_BLKEOL_MODE_LP_0;
 	/* Recovery mode 1 */
 	val |= 1 << DSI_VID_MAIN_CTL_RECOVERY_MODE_SHIFT;
@@ -420,13 +454,13 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 	writel(val, d->regs + DSI_VID_MAIN_CTL);
 
 	/* Vertical frame parameters are pretty straight-forward */
-	val = mode->vdisplay << DSI_VID_VSIZE_VSA_LENGTH_SHIFT;
+	val = mode->vdisplay << DSI_VID_VSIZE_VACT_LENGTH_SHIFT;
 	/* vertical front porch */
 	val |= (mode->vsync_start - mode->vdisplay)
 		<< DSI_VID_VSIZE_VFP_LENGTH_SHIFT;
 	/* vertical sync active */
 	val |= (mode->vsync_end - mode->vsync_start)
-		<< DSI_VID_VSIZE_VACT_LENGTH_SHIFT;
+		<< DSI_VID_VSIZE_VSA_LENGTH_SHIFT;
 	/* vertical back porch */
 	val |= (mode->vtotal - mode->vsync_end)
 		<< DSI_VID_VSIZE_VBP_LENGTH_SHIFT;
@@ -434,36 +468,54 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 
 	/*
 	 * Horizontal frame parameters:
-	 * horizontal resolution is given in pixels and must be re-calculated
-	 * into bytes since this is what the hardware expects.
+	 * horizontal resolution is given in pixels but must be re-calculated
+	 * into bytes since this is what the hardware expects, these registers
+	 * define the payload size of the packet.
+	 *
+	 * hfp = horizontal front porch in bytes
+	 * hbp = horizontal back porch in bytes
+	 * hsa = horizontal sync active in bytes
 	 *
 	 * 6 + 2 is HFP header + checksum
 	 */
-	hfp = (mode->hsync_start - mode->hdisplay) * bpp - 6 - 2;
+	hfp = (mode->hsync_start - mode->hdisplay) * cpp - 6 - 2;
 	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) {
 		/*
+		 * Use sync pulse for sync: explicit HSA time
 		 * 6 is HBP header + checksum
 		 * 4 is RGB header + checksum
 		 */
-		hbp = (mode->htotal - mode->hsync_end) * bpp - 4 - 6;
+		hbp = (mode->htotal - mode->hsync_end) * cpp - 4 - 6;
 		/*
 		 * 6 is HBP header + checksum
 		 * 4 is HSW packet bytes
 		 * 4 is RGB header + checksum
 		 */
-		hsa = (mode->hsync_end - mode->hsync_start) * bpp - 4 - 4 - 6;
+		hsa = (mode->hsync_end - mode->hsync_start) * cpp - 4 - 4 - 6;
 	} else {
 		/*
-		 * HBP includes both back porch and sync
+		 * Use event for sync: HBP includes both back porch and sync
 		 * 6 is HBP header + checksum
 		 * 4 is HSW packet bytes
 		 * 4 is RGB header + checksum
 		 */
-		hbp = (mode->htotal - mode->hsync_start) * bpp - 4 - 4 - 6;
-		/* HSA is not considered in this mode and set to 0 */
+		hbp = (mode->htotal - mode->hsync_start) * cpp - 4 - 4 - 6;
+		/* HSA is not present in this mode and set to 0 */
 		hsa = 0;
 	}
-	dev_dbg(d->dev, "hfp: %u, hbp: %u, hsa: %u\n",
+	if (hfp < 0) {
+		dev_info(d->dev, "hfp negative, set to 0\n");
+		hfp = 0;
+	}
+	if (hbp < 0) {
+		dev_info(d->dev, "hbp negative, set to 0\n");
+		hbp = 0;
+	}
+	if (hsa < 0) {
+		dev_info(d->dev, "hsa negative, set to 0\n");
+		hsa = 0;
+	}
+	dev_dbg(d->dev, "hfp: %u, hbp: %u, hsa: %u bytes\n",
 		hfp, hbp, hsa);
 
 	/* Frame parameters: horizontal sync active */
@@ -474,91 +526,185 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 	val |= hfp << DSI_VID_HSIZE1_HFP_LENGTH_SHIFT;
 	writel(val, d->regs + DSI_VID_HSIZE1);
 
-	/* RGB data length (bytes on one scanline) */
-	val = mode->hdisplay * (bpp / 8);
+	/* RGB data length (visible bytes on one scanline) */
+	val = mode->hdisplay * cpp;
 	writel(val, d->regs + DSI_VID_HSIZE2);
+	dev_dbg(d->dev, "RGB length, visible area on a line: %u bytes\n", val);
 
-	/* TODO: further adjustments for TVG mode here */
+	/*
+	 * Calculate the time between two pixels in picoseconds using
+	 * the supplied refresh rate and total resolution including
+	 * porches and sync.
+	 */
+	/* (ps/s) / (pixels/s) = ps/pixels */
+	pclk = DIV_ROUND_UP_ULL(1000000000000,
+				(mode->vrefresh * mode->htotal * mode->vtotal));
+	dev_dbg(d->dev, "picoseconds between two pixels: %llu\n",
+		pclk);
 
 	/*
-	 * EOL packet length from bits per line calculations: pixel clock
-	 * is given in kHz, calculate the time between two pixels in
-	 * picoseconds.
+	 * How many bytes per line will this update frequency yield?
+	 *
+	 * Calculate the number of picoseconds for one scanline (1), then
+	 * divide by 1000000000000 (2) to get in pixels per second we
+	 * want to output.
+	 *
+	 * Multiply with number of bytes per second at this video display
+	 * frequency (3) to get number of bytes transferred during this
+	 * time. Notice that we use the frequency the display wants,
+	 * not what we actually get from the DSI PLL, which is hs_freq.
+	 *
+	 * These arithmetics are done in a different order to avoid
+	 * overflow.
 	 */
-	bpl = mode->clock * mode->htotal;
-	bpl *= (d->hs_freq / 8);
-	do_div(bpl, 1000000); /* microseconds */
-	do_div(bpl, 1000000); /* seconds */
+	bpl = pclk * mode->htotal; /* (1) picoseconds per line */
+	dev_dbg(d->dev, "picoseconds per line: %llu\n", bpl);
+	/* Multiply with bytes per second (3) */
+	bpl *= (d->mdsi->hs_rate / 8);
+	/* Pixels per second (2) */
+	bpl = DIV_ROUND_DOWN_ULL(bpl, 1000000); /* microseconds */
+	bpl = DIV_ROUND_DOWN_ULL(bpl, 1000000); /* seconds */
+	/* parallel transactions in all lanes */
 	bpl *= d->mdsi->lanes;
-	dev_dbg(d->dev, "calculated bytes per line: %llu\n", bpl);
+	dev_dbg(d->dev,
+		"calculated bytes per line: %llu @ %d Hz with HS %lu Hz\n",
+		bpl, mode->vrefresh, d->mdsi->hs_rate);
+
 	/*
 	 * 6 is header + checksum, header = 4 bytes, checksum = 2 bytes
 	 * 4 is short packet for vsync/hsync
 	 */
 	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) {
-		/* Fixme: isn't the hsync width in pixels? */
+		/* Set the event packet size to 0 (not used) */
+		writel(0, d->regs + DSI_VID_BLKSIZE1);
+		/*
+		 * FIXME: isn't the hsync width in pixels? The porch and
+		 * sync area size is in pixels here, but this -6
+		 * seems to be for bytes. It looks like this in the vendor
+		 * code though. Is it completely untested?
+		 */
 		blkline_pck = bpl - (mode->hsync_end - mode->hsync_start) - 6;
 		val = blkline_pck << DSI_VID_BLKSIZE2_BLKLINE_PULSE_PCK_SHIFT;
 		writel(val, d->regs + DSI_VID_BLKSIZE2);
 	} else {
+		/* Set the sync pulse packet size to 0 (not used) */
+		writel(0, d->regs + DSI_VID_BLKSIZE2);
+		/* Specifying payload size in bytes (-4-6 from manual) */
 		blkline_pck = bpl - 4 - 6;
+		if (blkline_pck > 0x1FFF)
+			dev_err(d->dev, "blkline_pck too big %d bytes\n",
+				blkline_pck);
 		val = blkline_pck << DSI_VID_BLKSIZE1_BLKLINE_EVENT_PCK_SHIFT;
+		val &= DSI_VID_BLKSIZE1_BLKLINE_EVENT_PCK_MASK;
 		writel(val, d->regs + DSI_VID_BLKSIZE1);
 	}
 
-	line_duration = (blkline_pck + 6) / d->mdsi->lanes;
-	dev_dbg(d->dev, "line duration %u\n", line_duration);
+	/*
+	 * The line duration is used to scale back the frequency from
+	 * the max frequency supported by the HS clock to the desired
+	 * update frequency in vrefresh.
+	 */
+	line_duration = blkline_pck + 6;
+	/*
+	 * The datasheet contains this complex condition to decreasing
+	 * the line duration by 1 under very specific circumstances.
+	 * Here we also imply that LP is used during burst EOL.
+	 */
+	if (d->mdsi->lanes == 2 && (hsa & 0x01) && (hfp & 0x01)
+	    && (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST))
+		line_duration--;
+	line_duration = DIV_ROUND_CLOSEST(line_duration, d->mdsi->lanes);
+	dev_dbg(d->dev, "line duration %u bytes\n", line_duration);
 	val = line_duration << DSI_VID_DPHY_TIME_REG_LINE_DURATION_SHIFT;
 	/*
 	 * This is the time to perform LP->HS on D-PHY
 	 * FIXME: nowhere to get this from: DT property on the DSI?
+	 * The manual says this is "system dependent".
+	 * values like 48 and 72 seen in the vendor code.
 	 */
-	val |= 0 << DSI_VID_DPHY_TIME_REG_WAKEUP_TIME_SHIFT;
+	val |= 48 << DSI_VID_DPHY_TIME_REG_WAKEUP_TIME_SHIFT;
 	writel(val, d->regs + DSI_VID_DPHY_TIME);
 
-	/* Calculate block end of line */
-	blkeol_pck = bpl - mode->hdisplay * bpp - 6;
-	blkeol_duration = (blkeol_pck + 6) / d->mdsi->lanes;
-	dev_dbg(d->dev, "blkeol pck: %u, duration: %u\n",
-		 blkeol_pck, blkeol_duration);
-
+	/*
+	 * See the manual figure 657 page 2203 for understanding the impact
+	 * of the different burst mode settings.
+	 */
 	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
-		/* Set up EOL clock for burst mode */
+		int blkeol_pck, blkeol_duration;
+		/*
+		 * Packet size at EOL for burst mode, this is only used
+		 * if DSI_VID_MAIN_CTL_REG_BLKEOL_MODE_LP_0 is NOT set,
+		 * but we instead send NULL or blanking packets at EOL.
+		 * This is given in number of bytes.
+		 *
+		 * See the manual page 2198 for the 13 reg_blkeol_pck bits.
+		 */
+		blkeol_pck = bpl - (mode->htotal * cpp) - 6;
+		if (blkeol_pck < 0) {
+			dev_err(d->dev, "video block does not fit on line!\n");
+			dev_err(d->dev,
+				"calculated bytes per line: %llu @ %d Hz\n",
+				bpl, mode->vrefresh);
+			dev_err(d->dev,
+				"bytes per line (blkline_pck) %u bytes\n",
+				blkline_pck);
+			dev_err(d->dev,
+				"blkeol_pck becomes %d bytes\n", blkeol_pck);
+			return;
+		}
+		dev_dbg(d->dev, "BLKEOL packet: %d bytes\n", blkeol_pck);
+
 		val = readl(d->regs + DSI_VID_BLKSIZE1);
+		val &= ~DSI_VID_BLKSIZE1_BLKEOL_PCK_MASK;
 		val |= blkeol_pck << DSI_VID_BLKSIZE1_BLKEOL_PCK_SHIFT;
 		writel(val, d->regs + DSI_VID_BLKSIZE1);
-		writel(blkeol_pck, d->regs + DSI_VID_VCA_SETTING2);
-
-		writel(blkeol_duration, d->regs + DSI_VID_PCK_TIME);
-		writel(blkeol_duration - 6, d->regs + DSI_VID_VCA_SETTING1);
+		/* Use the same value for exact burst limit */
+		val = blkeol_pck <<
+			DSI_VID_VCA_SETTING2_EXACT_BURST_LIMIT_SHIFT;
+		val &= DSI_VID_VCA_SETTING2_EXACT_BURST_LIMIT_MASK;
+		writel(val, d->regs + DSI_VID_VCA_SETTING2);
+		/*
+		 * This BLKEOL duration is claimed to be the duration in clock
+		 * cycles of the BLLP end-of-line (EOL) period for each line if
+		 * DSI_VID_MAIN_CTL_REG_BLKEOL_MODE_LP_0 is set.
+		 *
+		 * It is hard to trust the manuals' claim that this is in clock
+		 * cycles as we mimic the behaviour of the vendor code, which
+		 * appears to write a number of bytes that would have been
+		 * transferred on a single lane.
+		 *
+		 * See the manual figure 657 page 2203 and page 2198 for the 13
+		 * reg_blkeol_duration bits.
+		 *
+		 * FIXME: should this also be set up also for non-burst mode
+		 * according to figure 565 page 2202?
+		 */
+		blkeol_duration = DIV_ROUND_CLOSEST(blkeol_pck + 6,
+						    d->mdsi->lanes);
+		dev_dbg(d->dev, "BLKEOL duration: %d clock cycles\n",
+			blkeol_duration);
+
+		val = readl(d->regs + DSI_VID_PCK_TIME);
+		val &= ~DSI_VID_PCK_TIME_BLKEOL_DURATION_MASK;
+		val |= blkeol_duration <<
+			DSI_VID_PCK_TIME_BLKEOL_DURATION_SHIFT;
+		writel(val, d->regs + DSI_VID_PCK_TIME);
+
+		/* Max burst limit, this is given in bytes */
+		val = readl(d->regs + DSI_VID_VCA_SETTING1);
+		val &= ~DSI_VID_VCA_SETTING1_MAX_BURST_LIMIT_MASK;
+		val |= (blkeol_pck - 6) <<
+			DSI_VID_VCA_SETTING1_MAX_BURST_LIMIT_SHIFT;
+		writel(val, d->regs + DSI_VID_VCA_SETTING1);
 	}
 
 	/* Maximum line limit */
 	val = readl(d->regs + DSI_VID_VCA_SETTING2);
-	val |= blkline_pck <<
-		DSI_VID_VCA_SETTING2_EXACT_BURST_LIMIT_SHIFT;
+	val &= ~DSI_VID_VCA_SETTING2_MAX_LINE_LIMIT_MASK;
+	val |= (blkline_pck - 6) <<
+		DSI_VID_VCA_SETTING2_MAX_LINE_LIMIT_SHIFT;
 	writel(val, d->regs + DSI_VID_VCA_SETTING2);
-
-	/* Put IF1 into video mode */
-	val = readl(d->regs + DSI_MCTL_MAIN_DATA_CTL);
-	val |= DSI_MCTL_MAIN_DATA_CTL_IF1_MODE;
-	writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
-
-	/* Disable command mode on IF1 */
-	val = readl(d->regs + DSI_CMD_MODE_CTL);
-	val &= ~DSI_CMD_MODE_CTL_IF1_LP_EN;
-	writel(val, d->regs + DSI_CMD_MODE_CTL);
-
-	/* Enable some error interrupts */
-	val = readl(d->regs + DSI_VID_MODE_STS_CTL);
-	val |= DSI_VID_MODE_STS_CTL_ERR_MISSING_VSYNC;
-	val |= DSI_VID_MODE_STS_CTL_ERR_MISSING_DATA;
-	writel(val, d->regs + DSI_VID_MODE_STS_CTL);
-
-	/* Enable video mode */
-	val = readl(d->regs + DSI_MCTL_MAIN_DATA_CTL);
-	val |= DSI_MCTL_MAIN_DATA_CTL_VID_EN;
-	writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
+	dev_dbg(d->dev, "blkline pck: %d bytes\n", blkline_pck - 6);
 }
 
 static void mcde_dsi_start(struct mcde_dsi *d)
@@ -670,30 +816,25 @@ static void mcde_dsi_start(struct mcde_dsi *d)
 static void mcde_dsi_bridge_enable(struct drm_bridge *bridge)
 {
 	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
+	u32 val;
+
+	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
+		/* Enable video mode */
+		val = readl(d->regs + DSI_MCTL_MAIN_DATA_CTL);
+		val |= DSI_MCTL_MAIN_DATA_CTL_VID_EN;
+		writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
+	}
 
 	dev_info(d->dev, "enable DSI master\n");
 };
 
-static void mcde_dsi_bridge_mode_set(struct drm_bridge *bridge,
-				     const struct drm_display_mode *mode,
-				     const struct drm_display_mode *adj)
+static void mcde_dsi_bridge_pre_enable(struct drm_bridge *bridge)
 {
 	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
-	unsigned long pixel_clock_hz = mode->clock * 1000;
 	unsigned long hs_freq, lp_freq;
 	u32 val;
 	int ret;
 
-	if (!d->mdsi) {
-		dev_err(d->dev, "no DSI device attached to encoder!\n");
-		return;
-	}
-
-	dev_info(d->dev, "set DSI master to %dx%d %lu Hz %s mode\n",
-		 mode->hdisplay, mode->vdisplay, pixel_clock_hz,
-		 (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO) ? "VIDEO" : "CMD"
-		);
-
 	/* Copy maximum clock frequencies */
 	if (d->mdsi->lp_rate)
 		lp_freq = d->mdsi->lp_rate;
@@ -732,7 +873,21 @@ static void mcde_dsi_bridge_mode_set(struct drm_bridge *bridge,
 			 d->hs_freq);
 
 	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
-		mcde_dsi_setup_video_mode(d, mode);
+		/* Put IF1 into video mode */
+		val = readl(d->regs + DSI_MCTL_MAIN_DATA_CTL);
+		val |= DSI_MCTL_MAIN_DATA_CTL_IF1_MODE;
+		writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
+
+		/* Disable command mode on IF1 */
+		val = readl(d->regs + DSI_CMD_MODE_CTL);
+		val &= ~DSI_CMD_MODE_CTL_IF1_LP_EN;
+		writel(val, d->regs + DSI_CMD_MODE_CTL);
+
+		/* Enable some error interrupts */
+		val = readl(d->regs + DSI_VID_MODE_STS_CTL);
+		val |= DSI_VID_MODE_STS_CTL_ERR_MISSING_VSYNC;
+		val |= DSI_VID_MODE_STS_CTL_ERR_MISSING_DATA;
+		writel(val, d->regs + DSI_VID_MODE_STS_CTL);
 	} else {
 		/* Command mode, clear IF1 ID */
 		val = readl(d->regs + DSI_CMD_MODE_CTL);
@@ -746,6 +901,26 @@ static void mcde_dsi_bridge_mode_set(struct drm_bridge *bridge,
 	}
 }
 
+static void mcde_dsi_bridge_mode_set(struct drm_bridge *bridge,
+				     const struct drm_display_mode *mode,
+				     const struct drm_display_mode *adj)
+{
+	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
+
+	if (!d->mdsi) {
+		dev_err(d->dev, "no DSI device attached to encoder!\n");
+		return;
+	}
+
+	dev_info(d->dev, "set DSI master to %dx%d %u Hz %s mode\n",
+		 mode->hdisplay, mode->vdisplay, mode->clock * 1000,
+		 (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO) ? "VIDEO" : "CMD"
+		);
+
+	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO)
+		mcde_dsi_setup_video_mode(d, mode);
+}
+
 static void mcde_dsi_wait_for_command_mode_stop(struct mcde_dsi *d)
 {
 	u32 val;
@@ -811,67 +986,23 @@ static void mcde_dsi_bridge_disable(struct drm_bridge *bridge)
 	clk_disable_unprepare(d->lp_clk);
 }
 
-/*
- * This connector needs no special handling, just use the default
- * helpers for everything. It's pretty dummy.
- */
-static const struct drm_connector_funcs mcde_dsi_connector_funcs = {
-	.reset = drm_atomic_helper_connector_reset,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = drm_connector_cleanup,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-};
-
-static int mcde_dsi_get_modes(struct drm_connector *connector)
-{
-	struct mcde_dsi *d = connector_to_mcde_dsi(connector);
-
-	/* Just pass the question to the panel */
-	if (d->panel)
-		return drm_panel_get_modes(d->panel);
-
-	/* TODO: deal with bridges */
-
-	return 0;
-}
-
-static const struct drm_connector_helper_funcs
-mcde_dsi_connector_helper_funcs = {
-	.get_modes = mcde_dsi_get_modes,
-};
-
 static int mcde_dsi_bridge_attach(struct drm_bridge *bridge)
 {
 	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
 	struct drm_device *drm = bridge->dev;
 	int ret;
 
-	drm_connector_helper_add(&d->connector,
-				 &mcde_dsi_connector_helper_funcs);
-
 	if (!drm_core_check_feature(drm, DRIVER_ATOMIC)) {
 		dev_err(d->dev, "we need atomic updates\n");
 		return -ENOTSUPP;
 	}
 
-	ret = drm_connector_init(drm, &d->connector,
-				 &mcde_dsi_connector_funcs,
-				 DRM_MODE_CONNECTOR_DSI);
-	if (ret) {
-		dev_err(d->dev, "failed to initialize DSI bridge connector\n");
-		return ret;
-	}
-	d->connector.polled = DRM_CONNECTOR_POLL_CONNECT;
-	/* The encoder in the bridge attached to the DSI bridge */
-	drm_connector_attach_encoder(&d->connector, bridge->encoder);
-	/* Then we attach the DSI bridge to the output (panel etc) bridge */
+	/* Attach the DSI bridge to the output (panel etc) bridge */
 	ret = drm_bridge_attach(bridge->encoder, d->bridge_out, bridge);
 	if (ret) {
 		dev_err(d->dev, "failed to attach the DSI bridge\n");
 		return ret;
 	}
-	d->connector.status = connector_status_connected;
 
 	return 0;
 }
@@ -881,6 +1012,7 @@ static const struct drm_bridge_funcs mcde_dsi_bridge_funcs = {
 	.mode_set = mcde_dsi_bridge_mode_set,
 	.disable = mcde_dsi_bridge_disable,
 	.enable = mcde_dsi_bridge_enable,
+	.pre_enable = mcde_dsi_bridge_pre_enable,
 };
 
 static int mcde_dsi_bind(struct device *dev, struct device *master,
@@ -901,7 +1033,7 @@ static int mcde_dsi_bind(struct device *dev, struct device *master,
 	d->mcde = mcde;
 	/* If the display attached before binding, set this up */
 	if (d->mdsi)
-		d->mcde->mdsi = d->mdsi;
+		mcde_dsi_attach_to_mcde(d);
 
 	/* Obtain the clocks */
 	d->hs_clk = devm_clk_get(dev, "hs");
diff --git a/drivers/gpu/drm/mcde/mcde_dsi_regs.h b/drivers/gpu/drm/mcde/mcde_dsi_regs.h
index c9253321a3be..16551af1089e 100644
--- a/drivers/gpu/drm/mcde/mcde_dsi_regs.h
+++ b/drivers/gpu/drm/mcde/mcde_dsi_regs.h
@@ -123,17 +123,6 @@
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_LONGNOTSHORT BIT(3)
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SHIFT 8
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_MASK 0x00003F00
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_TURN_ON_PERIPHERAL 50
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SHUT_DOWN_PERIPHERAL 34
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_GENERIC_SHORT_WRITE_0 3
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_GENERIC_SHORT_WRITE_1 19
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_GENERIC_SHORT_WRITE_2 35
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_GENERIC_LONG_WRITE 41
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_SHORT_WRITE_0 5
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_SHORT_WRITE_1 21
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_LONG_WRITE 57
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_READ 6
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SET_MAX_PKT_SIZE 55
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_ID_SHIFT 14
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_SIZE_SHIFT 16
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_LP_EN BIT(21)
@@ -239,6 +228,7 @@
 
 #define DSI_VID_PCK_TIME 0x000000A8
 #define DSI_VID_PCK_TIME_BLKEOL_DURATION_SHIFT 0
+#define DSI_VID_PCK_TIME_BLKEOL_DURATION_MASK 0x00000FFF
 
 #define DSI_VID_DPHY_TIME 0x000000AC
 #define DSI_VID_DPHY_TIME_REG_LINE_DURATION_SHIFT 0
@@ -248,6 +238,16 @@
 
 #define DSI_VID_MODE_STS 0x000000BC
 #define DSI_VID_MODE_STS_VSG_RUNNING BIT(0)
+#define DSI_VID_MODE_STS_ERR_MISSING_DATA BIT(1)
+#define DSI_VID_MODE_STS_ERR_MISSING_HSYNC BIT(2)
+#define DSI_VID_MODE_STS_ERR_MISSING_VSYNC BIT(3)
+#define DSI_VID_MODE_STS_REG_ERR_SMALL_LENGTH BIT(4)
+#define DSI_VID_MODE_STS_REG_ERR_SMALL_HEIGHT BIT(5)
+#define DSI_VID_MODE_STS_ERR_BURSTWRITE BIT(6)
+#define DSI_VID_MODE_STS_ERR_LINEWRITE BIT(7)
+#define DSI_VID_MODE_STS_ERR_LONGREAD BIT(8)
+#define DSI_VID_MODE_STS_ERR_VRS_WRONG_LENGTH BIT(9)
+#define DSI_VID_MODE_STS_VSG_RECOVERY BIT(10)
 
 #define DSI_VID_VCA_SETTING1 0x000000C0
 #define DSI_VID_VCA_SETTING1_MAX_BURST_LIMIT_SHIFT 0
diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile
index 8067a4be8311..b7a82ed5788f 100644
--- a/drivers/gpu/drm/mediatek/Makefile
+++ b/drivers/gpu/drm/mediatek/Makefile
@@ -7,7 +7,6 @@ mediatek-drm-y := mtk_disp_color.o \
 		  mtk_drm_ddp.o \
 		  mtk_drm_ddp_comp.o \
 		  mtk_drm_drv.o \
-		  mtk_drm_fb.o \
 		  mtk_drm_gem.o \
 		  mtk_drm_plane.o \
 		  mtk_dsi.o \
@@ -21,7 +20,7 @@ obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o
 mediatek-drm-hdmi-objs := mtk_cec.o \
 			  mtk_hdmi.o \
 			  mtk_hdmi_ddc.o \
-                          mtk_mt2701_hdmi_phy.o \
+			  mtk_mt2701_hdmi_phy.o \
 			  mtk_mt8173_hdmi_phy.o \
 			  mtk_hdmi_phy.o
 
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_color.c b/drivers/gpu/drm/mediatek/mtk_disp_color.c
index 59de2a46aa49..6fb0d6983a4a 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_color.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_color.c
@@ -9,6 +9,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -45,12 +46,12 @@ static inline struct mtk_disp_color *comp_to_color(struct mtk_ddp_comp *comp)
 
 static void mtk_color_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_color *color = comp_to_color(comp);
 
-	writel(w, comp->regs + DISP_COLOR_WIDTH(color));
-	writel(h, comp->regs + DISP_COLOR_HEIGHT(color));
+	mtk_ddp_write(cmdq_pkt, w, comp, DISP_COLOR_WIDTH(color));
+	mtk_ddp_write(cmdq_pkt, h, comp, DISP_COLOR_HEIGHT(color));
 }
 
 static void mtk_color_start(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 4a55bb6e2213..891d80c73e04 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -11,6 +11,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -124,14 +125,15 @@ static void mtk_ovl_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_ovl_config(struct mtk_ddp_comp *comp, unsigned int w,
 			   unsigned int h, unsigned int vrefresh,
-			   unsigned int bpc)
+			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	if (w != 0 && h != 0)
-		writel_relaxed(h << 16 | w, comp->regs + DISP_REG_OVL_ROI_SIZE);
-	writel_relaxed(0x0, comp->regs + DISP_REG_OVL_ROI_BGCLR);
+		mtk_ddp_write_relaxed(cmdq_pkt, h << 16 | w, comp,
+				      DISP_REG_OVL_ROI_SIZE);
+	mtk_ddp_write_relaxed(cmdq_pkt, 0x0, comp, DISP_REG_OVL_ROI_BGCLR);
 
-	writel(0x1, comp->regs + DISP_REG_OVL_RST);
-	writel(0x0, comp->regs + DISP_REG_OVL_RST);
+	mtk_ddp_write(cmdq_pkt, 0x1, comp, DISP_REG_OVL_RST);
+	mtk_ddp_write(cmdq_pkt, 0x0, comp, DISP_REG_OVL_RST);
 }
 
 static unsigned int mtk_ovl_layer_nr(struct mtk_ddp_comp *comp)
@@ -175,16 +177,16 @@ static int mtk_ovl_layer_check(struct mtk_ddp_comp *comp, unsigned int idx,
 	return 0;
 }
 
-static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
+static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx,
+			     struct cmdq_pkt *cmdq_pkt)
 {
-	unsigned int reg;
 	unsigned int gmc_thrshd_l;
 	unsigned int gmc_thrshd_h;
 	unsigned int gmc_value;
 	struct mtk_disp_ovl *ovl = comp_to_ovl(comp);
 
-	writel(0x1, comp->regs + DISP_REG_OVL_RDMA_CTRL(idx));
-
+	mtk_ddp_write(cmdq_pkt, 0x1, comp,
+		      DISP_REG_OVL_RDMA_CTRL(idx));
 	gmc_thrshd_l = GMC_THRESHOLD_LOW >>
 		      (GMC_THRESHOLD_BITS - ovl->data->gmc_bits);
 	gmc_thrshd_h = GMC_THRESHOLD_HIGH >>
@@ -194,22 +196,19 @@ static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
 	else
 		gmc_value = gmc_thrshd_l | gmc_thrshd_l << 8 |
 			    gmc_thrshd_h << 16 | gmc_thrshd_h << 24;
-	writel(gmc_value, comp->regs + DISP_REG_OVL_RDMA_GMC(idx));
-
-	reg = readl(comp->regs + DISP_REG_OVL_SRC_CON);
-	reg = reg | BIT(idx);
-	writel(reg, comp->regs + DISP_REG_OVL_SRC_CON);
+	mtk_ddp_write(cmdq_pkt, gmc_value,
+		      comp, DISP_REG_OVL_RDMA_GMC(idx));
+	mtk_ddp_write_mask(cmdq_pkt, BIT(idx), comp,
+			   DISP_REG_OVL_SRC_CON, BIT(idx));
 }
 
-static void mtk_ovl_layer_off(struct mtk_ddp_comp *comp, unsigned int idx)
+static void mtk_ovl_layer_off(struct mtk_ddp_comp *comp, unsigned int idx,
+			      struct cmdq_pkt *cmdq_pkt)
 {
-	unsigned int reg;
-
-	reg = readl(comp->regs + DISP_REG_OVL_SRC_CON);
-	reg = reg & ~BIT(idx);
-	writel(reg, comp->regs + DISP_REG_OVL_SRC_CON);
-
-	writel(0x0, comp->regs + DISP_REG_OVL_RDMA_CTRL(idx));
+	mtk_ddp_write_mask(cmdq_pkt, 0, comp,
+			   DISP_REG_OVL_SRC_CON, BIT(idx));
+	mtk_ddp_write(cmdq_pkt, 0, comp,
+		      DISP_REG_OVL_RDMA_CTRL(idx));
 }
 
 static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt)
@@ -249,7 +248,8 @@ static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt)
 }
 
 static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
-				 struct mtk_plane_state *state)
+				 struct mtk_plane_state *state,
+				 struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_ovl *ovl = comp_to_ovl(comp);
 	struct mtk_plane_pending_state *pending = &state->pending;
@@ -260,11 +260,13 @@ static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 	unsigned int src_size = (pending->height << 16) | pending->width;
 	unsigned int con;
 
-	if (!pending->enable)
-		mtk_ovl_layer_off(comp, idx);
+	if (!pending->enable) {
+		mtk_ovl_layer_off(comp, idx, cmdq_pkt);
+		return;
+	}
 
 	con = ovl_fmt_convert(ovl, fmt);
-	if (idx != 0)
+	if (state->base.fb->format->has_alpha)
 		con |= OVL_CON_AEN | OVL_CON_ALPHA;
 
 	if (pending->rotation & DRM_MODE_REFLECT_Y) {
@@ -277,14 +279,18 @@ static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 		addr += pending->pitch - 1;
 	}
 
-	writel_relaxed(con, comp->regs + DISP_REG_OVL_CON(idx));
-	writel_relaxed(pitch, comp->regs + DISP_REG_OVL_PITCH(idx));
-	writel_relaxed(src_size, comp->regs + DISP_REG_OVL_SRC_SIZE(idx));
-	writel_relaxed(offset, comp->regs + DISP_REG_OVL_OFFSET(idx));
-	writel_relaxed(addr, comp->regs + DISP_REG_OVL_ADDR(ovl, idx));
-
-	if (pending->enable)
-		mtk_ovl_layer_on(comp, idx);
+	mtk_ddp_write_relaxed(cmdq_pkt, con, comp,
+			      DISP_REG_OVL_CON(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, pitch, comp,
+			      DISP_REG_OVL_PITCH(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, src_size, comp,
+			      DISP_REG_OVL_SRC_SIZE(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, offset, comp,
+			      DISP_REG_OVL_OFFSET(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, addr, comp,
+			      DISP_REG_OVL_ADDR(ovl, idx));
+
+	mtk_ovl_layer_on(comp, idx, cmdq_pkt);
 }
 
 static void mtk_ovl_bgclr_in_on(struct mtk_ddp_comp *comp)
@@ -313,8 +319,6 @@ static const struct mtk_ddp_comp_funcs mtk_disp_ovl_funcs = {
 	.disable_vblank = mtk_ovl_disable_vblank,
 	.supported_rotations = mtk_ovl_supported_rotations,
 	.layer_nr = mtk_ovl_layer_nr,
-	.layer_on = mtk_ovl_layer_on,
-	.layer_off = mtk_ovl_layer_off,
 	.layer_check = mtk_ovl_layer_check,
 	.layer_config = mtk_ovl_layer_config,
 	.bgclr_in_on = mtk_ovl_bgclr_in_on,
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
index 405afef31407..0cb848d64206 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
@@ -9,6 +9,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -125,14 +126,16 @@ static void mtk_rdma_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_rdma_config(struct mtk_ddp_comp *comp, unsigned int width,
 			    unsigned int height, unsigned int vrefresh,
-			    unsigned int bpc)
+			    unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	unsigned int threshold;
 	unsigned int reg;
 	struct mtk_disp_rdma *rdma = comp_to_rdma(comp);
 
-	rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0, 0xfff, width);
-	rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_1, 0xfffff, height);
+	mtk_ddp_write_mask(cmdq_pkt, width, comp,
+			   DISP_REG_RDMA_SIZE_CON_0, 0xfff);
+	mtk_ddp_write_mask(cmdq_pkt, height, comp,
+			   DISP_REG_RDMA_SIZE_CON_1, 0xfffff);
 
 	/*
 	 * Enable FIFO underflow since DSI and DPI can't be blocked.
@@ -144,7 +147,7 @@ static void mtk_rdma_config(struct mtk_ddp_comp *comp, unsigned int width,
 	reg = RDMA_FIFO_UNDERFLOW_EN |
 	      RDMA_FIFO_PSEUDO_SIZE(RDMA_FIFO_SIZE(rdma)) |
 	      RDMA_OUTPUT_VALID_FIFO_THRESHOLD(threshold);
-	writel(reg, comp->regs + DISP_REG_RDMA_FIFO_CON);
+	mtk_ddp_write(cmdq_pkt, reg, comp, DISP_REG_RDMA_FIFO_CON);
 }
 
 static unsigned int rdma_fmt_convert(struct mtk_disp_rdma *rdma,
@@ -190,7 +193,8 @@ static unsigned int mtk_rdma_layer_nr(struct mtk_ddp_comp *comp)
 }
 
 static void mtk_rdma_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
-				  struct mtk_plane_state *state)
+				  struct mtk_plane_state *state,
+				  struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_rdma *rdma = comp_to_rdma(comp);
 	struct mtk_plane_pending_state *pending = &state->pending;
@@ -200,24 +204,27 @@ static void mtk_rdma_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 	unsigned int con;
 
 	con = rdma_fmt_convert(rdma, fmt);
-	writel_relaxed(con, comp->regs + DISP_RDMA_MEM_CON);
+	mtk_ddp_write_relaxed(cmdq_pkt, con, comp, DISP_RDMA_MEM_CON);
 
 	if (fmt == DRM_FORMAT_UYVY || fmt == DRM_FORMAT_YUYV) {
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_ENABLE, RDMA_MATRIX_ENABLE);
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_INT_MTX_SEL,
-				 RDMA_MATRIX_INT_MTX_BT601_to_RGB);
+		mtk_ddp_write_mask(cmdq_pkt, RDMA_MATRIX_ENABLE, comp,
+				   DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_ENABLE);
+		mtk_ddp_write_mask(cmdq_pkt, RDMA_MATRIX_INT_MTX_BT601_to_RGB,
+				   comp, DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_INT_MTX_SEL);
 	} else {
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_ENABLE, 0);
+		mtk_ddp_write_mask(cmdq_pkt, 0, comp,
+				   DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_ENABLE);
 	}
+	mtk_ddp_write_relaxed(cmdq_pkt, addr, comp, DISP_RDMA_MEM_START_ADDR);
+	mtk_ddp_write_relaxed(cmdq_pkt, pitch, comp, DISP_RDMA_MEM_SRC_PITCH);
+	mtk_ddp_write(cmdq_pkt, RDMA_MEM_GMC, comp,
+		      DISP_RDMA_MEM_GMC_SETTING_0);
+	mtk_ddp_write_mask(cmdq_pkt, RDMA_MODE_MEMORY, comp,
+			   DISP_REG_RDMA_GLOBAL_CON, RDMA_MODE_MEMORY);
 
-	writel_relaxed(addr, comp->regs + DISP_RDMA_MEM_START_ADDR);
-	writel_relaxed(pitch, comp->regs + DISP_RDMA_MEM_SRC_PITCH);
-	writel(RDMA_MEM_GMC, comp->regs + DISP_RDMA_MEM_GMC_SETTING_0);
-	rdma_update_bits(comp, DISP_REG_RDMA_GLOBAL_CON,
-			 RDMA_MODE_MEMORY, RDMA_MODE_MEMORY);
 }
 
 static const struct mtk_ddp_comp_funcs mtk_disp_rdma_funcs = {
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 3305a94fc930..0dfcd1787e65 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -5,6 +5,7 @@
 
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include <asm/barrier.h>
 #include <soc/mediatek/smi.h>
@@ -42,11 +43,20 @@ struct mtk_drm_crtc {
 	struct drm_plane		*planes;
 	unsigned int			layer_nr;
 	bool				pending_planes;
+	bool				pending_async_planes;
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct cmdq_client		*cmdq_client;
+	u32				cmdq_event;
+#endif
 
 	void __iomem			*config_regs;
 	struct mtk_disp_mutex		*mutex;
 	unsigned int			ddp_comp_nr;
 	struct mtk_ddp_comp		**ddp_comp;
+
+	/* lock for display hardware access */
+	struct mutex			hw_lock;
 };
 
 struct mtk_crtc_state {
@@ -230,6 +240,13 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
 	return NULL;
 }
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+static void ddp_cmdq_cb(struct cmdq_cb_data data)
+{
+	cmdq_pkt_destroy(data.data);
+}
+#endif
+
 static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_crtc *crtc = &mtk_crtc->base;
@@ -298,7 +315,7 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 		if (i == 1)
 			mtk_ddp_comp_bgclr_in_on(comp);
 
-		mtk_ddp_comp_config(comp, width, height, vrefresh, bpc);
+		mtk_ddp_comp_config(comp, width, height, vrefresh, bpc, NULL);
 		mtk_ddp_comp_start(comp);
 	}
 
@@ -313,7 +330,7 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 		comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
 		if (comp)
 			mtk_ddp_comp_layer_config(comp, local_layer,
-						  plane_state);
+						  plane_state, NULL);
 	}
 
 	return 0;
@@ -328,6 +345,7 @@ err_pm_runtime_put:
 static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_device *drm = mtk_crtc->base.dev;
+	struct drm_crtc *crtc = &mtk_crtc->base;
 	int i;
 
 	DRM_DEBUG_DRIVER("%s\n", __func__);
@@ -353,9 +371,17 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 	mtk_disp_mutex_unprepare(mtk_crtc->mutex);
 
 	pm_runtime_put(drm->dev);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
 }
 
-static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
+static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
+				struct cmdq_pkt *cmdq_handle)
 {
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_crtc_state *state = to_mtk_crtc_state(mtk_crtc->base.state);
@@ -371,7 +397,8 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 	if (state->pending_config) {
 		mtk_ddp_comp_config(comp, state->pending_width,
 				    state->pending_height,
-				    state->pending_vrefresh, 0);
+				    state->pending_vrefresh, 0,
+				    cmdq_handle);
 
 		state->pending_config = false;
 	}
@@ -391,11 +418,82 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 
 			if (comp)
 				mtk_ddp_comp_layer_config(comp, local_layer,
-							  plane_state);
+							  plane_state,
+							  cmdq_handle);
 			plane_state->pending.config = false;
 		}
 		mtk_crtc->pending_planes = false;
 	}
+
+	if (mtk_crtc->pending_async_planes) {
+		for (i = 0; i < mtk_crtc->layer_nr; i++) {
+			struct drm_plane *plane = &mtk_crtc->planes[i];
+			struct mtk_plane_state *plane_state;
+
+			plane_state = to_mtk_plane_state(plane->state);
+
+			if (!plane_state->pending.async_config)
+				continue;
+
+			comp = mtk_drm_ddp_comp_for_plane(crtc, plane,
+							  &local_layer);
+
+			if (comp)
+				mtk_ddp_comp_layer_config(comp, local_layer,
+							  plane_state,
+							  cmdq_handle);
+			plane_state->pending.async_config = false;
+		}
+		mtk_crtc->pending_async_planes = false;
+	}
+}
+
+static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct cmdq_pkt *cmdq_handle;
+#endif
+	struct drm_crtc *crtc = &mtk_crtc->base;
+	struct mtk_drm_private *priv = crtc->dev->dev_private;
+	unsigned int pending_planes = 0, pending_async_planes = 0;
+	int i;
+
+	mutex_lock(&mtk_crtc->hw_lock);
+	for (i = 0; i < mtk_crtc->layer_nr; i++) {
+		struct drm_plane *plane = &mtk_crtc->planes[i];
+		struct mtk_plane_state *plane_state;
+
+		plane_state = to_mtk_plane_state(plane->state);
+		if (plane_state->pending.dirty) {
+			plane_state->pending.config = true;
+			plane_state->pending.dirty = false;
+			pending_planes |= BIT(i);
+		} else if (plane_state->pending.async_dirty) {
+			plane_state->pending.async_config = true;
+			plane_state->pending.async_dirty = false;
+			pending_async_planes |= BIT(i);
+		}
+	}
+	if (pending_planes)
+		mtk_crtc->pending_planes = true;
+	if (pending_async_planes)
+		mtk_crtc->pending_async_planes = true;
+
+	if (priv->data->shadow_register) {
+		mtk_disp_mutex_acquire(mtk_crtc->mutex);
+		mtk_crtc_ddp_config(crtc, NULL);
+		mtk_disp_mutex_release(mtk_crtc->mutex);
+	}
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (mtk_crtc->cmdq_client) {
+		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
+		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
+		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event);
+		mtk_crtc_ddp_config(crtc, cmdq_handle);
+		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
+	}
+#endif
+	mutex_unlock(&mtk_crtc->hw_lock);
 }
 
 int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
@@ -410,6 +508,20 @@ int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 	return 0;
 }
 
+void mtk_drm_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
+			       struct drm_plane_state *new_state)
+{
+	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	const struct drm_plane_helper_funcs *plane_helper_funcs =
+			plane->helper_private;
+
+	if (!mtk_crtc->enabled)
+		return;
+
+	plane_helper_funcs->atomic_update(plane, new_state);
+	mtk_drm_crtc_hw_config(mtk_crtc);
+}
+
 static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc,
 				       struct drm_crtc_state *old_state)
 {
@@ -457,6 +569,7 @@ static void mtk_drm_crtc_atomic_disable(struct drm_crtc *crtc,
 	}
 	mtk_crtc->pending_planes = true;
 
+	mtk_drm_crtc_hw_config(mtk_crtc);
 	/* Wait for planes to be disabled */
 	drm_crtc_wait_one_vblank(crtc);
 
@@ -488,34 +601,16 @@ static void mtk_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 				      struct drm_crtc_state *old_crtc_state)
 {
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
-	struct mtk_drm_private *priv = crtc->dev->dev_private;
-	unsigned int pending_planes = 0;
 	int i;
 
 	if (mtk_crtc->event)
 		mtk_crtc->pending_needs_vblank = true;
-	for (i = 0; i < mtk_crtc->layer_nr; i++) {
-		struct drm_plane *plane = &mtk_crtc->planes[i];
-		struct mtk_plane_state *plane_state;
-
-		plane_state = to_mtk_plane_state(plane->state);
-		if (plane_state->pending.dirty) {
-			plane_state->pending.config = true;
-			plane_state->pending.dirty = false;
-			pending_planes |= BIT(i);
-		}
-	}
-	if (pending_planes)
-		mtk_crtc->pending_planes = true;
 	if (crtc->state->color_mgmt_changed)
-		for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
+		for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 			mtk_ddp_gamma_set(mtk_crtc->ddp_comp[i], crtc->state);
-
-	if (priv->data->shadow_register) {
-		mtk_disp_mutex_acquire(mtk_crtc->mutex);
-		mtk_crtc_ddp_config(crtc);
-		mtk_disp_mutex_release(mtk_crtc->mutex);
-	}
+			mtk_ddp_ctm_set(mtk_crtc->ddp_comp[i], crtc->state);
+		}
+	mtk_drm_crtc_hw_config(mtk_crtc);
 }
 
 static const struct drm_crtc_funcs mtk_crtc_funcs = {
@@ -565,8 +660,12 @@ void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *comp)
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (!priv->data->shadow_register && !mtk_crtc->cmdq_client)
+#else
 	if (!priv->data->shadow_register)
-		mtk_crtc_ddp_config(crtc);
+#endif
+		mtk_crtc_ddp_config(crtc, NULL);
 
 	mtk_drm_finish_page_flip(mtk_crtc);
 }
@@ -633,6 +732,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	int pipe = priv->num_pipes;
 	int ret;
 	int i;
+	bool has_ctm = false;
+	uint gamma_lut_size = 0;
 
 	if (!path)
 		return 0;
@@ -683,6 +784,14 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 		}
 
 		mtk_crtc->ddp_comp[i] = comp;
+
+		if (comp->funcs) {
+			if (comp->funcs->gamma_set)
+				gamma_lut_size = MTK_LUT_SIZE;
+
+			if (comp->funcs->ctm_set)
+				has_ctm = true;
+		}
 	}
 
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
@@ -703,9 +812,28 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 				NULL, pipe);
 	if (ret < 0)
 		return ret;
-	drm_mode_crtc_set_gamma_size(&mtk_crtc->base, MTK_LUT_SIZE);
-	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, false, MTK_LUT_SIZE);
-	priv->num_pipes++;
 
+	if (gamma_lut_size)
+		drm_mode_crtc_set_gamma_size(&mtk_crtc->base, gamma_lut_size);
+	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, has_ctm, gamma_lut_size);
+	priv->num_pipes++;
+	mutex_init(&mtk_crtc->hw_lock);
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	mtk_crtc->cmdq_client =
+			cmdq_mbox_create(dev, drm_crtc_index(&mtk_crtc->base),
+					 2000);
+	if (IS_ERR(mtk_crtc->cmdq_client)) {
+		dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n",
+			drm_crtc_index(&mtk_crtc->base));
+		mtk_crtc->cmdq_client = NULL;
+	}
+	ret = of_property_read_u32_index(dev->of_node, "mediatek,gce-events",
+					 drm_crtc_index(&mtk_crtc->base),
+					 &mtk_crtc->cmdq_event);
+	if (ret)
+		dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n",
+			drm_crtc_index(&mtk_crtc->base));
+#endif
 	return 0;
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.h b/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
index 6afe1c19557a..a2b4677a451c 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
@@ -21,5 +21,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			unsigned int path_len);
 int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 			     struct mtk_plane_state *state);
+void mtk_drm_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
+			       struct drm_plane_state *plane_state);
 
 #endif /* MTK_DRM_CRTC_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 7f21307cda75..1f5a112bb034 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -12,7 +12,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
-
+#include <linux/soc/mediatek/mtk-cmdq.h>
 #include "mtk_drm_drv.h"
 #include "mtk_drm_plane.h"
 #include "mtk_drm_ddp_comp.h"
@@ -37,7 +37,15 @@
 #define CCORR_EN				BIT(0)
 #define DISP_CCORR_CFG				0x0020
 #define CCORR_RELAY_MODE			BIT(0)
+#define CCORR_ENGINE_EN				BIT(1)
+#define CCORR_GAMMA_OFF				BIT(2)
+#define CCORR_WGAMUT_SRC_CLIP			BIT(3)
 #define DISP_CCORR_SIZE				0x0030
+#define DISP_CCORR_COEF_0			0x0080
+#define DISP_CCORR_COEF_1			0x0084
+#define DISP_CCORR_COEF_2			0x0088
+#define DISP_CCORR_COEF_3			0x008C
+#define DISP_CCORR_COEF_4			0x0090
 
 #define DISP_DITHER_EN				0x0000
 #define DITHER_EN				BIT(0)
@@ -76,36 +84,84 @@
 #define DITHER_ADD_LSHIFT_G(x)			(((x) & 0x7) << 4)
 #define DITHER_ADD_RSHIFT_G(x)			(((x) & 0x7) << 0)
 
+void mtk_ddp_write(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+		   struct mtk_ddp_comp *comp, unsigned int offset)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt)
+		cmdq_pkt_write(cmdq_pkt, comp->subsys,
+			       comp->regs_pa + offset, value);
+	else
+#endif
+		writel(value, comp->regs + offset);
+}
+
+void mtk_ddp_write_relaxed(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			   struct mtk_ddp_comp *comp,
+			   unsigned int offset)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt)
+		cmdq_pkt_write(cmdq_pkt, comp->subsys,
+			       comp->regs_pa + offset, value);
+	else
+#endif
+		writel_relaxed(value, comp->regs + offset);
+}
+
+void mtk_ddp_write_mask(struct cmdq_pkt *cmdq_pkt,
+			unsigned int value,
+			struct mtk_ddp_comp *comp,
+			unsigned int offset,
+			unsigned int mask)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt) {
+		cmdq_pkt_write_mask(cmdq_pkt, comp->subsys,
+				    comp->regs_pa + offset, value, mask);
+	} else {
+#endif
+		u32 tmp = readl(comp->regs + offset);
+
+		tmp = (tmp & ~mask) | (value & mask);
+		writel(tmp, comp->regs + offset);
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	}
+#endif
+}
+
 void mtk_dither_set(struct mtk_ddp_comp *comp, unsigned int bpc,
-		    unsigned int CFG)
+		    unsigned int CFG, struct cmdq_pkt *cmdq_pkt)
 {
 	/* If bpc equal to 0, the dithering function didn't be enabled */
 	if (bpc == 0)
 		return;
 
 	if (bpc >= MTK_MIN_BPC) {
-		writel(0, comp->regs + DISP_DITHER_5);
-		writel(0, comp->regs + DISP_DITHER_7);
-		writel(DITHER_LSB_ERR_SHIFT_R(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_R(MTK_MAX_BPC - bpc) |
-		       DITHER_NEW_BIT_MODE,
-		       comp->regs + DISP_DITHER_15);
-		writel(DITHER_LSB_ERR_SHIFT_B(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_B(MTK_MAX_BPC - bpc) |
-		       DITHER_LSB_ERR_SHIFT_G(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_G(MTK_MAX_BPC - bpc),
-		       comp->regs + DISP_DITHER_16);
-		writel(DISP_DITHERING, comp->regs + CFG);
+		mtk_ddp_write(cmdq_pkt, 0, comp, DISP_DITHER_5);
+		mtk_ddp_write(cmdq_pkt, 0, comp, DISP_DITHER_7);
+		mtk_ddp_write(cmdq_pkt,
+			      DITHER_LSB_ERR_SHIFT_R(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_R(MTK_MAX_BPC - bpc) |
+			      DITHER_NEW_BIT_MODE,
+			      comp, DISP_DITHER_15);
+		mtk_ddp_write(cmdq_pkt,
+			      DITHER_LSB_ERR_SHIFT_B(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_B(MTK_MAX_BPC - bpc) |
+			      DITHER_LSB_ERR_SHIFT_G(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_G(MTK_MAX_BPC - bpc),
+			      comp, DISP_DITHER_16);
+		mtk_ddp_write(cmdq_pkt, DISP_DITHERING, comp, CFG);
 	}
 }
 
 static void mtk_od_config(struct mtk_ddp_comp *comp, unsigned int w,
 			  unsigned int h, unsigned int vrefresh,
-			  unsigned int bpc)
+			  unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(w << 16 | h, comp->regs + DISP_OD_SIZE);
-	writel(OD_RELAYMODE, comp->regs + DISP_OD_CFG);
-	mtk_dither_set(comp, bpc, DISP_OD_CFG);
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, comp, DISP_OD_SIZE);
+	mtk_ddp_write(cmdq_pkt, OD_RELAYMODE, comp, DISP_OD_CFG);
+	mtk_dither_set(comp, bpc, DISP_OD_CFG, cmdq_pkt);
 }
 
 static void mtk_od_start(struct mtk_ddp_comp *comp)
@@ -120,9 +176,9 @@ static void mtk_ufoe_start(struct mtk_ddp_comp *comp)
 
 static void mtk_aal_config(struct mtk_ddp_comp *comp, unsigned int w,
 			   unsigned int h, unsigned int vrefresh,
-			   unsigned int bpc)
+			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_AAL_SIZE);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_AAL_SIZE);
 }
 
 static void mtk_aal_start(struct mtk_ddp_comp *comp)
@@ -137,10 +193,10 @@ static void mtk_aal_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_ccorr_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_CCORR_SIZE);
-	writel(CCORR_RELAY_MODE, comp->regs + DISP_CCORR_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_CCORR_SIZE);
+	mtk_ddp_write(cmdq_pkt, CCORR_ENGINE_EN, comp, DISP_CCORR_CFG);
 }
 
 static void mtk_ccorr_start(struct mtk_ddp_comp *comp)
@@ -153,12 +209,63 @@ static void mtk_ccorr_stop(struct mtk_ddp_comp *comp)
 	writel_relaxed(0x0, comp->regs + DISP_CCORR_EN);
 }
 
+/* Converts a DRM S31.32 value to the HW S1.10 format. */
+static u16 mtk_ctm_s31_32_to_s1_10(u64 in)
+{
+	u16 r;
+
+	/* Sign bit. */
+	r = in & BIT_ULL(63) ? BIT(11) : 0;
+
+	if ((in & GENMASK_ULL(62, 33)) > 0) {
+		/* identity value 0x100000000 -> 0x400, */
+		/* if bigger this, set it to max 0x7ff. */
+		r |= GENMASK(10, 0);
+	} else {
+		/* take the 11 most important bits. */
+		r |= (in >> 22) & GENMASK(10, 0);
+	}
+
+	return r;
+}
+
+static void mtk_ccorr_ctm_set(struct mtk_ddp_comp *comp,
+			      struct drm_crtc_state *state)
+{
+	struct drm_property_blob *blob = state->ctm;
+	struct drm_color_ctm *ctm;
+	const u64 *input;
+	uint16_t coeffs[9] = { 0 };
+	int i;
+	struct cmdq_pkt *cmdq_pkt = NULL;
+
+	if (!blob)
+		return;
+
+	ctm = (struct drm_color_ctm *)blob->data;
+	input = ctm->matrix;
+
+	for (i = 0; i < ARRAY_SIZE(coeffs); i++)
+		coeffs[i] = mtk_ctm_s31_32_to_s1_10(input[i]);
+
+	mtk_ddp_write(cmdq_pkt, coeffs[0] << 16 | coeffs[1],
+		      comp, DISP_CCORR_COEF_0);
+	mtk_ddp_write(cmdq_pkt, coeffs[2] << 16 | coeffs[3],
+		      comp, DISP_CCORR_COEF_1);
+	mtk_ddp_write(cmdq_pkt, coeffs[4] << 16 | coeffs[5],
+		      comp, DISP_CCORR_COEF_2);
+	mtk_ddp_write(cmdq_pkt, coeffs[6] << 16 | coeffs[7],
+		      comp, DISP_CCORR_COEF_3);
+	mtk_ddp_write(cmdq_pkt, coeffs[8] << 16,
+		      comp, DISP_CCORR_COEF_4);
+}
+
 static void mtk_dither_config(struct mtk_ddp_comp *comp, unsigned int w,
 			      unsigned int h, unsigned int vrefresh,
-			      unsigned int bpc)
+			      unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_DITHER_SIZE);
-	writel(DITHER_RELAY_MODE, comp->regs + DISP_DITHER_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_DITHER_SIZE);
+	mtk_ddp_write(cmdq_pkt, DITHER_RELAY_MODE, comp, DISP_DITHER_CFG);
 }
 
 static void mtk_dither_start(struct mtk_ddp_comp *comp)
@@ -173,10 +280,10 @@ static void mtk_dither_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_gamma_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_GAMMA_SIZE);
-	mtk_dither_set(comp, bpc, DISP_GAMMA_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_GAMMA_SIZE);
+	mtk_dither_set(comp, bpc, DISP_GAMMA_CFG, cmdq_pkt);
 }
 
 static void mtk_gamma_start(struct mtk_ddp_comp *comp)
@@ -223,6 +330,7 @@ static const struct mtk_ddp_comp_funcs ddp_ccorr = {
 	.config = mtk_ccorr_config,
 	.start = mtk_ccorr_start,
 	.stop = mtk_ccorr_stop,
+	.ctm_set = mtk_ccorr_ctm_set,
 };
 
 static const struct mtk_ddp_comp_funcs ddp_dither = {
@@ -326,6 +434,11 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 	enum mtk_ddp_comp_type type;
 	struct device_node *larb_node;
 	struct platform_device *larb_pdev;
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct resource res;
+	struct cmdq_client_reg cmdq_reg;
+	int ret;
+#endif
 
 	if (comp_id < 0 || comp_id >= DDP_COMPONENT_ID_MAX)
 		return -EINVAL;
@@ -379,6 +492,19 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 
 	comp->larb_dev = &larb_pdev->dev;
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (of_address_to_resource(node, 0, &res) != 0) {
+		dev_err(dev, "Missing reg in %s node\n", node->full_name);
+		return -EINVAL;
+	}
+	comp->regs_pa = res.start;
+
+	ret = cmdq_dev_get_client_reg(dev, &cmdq_reg, 0);
+	if (ret)
+		dev_dbg(dev, "get mediatek,gce-client-reg fail!\n");
+	else
+		comp->subsys = cmdq_reg.subsys;
+#endif
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 2f1e9e75b8da..debe36395fe7 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -69,27 +69,29 @@ enum mtk_ddp_comp_id {
 };
 
 struct mtk_ddp_comp;
-
+struct cmdq_pkt;
 struct mtk_ddp_comp_funcs {
 	void (*config)(struct mtk_ddp_comp *comp, unsigned int w,
-		       unsigned int h, unsigned int vrefresh, unsigned int bpc);
+		       unsigned int h, unsigned int vrefresh,
+		       unsigned int bpc, struct cmdq_pkt *cmdq_pkt);
 	void (*start)(struct mtk_ddp_comp *comp);
 	void (*stop)(struct mtk_ddp_comp *comp);
 	void (*enable_vblank)(struct mtk_ddp_comp *comp, struct drm_crtc *crtc);
 	void (*disable_vblank)(struct mtk_ddp_comp *comp);
 	unsigned int (*supported_rotations)(struct mtk_ddp_comp *comp);
 	unsigned int (*layer_nr)(struct mtk_ddp_comp *comp);
-	void (*layer_on)(struct mtk_ddp_comp *comp, unsigned int idx);
-	void (*layer_off)(struct mtk_ddp_comp *comp, unsigned int idx);
 	int (*layer_check)(struct mtk_ddp_comp *comp,
 			   unsigned int idx,
 			   struct mtk_plane_state *state);
 	void (*layer_config)(struct mtk_ddp_comp *comp, unsigned int idx,
-			     struct mtk_plane_state *state);
+			     struct mtk_plane_state *state,
+			     struct cmdq_pkt *cmdq_pkt);
 	void (*gamma_set)(struct mtk_ddp_comp *comp,
 			  struct drm_crtc_state *state);
 	void (*bgclr_in_on)(struct mtk_ddp_comp *comp);
 	void (*bgclr_in_off)(struct mtk_ddp_comp *comp);
+	void (*ctm_set)(struct mtk_ddp_comp *comp,
+			struct drm_crtc_state *state);
 };
 
 struct mtk_ddp_comp {
@@ -99,14 +101,17 @@ struct mtk_ddp_comp {
 	struct device *larb_dev;
 	enum mtk_ddp_comp_id id;
 	const struct mtk_ddp_comp_funcs *funcs;
+	resource_size_t regs_pa;
+	u8 subsys;
 };
 
 static inline void mtk_ddp_comp_config(struct mtk_ddp_comp *comp,
 				       unsigned int w, unsigned int h,
-				       unsigned int vrefresh, unsigned int bpc)
+				       unsigned int vrefresh, unsigned int bpc,
+				       struct cmdq_pkt *cmdq_pkt)
 {
 	if (comp->funcs && comp->funcs->config)
-		comp->funcs->config(comp, w, h, vrefresh, bpc);
+		comp->funcs->config(comp, w, h, vrefresh, bpc, cmdq_pkt);
 }
 
 static inline void mtk_ddp_comp_start(struct mtk_ddp_comp *comp)
@@ -151,20 +156,6 @@ static inline unsigned int mtk_ddp_comp_layer_nr(struct mtk_ddp_comp *comp)
 	return 0;
 }
 
-static inline void mtk_ddp_comp_layer_on(struct mtk_ddp_comp *comp,
-					 unsigned int idx)
-{
-	if (comp->funcs && comp->funcs->layer_on)
-		comp->funcs->layer_on(comp, idx);
-}
-
-static inline void mtk_ddp_comp_layer_off(struct mtk_ddp_comp *comp,
-					  unsigned int idx)
-{
-	if (comp->funcs && comp->funcs->layer_off)
-		comp->funcs->layer_off(comp, idx);
-}
-
 static inline int mtk_ddp_comp_layer_check(struct mtk_ddp_comp *comp,
 					   unsigned int idx,
 					   struct mtk_plane_state *state)
@@ -176,10 +167,11 @@ static inline int mtk_ddp_comp_layer_check(struct mtk_ddp_comp *comp,
 
 static inline void mtk_ddp_comp_layer_config(struct mtk_ddp_comp *comp,
 					     unsigned int idx,
-					     struct mtk_plane_state *state)
+					     struct mtk_plane_state *state,
+					     struct cmdq_pkt *cmdq_pkt)
 {
 	if (comp->funcs && comp->funcs->layer_config)
-		comp->funcs->layer_config(comp, idx, state);
+		comp->funcs->layer_config(comp, idx, state, cmdq_pkt);
 }
 
 static inline void mtk_ddp_gamma_set(struct mtk_ddp_comp *comp,
@@ -201,6 +193,13 @@ static inline void mtk_ddp_comp_bgclr_in_off(struct mtk_ddp_comp *comp)
 		comp->funcs->bgclr_in_off(comp);
 }
 
+static inline void mtk_ddp_ctm_set(struct mtk_ddp_comp *comp,
+				   struct drm_crtc_state *state)
+{
+	if (comp->funcs && comp->funcs->ctm_set)
+		comp->funcs->ctm_set(comp, state);
+}
+
 int mtk_ddp_comp_get_id(struct device_node *node,
 			enum mtk_ddp_comp_type comp_type);
 int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node,
@@ -209,6 +208,13 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node,
 int mtk_ddp_comp_register(struct drm_device *drm, struct mtk_ddp_comp *comp);
 void mtk_ddp_comp_unregister(struct drm_device *drm, struct mtk_ddp_comp *comp);
 void mtk_dither_set(struct mtk_ddp_comp *comp, unsigned int bpc,
-		    unsigned int CFG);
-
+		    unsigned int CFG, struct cmdq_pkt *cmdq_pkt);
+enum mtk_ddp_comp_type mtk_ddp_comp_get_type(enum mtk_ddp_comp_id comp_id);
+void mtk_ddp_write(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+		   struct mtk_ddp_comp *comp, unsigned int offset);
+void mtk_ddp_write_relaxed(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			   struct mtk_ddp_comp *comp, unsigned int offset);
+void mtk_ddp_write_mask(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			struct mtk_ddp_comp *comp, unsigned int offset,
+			unsigned int mask);
 #endif /* MTK_DRM_DDP_COMP_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 84d14213d992..0563c6813333 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -16,8 +16,10 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_fourcc.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_of.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
@@ -27,7 +29,6 @@
 #include "mtk_drm_ddp.h"
 #include "mtk_drm_ddp_comp.h"
 #include "mtk_drm_drv.h"
-#include "mtk_drm_fb.h"
 #include "mtk_drm_gem.h"
 
 #define DRIVER_NAME "mediatek"
@@ -36,89 +37,27 @@
 #define DRIVER_MAJOR 1
 #define DRIVER_MINOR 0
 
-static void mtk_atomic_schedule(struct mtk_drm_private *private,
-				struct drm_atomic_state *state)
-{
-	private->commit.state = state;
-	schedule_work(&private->commit.work);
-}
-
-static void mtk_atomic_complete(struct mtk_drm_private *private,
-				struct drm_atomic_state *state)
-{
-	struct drm_device *drm = private->drm;
-
-	drm_atomic_helper_wait_for_fences(drm, state, false);
-
-	/*
-	 * Mediatek drm supports runtime PM, so plane registers cannot be
-	 * written when their crtc is disabled.
-	 *
-	 * The comment for drm_atomic_helper_commit states:
-	 *     For drivers supporting runtime PM the recommended sequence is
-	 *
-	 *     drm_atomic_helper_commit_modeset_disables(dev, state);
-	 *     drm_atomic_helper_commit_modeset_enables(dev, state);
-	 *     drm_atomic_helper_commit_planes(dev, state,
-	 *                                     DRM_PLANE_COMMIT_ACTIVE_ONLY);
-	 *
-	 * See the kerneldoc entries for these three functions for more details.
-	 */
-	drm_atomic_helper_commit_modeset_disables(drm, state);
-	drm_atomic_helper_commit_modeset_enables(drm, state);
-	drm_atomic_helper_commit_planes(drm, state,
-					DRM_PLANE_COMMIT_ACTIVE_ONLY);
-
-	drm_atomic_helper_wait_for_vblanks(drm, state);
-
-	drm_atomic_helper_cleanup_planes(drm, state);
-	drm_atomic_state_put(state);
-}
-
-static void mtk_atomic_work(struct work_struct *work)
-{
-	struct mtk_drm_private *private = container_of(work,
-			struct mtk_drm_private, commit.work);
-
-	mtk_atomic_complete(private, private->commit.state);
-}
+static const struct drm_mode_config_helper_funcs mtk_drm_mode_config_helpers = {
+	.atomic_commit_tail = drm_atomic_helper_commit_tail_rpm,
+};
 
-static int mtk_atomic_commit(struct drm_device *drm,
-			     struct drm_atomic_state *state,
-			     bool async)
+static struct drm_framebuffer *
+mtk_drm_mode_fb_create(struct drm_device *dev,
+		       struct drm_file *file,
+		       const struct drm_mode_fb_cmd2 *cmd)
 {
-	struct mtk_drm_private *private = drm->dev_private;
-	int ret;
-
-	ret = drm_atomic_helper_prepare_planes(drm, state);
-	if (ret)
-		return ret;
+	const struct drm_format_info *info = drm_get_format_info(dev, cmd);
 
-	mutex_lock(&private->commit.lock);
-	flush_work(&private->commit.work);
+	if (info->num_planes != 1)
+		return ERR_PTR(-EINVAL);
 
-	ret = drm_atomic_helper_swap_state(state, true);
-	if (ret) {
-		mutex_unlock(&private->commit.lock);
-		drm_atomic_helper_cleanup_planes(drm, state);
-		return ret;
-	}
-
-	drm_atomic_state_get(state);
-	if (async)
-		mtk_atomic_schedule(private, state);
-	else
-		mtk_atomic_complete(private, state);
-
-	mutex_unlock(&private->commit.lock);
-
-	return 0;
+	return drm_gem_fb_create(dev, file, cmd);
 }
 
 static const struct drm_mode_config_funcs mtk_drm_mode_config_funcs = {
 	.fb_create = mtk_drm_mode_fb_create,
 	.atomic_check = drm_atomic_helper_check,
-	.atomic_commit = mtk_atomic_commit,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 static const enum mtk_ddp_comp_id mt2701_mtk_ddp_main[] = {
@@ -236,6 +175,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	drm->mode_config.max_width = 4096;
 	drm->mode_config.max_height = 4096;
 	drm->mode_config.funcs = &mtk_drm_mode_config_funcs;
+	drm->mode_config.helper_private = &mtk_drm_mode_config_helpers;
 
 	ret = component_bind_all(drm->dev, drm);
 	if (ret)
@@ -495,8 +435,6 @@ static int mtk_drm_probe(struct platform_device *pdev)
 	if (!private)
 		return -ENOMEM;
 
-	mutex_init(&private->commit.lock);
-	INIT_WORK(&private->commit.work, mtk_atomic_work);
 	private->data = of_device_get_match_data(dev);
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
index e03fea12ff59..17bc99b9f5d4 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
@@ -43,13 +43,6 @@ struct mtk_drm_private {
 	struct device_node *comp_node[DDP_COMPONENT_ID_MAX];
 	struct mtk_ddp_comp *ddp_comp[DDP_COMPONENT_ID_MAX];
 	const struct mtk_mmsys_driver_data *data;
-
-	struct {
-		struct drm_atomic_state *state;
-		struct work_struct work;
-		struct mutex lock;
-	} commit;
-
 	struct drm_atomic_state *suspend_state;
 
 	bool dma_parms_allocated;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.c b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
deleted file mode 100644
index 3f230a28a2dc..000000000000
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.c
+++ /dev/null
@@ -1,92 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (c) 2015 MediaTek Inc.
- */
-
-#include <linux/dma-buf.h>
-#include <linux/dma-resv.h>
-
-#include <drm/drm_modeset_helper.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_gem.h>
-#include <drm/drm_gem_framebuffer_helper.h>
-
-#include "mtk_drm_drv.h"
-#include "mtk_drm_fb.h"
-#include "mtk_drm_gem.h"
-
-static const struct drm_framebuffer_funcs mtk_drm_fb_funcs = {
-	.create_handle = drm_gem_fb_create_handle,
-	.destroy = drm_gem_fb_destroy,
-};
-
-static struct drm_framebuffer *mtk_drm_framebuffer_init(struct drm_device *dev,
-					const struct drm_mode_fb_cmd2 *mode,
-					struct drm_gem_object *obj)
-{
-	const struct drm_format_info *info = drm_get_format_info(dev, mode);
-	struct drm_framebuffer *fb;
-	int ret;
-
-	if (info->num_planes != 1)
-		return ERR_PTR(-EINVAL);
-
-	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
-	if (!fb)
-		return ERR_PTR(-ENOMEM);
-
-	drm_helper_mode_fill_fb_struct(dev, fb, mode);
-
-	fb->obj[0] = obj;
-
-	ret = drm_framebuffer_init(dev, fb, &mtk_drm_fb_funcs);
-	if (ret) {
-		DRM_ERROR("failed to initialize framebuffer\n");
-		kfree(fb);
-		return ERR_PTR(ret);
-	}
-
-	return fb;
-}
-
-struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
-					       struct drm_file *file,
-					       const struct drm_mode_fb_cmd2 *cmd)
-{
-	const struct drm_format_info *info = drm_get_format_info(dev, cmd);
-	struct drm_framebuffer *fb;
-	struct drm_gem_object *gem;
-	unsigned int width = cmd->width;
-	unsigned int height = cmd->height;
-	unsigned int size, bpp;
-	int ret;
-
-	if (info->num_planes != 1)
-		return ERR_PTR(-EINVAL);
-
-	gem = drm_gem_object_lookup(file, cmd->handles[0]);
-	if (!gem)
-		return ERR_PTR(-ENOENT);
-
-	bpp = info->cpp[0];
-	size = (height - 1) * cmd->pitches[0] + width * bpp;
-	size += cmd->offsets[0];
-
-	if (gem->size < size) {
-		ret = -EINVAL;
-		goto unreference;
-	}
-
-	fb = mtk_drm_framebuffer_init(dev, cmd, gem);
-	if (IS_ERR(fb)) {
-		ret = PTR_ERR(fb);
-		goto unreference;
-	}
-
-	return fb;
-
-unreference:
-	drm_gem_object_put_unlocked(gem);
-	return ERR_PTR(ret);
-}
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.h b/drivers/gpu/drm/mediatek/mtk_drm_fb.h
deleted file mode 100644
index eb64d26001c6..000000000000
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (c) 2015 MediaTek Inc.
- */
-
-#ifndef MTK_DRM_FB_H
-#define MTK_DRM_FB_H
-
-struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
-					       struct drm_file *file,
-					       const struct drm_mode_fb_cmd2 *cmd);
-
-#endif /* MTK_DRM_FB_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 3b0cc91c7023..914cc7619cd7 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -7,13 +7,13 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_atomic_uapi.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
 #include "mtk_drm_drv.h"
-#include "mtk_drm_fb.h"
 #include "mtk_drm_gem.h"
 #include "mtk_drm_plane.h"
 
@@ -76,6 +76,50 @@ static void mtk_drm_plane_destroy_state(struct drm_plane *plane,
 	kfree(to_mtk_plane_state(state));
 }
 
+static int mtk_plane_atomic_async_check(struct drm_plane *plane,
+					struct drm_plane_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+
+	if (plane != state->crtc->cursor)
+		return -EINVAL;
+
+	if (!plane->state)
+		return -EINVAL;
+
+	if (!plane->state->fb)
+		return -EINVAL;
+
+	if (state->state)
+		crtc_state = drm_atomic_get_existing_crtc_state(state->state,
+								state->crtc);
+	else /* Special case for asynchronous cursor updates. */
+		crtc_state = state->crtc->state;
+
+	return drm_atomic_helper_check_plane_state(plane->state, crtc_state,
+						   DRM_PLANE_HELPER_NO_SCALING,
+						   DRM_PLANE_HELPER_NO_SCALING,
+						   true, true);
+}
+
+static void mtk_plane_atomic_async_update(struct drm_plane *plane,
+					  struct drm_plane_state *new_state)
+{
+	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
+
+	plane->state->crtc_x = new_state->crtc_x;
+	plane->state->crtc_y = new_state->crtc_y;
+	plane->state->crtc_h = new_state->crtc_h;
+	plane->state->crtc_w = new_state->crtc_w;
+	plane->state->src_x = new_state->src_x;
+	plane->state->src_y = new_state->src_y;
+	plane->state->src_h = new_state->src_h;
+	plane->state->src_w = new_state->src_w;
+	state->pending.async_dirty = true;
+
+	mtk_drm_crtc_async_update(new_state->crtc, plane, new_state);
+}
+
 static const struct drm_plane_funcs mtk_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
@@ -95,7 +139,7 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 	if (!fb)
 		return 0;
 
-	if (!state->crtc)
+	if (WARN_ON(!state->crtc))
 		return 0;
 
 	ret = mtk_drm_crtc_plane_check(state->crtc, plane,
@@ -164,6 +208,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 	.atomic_check = mtk_plane_atomic_check,
 	.atomic_update = mtk_plane_atomic_update,
 	.atomic_disable = mtk_plane_atomic_disable,
+	.atomic_async_update = mtk_plane_atomic_async_update,
+	.atomic_async_check = mtk_plane_atomic_async_check,
 };
 
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.h b/drivers/gpu/drm/mediatek/mtk_drm_plane.h
index 760885e35b27..d454bece9535 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.h
@@ -22,6 +22,8 @@ struct mtk_plane_pending_state {
 	unsigned int			height;
 	unsigned int			rotation;
 	bool				dirty;
+	bool				async_dirty;
+	bool				async_config;
 };
 
 struct mtk_plane_state {
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index d77c9f484ce3..5fa1073cf26b 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -830,7 +830,7 @@ static int mtk_dsi_connector_get_modes(struct drm_connector *connector)
 {
 	struct mtk_dsi *dsi = connector_to_dsi(connector);
 
-	return drm_panel_get_modes(dsi->panel);
+	return drm_panel_get_modes(dsi->panel, connector);
 }
 
 static const struct drm_encoder_helper_funcs mtk_dsi_encoder_helper_funcs = {
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index c79b1f855d89..5e4a4dbda443 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1238,17 +1238,19 @@ static int mtk_hdmi_conn_mode_valid(struct drm_connector *conn,
 				    struct drm_display_mode *mode)
 {
 	struct mtk_hdmi *hdmi = hdmi_ctx_from_conn(conn);
+	struct drm_bridge *next_bridge;
 
 	dev_dbg(hdmi->dev, "xres=%d, yres=%d, refresh=%d, intl=%d clock=%d\n",
 		mode->hdisplay, mode->vdisplay, mode->vrefresh,
 		!!(mode->flags & DRM_MODE_FLAG_INTERLACE), mode->clock * 1000);
 
-	if (hdmi->bridge.next) {
+	next_bridge = drm_bridge_get_next_bridge(&hdmi->bridge);
+	if (next_bridge) {
 		struct drm_display_mode adjusted_mode;
 
 		drm_mode_copy(&adjusted_mode, mode);
-		if (!drm_bridge_mode_fixup(hdmi->bridge.next, mode,
-					   &adjusted_mode))
+		if (!drm_bridge_chain_mode_fixup(next_bridge, mode,
+						 &adjusted_mode))
 			return MODE_BAD;
 	}
 
@@ -1300,9 +1302,10 @@ static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge)
 	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
 	int ret;
 
-	ret = drm_connector_init(bridge->encoder->dev, &hdmi->conn,
-				 &mtk_hdmi_connector_funcs,
-				 DRM_MODE_CONNECTOR_HDMIA);
+	ret = drm_connector_init_with_ddc(bridge->encoder->dev, &hdmi->conn,
+					  &mtk_hdmi_connector_funcs,
+					  DRM_MODE_CONNECTOR_HDMIA,
+					  hdmi->ddc_adpt);
 	if (ret) {
 		dev_err(hdmi->dev, "Failed to initialize connector: %d\n", ret);
 		return ret;
diff --git a/drivers/gpu/drm/meson/Makefile b/drivers/gpu/drm/meson/Makefile
index c389e2399133..28a519cdf66b 100644
--- a/drivers/gpu/drm/meson/Makefile
+++ b/drivers/gpu/drm/meson/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 meson-drm-y := meson_drv.o meson_plane.o meson_crtc.o meson_venc_cvbs.o
 meson-drm-y += meson_viu.o meson_vpp.o meson_venc.o meson_vclk.o meson_overlay.o
+meson-drm-y += meson_rdma.o meson_osd_afbcd.o
 
 obj-$(CONFIG_DRM_MESON) += meson-drm.o
 obj-$(CONFIG_DRM_MESON_DW_HDMI) += meson_dw_hdmi.o
diff --git a/drivers/gpu/drm/meson/meson_crtc.c b/drivers/gpu/drm/meson/meson_crtc.c
index 57ae1c13d1e6..e66b6271ff58 100644
--- a/drivers/gpu/drm/meson/meson_crtc.c
+++ b/drivers/gpu/drm/meson/meson_crtc.c
@@ -23,7 +23,9 @@
 #include "meson_registers.h"
 #include "meson_venc.h"
 #include "meson_viu.h"
+#include "meson_rdma.h"
 #include "meson_vpp.h"
+#include "meson_osd_afbcd.h"
 
 #define MESON_G12A_VIU_OFFSET	0x5ec0
 
@@ -35,7 +37,11 @@ struct meson_crtc {
 	struct meson_drm *priv;
 	void (*enable_osd1)(struct meson_drm *priv);
 	void (*enable_vd1)(struct meson_drm *priv);
+	void (*enable_osd1_afbc)(struct meson_drm *priv);
+	void (*disable_osd1_afbc)(struct meson_drm *priv);
 	unsigned int viu_offset;
+	bool vsync_forced;
+	bool vsync_disabled;
 };
 #define to_meson_crtc(x) container_of(x, struct meson_crtc, base)
 
@@ -46,6 +52,7 @@ static int meson_crtc_enable_vblank(struct drm_crtc *crtc)
 	struct meson_crtc *meson_crtc = to_meson_crtc(crtc);
 	struct meson_drm *priv = meson_crtc->priv;
 
+	meson_crtc->vsync_disabled = false;
 	meson_venc_enable_vsync(priv);
 
 	return 0;
@@ -56,7 +63,10 @@ static void meson_crtc_disable_vblank(struct drm_crtc *crtc)
 	struct meson_crtc *meson_crtc = to_meson_crtc(crtc);
 	struct meson_drm *priv = meson_crtc->priv;
 
-	meson_venc_disable_vsync(priv);
+	if (!meson_crtc->vsync_forced) {
+		meson_crtc->vsync_disabled = true;
+		meson_venc_disable_vsync(priv);
+	}
 }
 
 static const struct drm_crtc_funcs meson_crtc_funcs = {
@@ -236,6 +246,26 @@ static void meson_crtc_enable_osd1(struct meson_drm *priv)
 			    priv->io_base + _REG(VPP_MISC));
 }
 
+static void meson_crtc_g12a_enable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_relaxed(priv->viu.osd1_blk2_cfg4,
+		       priv->io_base + _REG(VIU_OSD1_BLK2_CFG_W4));
+
+	writel_bits_relaxed(OSD_MEM_LINEAR_ADDR, OSD_MEM_LINEAR_ADDR,
+			    priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+
+	writel_relaxed(priv->viu.osd1_blk1_cfg4,
+		       priv->io_base + _REG(VIU_OSD1_BLK1_CFG_W4));
+
+	meson_viu_g12a_enable_osd1_afbc(priv);
+
+	writel_bits_relaxed(OSD_MEM_LINEAR_ADDR, OSD_MEM_LINEAR_ADDR,
+			    priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+
+	writel_bits_relaxed(OSD_MALI_SRC_EN, OSD_MALI_SRC_EN,
+			    priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W0));
+}
+
 static void meson_g12a_crtc_enable_osd1(struct meson_drm *priv)
 {
 	writel_relaxed(priv->viu.osd_blend_din0_scope_h,
@@ -281,6 +311,8 @@ void meson_crtc_irq(struct meson_drm *priv)
 	if (priv->viu.osd1_enabled && priv->viu.osd1_commit) {
 		writel_relaxed(priv->viu.osd1_ctrl_stat,
 				priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+		writel_relaxed(priv->viu.osd1_ctrl_stat2,
+				priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[0],
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W0));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[1],
@@ -291,6 +323,20 @@ void meson_crtc_irq(struct meson_drm *priv)
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W3));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[4],
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W4));
+
+		if (priv->viu.osd1_afbcd) {
+			if (meson_crtc->enable_osd1_afbc)
+				meson_crtc->enable_osd1_afbc(priv);
+		} else {
+			if (meson_crtc->disable_osd1_afbc)
+				meson_crtc->disable_osd1_afbc(priv);
+			if (priv->afbcd.ops) {
+				priv->afbcd.ops->reset(priv);
+				priv->afbcd.ops->disable(priv);
+			}
+			meson_crtc->vsync_forced = false;
+		}
+
 		writel_relaxed(priv->viu.osd_sc_ctrl0,
 				priv->io_base + _REG(VPP_OSD_SC_CTRL0));
 		writel_relaxed(priv->viu.osd_sc_i_wh_m1,
@@ -312,15 +358,25 @@ void meson_crtc_irq(struct meson_drm *priv)
 		writel_relaxed(priv->viu.osd_sc_v_ctrl0,
 				priv->io_base + _REG(VPP_OSD_VSC_CTRL0));
 
-		meson_canvas_config(priv->canvas, priv->canvas_id_osd1,
-				priv->viu.osd1_addr, priv->viu.osd1_stride,
-				priv->viu.osd1_height, MESON_CANVAS_WRAP_NONE,
-				MESON_CANVAS_BLKMODE_LINEAR, 0);
+		if (!priv->viu.osd1_afbcd)
+			meson_canvas_config(priv->canvas, priv->canvas_id_osd1,
+					    priv->viu.osd1_addr,
+					    priv->viu.osd1_stride,
+					    priv->viu.osd1_height,
+					    MESON_CANVAS_WRAP_NONE,
+					    MESON_CANVAS_BLKMODE_LINEAR, 0);
 
 		/* Enable OSD1 */
 		if (meson_crtc->enable_osd1)
 			meson_crtc->enable_osd1(priv);
 
+		if (priv->viu.osd1_afbcd) {
+			priv->afbcd.ops->reset(priv);
+			priv->afbcd.ops->setup(priv);
+			priv->afbcd.ops->enable(priv);
+			meson_crtc->vsync_forced = true;
+		}
+
 		priv->viu.osd1_commit = false;
 	}
 
@@ -357,7 +413,7 @@ void meson_crtc_irq(struct meson_drm *priv)
 					    MESON_CANVAS_WRAP_NONE,
 					    MESON_CANVAS_BLKMODE_LINEAR,
 					    MESON_CANVAS_ENDIAN_SWAP64);
-		};
+		}
 
 		writel_relaxed(priv->viu.vd1_if0_gen_reg,
 				priv->io_base + meson_crtc->viu_offset +
@@ -543,6 +599,9 @@ void meson_crtc_irq(struct meson_drm *priv)
 		priv->viu.vd1_commit = false;
 	}
 
+	if (meson_crtc->vsync_disabled)
+		return;
+
 	drm_crtc_handle_vblank(priv->crtc);
 
 	spin_lock_irqsave(&priv->drm->event_lock, flags);
@@ -579,10 +638,20 @@ int meson_crtc_create(struct meson_drm *priv)
 		meson_crtc->enable_osd1 = meson_g12a_crtc_enable_osd1;
 		meson_crtc->enable_vd1 = meson_g12a_crtc_enable_vd1;
 		meson_crtc->viu_offset = MESON_G12A_VIU_OFFSET;
+		meson_crtc->enable_osd1_afbc =
+					meson_crtc_g12a_enable_osd1_afbc;
+		meson_crtc->disable_osd1_afbc =
+					meson_viu_g12a_disable_osd1_afbc;
 		drm_crtc_helper_add(crtc, &meson_g12a_crtc_helper_funcs);
 	} else {
 		meson_crtc->enable_osd1 = meson_crtc_enable_osd1;
 		meson_crtc->enable_vd1 = meson_crtc_enable_vd1;
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM)) {
+			meson_crtc->enable_osd1_afbc =
+					meson_viu_gxm_enable_osd1_afbc;
+			meson_crtc->disable_osd1_afbc =
+					meson_viu_gxm_disable_osd1_afbc;
+		}
 		drm_crtc_helper_add(crtc, &meson_crtc_helper_funcs);
 	}
 
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 397c33182f4f..b5f5eb7b4bb9 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -28,10 +28,12 @@
 #include "meson_drv.h"
 #include "meson_overlay.h"
 #include "meson_plane.h"
+#include "meson_osd_afbcd.h"
 #include "meson_registers.h"
 #include "meson_venc_cvbs.h"
 #include "meson_viu.h"
 #include "meson_vpp.h"
+#include "meson_rdma.h"
 
 #define DRIVER_NAME "meson"
 #define DRIVER_DESC "Amlogic Meson DRM driver"
@@ -184,6 +186,7 @@ static void meson_remove_framebuffers(void)
 static int meson_drv_bind_master(struct device *dev, bool has_components)
 {
 	struct platform_device *pdev = to_platform_device(dev);
+	const struct meson_drm_match_data *match;
 	struct meson_drm *priv;
 	struct drm_device *drm;
 	struct resource *res;
@@ -196,6 +199,10 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 		return -ENODEV;
 	}
 
+	match = of_device_get_match_data(dev);
+	if (!match)
+		return -ENODEV;
+
 	drm = drm_dev_alloc(&meson_driver, dev);
 	if (IS_ERR(drm))
 		return PTR_ERR(drm);
@@ -208,8 +215,8 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	drm->dev_private = priv;
 	priv->drm = drm;
 	priv->dev = dev;
-
-	priv->compat = (enum vpu_compatible)of_device_get_match_data(priv->dev);
+	priv->compat = match->compat;
+	priv->afbcd.ops = match->afbcd_ops;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vpu");
 	regs = devm_ioremap_resource(dev, res);
@@ -289,6 +296,11 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	meson_venc_init(priv);
 	meson_vpp_init(priv);
 	meson_viu_init(priv);
+	if (priv->afbcd.ops) {
+		ret = priv->afbcd.ops->init(priv);
+		if (ret)
+			return ret;
+	}
 
 	/* Encoder Initialization */
 
@@ -359,12 +371,16 @@ static void meson_drv_unbind(struct device *dev)
 		meson_canvas_free(priv->canvas, priv->canvas_id_vd1_2);
 	}
 
+	if (priv->afbcd.ops) {
+		priv->afbcd.ops->reset(priv);
+		meson_rdma_free(priv);
+	}
+
 	drm_dev_unregister(drm);
 	drm_irq_uninstall(drm);
 	drm_kms_helper_poll_fini(drm);
 	drm_mode_config_cleanup(drm);
 	drm_dev_put(drm);
-
 }
 
 static const struct component_master_ops meson_drv_master_ops = {
@@ -393,6 +409,8 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev)
 	meson_venc_init(priv);
 	meson_vpp_init(priv);
 	meson_viu_init(priv);
+	if (priv->afbcd.ops)
+		priv->afbcd.ops->init(priv);
 
 	drm_mode_config_helper_resume(priv->drm);
 
@@ -481,15 +499,33 @@ static int meson_drv_probe(struct platform_device *pdev)
 	return 0;
 };
 
+static struct meson_drm_match_data meson_drm_gxbb_data = {
+	.compat = VPU_COMPATIBLE_GXBB,
+};
+
+static struct meson_drm_match_data meson_drm_gxl_data = {
+	.compat = VPU_COMPATIBLE_GXL,
+};
+
+static struct meson_drm_match_data meson_drm_gxm_data = {
+	.compat = VPU_COMPATIBLE_GXM,
+	.afbcd_ops = &meson_afbcd_gxm_ops,
+};
+
+static struct meson_drm_match_data meson_drm_g12a_data = {
+	.compat = VPU_COMPATIBLE_G12A,
+	.afbcd_ops = &meson_afbcd_g12a_ops,
+};
+
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "amlogic,meson-gxbb-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXBB },
+	  .data       = (void *)&meson_drm_gxbb_data },
 	{ .compatible = "amlogic,meson-gxl-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXL },
+	  .data       = (void *)&meson_drm_gxl_data },
 	{ .compatible = "amlogic,meson-gxm-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXM },
+	  .data       = (void *)&meson_drm_gxm_data },
 	{ .compatible = "amlogic,meson-g12a-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_G12A },
+	  .data       = (void *)&meson_drm_g12a_data },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h
index 820d07bdd42a..04fdf3826643 100644
--- a/drivers/gpu/drm/meson/meson_drv.h
+++ b/drivers/gpu/drm/meson/meson_drv.h
@@ -16,6 +16,7 @@ struct drm_crtc;
 struct drm_device;
 struct drm_plane;
 struct meson_drm;
+struct meson_afbcd_ops;
 
 enum vpu_compatible {
 	VPU_COMPATIBLE_GXBB = 0,
@@ -24,6 +25,11 @@ enum vpu_compatible {
 	VPU_COMPATIBLE_G12A = 3,
 };
 
+struct meson_drm_match_data {
+	enum vpu_compatible compat;
+	struct meson_afbcd_ops *afbcd_ops;
+};
+
 struct meson_drm {
 	struct device *dev;
 	enum vpu_compatible compat;
@@ -47,11 +53,16 @@ struct meson_drm {
 		bool osd1_enabled;
 		bool osd1_interlace;
 		bool osd1_commit;
+		bool osd1_afbcd;
 		uint32_t osd1_ctrl_stat;
+		uint32_t osd1_ctrl_stat2;
 		uint32_t osd1_blk0_cfg[5];
+		uint32_t osd1_blk1_cfg4;
+		uint32_t osd1_blk2_cfg4;
 		uint32_t osd1_addr;
 		uint32_t osd1_stride;
 		uint32_t osd1_height;
+		uint32_t osd1_width;
 		uint32_t osd_sc_ctrl0;
 		uint32_t osd_sc_i_wh_m1;
 		uint32_t osd_sc_o_h_start_end;
@@ -122,6 +133,18 @@ struct meson_drm {
 		bool venc_repeat;
 		bool hdmi_use_enci;
 	} venc;
+
+	struct {
+		dma_addr_t addr_dma;
+		uint32_t *addr;
+		unsigned int offset;
+	} rdma;
+
+	struct {
+		struct meson_afbcd_ops *ops;
+		u64 modifier;
+		u32 format;
+	} afbcd;
 };
 
 static inline int meson_vpu_is_compatible(struct meson_drm *priv,
diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.c b/drivers/gpu/drm/meson/meson_osd_afbcd.c
new file mode 100644
index 000000000000..f12e0271f166
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_osd_afbcd.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include <linux/bitfield.h>
+
+#include <drm/drm_print.h>
+#include <drm/drm_fourcc.h>
+
+#include "meson_drv.h"
+#include "meson_registers.h"
+#include "meson_viu.h"
+#include "meson_rdma.h"
+#include "meson_osd_afbcd.h"
+
+/*
+ * DOC: Driver for the ARM FrameBuffer Compression Decoders
+ *
+ * The Amlogic GXM and G12A SoC families embeds an AFBC Decoder,
+ * to decode compressed buffers generated by the ARM Mali GPU.
+ *
+ * For the GXM Family, Amlogic designed their own Decoder, named in
+ * the vendor source as "MESON_AFBC", and a single decoder is available
+ * for the 2 OSD planes.
+ * This decoder is compatible with the AFBC 1.0 specifications and the
+ * Mali T820 GPU capabilities.
+ * It supports :
+ * - basic AFBC buffer for RGB32 only, thus YTR feature is mandatory
+ * - SPARSE layout and SPLIT layout
+ * - only 16x16 superblock
+ *
+ * The decoder reads the data from the SDRAM, decodes and sends the
+ * decoded pixel stream to the OSD1 Plane pixel composer.
+ *
+ * For the G12A Family, Amlogic integrated an ARM AFBC Decoder, named
+ * in the vendor source as "MALI_AFBC", and the decoder can decode up
+ * to 4 surfaces, one for each of the 4 available OSDs.
+ * This decoder is compatible with the AFBC 1.2 specifications for the
+ * Mali G31 and G52 GPUs.
+ * Is supports :
+ * - basic AFBC buffer for multiple RGB and YUV pixel formats
+ * - SPARSE layout and SPLIT layout
+ * - 16x16 and 32x8 "wideblk" superblocks
+ * - Tiled header
+ *
+ * The ARM AFBC Decoder independent from the VPU Pixel Pipeline, so
+ * the ARM AFBC Decoder reads the data from the SDRAM then decodes
+ * into a private internal physical address where the OSD1 Plane pixel
+ * composer unpacks the decoded data.
+ */
+
+/* Amlogic AFBC Decoder for GXM Family */
+
+#define OSD1_AFBCD_RGB32	0x15
+
+static int meson_gxm_afbcd_pixel_fmt(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return OSD1_AFBCD_RGB32;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static bool meson_gxm_afbcd_supported_fmt(u64 modifier, uint32_t format)
+{
+	if (modifier & AFBC_FORMAT_MOD_BLOCK_SIZE_32x8)
+		return false;
+
+	if (!(modifier & AFBC_FORMAT_MOD_YTR))
+		return false;
+
+	return meson_gxm_afbcd_pixel_fmt(modifier, format) >= 0;
+}
+
+static int meson_gxm_afbcd_init(struct meson_drm *priv)
+{
+	return 0;
+}
+
+static int meson_gxm_afbcd_reset(struct meson_drm *priv)
+{
+	writel_relaxed(VIU_SW_RESET_OSD1_AFBCD,
+		       priv->io_base + _REG(VIU_SW_RESET));
+	writel_relaxed(0, priv->io_base + _REG(VIU_SW_RESET));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_enable(struct meson_drm *priv)
+{
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_ID_FIFO_THRD, 0x40) |
+		       OSD1_AFBCD_DEC_ENABLE,
+		       priv->io_base + _REG(OSD1_AFBCD_ENABLE));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_disable(struct meson_drm *priv)
+{
+	writel_bits_relaxed(OSD1_AFBCD_DEC_ENABLE, 0,
+			    priv->io_base + _REG(OSD1_AFBCD_ENABLE));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_setup(struct meson_drm *priv)
+{
+	u32 conv_lbuf_len;
+	u32 mode = FIELD_PREP(OSD1_AFBCD_MIF_URGENT, 3) |
+		   FIELD_PREP(OSD1_AFBCD_HOLD_LINE_NUM, 4) |
+		   FIELD_PREP(OSD1_AFBCD_RGBA_EXCHAN_CTRL, 0x34) |
+		   meson_gxm_afbcd_pixel_fmt(priv->afbcd.modifier,
+					     priv->afbcd.format);
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPARSE)
+		mode |= OSD1_AFBCD_HREG_HALF_BLOCK;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPLIT)
+		mode |= OSD1_AFBCD_HREG_BLOCK_SPLIT;
+
+	writel_relaxed(mode, priv->io_base + _REG(OSD1_AFBCD_MODE));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_HREG_VSIZE_IN,
+				  priv->viu.osd1_width) |
+		       FIELD_PREP(OSD1_AFBCD_HREG_HSIZE_IN,
+				  priv->viu.osd1_height),
+		       priv->io_base + _REG(OSD1_AFBCD_SIZE_IN));
+
+	writel_relaxed(priv->viu.osd1_addr >> 4,
+		       priv->io_base + _REG(OSD1_AFBCD_HDR_PTR));
+	writel_relaxed(priv->viu.osd1_addr >> 4,
+		       priv->io_base + _REG(OSD1_AFBCD_FRAME_PTR));
+	/* TOFIX: bits 31:24 are not documented, nor the meaning of 0xe4 */
+	writel_relaxed((0xe4 << 24) | (priv->viu.osd1_addr & 0xffffff),
+		       priv->io_base + _REG(OSD1_AFBCD_CHROMA_PTR));
+
+	if (priv->viu.osd1_width <= 128)
+		conv_lbuf_len = 32;
+	else if (priv->viu.osd1_width <= 256)
+		conv_lbuf_len = 64;
+	else if (priv->viu.osd1_width <= 512)
+		conv_lbuf_len = 128;
+	else if (priv->viu.osd1_width <= 1024)
+		conv_lbuf_len = 256;
+	else if (priv->viu.osd1_width <= 2048)
+		conv_lbuf_len = 512;
+	else
+		conv_lbuf_len = 1024;
+
+	writel_relaxed(conv_lbuf_len,
+		       priv->io_base + _REG(OSD1_AFBCD_CONV_CTRL));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_BGN_H, 0) |
+		       FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_END_H,
+				  priv->viu.osd1_width - 1),
+		       priv->io_base + _REG(OSD1_AFBCD_PIXEL_HSCOPE));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_BGN_V, 0) |
+		       FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_END_V,
+				  priv->viu.osd1_height - 1),
+		       priv->io_base + _REG(OSD1_AFBCD_PIXEL_VSCOPE));
+
+	return 0;
+}
+
+struct meson_afbcd_ops meson_afbcd_gxm_ops = {
+	.init = meson_gxm_afbcd_init,
+	.reset = meson_gxm_afbcd_reset,
+	.enable = meson_gxm_afbcd_enable,
+	.disable = meson_gxm_afbcd_disable,
+	.setup = meson_gxm_afbcd_setup,
+	.supported_fmt = meson_gxm_afbcd_supported_fmt,
+};
+
+/* ARM AFBC Decoder for G12A Family */
+
+/* Amlogic G12A Mali AFBC Decoder supported formats */
+enum {
+	MAFBC_FMT_RGB565 = 0,
+	MAFBC_FMT_RGBA5551,
+	MAFBC_FMT_RGBA1010102,
+	MAFBC_FMT_YUV420_10B,
+	MAFBC_FMT_RGB888,
+	MAFBC_FMT_RGBA8888,
+	MAFBC_FMT_RGBA4444,
+	MAFBC_FMT_R8,
+	MAFBC_FMT_RG88,
+	MAFBC_FMT_YUV420_8B,
+	MAFBC_FMT_YUV422_8B = 11,
+	MAFBC_FMT_YUV422_10B = 14,
+};
+
+static int meson_g12a_afbcd_pixel_fmt(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+	/* fall through */
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return MAFBC_FMT_RGBA8888;
+	case DRM_FORMAT_RGB888:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+		return MAFBC_FMT_RGB888;
+	case DRM_FORMAT_RGB565:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+		return MAFBC_FMT_RGB565;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static int meson_g12a_afbcd_bpp(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return 32;
+	case DRM_FORMAT_RGB888:
+		return 24;
+	case DRM_FORMAT_RGB565:
+		return 16;
+	/* TOFIX support mode formats */
+	default:
+		DRM_ERROR("unsupported afbc format[%08x]\n", format);
+		return 0;
+	}
+}
+
+static int meson_g12a_afbcd_fmt_to_blk_mode(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return OSD_MALI_COLOR_MODE_RGBA8888;
+	case DRM_FORMAT_RGB888:
+		return OSD_MALI_COLOR_MODE_RGB888;
+	case DRM_FORMAT_RGB565:
+		return OSD_MALI_COLOR_MODE_RGB565;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static bool meson_g12a_afbcd_supported_fmt(u64 modifier, uint32_t format)
+{
+	return meson_g12a_afbcd_pixel_fmt(modifier, format) >= 0;
+}
+
+static int meson_g12a_afbcd_init(struct meson_drm *priv)
+{
+	int ret;
+
+	ret = meson_rdma_init(priv);
+	if (ret)
+		return ret;
+
+	meson_rdma_setup(priv);
+
+	/* Handle AFBC Decoder reset manually */
+	writel_bits_relaxed(MALI_AFBCD_MANUAL_RESET, MALI_AFBCD_MANUAL_RESET,
+			    priv->io_base + _REG(MALI_AFBCD_TOP_CTRL));
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_reset(struct meson_drm *priv)
+{
+	meson_rdma_reset(priv);
+
+	meson_rdma_writel_sync(priv, VIU_SW_RESET_G12A_AFBC_ARB |
+			       VIU_SW_RESET_G12A_OSD1_AFBCD,
+			       VIU_SW_RESET);
+	meson_rdma_writel_sync(priv, 0, VIU_SW_RESET);
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_enable(struct meson_drm *priv)
+{
+	meson_rdma_writel_sync(priv, VPU_MAFBC_IRQ_SURFACES_COMPLETED |
+			       VPU_MAFBC_IRQ_CONFIGURATION_SWAPPED |
+			       VPU_MAFBC_IRQ_DECODE_ERROR |
+			       VPU_MAFBC_IRQ_DETILING_ERROR,
+			       VPU_MAFBC_IRQ_MASK);
+
+	meson_rdma_writel_sync(priv, VPU_MAFBC_S0_ENABLE,
+			       VPU_MAFBC_SURFACE_CFG);
+
+	meson_rdma_writel_sync(priv, VPU_MAFBC_DIRECT_SWAP,
+			       VPU_MAFBC_COMMAND);
+
+	/* This will enable the RDMA replaying the register writes on vsync */
+	meson_rdma_flush(priv);
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_disable(struct meson_drm *priv)
+{
+	writel_bits_relaxed(VPU_MAFBC_S0_ENABLE, 0,
+			    priv->io_base + _REG(VPU_MAFBC_SURFACE_CFG));
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_setup(struct meson_drm *priv)
+{
+	u32 format = meson_g12a_afbcd_pixel_fmt(priv->afbcd.modifier,
+						priv->afbcd.format);
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_YTR)
+		format |= VPU_MAFBC_YUV_TRANSFORM;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPLIT)
+		format |= VPU_MAFBC_BLOCK_SPLIT;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_TILED)
+		format |= VPU_MAFBC_TILED_HEADER_EN;
+
+	if ((priv->afbcd.modifier & AFBC_FORMAT_MOD_BLOCK_SIZE_MASK) ==
+		AFBC_FORMAT_MOD_BLOCK_SIZE_32x8)
+		format |= FIELD_PREP(VPU_MAFBC_SUPER_BLOCK_ASPECT, 1);
+
+	meson_rdma_writel_sync(priv, format,
+			       VPU_MAFBC_FORMAT_SPECIFIER_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_addr,
+			       VPU_MAFBC_HEADER_BUF_ADDR_LOW_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width,
+			       VPU_MAFBC_BUFFER_WIDTH_S0);
+	meson_rdma_writel_sync(priv, ALIGN(priv->viu.osd1_height, 32),
+			       VPU_MAFBC_BUFFER_HEIGHT_S0);
+
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_BOUNDING_BOX_X_START_S0);
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width - 1,
+			       VPU_MAFBC_BOUNDING_BOX_X_END_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_BOUNDING_BOX_Y_START_S0);
+	meson_rdma_writel_sync(priv, priv->viu.osd1_height - 1,
+			       VPU_MAFBC_BOUNDING_BOX_Y_END_S0);
+
+	meson_rdma_writel_sync(priv, MESON_G12A_AFBCD_OUT_ADDR,
+			       VPU_MAFBC_OUTPUT_BUF_ADDR_LOW_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_OUTPUT_BUF_ADDR_HIGH_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width *
+			       (meson_g12a_afbcd_bpp(priv->afbcd.format) / 8),
+			       VPU_MAFBC_OUTPUT_BUF_STRIDE_S0);
+
+	return 0;
+}
+
+struct meson_afbcd_ops meson_afbcd_g12a_ops = {
+	.init = meson_g12a_afbcd_init,
+	.reset = meson_g12a_afbcd_reset,
+	.enable = meson_g12a_afbcd_enable,
+	.disable = meson_g12a_afbcd_disable,
+	.setup = meson_g12a_afbcd_setup,
+	.fmt_to_blk_mode = meson_g12a_afbcd_fmt_to_blk_mode,
+	.supported_fmt = meson_g12a_afbcd_supported_fmt,
+};
diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.h b/drivers/gpu/drm/meson/meson_osd_afbcd.h
new file mode 100644
index 000000000000..5e5523304f42
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_osd_afbcd.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef __MESON_OSD_AFBCD_H
+#define __MESON_OSD_AFBCD_H
+
+#include "meson_drv.h"
+
+/* This is an internal address used to transfer pixel from AFBC to the VIU */
+#define MESON_G12A_AFBCD_OUT_ADDR	0x1000000
+
+struct meson_afbcd_ops {
+	int (*init)(struct meson_drm *priv);
+	int (*reset)(struct meson_drm *priv);
+	int (*enable)(struct meson_drm *priv);
+	int (*disable)(struct meson_drm *priv);
+	int (*setup)(struct meson_drm *priv);
+	int (*fmt_to_blk_mode)(u64 modifier, uint32_t format);
+	bool (*supported_fmt)(u64 modifier, uint32_t format);
+};
+
+extern struct meson_afbcd_ops meson_afbcd_gxm_ops;
+extern struct meson_afbcd_ops meson_afbcd_g12a_ops;
+
+#endif /* __MESON_OSD_AFBCD_H */
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index ed543227b00d..d5cbc47835bf 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -23,6 +23,7 @@
 #include "meson_plane.h"
 #include "meson_registers.h"
 #include "meson_viu.h"
+#include "meson_osd_afbcd.h"
 
 /* OSD_SCI_WH_M1 */
 #define SCI_WH_M1_W(w)			FIELD_PREP(GENMASK(28, 16), w)
@@ -92,12 +93,38 @@ static int meson_plane_atomic_check(struct drm_plane *plane,
 						   false, true);
 }
 
+#define MESON_MOD_AFBC_VALID_BITS (AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |	\
+				   AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |	\
+				   AFBC_FORMAT_MOD_YTR |		\
+				   AFBC_FORMAT_MOD_SPARSE |		\
+				   AFBC_FORMAT_MOD_SPLIT)
+
 /* Takes a fixed 16.16 number and converts it to integer. */
 static inline int64_t fixed16_to_int(int64_t value)
 {
 	return value >> 16;
 }
 
+static u32 meson_g12a_afbcd_line_stride(struct meson_drm *priv)
+{
+	u32 line_stride = 0;
+
+	switch (priv->afbcd.format) {
+	case DRM_FORMAT_RGB565:
+		line_stride = ((priv->viu.osd1_width << 4) + 127) >> 7;
+		break;
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		line_stride = ((priv->viu.osd1_width << 5) + 127) >> 7;
+		break;
+	}
+
+	return ((line_stride + 1) >> 1) << 1;
+}
+
 static void meson_plane_atomic_update(struct drm_plane *plane,
 				      struct drm_plane_state *old_state)
 {
@@ -126,59 +153,91 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 	 */
 	spin_lock_irqsave(&priv->drm->event_lock, flags);
 
+	/* Check if AFBC decoder is required for this buffer */
+	if ((meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
+	     meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) &&
+	    fb->modifier & DRM_FORMAT_MOD_ARM_AFBC(MESON_MOD_AFBC_VALID_BITS))
+		priv->viu.osd1_afbcd = true;
+	else
+		priv->viu.osd1_afbcd = false;
+
 	/* Enable OSD and BLK0, set max global alpha */
 	priv->viu.osd1_ctrl_stat = OSD_ENABLE |
 				   (0xFF << OSD_GLOBAL_ALPHA_SHIFT) |
 				   OSD_BLK0_ENABLE;
 
+	priv->viu.osd1_ctrl_stat2 = readl(priv->io_base +
+					  _REG(VIU_OSD1_CTRL_STAT2));
+
 	canvas_id_osd1 = priv->canvas_id_osd1;
 
 	/* Set up BLK0 to point to the right canvas */
-	priv->viu.osd1_blk0_cfg[0] = ((canvas_id_osd1 << OSD_CANVAS_SEL) |
-				      OSD_ENDIANNESS_LE);
+	priv->viu.osd1_blk0_cfg[0] = canvas_id_osd1 << OSD_CANVAS_SEL;
+
+	if (priv->viu.osd1_afbcd) {
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
+			/* This is the internal decoding memory address */
+			priv->viu.osd1_blk1_cfg4 = MESON_G12A_AFBCD_OUT_ADDR;
+			priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_BE;
+			priv->viu.osd1_ctrl_stat2 |= OSD_PENDING_STAT_CLEAN;
+			priv->viu.osd1_ctrl_stat |= VIU_OSD1_CFG_SYN_EN;
+		}
+
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM)) {
+			priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_LE;
+			priv->viu.osd1_ctrl_stat2 |= OSD_DPATH_MALI_AFBCD;
+		}
+	} else {
+		priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_LE;
+
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+			priv->viu.osd1_ctrl_stat2 &= ~OSD_DPATH_MALI_AFBCD;
+	}
 
 	/* On GXBB, Use the old non-HDR RGB2YUV converter */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB))
 		priv->viu.osd1_blk0_cfg[0] |= OSD_OUTPUT_COLOR_RGB;
 
+	if (priv->viu.osd1_afbcd &&
+	    meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
+		priv->viu.osd1_blk0_cfg[0] |= OSD_MALI_SRC_EN |
+			priv->afbcd.ops->fmt_to_blk_mode(fb->modifier,
+							  fb->format->format);
+	} else {
+		switch (fb->format->format) {
+		case DRM_FORMAT_XRGB8888:
+		case DRM_FORMAT_ARGB8888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
+						OSD_COLOR_MATRIX_32_ARGB;
+			break;
+		case DRM_FORMAT_XBGR8888:
+		case DRM_FORMAT_ABGR8888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
+						OSD_COLOR_MATRIX_32_ABGR;
+			break;
+		case DRM_FORMAT_RGB888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_24 |
+						OSD_COLOR_MATRIX_24_RGB;
+			break;
+		case DRM_FORMAT_RGB565:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_16 |
+						OSD_COLOR_MATRIX_16_RGB565;
+			break;
+		};
+	}
+
 	switch (fb->format->format) {
 	case DRM_FORMAT_XRGB8888:
-		/* For XRGB, replace the pixel's alpha by 0xFF */
-		writel_bits_relaxed(OSD_REPLACE_EN, OSD_REPLACE_EN,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ARGB;
-		break;
 	case DRM_FORMAT_XBGR8888:
 		/* For XRGB, replace the pixel's alpha by 0xFF */
-		writel_bits_relaxed(OSD_REPLACE_EN, OSD_REPLACE_EN,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ABGR;
+		priv->viu.osd1_ctrl_stat2 |= OSD_REPLACE_EN;
 		break;
 	case DRM_FORMAT_ARGB8888:
-		/* For ARGB, use the pixel's alpha */
-		writel_bits_relaxed(OSD_REPLACE_EN, 0,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ARGB;
-		break;
 	case DRM_FORMAT_ABGR8888:
 		/* For ARGB, use the pixel's alpha */
-		writel_bits_relaxed(OSD_REPLACE_EN, 0,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ABGR;
+		priv->viu.osd1_ctrl_stat2 &= ~OSD_REPLACE_EN;
 		break;
-	case DRM_FORMAT_RGB888:
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_24 |
-					      OSD_COLOR_MATRIX_24_RGB;
-		break;
-	case DRM_FORMAT_RGB565:
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_16 |
-					      OSD_COLOR_MATRIX_16_RGB565;
-		break;
-	};
+	}
 
 	/* Default scaler parameters */
 	vsc_bot_rcv_num = 0;
@@ -305,6 +364,17 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 	priv->viu.osd1_addr = gem->paddr;
 	priv->viu.osd1_stride = fb->pitches[0];
 	priv->viu.osd1_height = fb->height;
+	priv->viu.osd1_width = fb->width;
+
+	if (priv->viu.osd1_afbcd) {
+		priv->afbcd.modifier = fb->modifier;
+		priv->afbcd.format = fb->format->format;
+
+		/* Calculate decoder write stride */
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+			priv->viu.osd1_blk2_cfg4 =
+				meson_g12a_afbcd_line_stride(priv);
+	}
 
 	if (!meson_plane->enabled) {
 		/* Reset OSD1 before enabling it on GXL+ SoCs */
@@ -326,6 +396,11 @@ static void meson_plane_atomic_disable(struct drm_plane *plane,
 	struct meson_plane *meson_plane = to_meson_plane(plane);
 	struct meson_drm *priv = meson_plane->priv;
 
+	if (priv->afbcd.ops) {
+		priv->afbcd.ops->reset(priv);
+		priv->afbcd.ops->disable(priv);
+	}
+
 	/* Disable OSD1 */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
 		writel_bits_relaxed(VIU_OSD1_POSTBLD_SRC_OSD1, 0,
@@ -345,6 +420,42 @@ static const struct drm_plane_helper_funcs meson_plane_helper_funcs = {
 	.prepare_fb	= drm_gem_fb_prepare_fb,
 };
 
+static bool meson_plane_format_mod_supported(struct drm_plane *plane,
+					     u32 format, u64 modifier)
+{
+	struct meson_plane *meson_plane = to_meson_plane(plane);
+	struct meson_drm *priv = meson_plane->priv;
+	int i;
+
+	if (modifier == DRM_FORMAT_MOD_INVALID)
+		return false;
+
+	if (modifier == DRM_FORMAT_MOD_LINEAR)
+		return true;
+
+	if (!meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) &&
+	    !meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+		return false;
+
+	if (modifier & ~DRM_FORMAT_MOD_ARM_AFBC(MESON_MOD_AFBC_VALID_BITS))
+		return false;
+
+	for (i = 0 ; i < plane->modifier_count ; ++i)
+		if (plane->modifiers[i] == modifier)
+			break;
+
+	if (i == plane->modifier_count) {
+		DRM_DEBUG_KMS("Unsupported modifier\n");
+		return false;
+	}
+
+	if (priv->afbcd.ops && priv->afbcd.ops->supported_fmt)
+		return priv->afbcd.ops->supported_fmt(modifier, format);
+
+	DRM_DEBUG_KMS("AFBC Unsupported\n");
+	return false;
+}
+
 static const struct drm_plane_funcs meson_plane_funcs = {
 	.update_plane		= drm_atomic_helper_update_plane,
 	.disable_plane		= drm_atomic_helper_disable_plane,
@@ -352,6 +463,7 @@ static const struct drm_plane_funcs meson_plane_funcs = {
 	.reset			= drm_atomic_helper_plane_reset,
 	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
 	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+	.format_mod_supported   = meson_plane_format_mod_supported,
 };
 
 static const uint32_t supported_drm_formats[] = {
@@ -363,10 +475,60 @@ static const uint32_t supported_drm_formats[] = {
 	DRM_FORMAT_RGB565,
 };
 
+static const uint64_t format_modifiers_afbc_gxm[] = {
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_YTR),
+	/* SPLIT mandates SPARSE, RGB modes mandates YTR */
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
+static const uint64_t format_modifiers_afbc_g12a[] = {
+	/*
+	 * - TOFIX Support AFBC modifiers for YUV formats (16x16 + TILED)
+	 * - SPLIT is mandatory for performances reasons when in 16x16
+	 *   block size
+	 * - 32x8 block size + SPLIT is mandatory with 4K frame size
+	 *   for performances reasons
+	 */
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_SPARSE),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
+static const uint64_t format_modifiers_default[] = {
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
 int meson_plane_create(struct meson_drm *priv)
 {
 	struct meson_plane *meson_plane;
 	struct drm_plane *plane;
+	const uint64_t *format_modifiers = format_modifiers_default;
 
 	meson_plane = devm_kzalloc(priv->drm->dev, sizeof(*meson_plane),
 				   GFP_KERNEL);
@@ -376,11 +538,16 @@ int meson_plane_create(struct meson_drm *priv)
 	meson_plane->priv = priv;
 	plane = &meson_plane->base;
 
+	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+		format_modifiers = format_modifiers_afbc_gxm;
+	else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+		format_modifiers = format_modifiers_afbc_g12a;
+
 	drm_universal_plane_init(priv->drm, plane, 0xFF,
 				 &meson_plane_funcs,
 				 supported_drm_formats,
 				 ARRAY_SIZE(supported_drm_formats),
-				 NULL,
+				 format_modifiers,
 				 DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane");
 
 	drm_plane_helper_add(plane, &meson_plane_helper_funcs);
diff --git a/drivers/gpu/drm/meson/meson_rdma.c b/drivers/gpu/drm/meson/meson_rdma.c
new file mode 100644
index 000000000000..130382178c63
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_rdma.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/dma-mapping.h>
+
+#include "meson_drv.h"
+#include "meson_registers.h"
+#include "meson_rdma.h"
+
+/*
+ * The VPU embeds a "Register DMA" that can write a sequence of registers
+ * on the VPU AHB bus, either manually or triggered by an internal IRQ
+ * event like VSYNC or a line input counter.
+ * The initial implementation handles a single channel (over 8), triggered
+ * by the VSYNC irq and does not handle the RDMA irq.
+ */
+
+#define RDMA_DESC_SIZE	(sizeof(uint32_t) * 2)
+
+int meson_rdma_init(struct meson_drm *priv)
+{
+	if (!priv->rdma.addr) {
+		/* Allocate a PAGE buffer */
+		priv->rdma.addr =
+			dma_alloc_coherent(priv->dev, SZ_4K,
+					   &priv->rdma.addr_dma,
+					   GFP_KERNEL);
+		if (!priv->rdma.addr)
+			return -ENOMEM;
+	}
+
+	priv->rdma.offset = 0;
+
+	writel_relaxed(RDMA_CTRL_SW_RESET,
+		       priv->io_base + _REG(RDMA_CTRL));
+	writel_relaxed(RDMA_DEFAULT_CONFIG |
+		       FIELD_PREP(RDMA_CTRL_AHB_WR_BURST, 3) |
+		       FIELD_PREP(RDMA_CTRL_AHB_RD_BURST, 0),
+		       priv->io_base + _REG(RDMA_CTRL));
+
+	return 0;
+}
+
+void meson_rdma_free(struct meson_drm *priv)
+{
+	if (!priv->rdma.addr && !priv->rdma.addr_dma)
+		return;
+
+	meson_rdma_stop(priv);
+
+	dma_free_coherent(priv->dev, SZ_4K,
+			  priv->rdma.addr, priv->rdma.addr_dma);
+
+	priv->rdma.addr = NULL;
+	priv->rdma.addr_dma = (dma_addr_t)0;
+}
+
+void meson_rdma_setup(struct meson_drm *priv)
+{
+	/* Channel 1: Write Flag, No Address Increment */
+	writel_bits_relaxed(RDMA_ACCESS_RW_FLAG_CHAN1 |
+			    RDMA_ACCESS_ADDR_INC_CHAN1,
+			    RDMA_ACCESS_RW_FLAG_CHAN1,
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+}
+
+void meson_rdma_stop(struct meson_drm *priv)
+{
+	writel_bits_relaxed(RDMA_IRQ_CLEAR_CHAN1,
+			    RDMA_IRQ_CLEAR_CHAN1,
+			    priv->io_base + _REG(RDMA_CTRL));
+
+	/* Stop Channel 1 */
+	writel_bits_relaxed(RDMA_ACCESS_TRIGGER_CHAN1,
+			    FIELD_PREP(RDMA_ACCESS_ADDR_INC_CHAN1,
+				       RDMA_ACCESS_TRIGGER_STOP),
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+}
+
+void meson_rdma_reset(struct meson_drm *priv)
+{
+	meson_rdma_stop(priv);
+
+	priv->rdma.offset = 0;
+}
+
+static void meson_rdma_writel(struct meson_drm *priv, uint32_t val,
+			      uint32_t reg)
+{
+	if (priv->rdma.offset >= (SZ_4K / RDMA_DESC_SIZE)) {
+		dev_warn_once(priv->dev, "%s: overflow\n", __func__);
+		return;
+	}
+
+	priv->rdma.addr[priv->rdma.offset++] = reg;
+	priv->rdma.addr[priv->rdma.offset++] = val;
+}
+
+/*
+ * This will add the register to the RDMA buffer and write it to the
+ * hardware at the same time.
+ * When meson_rdma_flush is called, the RDMA will replay the register
+ * writes in order.
+ */
+void meson_rdma_writel_sync(struct meson_drm *priv, uint32_t val, uint32_t reg)
+{
+	meson_rdma_writel(priv, val, reg);
+
+	writel_relaxed(val, priv->io_base + _REG(reg));
+}
+
+void meson_rdma_flush(struct meson_drm *priv)
+{
+	meson_rdma_stop(priv);
+
+	/* Start of Channel 1 register writes buffer */
+	writel(priv->rdma.addr_dma,
+	       priv->io_base + _REG(RDMA_AHB_START_ADDR_1));
+
+	/* Last byte on Channel 1 register writes buffer */
+	writel(priv->rdma.addr_dma + (priv->rdma.offset * RDMA_DESC_SIZE) - 1,
+	       priv->io_base + _REG(RDMA_AHB_END_ADDR_1));
+
+	/* Trigger Channel 1 on VSYNC event */
+	writel_bits_relaxed(RDMA_ACCESS_TRIGGER_CHAN1,
+			    FIELD_PREP(RDMA_ACCESS_TRIGGER_CHAN1,
+				       RDMA_ACCESS_TRIGGER_VSYNC),
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+
+	priv->rdma.offset = 0;
+}
diff --git a/drivers/gpu/drm/meson/meson_rdma.h b/drivers/gpu/drm/meson/meson_rdma.h
new file mode 100644
index 000000000000..3870bff7b47f
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_rdma.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef __MESON_RDMA_H
+#define __MESON_RDMA_H
+
+#include "meson_drv.h"
+
+int meson_rdma_init(struct meson_drm *priv);
+void meson_rdma_free(struct meson_drm *priv);
+void meson_rdma_setup(struct meson_drm *priv);
+void meson_rdma_reset(struct meson_drm *priv);
+void meson_rdma_stop(struct meson_drm *priv);
+
+void meson_rdma_writel_sync(struct meson_drm *priv, uint32_t val, uint32_t reg);
+void meson_rdma_flush(struct meson_drm *priv);
+
+#endif /* __MESON_RDMA_H */
diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h
index 05fce48ceee0..8ea00546cd4e 100644
--- a/drivers/gpu/drm/meson/meson_registers.h
+++ b/drivers/gpu/drm/meson/meson_registers.h
@@ -138,19 +138,25 @@
 #define VIU_ADDR_START 0x1a00
 #define VIU_ADDR_END 0x1aff
 #define VIU_SW_RESET 0x1a01
+#define		VIU_SW_RESET_OSD1_AFBCD		BIT(31)
+#define		VIU_SW_RESET_G12A_OSD1_AFBCD	BIT(21)
+#define		VIU_SW_RESET_G12A_AFBC_ARB	BIT(19)
 #define		VIU_SW_RESET_OSD1               BIT(0)
 #define VIU_MISC_CTRL0 0x1a06
 #define		VIU_CTRL0_VD1_AFBC_MASK         0x170000
 #define VIU_MISC_CTRL1 0x1a07
+#define		MALI_AFBC_MISC			GENMASK(15, 8)
 #define D2D3_INTF_LENGTH 0x1a08
 #define D2D3_INTF_CTRL0 0x1a09
 #define VIU_OSD1_CTRL_STAT 0x1a10
 #define		VIU_OSD1_OSD_BLK_ENABLE         BIT(0)
+#define		VIU_OSD1_OSD_MEM_MODE_LINEAR	BIT(2)
 #define		VIU_OSD1_POSTBLD_SRC_VD1        (1 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_VD2        (2 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_OSD1       (3 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_OSD2       (4 << 8)
 #define		VIU_OSD1_OSD_ENABLE             BIT(21)
+#define		VIU_OSD1_CFG_SYN_EN             BIT(31)
 #define VIU_OSD1_CTRL_STAT2 0x1a2d
 #define VIU_OSD1_COLOR_ADDR 0x1a11
 #define VIU_OSD1_COLOR 0x1a12
@@ -181,6 +187,16 @@
 #define VIU_OSD1_FIFO_CTRL_STAT 0x1a2b
 #define VIU_OSD1_TEST_RDDATA 0x1a2c
 #define VIU_OSD1_PROT_CTRL 0x1a2e
+#define VIU_OSD1_MALI_UNPACK_CTRL 0x1a2f
+#define		VIU_OSD1_MALI_UNPACK_EN		BIT(31)
+#define		VIU_OSD1_MALI_AFBCD_R_REORDER	GENMASK(15, 12)
+#define		VIU_OSD1_MALI_AFBCD_G_REORDER	GENMASK(11, 8)
+#define		VIU_OSD1_MALI_AFBCD_B_REORDER	GENMASK(7, 4)
+#define		VIU_OSD1_MALI_AFBCD_A_REORDER	GENMASK(3, 0)
+#define		VIU_OSD1_MALI_REORDER_R		1
+#define		VIU_OSD1_MALI_REORDER_G		2
+#define		VIU_OSD1_MALI_REORDER_B		3
+#define		VIU_OSD1_MALI_REORDER_A		4
 #define VIU_OSD2_CTRL_STAT 0x1a30
 #define VIU_OSD2_CTRL_STAT2 0x1a4d
 #define VIU_OSD2_COLOR_ADDR 0x1a31
@@ -1195,11 +1211,59 @@
 #define RDMA_AHB_START_ADDR_7 0x110e
 #define RDMA_AHB_END_ADDR_7 0x110f
 #define RDMA_ACCESS_AUTO 0x1110
+#define		RDMA_ACCESS_TRIGGER_CHAN3	GENMASK(31, 24)
+#define		RDMA_ACCESS_TRIGGER_CHAN2	GENMASK(23, 16)
+#define		RDMA_ACCESS_TRIGGER_CHAN1	GENMASK(15, 8)
+#define		RDMA_ACCESS_TRIGGER_STOP	0
+#define		RDMA_ACCESS_TRIGGER_VSYNC	1
+#define		RDMA_ACCESS_TRIGGER_LINE	32
+#define		RDMA_ACCESS_RW_FLAG_CHAN3	BIT(7)
+#define		RDMA_ACCESS_RW_FLAG_CHAN2	BIT(6)
+#define		RDMA_ACCESS_RW_FLAG_CHAN1	BIT(5)
+#define		RDMA_ACCESS_ADDR_INC_CHAN3	BIT(3)
+#define		RDMA_ACCESS_ADDR_INC_CHAN2	BIT(2)
+#define		RDMA_ACCESS_ADDR_INC_CHAN1	BIT(1)
 #define RDMA_ACCESS_AUTO2 0x1111
+#define		RDMA_ACCESS_RW_FLAG_CHAN7	BIT(7)
+#define		RDMA_ACCESS_RW_FLAG_CHAN6	BIT(6)
+#define		RDMA_ACCESS_RW_FLAG_CHAN5	BIT(5)
+#define		RDMA_ACCESS_RW_FLAG_CHAN4	BIT(4)
+#define		RDMA_ACCESS_ADDR_INC_CHAN7	BIT(3)
+#define		RDMA_ACCESS_ADDR_INC_CHAN6	BIT(2)
+#define		RDMA_ACCESS_ADDR_INC_CHAN5	BIT(1)
+#define		RDMA_ACCESS_ADDR_INC_CHAN4	BIT(0)
 #define RDMA_ACCESS_AUTO3 0x1112
+#define		RDMA_ACCESS_TRIGGER_CHAN7	GENMASK(31, 24)
+#define		RDMA_ACCESS_TRIGGER_CHAN6	GENMASK(23, 16)
+#define		RDMA_ACCESS_TRIGGER_CHAN5	GENMASK(15, 8)
+#define		RDMA_ACCESS_TRIGGER_CHAN4	GENMASK(7, 0)
 #define RDMA_ACCESS_MAN 0x1113
+#define		RDMA_ACCESS_MAN_RW_FLAG		BIT(2)
+#define		RDMA_ACCESS_MAN_ADDR_INC	BIT(1)
+#define		RDMA_ACCESS_MAN_START		BIT(0)
 #define RDMA_CTRL 0x1114
+#define		RDMA_IRQ_CLEAR_CHAN7	BIT(31)
+#define		RDMA_IRQ_CLEAR_CHAN6	BIT(30)
+#define		RDMA_IRQ_CLEAR_CHAN5	BIT(29)
+#define		RDMA_IRQ_CLEAR_CHAN4	BIT(28)
+#define		RDMA_IRQ_CLEAR_CHAN3	BIT(27)
+#define		RDMA_IRQ_CLEAR_CHAN2	BIT(26)
+#define		RDMA_IRQ_CLEAR_CHAN1	BIT(25)
+#define		RDMA_IRQ_CLEAR_CHAN_MAN	BIT(24)
+#define		RDMA_DEFAULT_CONFIG	(BIT(7) | BIT(6))
+#define		RDMA_CTRL_AHB_WR_BURST	GENMASK(5, 4)
+#define		RDMA_CTRL_AHB_RD_BURST	GENMASK(3, 2)
+#define		RDMA_CTRL_SW_RESET	BIT(1)
+#define		RDMA_CTRL_FREE_CLK_EN	BIT(0)
 #define RDMA_STATUS 0x1115
+#define		RDMA_IRQ_STAT_CHAN7	BIT(31)
+#define		RDMA_IRQ_STAT_CHAN6	BIT(30)
+#define		RDMA_IRQ_STAT_CHAN5	BIT(29)
+#define		RDMA_IRQ_STAT_CHAN4	BIT(28)
+#define		RDMA_IRQ_STAT_CHAN3	BIT(27)
+#define		RDMA_IRQ_STAT_CHAN2	BIT(26)
+#define		RDMA_IRQ_STAT_CHAN1	BIT(25)
+#define		RDMA_IRQ_STAT_CHAN_MAN	BIT(24)
 #define RDMA_STATUS2 0x1116
 #define RDMA_STATUS3 0x1117
 #define L_GAMMA_CNTL_PORT 0x1400
@@ -1595,15 +1659,33 @@
 
 /* osd afbcd on gxtvbb */
 #define OSD1_AFBCD_ENABLE 0x31a0
+#define		OSD1_AFBCD_ID_FIFO_THRD			GENMASK(15, 9)
+#define		OSD1_AFBCD_DEC_ENABLE			BIT(8)
+#define		OSD1_AFBCD_FRM_START			BIT(0)
 #define OSD1_AFBCD_MODE 0x31a1
+#define		OSD1_AFBCD_SOFT_RESET			BIT(31)
+#define		OSD1_AFBCD_AXI_REORDER_MODE		BIT(28)
+#define		OSD1_AFBCD_MIF_URGENT			GENMASK(25, 24)
+#define		OSD1_AFBCD_HOLD_LINE_NUM		GENMASK(22, 16)
+#define		OSD1_AFBCD_RGBA_EXCHAN_CTRL		GENMASK(15, 8)
+#define		OSD1_AFBCD_HREG_BLOCK_SPLIT		BIT(6)
+#define		OSD1_AFBCD_HREG_HALF_BLOCK		BIT(5)
+#define		OSD1_AFBCD_HREG_PIXEL_PACKING_FMT	GENMASK(4, 0)
 #define OSD1_AFBCD_SIZE_IN 0x31a2
+#define		OSD1_AFBCD_HREG_VSIZE_IN		GENMASK(31, 16)
+#define		OSD1_AFBCD_HREG_HSIZE_IN		GENMASK(15, 0)
 #define OSD1_AFBCD_HDR_PTR 0x31a3
 #define OSD1_AFBCD_FRAME_PTR 0x31a4
 #define OSD1_AFBCD_CHROMA_PTR 0x31a5
 #define OSD1_AFBCD_CONV_CTRL 0x31a6
+#define		OSD1_AFBCD_CONV_LBUF_LEN		GENMASK(15, 0)
 #define OSD1_AFBCD_STATUS 0x31a8
 #define OSD1_AFBCD_PIXEL_HSCOPE 0x31a9
+#define		OSD1_AFBCD_DEC_PIXEL_BGN_H		GENMASK(31, 16)
+#define		OSD1_AFBCD_DEC_PIXEL_END_H		GENMASK(15, 0)
 #define OSD1_AFBCD_PIXEL_VSCOPE 0x31aa
+#define		OSD1_AFBCD_DEC_PIXEL_BGN_V		GENMASK(31, 16)
+#define		OSD1_AFBCD_DEC_PIXEL_END_V		GENMASK(15, 0)
 
 /* add for gxm and 962e dv core2 */
 #define DOLBY_CORE2A_SWAP_CTRL1	0x3434
@@ -1615,12 +1697,34 @@
 #define VPU_MAFBC_IRQ_CLEAR 0x3a02
 #define VPU_MAFBC_IRQ_MASK 0x3a03
 #define VPU_MAFBC_IRQ_STATUS 0x3a04
+#define		VPU_MAFBC_IRQ_SECURE_ID_ERROR		BIT(5)
+#define		VPU_MAFBC_IRQ_AXI_ERROR			BIT(4)
+#define		VPU_MAFBC_IRQ_DETILING_ERROR		BIT(3)
+#define		VPU_MAFBC_IRQ_DECODE_ERROR		BIT(2)
+#define		VPU_MAFBC_IRQ_CONFIGURATION_SWAPPED	BIT(1)
+#define		VPU_MAFBC_IRQ_SURFACES_COMPLETED	BIT(0)
 #define VPU_MAFBC_COMMAND 0x3a05
+#define		VPU_MAFBC_PENDING_SWAP	BIT(1)
+#define		VPU_MAFBC_DIRECT_SWAP	BIT(0)
 #define VPU_MAFBC_STATUS 0x3a06
+#define		VPU_MAFBC_ERROR		BIT(2)
+#define		VPU_MAFBC_SWAPPING	BIT(1)
+#define		VPU_MAFBC_ACTIVE	BIT(0)
 #define VPU_MAFBC_SURFACE_CFG 0x3a07
+#define		VPU_MAFBC_CONTINUOUS_DECODING_ENABLE	BIT(16)
+#define		VPU_MAFBC_S3_ENABLE			BIT(3)
+#define		VPU_MAFBC_S2_ENABLE			BIT(2)
+#define		VPU_MAFBC_S1_ENABLE			BIT(1)
+#define		VPU_MAFBC_S0_ENABLE			BIT(0)
 #define VPU_MAFBC_HEADER_BUF_ADDR_LOW_S0 0x3a10
 #define VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S0 0x3a11
 #define VPU_MAFBC_FORMAT_SPECIFIER_S0 0x3a12
+#define		VPU_MAFBC_PAYLOAD_LIMIT_EN	BIT(19)
+#define		VPU_MAFBC_TILED_HEADER_EN	BIT(18)
+#define		VPU_MAFBC_SUPER_BLOCK_ASPECT	GENMASK(17, 16)
+#define		VPU_MAFBC_BLOCK_SPLIT		BIT(9)
+#define		VPU_MAFBC_YUV_TRANSFORM		BIT(8)
+#define		VPU_MAFBC_PIXEL_FORMAT		GENMASK(3, 0)
 #define VPU_MAFBC_BUFFER_WIDTH_S0 0x3a13
 #define VPU_MAFBC_BUFFER_HEIGHT_S0 0x3a14
 #define VPU_MAFBC_BOUNDING_BOX_X_START_S0 0x3a15
@@ -1631,6 +1735,8 @@
 #define VPU_MAFBC_OUTPUT_BUF_ADDR_HIGH_S0 0x3a1a
 #define VPU_MAFBC_OUTPUT_BUF_STRIDE_S0 0x3a1b
 #define VPU_MAFBC_PREFETCH_CFG_S0 0x3a1c
+#define		VPU_MAFBC_PREFETCH_READ_DIRECTION_Y	BIT(1)
+#define		VPU_MAFBC_PREFETCH_READ_DIRECTION_X	BIT(0)
 
 #define VPU_MAFBC_HEADER_BUF_ADDR_LOW_S1 0x3a30
 #define VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S1 0x3a31
@@ -1677,7 +1783,11 @@
 #define DOLBY_PATH_CTRL 0x1a0c
 #define		DOLBY_BYPASS_EN(val)            (val & 0xf)
 #define OSD_PATH_MISC_CTRL 0x1a0e
+#define		OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD	BIT(4)
+#define		OSD_PATH_OSD_AXI_SEL_OSD2_AFBCD	BIT(5)
+#define		OSD_PATH_OSD_AXI_SEL_OSD3_AFBCD	BIT(6)
 #define MALI_AFBCD_TOP_CTRL 0x1a0f
+#define		MALI_AFBCD_MANUAL_RESET		BIT(23)
 
 #define VIU_OSD_BLEND_CTRL 0x39b0
 #define		VIU_OSD_BLEND_REORDER(dest, src)      ((src) << (dest * 4))
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index 68cf2c2eca5f..304f8ff1339c 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -7,6 +7,9 @@
  */
 
 #include <linux/export.h>
+#include <linux/bitfield.h>
+
+#include <drm/drm_fourcc.h>
 
 #include "meson_drv.h"
 #include "meson_viu.h"
@@ -335,6 +338,79 @@ void meson_viu_osd1_reset(struct meson_drm *priv)
 	meson_viu_load_matrix(priv);
 }
 
+#define OSD1_MALI_ORDER_ABGR				\
+	(FIELD_PREP(VIU_OSD1_MALI_AFBCD_A_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_A) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_B_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_B) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_G_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_G) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_R_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_R))
+
+#define OSD1_MALI_ORDER_ARGB				\
+	(FIELD_PREP(VIU_OSD1_MALI_AFBCD_A_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_A) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_B_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_R) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_G_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_G) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_R_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_B))
+
+void meson_viu_g12a_enable_osd1_afbc(struct meson_drm *priv)
+{
+	u32 afbc_order = OSD1_MALI_ORDER_ARGB;
+
+	/* Enable Mali AFBC Unpack */
+	writel_bits_relaxed(VIU_OSD1_MALI_UNPACK_EN,
+			    VIU_OSD1_MALI_UNPACK_EN,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+
+	switch (priv->afbcd.format) {
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		afbc_order = OSD1_MALI_ORDER_ABGR;
+		break;
+	}
+
+	/* Setup RGBA Reordering */
+	writel_bits_relaxed(VIU_OSD1_MALI_AFBCD_A_REORDER |
+			    VIU_OSD1_MALI_AFBCD_B_REORDER |
+			    VIU_OSD1_MALI_AFBCD_G_REORDER |
+			    VIU_OSD1_MALI_AFBCD_R_REORDER,
+			    afbc_order,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+
+	/* Select AFBCD path for OSD1 */
+	writel_bits_relaxed(OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD,
+			    OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD,
+			    priv->io_base + _REG(OSD_PATH_MISC_CTRL));
+}
+
+void meson_viu_g12a_disable_osd1_afbc(struct meson_drm *priv)
+{
+	/* Disable AFBCD path for OSD1 */
+	writel_bits_relaxed(OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD, 0,
+			    priv->io_base + _REG(OSD_PATH_MISC_CTRL));
+
+	/* Disable AFBCD unpack */
+	writel_bits_relaxed(VIU_OSD1_MALI_UNPACK_EN, 0,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+}
+
+void meson_viu_gxm_enable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_bits_relaxed(MALI_AFBC_MISC, FIELD_PREP(MALI_AFBC_MISC, 0x90),
+			    priv->io_base + _REG(VIU_MISC_CTRL1));
+}
+
+void meson_viu_gxm_disable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_bits_relaxed(MALI_AFBC_MISC, FIELD_PREP(MALI_AFBC_MISC, 0x00),
+			    priv->io_base + _REG(VIU_MISC_CTRL1));
+}
+
 static inline uint32_t meson_viu_osd_burst_length_reg(uint32_t length)
 {
 	uint32_t val = (((length & 0x80) % 24) / 12);
@@ -362,7 +438,7 @@ void meson_viu_init(struct meson_drm *priv)
 
 	/* Initialize OSD1 fifo control register */
 	reg = VIU_OSD_DDR_PRIORITY_URGENT |
-		VIU_OSD_HOLD_FIFO_LINES(4) |
+		VIU_OSD_HOLD_FIFO_LINES(31) |
 		VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */
 		VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */
 		VIU_OSD_FIFO_LIMITS(2);      /* fifo_lim: 2*16=32 */
@@ -420,8 +496,13 @@ void meson_viu_init(struct meson_drm *priv)
 
 		writel_bits_relaxed(DOLBY_BYPASS_EN(0xc), DOLBY_BYPASS_EN(0xc),
 				    priv->io_base + _REG(DOLBY_PATH_CTRL));
+
+		meson_viu_g12a_disable_osd1_afbc(priv);
 	}
 
+	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+		meson_viu_gxm_disable_osd1_afbc(priv);
+
 	priv->viu.osd1_enabled = false;
 	priv->viu.osd1_commit = false;
 	priv->viu.osd1_interlace = false;
diff --git a/drivers/gpu/drm/meson/meson_viu.h b/drivers/gpu/drm/meson/meson_viu.h
index a112e8d18850..e4a2f24d7c38 100644
--- a/drivers/gpu/drm/meson/meson_viu.h
+++ b/drivers/gpu/drm/meson/meson_viu.h
@@ -10,6 +10,8 @@
 #define __MESON_VIU_H
 
 /* OSDx_BLKx_CFG */
+#define OSD_MALI_SRC_EN		BIT(30)
+
 #define OSD_CANVAS_SEL		16
 
 #define OSD_ENDIANNESS_LE	BIT(15)
@@ -33,21 +35,38 @@
 #define OSD_COLOR_MATRIX_16_RGB655	(0x00 << 2)
 #define OSD_COLOR_MATRIX_16_RGB565	(0x04 << 2)
 
+#define OSD_MALI_COLOR_MODE_R8		(0 << 8)
+#define OSD_MALI_COLOR_MODE_YUV422	(1 << 8)
+#define OSD_MALI_COLOR_MODE_RGB565	(2 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA5551	(3 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA4444	(4 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA8888	(5 << 8)
+#define OSD_MALI_COLOR_MODE_RGB888	(7 << 8)
+#define OSD_MALI_COLOR_MODE_YUV422_10B	(8 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA1010102	(9 << 8)
+
 #define OSD_INTERLACE_ENABLED	BIT(1)
 #define OSD_INTERLACE_ODD	BIT(0)
 #define OSD_INTERLACE_EVEN	(0)
 
 /* OSDx_CTRL_STAT */
 #define OSD_ENABLE		BIT(21)
+#define OSD_MEM_LINEAR_ADDR	BIT(2)
 #define OSD_BLK0_ENABLE		BIT(0)
 
 #define OSD_GLOBAL_ALPHA_SHIFT	12
 
 /* OSDx_CTRL_STAT2 */
+#define OSD_DPATH_MALI_AFBCD	BIT(15)
 #define OSD_REPLACE_EN		BIT(14)
 #define OSD_REPLACE_SHIFT	6
+#define OSD_PENDING_STAT_CLEAN	BIT(1)
 
 void meson_viu_osd1_reset(struct meson_drm *priv);
+void meson_viu_g12a_enable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_g12a_disable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_gxm_enable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_gxm_disable_osd1_afbc(struct meson_drm *priv);
 void meson_viu_init(struct meson_drm *priv);
 
 #endif /* __MESON_VIU_H */
diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h
index d5deecb93975..66df51607896 100644
--- a/drivers/gpu/drm/mga/mga_drv.h
+++ b/drivers/gpu/drm/mga/mga_drv.h
@@ -32,6 +32,7 @@
 #define __MGA_DRV_H__
 
 #include <linux/irqreturn.h>
+#include <linux/pci.h>
 #include <linux/slab.h>
 
 #include <drm/drm_agpsupport.h>
@@ -40,7 +41,6 @@
 #include <drm/drm_ioctl.h>
 #include <drm/drm_irq.h>
 #include <drm/drm_legacy.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_print.h>
 #include <drm/drm_sarea.h>
 #include <drm/drm_vblank.h>
diff --git a/drivers/gpu/drm/mgag200/Kconfig b/drivers/gpu/drm/mgag200/Kconfig
index aed11f4f4c55..d60aa4b9ccd4 100644
--- a/drivers/gpu/drm/mgag200/Kconfig
+++ b/drivers/gpu/drm/mgag200/Kconfig
@@ -8,8 +8,8 @@ config DRM_MGAG200
 	select DRM_TTM_HELPER
 	help
 	 This is a KMS driver for the MGA G200 server chips, it
-         does not support the original MGA G200 or any of the desktop
-         chips. It requires 0.3.0 of the modesetting userspace driver,
-         and a version of mga driver that will fail on KMS enabled
-         devices.
+	 does not support the original MGA G200 or any of the desktop
+	 chips. It requires 0.3.0 of the modesetting userspace driver,
+	 and a version of mga driver that will fail on KMS enabled
+	 devices.
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_cursor.c b/drivers/gpu/drm/mgag200/mgag200_cursor.c
index 79711dbb5b03..d491edd317ff 100644
--- a/drivers/gpu/drm/mgag200/mgag200_cursor.c
+++ b/drivers/gpu/drm/mgag200/mgag200_cursor.c
@@ -5,7 +5,7 @@
  * Author: Christopher Harvey <charvey@matrox.com>
  */
 
-#include <drm/drm_pci.h>
+#include <linux/pci.h>
 
 #include "mgag200_drv.h"
 
@@ -208,8 +208,7 @@ int mgag200_cursor_init(struct mga_device *mdev)
 		return -ENOMEM;
 
 	for (i = 0; i < ncursors; ++i) {
-		gbo = drm_gem_vram_create(dev, &dev->vram_mm->bdev,
-					  size, 0, false);
+		gbo = drm_gem_vram_create(dev, size, 0);
 		if (IS_ERR(gbo)) {
 			ret = PTR_ERR(gbo);
 			goto err_drm_gem_vram_put;
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index b113876c2428..7a5bad2f57d7 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -6,13 +6,13 @@
  *          Dave Airlie
  */
 
-#include <linux/module.h>
 #include <linux/console.h>
+#include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 
 #include "mgag200_drv.h"
@@ -27,6 +27,10 @@ int mgag200_modeset = -1;
 MODULE_PARM_DESC(modeset, "Disable/Enable modesetting");
 module_param_named(modeset, mgag200_modeset, int, 0400);
 
+int mgag200_hw_bug_no_startadd = -1;
+MODULE_PARM_DESC(modeset, "HW does not interpret scanout-buffer start address correctly");
+module_param_named(hw_bug_no_startadd, mgag200_hw_bug_no_startadd, int, 0400);
+
 static struct drm_driver driver;
 
 static const struct pci_device_id pciidlist[] = {
@@ -47,22 +51,66 @@ MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static int mga_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
+	struct drm_device *dev;
+	int ret;
+
 	drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, "mgag200drmfb");
 
-	return drm_get_pci_dev(pdev, ent, &driver);
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	dev = drm_dev_alloc(&driver, &pdev->dev);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto err_pci_disable_device;
+	}
+
+	dev->pdev = pdev;
+	pci_set_drvdata(pdev, dev);
+
+	ret = mgag200_driver_load(dev, ent->driver_data);
+	if (ret)
+		goto err_drm_dev_put;
+
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_mgag200_driver_unload;
+
+	return 0;
+
+err_mgag200_driver_unload:
+	mgag200_driver_unload(dev);
+err_drm_dev_put:
+	drm_dev_put(dev);
+err_pci_disable_device:
+	pci_disable_device(pdev);
+	return ret;
 }
 
 static void mga_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
-	drm_put_dev(dev);
+	drm_dev_unregister(dev);
+	mgag200_driver_unload(dev);
+	drm_dev_put(dev);
 }
 
 DEFINE_DRM_GEM_FOPS(mgag200_driver_fops);
 
 static bool mgag200_pin_bo_at_0(const struct mga_device *mdev)
 {
+	if (mgag200_hw_bug_no_startadd > 0) {
+		DRM_WARN_ONCE("Option hw_bug_no_startradd is enabled. Please "
+			      "report the output of 'lspci -vvnn' to "
+			      "<dri-devel@lists.freedesktop.org> if this "
+			      "option is required to make mgag200 work "
+			      "correctly on your system.\n");
+		return true;
+	} else if (!mgag200_hw_bug_no_startadd) {
+		return false;
+	}
 	return mdev->flags & MGAG200_FLAG_HW_BUG_NO_STARTADD;
 }
 
@@ -86,14 +134,11 @@ int mgag200_driver_dumb_create(struct drm_file *file,
 	if (mgag200_pin_bo_at_0(mdev))
 		pg_align = PFN_UP(mdev->mc.vram_size);
 
-	return drm_gem_vram_fill_create_dumb(file, dev, &dev->vram_mm->bdev,
-					     pg_align, false, args);
+	return drm_gem_vram_fill_create_dumb(file, dev, pg_align, 0, args);
 }
 
 static struct drm_driver driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET,
-	.load = mgag200_driver_load,
-	.unload = mgag200_driver_unload,
 	.fops = &mgag200_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c
index 51d4037f00d4..9f4635916d32 100644
--- a/drivers/gpu/drm/mgag200/mgag200_i2c.c
+++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c
@@ -29,8 +29,7 @@
 #include <linux/export.h>
 #include <linux/i2c-algo-bit.h>
 #include <linux/i2c.h>
-
-#include <drm/drm_pci.h>
+#include <linux/pci.h>
 
 #include "mgag200_drv.h"
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index e1bc5b0aa774..e278b6a547bd 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -8,9 +8,10 @@
  *          Dave Airlie
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_pci.h>
 
 #include "mgag200_drv.h"
 
@@ -118,8 +119,11 @@ static int mgag200_device_init(struct drm_device *dev,
 		return -ENOMEM;
 
 	/* stash G200 SE model number for later use */
-	if (IS_G200_SE(mdev))
+	if (IS_G200_SE(mdev)) {
 		mdev->unique_rev_id = RREG32(0x1e24);
+		DRM_DEBUG("G200 SE unique revision id is 0x%x\n",
+			  mdev->unique_rev_id);
+	}
 
 	ret = mga_vram_init(mdev);
 	if (ret)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 5ec697148fc1..62a8e9ccb16d 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -9,10 +9,10 @@
  */
 
 #include <linux/delay.h>
+#include <linux/pci.h>
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fourcc.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_probe_helper.h>
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 99997d737362..e89657630ea7 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -26,7 +26,7 @@
  * Authors: Dave Airlie <airlied@redhat.com>
  */
 
-#include <drm/drm_pci.h>
+#include <linux/pci.h>
 
 #include "mgag200_drv.h"
 
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 7ad14937fcdf..b67f88872726 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -506,6 +506,14 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	/*
+	 * Set the ICC path to maximum speed for now by multiplying the fastest
+	 * frequency by the bus width (8). We'll want to scale this later on to
+	 * improve battery life.
+	 */
+	icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+
 	return gpu;
 
 fail:
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index b01388a9e89e..253d8d85daad 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -591,6 +591,14 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	/*
+	 * Set the ICC path to maximum speed for now by multiplying the fastest
+	 * frequency by the bus width (8). We'll want to scale this later on to
+	 * improve battery life.
+	 */
+	icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+
 	return gpu;
 
 fail:
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index b02e2042547f..7d9e63e20ded 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -753,11 +753,18 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		gpu->funcs->flush(gpu, gpu->rb[0]);
 		if (!a5xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+	} else {
+		return ret;
 	}
 
 	/* Last step - yield the ringbuffer */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
index f44553ec3193..ed78fee2a262 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
@@ -16,11 +16,11 @@ The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
+- /home/smasetty/playarea/envytools/rnndb/adreno/a6xx.xml     ( 161969 bytes, from 2019-11-29 07:18:16)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
-Copyright (C) 2013-2018 by the following authors:
+Copyright (C) 2013-2019 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -2519,6 +2519,54 @@ static inline uint32_t A6XX_VBIF_TEST_BUS2_CTRL1_DATA_SEL(uint32_t val)
 
 #define REG_A6XX_VBIF_PERF_PWR_CNT_HIGH2			0x0000311a
 
+#define REG_A6XX_GBIF_SCACHE_CNTL1				0x00003c02
+
+#define REG_A6XX_GBIF_QSB_SIDE0					0x00003c03
+
+#define REG_A6XX_GBIF_QSB_SIDE1					0x00003c04
+
+#define REG_A6XX_GBIF_QSB_SIDE2					0x00003c05
+
+#define REG_A6XX_GBIF_QSB_SIDE3					0x00003c06
+
+#define REG_A6XX_GBIF_HALT					0x00003c45
+
+#define REG_A6XX_GBIF_HALT_ACK					0x00003c46
+
+#define REG_A6XX_GBIF_PERF_PWR_CNT_EN				0x00003cc0
+
+#define REG_A6XX_GBIF_PERF_CNT_SEL				0x00003cc2
+
+#define REG_A6XX_GBIF_PERF_PWR_CNT_SEL				0x00003cc3
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW0				0x00003cc4
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW1				0x00003cc5
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW2				0x00003cc6
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW3				0x00003cc7
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH0				0x00003cc8
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH1				0x00003cc9
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH2				0x00003cca
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH3				0x00003ccb
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW0				0x00003ccc
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW1				0x00003ccd
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW2				0x00003cce
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH0				0x00003ccf
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH1				0x00003cd0
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH2				0x00003cd1
+
 #define REG_A6XX_RB_WINDOW_OFFSET2				0x000088d4
 #define A6XX_RB_WINDOW_OFFSET2_WINDOW_OFFSET_DISABLE		0x80000000
 #define A6XX_RB_WINDOW_OFFSET2_X__MASK				0x00007fff
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 85f14feafdec..983afeaee737 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2017-2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */
 
 #include <linux/clk.h>
 #include <linux/interconnect.h>
@@ -149,6 +149,8 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
 		if (freq == gmu->gpu_freqs[perf_index])
 			break;
 
+	gmu->current_perf_index = perf_index;
+
 	__a6xx_gmu_set_freq(gmu, perf_index);
 }
 
@@ -433,6 +435,8 @@ static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev,
 
 static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct platform_device *pdev = to_platform_device(gmu->dev);
 	void __iomem *pdcptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc");
 	void __iomem *seqptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc_seq");
@@ -480,20 +484,34 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 4, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 4, 0x30000);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 4, 0x0);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 8, 0x10108);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30080);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30090);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30080);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 8, 0x0);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_ENABLE_BANK, 7);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_WAIT_FOR_CMPL_BANK, 0);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CONTROL, 0);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR, 0x30010);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA, 2);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 4, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 4, 0x30000);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x2);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3);
+
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 8, 0x10108);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30080);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30090);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30080);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 8, 0x3);
 
 	/* Setup GPU PDC */
@@ -741,8 +759,8 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK, ~A6XX_HFI_IRQ_MASK);
 	enable_irq(gmu->hfi_irq);
 
-	/* Set the GPU to the highest power frequency */
-	__a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1);
+	/* Set the GPU to the current freq */
+	__a6xx_gmu_set_freq(gmu, gmu->current_perf_index);
 
 	/*
 	 * "enable" the GX power domain which won't actually do anything but it
@@ -1166,6 +1184,8 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu)
 	gmu->nr_gpu_freqs = a6xx_gmu_build_freq_table(&gpu->pdev->dev,
 		gmu->gpu_freqs, ARRAY_SIZE(gmu->gpu_freqs));
 
+	gmu->current_perf_index = gmu->nr_gpu_freqs - 1;
+
 	/* Build the list of RPMh votes that we'll send to the GMU */
 	return a6xx_gmu_rpmh_votes_init(gmu);
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 39a26dd63674..2af91ed7ed0c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -63,6 +63,9 @@ struct a6xx_gmu {
 	struct clk_bulk_data *clocks;
 	struct clk *core_clk;
 
+	/* current performance index set externally */
+	int current_perf_index;
+
 	int nr_gpu_freqs;
 	unsigned long gpu_freqs[16];
 	u32 gx_arc_votes[16];
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index dc8ec2c94301..daf07800cde0 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2017-2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */
 
 
 #include "msm_gem.h"
@@ -378,6 +378,18 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	int ret;
 
+	/*
+	 * During a previous slumber, GBIF halt is asserted to ensure
+	 * no further transaction can go through GPU before GPU
+	 * headswitch is turned off.
+	 *
+	 * This halt is deasserted once headswitch goes off but
+	 * incase headswitch doesn't goes off clear GBIF halt
+	 * here to ensure GPU wake-up doesn't fail because of
+	 * halted GPU transactions.
+	 */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+
 	/* Make sure the GMU keeps the GPU on while we set it up */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 
@@ -406,12 +418,17 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
 
-	/* enable hardware clockgating */
-	a6xx_set_hwcg(gpu, true);
+	/*
+	 * enable hardware clockgating
+	 * For now enable clock gating only for a630
+	 */
+	if (adreno_is_a630(adreno_gpu))
+		a6xx_set_hwcg(gpu, true);
 
-	/* VBIF start */
-	gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
+	/* VBIF/GBIF start*/
 	gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3);
+	if (adreno_is_a630(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
 
 	/* Make all blocks contribute to the GPU BUSY perf counter */
 	gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xffffffff);
@@ -537,12 +554,19 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 		a6xx_flush(gpu, gpu->rb[0]);
 		if (!a6xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0);
 		ret = 0;
+	} else {
+		return ret;
 	}
 
 out:
@@ -724,6 +748,39 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL),
 };
 
+#define GBIF_CLIENT_HALT_MASK             BIT(0)
+#define GBIF_ARB_HALT_MASK                BIT(1)
+
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if(!a6xx_has_gbif(adreno_gpu)){
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
+								0xf) == 0xf);
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+
+		return;
+	}
+
+	/* Halt new client requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
+	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
+
+	/* Halt all AXI requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
+	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
+
+	/*
+	 * GMU needs DDR access in slumber path. Deassert GBIF halt now
+	 * to allow for GMU to access system memory.
+	 */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+}
+
 static int a6xx_pm_resume(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -748,6 +805,16 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	devfreq_suspend_device(gpu->devfreq.devfreq);
 
+	/*
+	 * Make sure the GMU is idle before continuing (because some transitions
+	 * may use VBIF
+	 */
+	a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu);
+
+	/* Clear the VBIF pipe before shutting down */
+	/* FIXME: This accesses the GPU - do we need to make sure it is on? */
+	a6xx_bus_clear_pending_transactions(adreno_gpu);
+
 	return a6xx_gmu_stop(a6xx_gpu);
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 64399554f2dd..7239b8b60939 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2017 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2017, 2019 The Linux Foundation. All rights reserved. */
 
 #ifndef __A6XX_GPU_H__
 #define __A6XX_GPU_H__
@@ -42,6 +42,13 @@ struct a6xx_gpu {
 #define A6XX_PROTECT_RDONLY(_reg, _len) \
 	((((_len) & 0x3FFF) << 18) | ((_reg) & 0x3FFFF))
 
+static inline bool a6xx_has_gbif(struct adreno_gpu *gpu)
+{
+	if(adreno_is_a630(gpu))
+		return false;
+
+	return true;
+}
 
 int a6xx_gmu_resume(struct a6xx_gpu *gpu);
 int a6xx_gmu_stop(struct a6xx_gpu *gpu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 691c1a277d91..d6023ba8033c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. */
 
 #include <linux/ascii85.h>
 #include "msm_gem.h"
@@ -320,6 +320,7 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 {
 	struct resource *res;
 	void __iomem *cxdbg = NULL;
+	int nr_debugbus_blocks;
 
 	/* Set up the GX debug bus */
 
@@ -374,9 +375,11 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_3, 0);
 	}
 
-	a6xx_state->debugbus = state_kcalloc(a6xx_state,
-		ARRAY_SIZE(a6xx_debugbus_blocks),
-		sizeof(*a6xx_state->debugbus));
+	nr_debugbus_blocks = ARRAY_SIZE(a6xx_debugbus_blocks) +
+		(a6xx_has_gbif(to_adreno_gpu(gpu)) ? 1 : 0);
+
+	a6xx_state->debugbus = state_kcalloc(a6xx_state, nr_debugbus_blocks,
+			sizeof(*a6xx_state->debugbus));
 
 	if (a6xx_state->debugbus) {
 		int i;
@@ -388,15 +391,31 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 				&a6xx_state->debugbus[i]);
 
 		a6xx_state->nr_debugbus = ARRAY_SIZE(a6xx_debugbus_blocks);
+
+		/*
+		 * GBIF has same debugbus as of other GPU blocks, fall back to
+		 * default path if GPU uses GBIF, also GBIF uses exactly same
+		 * ID as of VBIF.
+		 */
+		if (a6xx_has_gbif(to_adreno_gpu(gpu))) {
+			a6xx_get_debugbus_block(gpu, a6xx_state,
+				&a6xx_gbif_debugbus_block,
+				&a6xx_state->debugbus[i]);
+
+			a6xx_state->nr_debugbus += 1;
+		}
 	}
 
-	a6xx_state->vbif_debugbus =
-		state_kcalloc(a6xx_state, 1,
-			sizeof(*a6xx_state->vbif_debugbus));
+	/*  Dump the VBIF debugbus on applicable targets */
+	if (!a6xx_has_gbif(to_adreno_gpu(gpu))) {
+		a6xx_state->vbif_debugbus =
+			state_kcalloc(a6xx_state, 1,
+					sizeof(*a6xx_state->vbif_debugbus));
 
-	if (a6xx_state->vbif_debugbus)
-		a6xx_get_vbif_debugbus_block(gpu, a6xx_state,
-			a6xx_state->vbif_debugbus);
+		if (a6xx_state->vbif_debugbus)
+			a6xx_get_vbif_debugbus_block(gpu, a6xx_state,
+					a6xx_state->vbif_debugbus);
+	}
 
 	if (cxdbg) {
 		a6xx_state->cx_debugbus =
@@ -770,14 +789,16 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
 		&a6xx_state->gmu_registers[1]);
 }
 
+#define A6XX_GBIF_REGLIST_SIZE   1
 static void a6xx_get_registers(struct msm_gpu *gpu,
 		struct a6xx_gpu_state *a6xx_state,
 		struct a6xx_crashdumper *dumper)
 {
 	int i, count = ARRAY_SIZE(a6xx_ahb_reglist) +
 		ARRAY_SIZE(a6xx_reglist) +
-		ARRAY_SIZE(a6xx_hlsq_reglist);
+		ARRAY_SIZE(a6xx_hlsq_reglist) + A6XX_GBIF_REGLIST_SIZE;
 	int index = 0;
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 
 	a6xx_state->registers = state_kcalloc(a6xx_state,
 		count, sizeof(*a6xx_state->registers));
@@ -792,6 +813,15 @@ static void a6xx_get_registers(struct msm_gpu *gpu,
 			a6xx_state, &a6xx_ahb_reglist[i],
 			&a6xx_state->registers[index++]);
 
+	if (a6xx_has_gbif(adreno_gpu))
+		a6xx_get_ahb_gpu_registers(gpu,
+				a6xx_state, &a6xx_gbif_reglist,
+				&a6xx_state->registers[index++]);
+	else
+		a6xx_get_ahb_gpu_registers(gpu,
+				a6xx_state, &a6xx_vbif_reglist,
+				&a6xx_state->registers[index++]);
+
 	for (i = 0; i < ARRAY_SIZE(a6xx_reglist); i++)
 		a6xx_get_crashdumper_registers(gpu,
 			a6xx_state, &a6xx_reglist[i],
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index 68cccfa2870a..e67c20c415af 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. */
 
 #ifndef _A6XX_CRASH_DUMP_H_
 #define _A6XX_CRASH_DUMP_H_
@@ -307,11 +307,20 @@ static const u32 a6xx_vbif_registers[] = {
 	0x3410, 0x3410, 0x3800, 0x3801,
 };
 
+static const u32 a6xx_gbif_registers[] = {
+	0x3C00, 0X3C0B, 0X3C40, 0X3C47, 0X3CC0, 0X3CD1, 0xE3A, 0xE3A,
+};
+
 static const struct a6xx_registers a6xx_ahb_reglist[] = {
 	REGS(a6xx_ahb_registers, 0, 0),
-	REGS(a6xx_vbif_registers, 0, 0),
 };
 
+static const struct a6xx_registers a6xx_vbif_reglist =
+			REGS(a6xx_vbif_registers, 0, 0);
+
+static const struct a6xx_registers a6xx_gbif_reglist =
+			REGS(a6xx_gbif_registers, 0, 0);
+
 static const u32 a6xx_gmu_gx_registers[] = {
 	/* GMU GX */
 	0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b,
@@ -422,6 +431,9 @@ static const struct a6xx_debugbus_block {
 	DEBUGBUS(A6XX_DBGBUS_TPL1_3, 0x100),
 };
 
+static const struct a6xx_debugbus_block a6xx_gbif_debugbus_block =
+			DEBUGBUS(A6XX_DBGBUS_VBIF, 0x100);
+
 static const struct a6xx_debugbus_block a6xx_cx_debugbus_blocks[] = {
 	DEBUGBUS(A6XX_DBGBUS_GMU_CX, 0x100),
 	DEBUGBUS(A6XX_DBGBUS_CX, 0x100),
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index fbbdf86504f5..cb3a6e597d76 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -167,6 +167,17 @@ static const struct adreno_info gpulist[] = {
 		.init = a5xx_gpu_init,
 		.zapfw = "a540_zap.mdt",
 	}, {
+		.rev = ADRENO_REV(6, 1, 8, ANY_ID),
+		.revn = 618,
+		.name = "A618",
+		.fw = {
+			[ADRENO_FW_SQE] = "a630_sqe.fw",
+			[ADRENO_FW_GMU] = "a630_gmu.bin",
+		},
+		.gmem = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a6xx_gpu_init,
+	}, {
 		.rev = ADRENO_REV(6, 3, 0, ANY_ID),
 		.revn = 630,
 		.name = "A630",
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 0783e4b5486a..7fd29829b2fa 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -26,6 +26,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 {
 	struct device *dev = &gpu->pdev->dev;
 	const struct firmware *fw;
+	const char *signed_fwname = NULL;
 	struct device_node *np, *mem_np;
 	struct resource r;
 	phys_addr_t mem_phys;
@@ -58,8 +59,43 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 
 	mem_phys = r.start;
 
-	/* Request the MDT file for the firmware */
-	fw = adreno_request_fw(to_adreno_gpu(gpu), fwname);
+	/*
+	 * Check for a firmware-name property.  This is the new scheme
+	 * to handle firmware that may be signed with device specific
+	 * keys, allowing us to have a different zap fw path for different
+	 * devices.
+	 *
+	 * If the firmware-name property is found, we bypass the
+	 * adreno_request_fw() mechanism, because we don't need to handle
+	 * the /lib/firmware/qcom/... vs /lib/firmware/... case.
+	 *
+	 * If the firmware-name property is not found, for backwards
+	 * compatibility we fall back to the fwname from the gpulist
+	 * table.
+	 */
+	of_property_read_string_index(np, "firmware-name", 0, &signed_fwname);
+	if (signed_fwname) {
+		fwname = signed_fwname;
+		ret = request_firmware_direct(&fw, fwname, gpu->dev->dev);
+		if (ret)
+			fw = ERR_PTR(ret);
+	} else if (fwname) {
+		/* Request the MDT file from the default location: */
+		fw = adreno_request_fw(to_adreno_gpu(gpu), fwname);
+	} else {
+		/*
+		 * For new targets, we require the firmware-name property,
+		 * if a zap-shader is required, rather than falling back
+		 * to a firmware name specified in gpulist.
+		 *
+		 * Because the firmware is signed with a (potentially)
+		 * device specific key, having the name come from gpulist
+		 * was a bad idea, and is only provided for backwards
+		 * compatibility for older targets.
+		 */
+		return -ENODEV;
+	}
+
 	if (IS_ERR(fw)) {
 		DRM_DEV_ERROR(dev, "Unable to load %s\n", fwname);
 		return PTR_ERR(fw);
@@ -95,7 +131,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 	 * not.  But since we've already gotten through adreno_request_fw()
 	 * we know which of the two cases it is:
 	 */
-	if (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY) {
+	if (signed_fwname || (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY)) {
 		ret = qcom_mdt_load(dev, fw, fwname, pasid,
 				mem_region, mem_phys, mem_size, NULL);
 	} else {
@@ -146,14 +182,6 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid)
 		return -EPROBE_DEFER;
 	}
 
-	/* Each GPU has a target specific zap shader firmware name to use */
-	if (!adreno_gpu->info->zapfw) {
-		zap_available = false;
-		DRM_DEV_ERROR(&pdev->dev,
-			"Zap shader firmware file not specified for this target\n");
-		return -ENODEV;
-	}
-
 	return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid);
 }
 
@@ -826,7 +854,7 @@ static int adreno_get_legacy_pwrlevels(struct device *dev)
 
 	node = of_get_compatible_child(dev->of_node, "qcom,gpu-pwrlevels");
 	if (!node) {
-		DRM_DEV_ERROR(dev, "Could not find the GPU powerlevels\n");
+		DRM_DEV_DEBUG(dev, "Could not find the GPU powerlevels\n");
 		return -ENXIO;
 	}
 
@@ -887,10 +915,21 @@ static int adreno_get_pwrlevels(struct device *dev,
 	DBG("fast_rate=%u, slow_rate=27000000", gpu->fast_rate);
 
 	/* Check for an interconnect path for the bus */
-	gpu->icc_path = of_icc_get(dev, NULL);
+	gpu->icc_path = of_icc_get(dev, "gfx-mem");
+	if (!gpu->icc_path) {
+		/*
+		 * Keep compatbility with device trees that don't have an
+		 * interconnect-names property.
+		 */
+		gpu->icc_path = of_icc_get(dev, NULL);
+	}
 	if (IS_ERR(gpu->icc_path))
 		gpu->icc_path = NULL;
 
+	gpu->ocmem_icc_path = of_icc_get(dev, "ocmem");
+	if (IS_ERR(gpu->ocmem_icc_path))
+		gpu->ocmem_icc_path = NULL;
+
 	return 0;
 }
 
@@ -977,6 +1016,7 @@ void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 		release_firmware(adreno_gpu->fw[i]);
 
 	icc_put(gpu->icc_path);
+	icc_put(gpu->ocmem_icc_path);
 
 	msm_gpu_cleanup(&adreno_gpu->base);
 }
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index e71a7570ef72..9ff4e550e7bd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -3,7 +3,7 @@
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
- * Copyright (c) 2014,2017 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2014,2017, 2019 The Linux Foundation. All rights reserved.
  */
 
 #ifndef __ADRENO_GPU_H__
@@ -227,6 +227,16 @@ static inline int adreno_is_a540(struct adreno_gpu *gpu)
 	return gpu->revn == 540;
 }
 
+static inline int adreno_is_a618(struct adreno_gpu *gpu)
+{
+       return gpu->revn == 618;
+}
+
+static inline int adreno_is_a630(struct adreno_gpu *gpu)
+{
+       return gpu->revn == 630;
+}
+
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
 const struct firmware *adreno_request_fw(struct adreno_gpu *adreno_gpu,
 		const char *fwname);
@@ -330,10 +340,7 @@ OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt)
 static inline bool adreno_reg_check(struct adreno_gpu *gpu,
 		enum adreno_regs offset_name)
 {
-	if (offset_name >= REG_ADRENO_REGISTER_MAX ||
-			!gpu->reg_offsets[offset_name]) {
-		BUG();
-	}
+	BUG_ON(offset_name >= REG_ADRENO_REGISTER_MAX || !gpu->reg_offsets[offset_name]);
 
 	/*
 	 * REG_SKIP is a special value that tell us that the register in
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index f197dce54576..bf513411b243 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -197,10 +197,6 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc)
 	DPU_DEBUG("%s\n", dpu_crtc->name);
 
 	for (i = 0; i < cstate->num_mixers; i++) {
-		if (!mixer[i].hw_lm || !mixer[i].lm_ctl) {
-			DPU_ERROR("invalid lm or ctl assigned to mixer\n");
-			return;
-		}
 		mixer[i].mixer_op_mode = 0;
 		mixer[i].flush_mask = 0;
 		if (mixer[i].lm_ctl->ops.clear_all_blendstages)
@@ -1113,14 +1109,9 @@ static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
 
 	for (i = 0; i < cstate->num_mixers; ++i) {
 		m = &cstate->mixers[i];
-		if (!m->hw_lm)
-			seq_printf(s, "\tmixer[%d] has no lm\n", i);
-		else if (!m->lm_ctl)
-			seq_printf(s, "\tmixer[%d] has no ctl\n", i);
-		else
-			seq_printf(s, "\tmixer:%d ctl:%d width:%d height:%d\n",
-				m->hw_lm->idx - LM_0, m->lm_ctl->idx - CTL_0,
-				out_width, mode->vdisplay);
+		seq_printf(s, "\tmixer:%d ctl:%d width:%d height:%d\n",
+			m->hw_lm->idx - LM_0, m->lm_ctl->idx - CTL_0,
+			out_width, mode->vdisplay);
 	}
 
 	seq_puts(s, "\n");
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index f96e142c4361..f8ac3bf60fd6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -58,7 +58,7 @@
 
 #define IDLE_SHORT_TIMEOUT	1
 
-#define MAX_VDISPLAY_SPLIT 1080
+#define MAX_HDISPLAY_SPLIT 1080
 
 /* timeout in frames waiting for frame done */
 #define DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES 5
@@ -233,7 +233,7 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
 	u32 irq_status;
 	int ret;
 
-	if (!phys_enc || !wait_info || intr_idx >= INTR_IDX_MAX) {
+	if (!wait_info || intr_idx >= INTR_IDX_MAX) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -308,7 +308,7 @@ int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc,
 	struct dpu_encoder_irq *irq;
 	int ret = 0;
 
-	if (!phys_enc || intr_idx >= INTR_IDX_MAX) {
+	if (intr_idx >= INTR_IDX_MAX) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -363,10 +363,6 @@ int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
 	struct dpu_encoder_irq *irq;
 	int ret;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return -EINVAL;
-	}
 	irq = &phys_enc->irq[intr_idx];
 
 	/* silently skip irqs that weren't registered */
@@ -415,7 +411,7 @@ void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc,
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.get_hw_resources)
+		if (phys->ops.get_hw_resources)
 			phys->ops.get_hw_resources(phys, hw_res);
 	}
 }
@@ -438,7 +434,7 @@ static void dpu_encoder_destroy(struct drm_encoder *drm_enc)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.destroy) {
+		if (phys->ops.destroy) {
 			phys->ops.destroy(phys);
 			--dpu_enc->num_phys_encs;
 			dpu_enc->phys_encs[i] = NULL;
@@ -464,7 +460,7 @@ void dpu_encoder_helper_split_config(
 	struct dpu_hw_mdp *hw_mdptop;
 	struct msm_display_info *disp_info;
 
-	if (!phys_enc || !phys_enc->hw_mdptop || !phys_enc->parent) {
+	if (!phys_enc->hw_mdptop || !phys_enc->parent) {
 		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
 		return;
 	}
@@ -534,8 +530,23 @@ static struct msm_display_topology dpu_encoder_get_topology(
 		if (dpu_enc->phys_encs[i])
 			intf_count++;
 
-	/* User split topology for width > 1080 */
-	topology.num_lm = (mode->vdisplay > MAX_VDISPLAY_SPLIT) ? 2 : 1;
+	/* Datapath topology selection
+	 *
+	 * Dual display
+	 * 2 LM, 2 INTF ( Split display using 2 interfaces)
+	 *
+	 * Single display
+	 * 1 LM, 1 INTF
+	 * 2 LM, 1 INTF (stream merge to support high resolution interfaces)
+	 *
+	 */
+	if (intf_count == 2)
+		topology.num_lm = 2;
+	else if (!dpu_kms->catalog->caps->has_3d_merge)
+		topology.num_lm = 1;
+	else
+		topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1;
+
 	topology.num_enc = 0;
 	topology.num_intf = intf_count;
 
@@ -583,10 +594,10 @@ static int dpu_encoder_virt_atomic_check(
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.atomic_check)
+		if (phys->ops.atomic_check)
 			ret = phys->ops.atomic_check(phys, crtc_state,
 					conn_state);
-		else if (phys && phys->ops.mode_fixup)
+		else if (phys->ops.mode_fixup)
 			if (!phys->ops.mode_fixup(phys, mode, adj_mode))
 				ret = -EINVAL;
 
@@ -682,7 +693,7 @@ static void _dpu_encoder_irq_control(struct drm_encoder *drm_enc, bool enable)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.irq_control)
+		if (phys->ops.irq_control)
 			phys->ops.irq_control(phys, enable);
 	}
 
@@ -1032,46 +1043,43 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys) {
-			if (!dpu_enc->hw_pp[i]) {
-				DPU_ERROR_ENC(dpu_enc, "no pp block assigned"
-					     "at idx: %d\n", i);
-				goto error;
-			}
+		if (!dpu_enc->hw_pp[i]) {
+			DPU_ERROR_ENC(dpu_enc,
+				"no pp block assigned at idx: %d\n", i);
+			goto error;
+		}
 
-			if (!hw_ctl[i]) {
-				DPU_ERROR_ENC(dpu_enc, "no ctl block assigned"
-					     "at idx: %d\n", i);
-				goto error;
-			}
+		if (!hw_ctl[i]) {
+			DPU_ERROR_ENC(dpu_enc,
+				"no ctl block assigned at idx: %d\n", i);
+			goto error;
+		}
 
-			phys->hw_pp = dpu_enc->hw_pp[i];
-			phys->hw_ctl = hw_ctl[i];
+		phys->hw_pp = dpu_enc->hw_pp[i];
+		phys->hw_ctl = hw_ctl[i];
 
-			dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id,
-					    DPU_HW_BLK_INTF);
-			for (j = 0; j < MAX_CHANNELS_PER_ENC; j++) {
-				struct dpu_hw_intf *hw_intf;
+		dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id,
+				    DPU_HW_BLK_INTF);
+		for (j = 0; j < MAX_CHANNELS_PER_ENC; j++) {
+			struct dpu_hw_intf *hw_intf;
 
-				if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter))
-					break;
+			if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter))
+				break;
 
-				hw_intf = (struct dpu_hw_intf *)hw_iter.hw;
-				if (hw_intf->idx == phys->intf_idx)
-					phys->hw_intf = hw_intf;
-			}
+			hw_intf = (struct dpu_hw_intf *)hw_iter.hw;
+			if (hw_intf->idx == phys->intf_idx)
+				phys->hw_intf = hw_intf;
+		}
 
-			if (!phys->hw_intf) {
-				DPU_ERROR_ENC(dpu_enc,
-					      "no intf block assigned at idx: %d\n",
-					      i);
+		if (!phys->hw_intf) {
+			DPU_ERROR_ENC(dpu_enc,
+				      "no intf block assigned at idx: %d\n", i);
 				goto error;
-			}
-
-			phys->connector = conn->state->connector;
-			if (phys->ops.mode_set)
-				phys->ops.mode_set(phys, mode, adj_mode);
 		}
+
+		phys->connector = conn->state->connector;
+		if (phys->ops.mode_set)
+			phys->ops.mode_set(phys, mode, adj_mode);
 	}
 
 	dpu_enc->mode_set_complete = true;
@@ -1203,7 +1211,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.disable)
+		if (phys->ops.disable)
 			phys->ops.disable(phys);
 	}
 
@@ -1216,8 +1224,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP);
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
-		if (dpu_enc->phys_encs[i])
-			dpu_enc->phys_encs[i]->connector = NULL;
+		dpu_enc->phys_encs[i]->connector = NULL;
 	}
 
 	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
@@ -1307,7 +1314,7 @@ void dpu_encoder_toggle_vblank_for_crtc(struct drm_encoder *drm_enc,
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.control_vblank_irq)
+		if (phys->ops.control_vblank_irq)
 			phys->ops.control_vblank_irq(phys, enable);
 	}
 }
@@ -1419,7 +1426,7 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
 	}
 
 	ctl = phys->hw_ctl;
-	if (!ctl || !ctl->ops.trigger_flush) {
+	if (!ctl->ops.trigger_flush) {
 		DPU_ERROR("missing trigger cb\n");
 		return;
 	}
@@ -1463,13 +1470,8 @@ void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc)
 {
 	struct dpu_hw_ctl *ctl;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
-
 	ctl = phys_enc->hw_ctl;
-	if (ctl && ctl->ops.trigger_start) {
+	if (ctl->ops.trigger_start) {
 		ctl->ops.trigger_start(ctl);
 		trace_dpu_enc_trigger_start(DRMID(phys_enc->parent), ctl->idx);
 	}
@@ -1506,14 +1508,10 @@ static void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
 	struct dpu_hw_ctl *ctl;
 	int rc;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
 	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
 	ctl = phys_enc->hw_ctl;
 
-	if (!ctl || !ctl->ops.reset)
+	if (!ctl->ops.reset)
 		return;
 
 	DRM_DEBUG_KMS("id:%u ctl %d reset\n", DRMID(phys_enc->parent),
@@ -1550,12 +1548,10 @@ static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (!phys || phys->enable_state == DPU_ENC_DISABLED)
+		if (phys->enable_state == DPU_ENC_DISABLED)
 			continue;
 
 		ctl = phys->hw_ctl;
-		if (!ctl)
-			continue;
 
 		/*
 		 * This is cleared in frame_done worker, which isn't invoked
@@ -1603,17 +1599,15 @@ void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->hw_ctl) {
-			ctl = phys->hw_ctl;
-			if (ctl->ops.clear_pending_flush)
-				ctl->ops.clear_pending_flush(ctl);
+		ctl = phys->hw_ctl;
+		if (ctl->ops.clear_pending_flush)
+			ctl->ops.clear_pending_flush(ctl);
 
-			/* update only for command mode primary ctl */
-			if ((phys == dpu_enc->cur_master) &&
-			   (disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE)
-			    && ctl->ops.trigger_pending)
-				ctl->ops.trigger_pending(ctl);
-		}
+		/* update only for command mode primary ctl */
+		if ((phys == dpu_enc->cur_master) &&
+		   (disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE)
+		    && ctl->ops.trigger_pending)
+			ctl->ops.trigger_pending(ctl);
 	}
 }
 
@@ -1773,12 +1767,10 @@ void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc)
 	DPU_ATRACE_BEGIN("enc_prepare_for_kickoff");
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		phys = dpu_enc->phys_encs[i];
-		if (phys) {
-			if (phys->ops.prepare_for_kickoff)
-				phys->ops.prepare_for_kickoff(phys);
-			if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET)
-				needs_hw_reset = true;
-		}
+		if (phys->ops.prepare_for_kickoff)
+			phys->ops.prepare_for_kickoff(phys);
+		if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET)
+			needs_hw_reset = true;
 	}
 	DPU_ATRACE_END("enc_prepare_for_kickoff");
 
@@ -1819,7 +1811,7 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
 	/* allow phys encs to handle any post-kickoff business */
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		phys = dpu_enc->phys_encs[i];
-		if (phys && phys->ops.handle_post_kickoff)
+		if (phys->ops.handle_post_kickoff)
 			phys->ops.handle_post_kickoff(phys);
 	}
 
@@ -1848,7 +1840,7 @@ void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc)
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		phys = dpu_enc->phys_encs[i];
-		if (phys && phys->ops.prepare_commit)
+		if (phys->ops.prepare_commit)
 			phys->ops.prepare_commit(phys);
 	}
 }
@@ -1863,9 +1855,6 @@ static int _dpu_encoder_status_show(struct seq_file *s, void *data)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (!phys)
-			continue;
-
 		seq_printf(s, "intf:%d    vsync:%8d     underrun:%8d    ",
 				phys->intf_idx - INTF_0,
 				atomic_read(&phys->vsync_cnt),
@@ -1924,8 +1913,7 @@ static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 		dpu_enc->debugfs_root, dpu_enc, &debugfs_status_fops);
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++)
-		if (dpu_enc->phys_encs[i] &&
-				dpu_enc->phys_encs[i]->ops.late_register)
+		if (dpu_enc->phys_encs[i]->ops.late_register)
 			dpu_enc->phys_encs[i]->ops.late_register(
 					dpu_enc->phys_encs[i],
 					dpu_enc->debugfs_root);
@@ -2094,11 +2082,8 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
-
-		if (phys) {
-			atomic_set(&phys->vsync_cnt, 0);
-			atomic_set(&phys->underrun_cnt, 0);
-		}
+		atomic_set(&phys->vsync_cnt, 0);
+		atomic_set(&phys->underrun_cnt, 0);
 	}
 	mutex_unlock(&dpu_enc->enc_lock);
 
@@ -2240,8 +2225,6 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
-		if (!phys)
-			continue;
 
 		switch (event) {
 		case MSM_ENC_COMMIT_DONE:
@@ -2257,7 +2240,7 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
 			DPU_ERROR_ENC(dpu_enc, "unknown wait event %d\n",
 					event);
 			return -EINVAL;
-		};
+		}
 
 		if (fn_wait) {
 			DPU_ATRACE_BEGIN("wait_for_completion_event");
@@ -2274,7 +2257,6 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
 enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder)
 {
 	struct dpu_encoder_virt *dpu_enc = NULL;
-	int i;
 
 	if (!encoder) {
 		DPU_ERROR("invalid encoder\n");
@@ -2285,12 +2267,8 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder)
 	if (dpu_enc->cur_master)
 		return dpu_enc->cur_master->intf_mode;
 
-	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
-		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
-
-		if (phys)
-			return phys->intf_mode;
-	}
+	if (dpu_enc->num_phys_encs)
+		return dpu_enc->phys_encs[0]->intf_mode;
 
 	return INTF_MODE_NONE;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
index 047960949fbb..39e1e280ba44 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -45,8 +45,7 @@ static bool dpu_encoder_phys_cmd_mode_fixup(
 		const struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (phys_enc)
-		DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), "\n");
+	DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), "\n");
 	return true;
 }
 
@@ -58,11 +57,8 @@ static void _dpu_encoder_phys_cmd_update_intf_cfg(
 	struct dpu_hw_ctl *ctl;
 	struct dpu_hw_intf_cfg intf_cfg = { 0 };
 
-	if (!phys_enc)
-		return;
-
 	ctl = phys_enc->hw_ctl;
-	if (!ctl || !ctl->ops.setup_intf_cfg)
+	if (!ctl->ops.setup_intf_cfg)
 		return;
 
 	intf_cfg.intf = phys_enc->intf_idx;
@@ -79,7 +75,7 @@ static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx)
 	int new_cnt;
 	u32 event = DPU_ENCODER_FRAME_EVENT_DONE;
 
-	if (!phys_enc || !phys_enc->hw_pp)
+	if (!phys_enc->hw_pp)
 		return;
 
 	DPU_ATRACE_BEGIN("pp_done_irq");
@@ -106,7 +102,7 @@ static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx)
 	struct dpu_encoder_phys *phys_enc = arg;
 	struct dpu_encoder_phys_cmd *cmd_enc;
 
-	if (!phys_enc || !phys_enc->hw_pp)
+	if (!phys_enc->hw_pp)
 		return;
 
 	DPU_ATRACE_BEGIN("rd_ptr_irq");
@@ -125,9 +121,6 @@ static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
-	if (!phys_enc || !phys_enc->hw_ctl)
-		return;
-
 	DPU_ATRACE_BEGIN("ctl_start_irq");
 
 	atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0);
@@ -141,9 +134,6 @@ static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
-	if (!phys_enc)
-		return;
-
 	if (phys_enc->parent_ops->handle_underrun_virt)
 		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
 			phys_enc);
@@ -179,7 +169,7 @@ static void dpu_encoder_phys_cmd_mode_set(
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc || !mode || !adj_mode) {
+	if (!mode || !adj_mode) {
 		DPU_ERROR("invalid args\n");
 		return;
 	}
@@ -198,7 +188,7 @@ static int _dpu_encoder_phys_cmd_handle_ppdone_timeout(
 	u32 frame_event = DPU_ENCODER_FRAME_EVENT_ERROR;
 	bool do_log = false;
 
-	if (!phys_enc || !phys_enc->hw_pp || !phys_enc->hw_ctl)
+	if (!phys_enc->hw_pp)
 		return -EINVAL;
 
 	cmd_enc->pp_timeout_report_cnt++;
@@ -247,11 +237,6 @@ static int _dpu_encoder_phys_cmd_wait_for_idle(
 	struct dpu_encoder_wait_info wait_info;
 	int ret;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return -EINVAL;
-	}
-
 	wait_info.wq = &phys_enc->pending_kickoff_wq;
 	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
 	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
@@ -273,7 +258,7 @@ static int dpu_encoder_phys_cmd_control_vblank_irq(
 	int ret = 0;
 	int refcount;
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid encoder\n");
 		return -EINVAL;
 	}
@@ -314,9 +299,6 @@ end:
 static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
 		bool enable)
 {
-	if (!phys_enc)
-		return;
-
 	trace_dpu_enc_phys_cmd_irq_ctrl(DRMID(phys_enc->parent),
 			phys_enc->hw_pp->idx - PINGPONG_0,
 			enable, atomic_read(&phys_enc->vblank_refcount));
@@ -351,7 +333,7 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	u32 vsync_hz;
 	struct dpu_kms *dpu_kms;
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid encoder\n");
 		return;
 	}
@@ -428,8 +410,7 @@ static void _dpu_encoder_phys_cmd_pingpong_config(
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp
-			|| !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+	if (!phys_enc->hw_pp || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
 		DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != 0);
 		return;
 	}
@@ -458,7 +439,7 @@ static void dpu_encoder_phys_cmd_enable_helper(
 	struct dpu_hw_ctl *ctl;
 	u32 flush_mask = 0;
 
-	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
 		return;
 	}
@@ -480,7 +461,7 @@ static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc)
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid phys encoder\n");
 		return;
 	}
@@ -499,8 +480,7 @@ static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc)
 static void _dpu_encoder_phys_cmd_connect_te(
 		struct dpu_encoder_phys *phys_enc, bool enable)
 {
-	if (!phys_enc || !phys_enc->hw_pp ||
-			!phys_enc->hw_pp->ops.connect_external_te)
+	if (!phys_enc->hw_pp || !phys_enc->hw_pp->ops.connect_external_te)
 		return;
 
 	trace_dpu_enc_phys_cmd_connect_te(DRMID(phys_enc->parent), enable);
@@ -518,7 +498,7 @@ static int dpu_encoder_phys_cmd_get_line_count(
 {
 	struct dpu_hw_pingpong *hw_pp;
 
-	if (!phys_enc || !phys_enc->hw_pp)
+	if (!phys_enc->hw_pp)
 		return -EINVAL;
 
 	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
@@ -536,7 +516,7 @@ static void dpu_encoder_phys_cmd_disable(struct dpu_encoder_phys *phys_enc)
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid encoder\n");
 		return;
 	}
@@ -559,10 +539,6 @@ static void dpu_encoder_phys_cmd_destroy(struct dpu_encoder_phys *phys_enc)
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
 	kfree(cmd_enc);
 }
 
@@ -580,7 +556,7 @@ static void dpu_encoder_phys_cmd_prepare_for_kickoff(
 			to_dpu_encoder_phys_cmd(phys_enc);
 	int ret;
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid encoder\n");
 		return;
 	}
@@ -614,11 +590,6 @@ static int _dpu_encoder_phys_cmd_wait_for_ctl_start(
 	struct dpu_encoder_wait_info wait_info;
 	int ret;
 
-	if (!phys_enc || !phys_enc->hw_ctl) {
-		DPU_ERROR("invalid argument(s)\n");
-		return -EINVAL;
-	}
-
 	wait_info.wq = &phys_enc->pending_kickoff_wq;
 	wait_info.atomic_cnt = &phys_enc->pending_ctlstart_cnt;
 	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
@@ -639,9 +610,6 @@ static int dpu_encoder_phys_cmd_wait_for_tx_complete(
 {
 	int rc;
 
-	if (!phys_enc)
-		return -EINVAL;
-
 	rc = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
 	if (rc) {
 		DRM_ERROR("failed wait_for_idle: id:%u ret:%d intf:%d\n",
@@ -658,9 +626,6 @@ static int dpu_encoder_phys_cmd_wait_for_commit_done(
 	int rc = 0;
 	struct dpu_encoder_phys_cmd *cmd_enc;
 
-	if (!phys_enc)
-		return -EINVAL;
-
 	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
 
 	/* only required for master controller */
@@ -681,9 +646,6 @@ static int dpu_encoder_phys_cmd_wait_for_vblank(
 	struct dpu_encoder_phys_cmd *cmd_enc;
 	struct dpu_encoder_wait_info wait_info;
 
-	if (!phys_enc)
-		return -EINVAL;
-
 	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
 
 	/* only required for master controller */
@@ -715,9 +677,6 @@ static void dpu_encoder_phys_cmd_handle_post_kickoff(
 static void dpu_encoder_phys_cmd_trigger_start(
 		struct dpu_encoder_phys *phys_enc)
 {
-	if (!phys_enc)
-		return;
-
 	dpu_encoder_helper_trigger_start(phys_enc);
 }
 
@@ -816,6 +775,4 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
 	DPU_DEBUG_CMDENC(cmd_enc, "created\n");
 
 	return phys_enc;
-
-	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index 3123ef873cdf..c71c18de5966 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -220,8 +220,7 @@ static bool dpu_encoder_phys_vid_mode_fixup(
 		const struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (phys_enc)
-		DPU_DEBUG_VIDENC(phys_enc, "\n");
+	DPU_DEBUG_VIDENC(phys_enc, "\n");
 
 	/*
 	 * Modifying mode has consequences when the mode comes back to us
@@ -239,7 +238,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine(
 	unsigned long lock_flags;
 	struct dpu_hw_intf_cfg intf_cfg = { 0 };
 
-	if (!phys_enc || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+	if (!phys_enc->hw_ctl->ops.setup_intf_cfg) {
 		DPU_ERROR("invalid encoder %d\n", phys_enc != 0);
 		return;
 	}
@@ -280,6 +279,14 @@ static void dpu_encoder_phys_vid_setup_timing_engine(
 	phys_enc->hw_intf->ops.setup_timing_gen(phys_enc->hw_intf,
 			&timing_params, fmt);
 	phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
+
+	/* setup which pp blk will connect to this intf */
+	if (phys_enc->hw_intf->ops.bind_pingpong_blk)
+		phys_enc->hw_intf->ops.bind_pingpong_blk(
+				phys_enc->hw_intf,
+				true,
+				phys_enc->hw_pp->idx);
+
 	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
 
 	programmable_fetch_config(phys_enc, &timing_params);
@@ -293,12 +300,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
 	u32 flush_register = 0;
 	int new_cnt = -1, old_cnt = -1;
 
-	if (!phys_enc)
-		return;
-
 	hw_ctl = phys_enc->hw_ctl;
-	if (!hw_ctl)
-		return;
 
 	DPU_ATRACE_BEGIN("vblank_irq");
 
@@ -314,7 +316,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
 	 * so we need to double-check with hw that it accepted the flush bits
 	 */
 	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
-	if (hw_ctl && hw_ctl->ops.get_flush_register)
+	if (hw_ctl->ops.get_flush_register)
 		flush_register = hw_ctl->ops.get_flush_register(hw_ctl);
 
 	if (!(flush_register & hw_ctl->ops.get_pending_flush(hw_ctl)))
@@ -335,9 +337,6 @@ static void dpu_encoder_phys_vid_underrun_irq(void *arg, int irq_idx)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
-	if (!phys_enc)
-		return;
-
 	if (phys_enc->parent_ops->handle_underrun_virt)
 		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
 			phys_enc);
@@ -374,11 +373,6 @@ static void dpu_encoder_phys_vid_mode_set(
 		struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder/kms\n");
-		return;
-	}
-
 	if (adj_mode) {
 		phys_enc->cached_mode = *adj_mode;
 		drm_mode_debug_printmodeline(adj_mode);
@@ -395,11 +389,6 @@ static int dpu_encoder_phys_vid_control_vblank_irq(
 	int ret = 0;
 	int refcount;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return -EINVAL;
-	}
-
 	refcount = atomic_read(&phys_enc->vblank_refcount);
 
 	/* Slave encoders don't report vblank */
@@ -435,6 +424,7 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
 {
 	struct dpu_hw_ctl *ctl;
 	u32 flush_mask = 0;
+	u32 intf_flush_mask = 0;
 
 	ctl = phys_enc->hw_ctl;
 
@@ -459,10 +449,18 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
 	ctl->ops.get_bitmask_intf(ctl, &flush_mask, phys_enc->hw_intf->idx);
 	ctl->ops.update_pending_flush(ctl, flush_mask);
 
+	if (ctl->ops.get_bitmask_active_intf)
+		ctl->ops.get_bitmask_active_intf(ctl, &intf_flush_mask,
+			phys_enc->hw_intf->idx);
+
+	if (ctl->ops.update_pending_intf_flush)
+		ctl->ops.update_pending_intf_flush(ctl, intf_flush_mask);
+
 skip_flush:
 	DPU_DEBUG_VIDENC(phys_enc,
-			 "update pending flush ctl %d flush_mask %x\n",
-			 ctl->idx - CTL_0, flush_mask);
+		"update pending flush ctl %d flush_mask 0%x intf_mask 0x%x\n",
+		ctl->idx - CTL_0, flush_mask, intf_flush_mask);
+
 
 	/* ctl_flush & timing engine enable will be triggered by framework */
 	if (phys_enc->enable_state == DPU_ENC_DISABLED)
@@ -471,11 +469,6 @@ skip_flush:
 
 static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc)
 {
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
-
 	DPU_DEBUG_VIDENC(phys_enc, "\n");
 	kfree(phys_enc);
 }
@@ -493,11 +486,6 @@ static int dpu_encoder_phys_vid_wait_for_vblank(
 	struct dpu_encoder_wait_info wait_info;
 	int ret;
 
-	if (!phys_enc) {
-		pr_err("invalid encoder\n");
-		return -EINVAL;
-	}
-
 	wait_info.wq = &phys_enc->pending_kickoff_wq;
 	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
 	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
@@ -543,13 +531,8 @@ static void dpu_encoder_phys_vid_prepare_for_kickoff(
 	struct dpu_hw_ctl *ctl;
 	int rc;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder/parameters\n");
-		return;
-	}
-
 	ctl = phys_enc->hw_ctl;
-	if (!ctl || !ctl->ops.wait_reset_status)
+	if (!ctl->ops.wait_reset_status)
 		return;
 
 	/*
@@ -569,12 +552,12 @@ static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
 	unsigned long lock_flags;
 	int ret;
 
-	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev) {
+	if (!phys_enc->parent || !phys_enc->parent->dev) {
 		DPU_ERROR("invalid encoder/device\n");
 		return;
 	}
 
-	if (!phys_enc->hw_intf || !phys_enc->hw_ctl) {
+	if (!phys_enc->hw_intf) {
 		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
 				phys_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
 		return;
@@ -639,9 +622,6 @@ static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
 {
 	int ret;
 
-	if (!phys_enc)
-		return;
-
 	trace_dpu_enc_phys_vid_irq_ctrl(DRMID(phys_enc->parent),
 			    phys_enc->hw_intf->idx - INTF_0,
 			    enable,
@@ -662,9 +642,6 @@ static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
 static int dpu_encoder_phys_vid_get_line_count(
 		struct dpu_encoder_phys *phys_enc)
 {
-	if (!phys_enc)
-		return -EINVAL;
-
 	if (!dpu_encoder_phys_vid_is_master(phys_enc))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 24ab6249083a..528632690f1e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -489,12 +489,28 @@ static const struct dpu_format dpu_format_map_ubwc[] = {
 		true, 4, DPU_FORMAT_FLAG_COMPRESSED,
 		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
 
+	/* ARGB8888 and ABGR8888 purposely have the same color
+	 * ordering.  The hardware only supports ABGR8888 UBWC
+	 * natively.
+	 */
+	INTERLEAVED_RGB_FMT_TILED(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
 	INTERLEAVED_RGB_FMT_TILED(XBGR8888,
 		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
 		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
 		false, 4, DPU_FORMAT_FLAG_COMPRESSED,
 		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
 
+	INTERLEAVED_RGB_FMT_TILED(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
 	INTERLEAVED_RGB_FMT_TILED(ABGR2101010,
 		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
 		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
@@ -550,7 +566,9 @@ static int _dpu_format_get_media_color_ubwc(const struct dpu_format *fmt)
 {
 	static const struct dpu_media_color_map dpu_media_ubwc_map[] = {
 		{DRM_FORMAT_ABGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_ARGB8888, COLOR_FMT_RGBA8888_UBWC},
 		{DRM_FORMAT_XBGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_XRGB8888, COLOR_FMT_RGBA8888_UBWC},
 		{DRM_FORMAT_ABGR2101010, COLOR_FMT_RGBA1010102_UBWC},
 		{DRM_FORMAT_XBGR2101010, COLOR_FMT_RGBA1010102_UBWC},
 		{DRM_FORMAT_BGR565, COLOR_FMT_RGB565_UBWC},
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index 04c8c44f5b9c..c567917541e8 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -11,11 +11,17 @@
 #include "dpu_hw_catalog_format.h"
 #include "dpu_kms.h"
 
-#define VIG_SDM845_MASK \
-	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_SCALER_QSEED3) | BIT(DPU_SSPP_QOS) |\
+#define VIG_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\
 	BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_QOS_8LVL) |\
 	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT))
 
+#define VIG_SDM845_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3))
+
+#define VIG_SC7180_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED4))
+
 #define DMA_SDM845_MASK \
 	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\
 	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\
@@ -27,6 +33,9 @@
 #define MIXER_SDM845_MASK \
 	(BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER))
 
+#define MIXER_SC7180_MASK \
+	(BIT(DPU_DIM_LAYER))
+
 #define PINGPONG_SDM845_MASK BIT(DPU_PINGPONG_DITHER)
 
 #define PINGPONG_SDM845_SPLIT_MASK \
@@ -58,9 +67,20 @@ static const struct dpu_caps sdm845_dpu_caps = {
 	.has_src_split = true,
 	.has_dim_layer = true,
 	.has_idle_pc = true,
+	.has_3d_merge = true,
+};
+
+static const struct dpu_caps sc7180_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0x9,
+	.qseed_type = DPU_SSPP_SCALER_QSEED4,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.ubwc_version = DPU_HW_UBWC_VER_20,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
 };
 
-static struct dpu_mdp_cfg sdm845_mdp[] = {
+static const struct dpu_mdp_cfg sdm845_mdp[] = {
 	{
 	.name = "top_0", .id = MDP_TOP,
 	.base = 0x0, .len = 0x45C,
@@ -85,10 +105,27 @@ static struct dpu_mdp_cfg sdm845_mdp[] = {
 	},
 };
 
+static const struct dpu_mdp_cfg sc7180_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x494,
+	.features = 0,
+	.highest_bank_bit = 0x3,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+		.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+		.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA1] = {
+		.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+		.reg_off = 0x2BC, .bit_off = 8},
+	},
+};
+
 /*************************************************************
  * CTL sub blocks config
  *************************************************************/
-static struct dpu_ctl_cfg sdm845_ctl[] = {
+static const struct dpu_ctl_cfg sdm845_ctl[] = {
 	{
 	.name = "ctl_0", .id = CTL_0,
 	.base = 0x1000, .len = 0xE4,
@@ -116,6 +153,24 @@ static struct dpu_ctl_cfg sdm845_ctl[] = {
 	},
 };
 
+static const struct dpu_ctl_cfg sc7180_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0xE4,
+	.features = BIT(DPU_CTL_ACTIVE_CFG)
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0xE4,
+	.features = BIT(DPU_CTL_ACTIVE_CFG)
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0xE4,
+	.features = BIT(DPU_CTL_ACTIVE_CFG)
+	},
+};
+
 /*************************************************************
  * SSPP sub blocks config
  *************************************************************/
@@ -128,7 +183,7 @@ static const struct dpu_sspp_blks_common sdm845_sspp_common = {
 	.maxvdeciexp = MAX_VERT_DECIMATION,
 };
 
-#define _VIG_SBLK(num, sdma_pri) \
+#define _VIG_SBLK(num, sdma_pri, qseed_ver) \
 	{ \
 	.common = &sdm845_sspp_common, \
 	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
@@ -137,7 +192,7 @@ static const struct dpu_sspp_blks_common sdm845_sspp_common = {
 	.src_blk = {.name = STRCAT("sspp_src_", num), \
 		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
 	.scaler_blk = {.name = STRCAT("sspp_scaler", num), \
-		.id = DPU_SSPP_SCALER_QSEED3, \
+		.id = qseed_ver, \
 		.base = 0xa00, .len = 0xa0,}, \
 	.csc_blk = {.name = STRCAT("sspp_csc", num), \
 		.id = DPU_SSPP_CSC_10BIT, \
@@ -162,10 +217,14 @@ static const struct dpu_sspp_blks_common sdm845_sspp_common = {
 	.virt_num_formats = ARRAY_SIZE(plane_formats), \
 	}
 
-static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 = _VIG_SBLK("0", 5);
-static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 = _VIG_SBLK("1", 6);
-static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 = _VIG_SBLK("2", 7);
-static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 = _VIG_SBLK("3", 8);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 =
+				_VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 =
+				_VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 =
+				_VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 =
+				_VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED3);
 
 static const struct dpu_sspp_sub_blks sdm845_dma_sblk_0 = _DMA_SBLK("8", 1);
 static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK("9", 2);
@@ -184,7 +243,7 @@ static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK("11", 4);
 	.clk_ctrl = _clkctrl \
 	}
 
-static struct dpu_sspp_cfg sdm845_sspp[] = {
+static const struct dpu_sspp_cfg sdm845_sspp[] = {
 	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SDM845_MASK,
 		sdm845_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
 	SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SDM845_MASK,
@@ -203,9 +262,26 @@ static struct dpu_sspp_cfg sdm845_sspp[] = {
 		sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1),
 };
 
+static const struct dpu_sspp_sub_blks sc7180_vig_sblk_0 =
+				_VIG_SBLK("0", 4, DPU_SSPP_SCALER_QSEED4);
+
+static const struct dpu_sspp_cfg sc7180_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK,
+		sc7180_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+	SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1),
+	SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0),
+};
+
 /*************************************************************
  * MIXER sub blocks config
  *************************************************************/
+
+/* SDM845 */
+
 static const struct dpu_lm_sub_blks sdm845_lm_sblk = {
 	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
 	.maxblendstages = 11, /* excluding base layer */
@@ -215,23 +291,46 @@ static const struct dpu_lm_sub_blks sdm845_lm_sblk = {
 	},
 };
 
-#define LM_BLK(_name, _id, _base, _pp, _lmpair) \
+#define LM_BLK(_name, _id, _base, _fmask, _sblk, _pp, _lmpair) \
 	{ \
 	.name = _name, .id = _id, \
 	.base = _base, .len = 0x320, \
-	.features = MIXER_SDM845_MASK, \
-	.sblk = &sdm845_lm_sblk, \
+	.features = _fmask, \
+	.sblk = _sblk, \
 	.pingpong = _pp, \
 	.lm_pair_mask = (1 << _lmpair) \
 	}
 
-static struct dpu_lm_cfg sdm845_lm[] = {
-	LM_BLK("lm_0", LM_0, 0x44000, PINGPONG_0, LM_1),
-	LM_BLK("lm_1", LM_1, 0x45000, PINGPONG_1, LM_0),
-	LM_BLK("lm_2", LM_2, 0x46000, PINGPONG_2, LM_5),
-	LM_BLK("lm_3", LM_3, 0x0, PINGPONG_MAX, 0),
-	LM_BLK("lm_4", LM_4, 0x0, PINGPONG_MAX, 0),
-	LM_BLK("lm_5", LM_5, 0x49000, PINGPONG_3, LM_2),
+static const struct dpu_lm_cfg sdm845_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_0, LM_1),
+	LM_BLK("lm_1", LM_1, 0x45000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_1, LM_0),
+	LM_BLK("lm_2", LM_2, 0x46000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_2, LM_5),
+	LM_BLK("lm_3", LM_3, 0x0, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_MAX, 0),
+	LM_BLK("lm_4", LM_4, 0x0, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_MAX, 0),
+	LM_BLK("lm_5", LM_5, 0x49000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_3, LM_2),
+};
+
+/* SC7180 */
+
+static const struct dpu_lm_sub_blks sc7180_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 7, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x38, 0x50, 0x68, 0x80, 0x98, 0xb0
+	},
+};
+
+static const struct dpu_lm_cfg sc7180_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_0, LM_1),
+	LM_BLK("lm_1", LM_1, 0x45000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_1, LM_0),
 };
 
 /*************************************************************
@@ -264,13 +363,18 @@ static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = {
 	.sblk = &sdm845_pp_sblk \
 	}
 
-static struct dpu_pingpong_cfg sdm845_pp[] = {
+static const struct dpu_pingpong_cfg sdm845_pp[] = {
 	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000),
 	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800),
 	PP_BLK("pingpong_2", PINGPONG_2, 0x71000),
 	PP_BLK("pingpong_3", PINGPONG_3, 0x71800),
 };
 
+static struct dpu_pingpong_cfg sc7180_pp[] = {
+	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000),
+	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800),
+};
+
 /*************************************************************
  * INTF sub blocks config
  *************************************************************/
@@ -278,26 +382,32 @@ static struct dpu_pingpong_cfg sdm845_pp[] = {
 	{\
 	.name = _name, .id = _id, \
 	.base = _base, .len = 0x280, \
+	.features = BIT(DPU_CTL_ACTIVE_CFG), \
 	.type = _type, \
 	.controller_id = _ctrl_id, \
 	.prog_fetch_lines_worst_case = 24 \
 	}
 
-static struct dpu_intf_cfg sdm845_intf[] = {
+static const struct dpu_intf_cfg sdm845_intf[] = {
 	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0),
 	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0),
 	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1),
 	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1),
 };
 
+static const struct dpu_intf_cfg sc7180_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0),
+};
+
 /*************************************************************
  * VBIF sub blocks config
  *************************************************************/
 /* VBIF QOS remap */
-static u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6};
-static u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3};
+static const u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6};
+static const u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3};
 
-static struct dpu_vbif_cfg sdm845_vbif[] = {
+static const struct dpu_vbif_cfg sdm845_vbif[] = {
 	{
 	.name = "vbif_0", .id = VBIF_0,
 	.base = 0, .len = 0x1040,
@@ -316,7 +426,7 @@ static struct dpu_vbif_cfg sdm845_vbif[] = {
 	},
 };
 
-static struct dpu_reg_dma_cfg sdm845_regdma = {
+static const struct dpu_reg_dma_cfg sdm845_regdma = {
 	.base = 0x0, .version = 0x1, .trigger_sel_off = 0x119c
 };
 
@@ -325,7 +435,7 @@ static struct dpu_reg_dma_cfg sdm845_regdma = {
  *************************************************************/
 
 /* SSPP QOS LUTs */
-static struct dpu_qos_lut_entry sdm845_qos_linear[] = {
+static const struct dpu_qos_lut_entry sdm845_qos_linear[] = {
 	{.fl = 4, .lut = 0x357},
 	{.fl = 5, .lut = 0x3357},
 	{.fl = 6, .lut = 0x23357},
@@ -340,7 +450,11 @@ static struct dpu_qos_lut_entry sdm845_qos_linear[] = {
 	{.fl = 0, .lut = 0x11222222223357}
 };
 
-static struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
+static const struct dpu_qos_lut_entry sc7180_qos_linear[] = {
+	{.fl = 0, .lut = 0x0011222222335777},
+};
+
+static const struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
 	{.fl = 10, .lut = 0x344556677},
 	{.fl = 11, .lut = 0x3344556677},
 	{.fl = 12, .lut = 0x23344556677},
@@ -349,11 +463,19 @@ static struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
 	{.fl = 0, .lut = 0x112233344556677},
 };
 
-static struct dpu_qos_lut_entry sdm845_qos_nrt[] = {
+static const struct dpu_qos_lut_entry sc7180_qos_macrotile[] = {
+	{.fl = 0, .lut = 0x0011223344556677},
+};
+
+static const struct dpu_qos_lut_entry sdm845_qos_nrt[] = {
+	{.fl = 0, .lut = 0x0},
+};
+
+static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = {
 	{.fl = 0, .lut = 0x0},
 };
 
-static struct dpu_perf_cfg sdm845_perf_data = {
+static const struct dpu_perf_cfg sdm845_perf_data = {
 	.max_bw_low = 6800000,
 	.max_bw_high = 6800000,
 	.min_core_ib = 2400000,
@@ -392,6 +514,30 @@ static struct dpu_perf_cfg sdm845_perf_data = {
 	},
 };
 
+static const struct dpu_perf_cfg sc7180_perf_data = {
+	.max_bw_low = 3900000,
+	.max_bw_high = 5500000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.danger_lut_tbl = {0xff, 0xffff, 0x0},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sc7180_qos_linear),
+		.entries = sc7180_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_macrotile),
+		.entries = sc7180_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_nrt),
+		.entries = sc7180_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+};
+
 /*************************************************************
  * Hardware catalog init
  *************************************************************/
@@ -421,12 +567,43 @@ static void sdm845_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
 		.reg_dma_count = 1,
 		.dma_cfg = sdm845_regdma,
 		.perf = sdm845_perf_data,
+		.mdss_irqs = 0x3ff,
+	};
+}
+
+/*
+ * sc7180_cfg_init(): populate sc7180 dpu sub-blocks reg offsets
+ * and instance counts.
+ */
+static void sc7180_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
+{
+	*dpu_cfg = (struct dpu_mdss_cfg){
+		.caps = &sc7180_dpu_caps,
+		.mdp_count = ARRAY_SIZE(sc7180_mdp),
+		.mdp = sc7180_mdp,
+		.ctl_count = ARRAY_SIZE(sc7180_ctl),
+		.ctl = sc7180_ctl,
+		.sspp_count = ARRAY_SIZE(sc7180_sspp),
+		.sspp = sc7180_sspp,
+		.mixer_count = ARRAY_SIZE(sc7180_lm),
+		.mixer = sc7180_lm,
+		.pingpong_count = ARRAY_SIZE(sc7180_pp),
+		.pingpong = sc7180_pp,
+		.intf_count = ARRAY_SIZE(sc7180_intf),
+		.intf = sc7180_intf,
+		.vbif_count = ARRAY_SIZE(sdm845_vbif),
+		.vbif = sdm845_vbif,
+		.reg_dma_count = 1,
+		.dma_cfg = sdm845_regdma,
+		.perf = sc7180_perf_data,
+		.mdss_irqs = 0x3f,
 	};
 }
 
-static struct dpu_mdss_hw_cfg_handler cfg_handler[] = {
+static const struct dpu_mdss_hw_cfg_handler cfg_handler[] = {
 	{ .hw_rev = DPU_HW_VER_400, .cfg_init = sdm845_cfg_init},
 	{ .hw_rev = DPU_HW_VER_401, .cfg_init = sdm845_cfg_init},
+	{ .hw_rev = DPU_HW_VER_620, .cfg_init = sc7180_cfg_init},
 };
 
 void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
index ec76b8687a98..09df7d87dd43 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -38,6 +38,7 @@
 #define DPU_HW_VER_401	DPU_HW_VER(4, 0, 1) /* sdm845 v2.0 */
 #define DPU_HW_VER_410	DPU_HW_VER(4, 1, 0) /* sdm670 v1.0 */
 #define DPU_HW_VER_500	DPU_HW_VER(5, 0, 0) /* sdm855 v1.0 */
+#define DPU_HW_VER_620	DPU_HW_VER(6, 2, 0) /* sc7180 v1.0 */
 
 
 #define IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170)
@@ -45,6 +46,7 @@
 #define IS_SDM845_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_400)
 #define IS_SDM670_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_410)
 #define IS_SDM855_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_500)
+#define IS_SC7180_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_620)
 
 
 #define DPU_HW_BLK_NAME_LEN	16
@@ -92,6 +94,7 @@ enum {
  * @DPU_SSPP_SRC             Src and fetch part of the pipes,
  * @DPU_SSPP_SCALER_QSEED2,  QSEED2 algorithm support
  * @DPU_SSPP_SCALER_QSEED3,  QSEED3 alogorithm support
+ * @DPU_SSPP_SCALER_QSEED4,  QSEED4 algorithm support
  * @DPU_SSPP_SCALER_RGB,     RGB Scaler, supported by RGB pipes
  * @DPU_SSPP_CSC,            Support of Color space converion
  * @DPU_SSPP_CSC_10BIT,      Support of 10-bit Color space conversion
@@ -110,6 +113,7 @@ enum {
 	DPU_SSPP_SRC = 0x1,
 	DPU_SSPP_SCALER_QSEED2,
 	DPU_SSPP_SCALER_QSEED3,
+	DPU_SSPP_SCALER_QSEED4,
 	DPU_SSPP_SCALER_RGB,
 	DPU_SSPP_CSC,
 	DPU_SSPP_CSC_10BIT,
@@ -166,6 +170,7 @@ enum {
  */
 enum {
 	DPU_CTL_SPLIT_DISPLAY = 0x1,
+	DPU_CTL_ACTIVE_CFG,
 	DPU_CTL_MAX
 };
 
@@ -269,7 +274,7 @@ struct dpu_qos_lut_entry {
  */
 struct dpu_qos_lut_tbl {
 	u32 nentry;
-	struct dpu_qos_lut_entry *entries;
+	const struct dpu_qos_lut_entry *entries;
 };
 
 /**
@@ -283,6 +288,7 @@ struct dpu_qos_lut_tbl {
  * @has_src_split      source split feature status
  * @has_dim_layer      dim layer feature status
  * @has_idle_pc        indicate if idle power collapse feature is supported
+ * @has_3d_merge       indicate if 3D merge is supported
  */
 struct dpu_caps {
 	u32 max_mixer_width;
@@ -293,6 +299,7 @@ struct dpu_caps {
 	bool has_src_split;
 	bool has_dim_layer;
 	bool has_idle_pc;
+	bool has_3d_merge;
 };
 
 /**
@@ -320,6 +327,7 @@ struct dpu_sspp_blks_common {
  * @maxupscale:  maxupscale ratio supported
  * @smart_dma_priority: hw priority of rect1 of multirect pipe
  * @max_per_pipe_bw: maximum allowable bandwidth of this pipe in kBps
+ * @qseed_ver: qseed version
  * @src_blk:
  * @scaler_blk:
  * @csc_blk:
@@ -340,6 +348,7 @@ struct dpu_sspp_sub_blks {
 	u32 maxupscale;
 	u32 smart_dma_priority;
 	u32 max_per_pipe_bw;
+	u32 qseed_ver;
 	struct dpu_src_blk src_blk;
 	struct dpu_scaler_blk scaler_blk;
 	struct dpu_pp_blk csc_blk;
@@ -511,7 +520,7 @@ struct dpu_vbif_dynamic_ot_cfg {
  */
 struct dpu_vbif_dynamic_ot_tbl {
 	u32 count;
-	struct dpu_vbif_dynamic_ot_cfg *cfg;
+	const struct dpu_vbif_dynamic_ot_cfg *cfg;
 };
 
 /**
@@ -521,7 +530,7 @@ struct dpu_vbif_dynamic_ot_tbl {
  */
 struct dpu_vbif_qos_tbl {
 	u32 npriority_lvl;
-	u32 *priority_lvl;
+	const u32 *priority_lvl;
 };
 
 /**
@@ -646,6 +655,7 @@ struct dpu_perf_cfg {
  * @dma_formats        Supported formats for dma pipe
  * @cursor_formats     Supported formats for cursor pipe
  * @vig_formats        Supported formats for vig pipe
+ * @mdss_irqs:         Bitmap with the irqs supported by the target
  */
 struct dpu_mdss_cfg {
 	u32 hwversion;
@@ -653,25 +663,25 @@ struct dpu_mdss_cfg {
 	const struct dpu_caps *caps;
 
 	u32 mdp_count;
-	struct dpu_mdp_cfg *mdp;
+	const struct dpu_mdp_cfg *mdp;
 
 	u32 ctl_count;
-	struct dpu_ctl_cfg *ctl;
+	const struct dpu_ctl_cfg *ctl;
 
 	u32 sspp_count;
-	struct dpu_sspp_cfg *sspp;
+	const struct dpu_sspp_cfg *sspp;
 
 	u32 mixer_count;
-	struct dpu_lm_cfg *mixer;
+	const struct dpu_lm_cfg *mixer;
 
 	u32 pingpong_count;
-	struct dpu_pingpong_cfg *pingpong;
+	const struct dpu_pingpong_cfg *pingpong;
 
 	u32 intf_count;
-	struct dpu_intf_cfg *intf;
+	const struct dpu_intf_cfg *intf;
 
 	u32 vbif_count;
-	struct dpu_vbif_cfg *vbif;
+	const struct dpu_vbif_cfg *vbif;
 
 	u32 reg_dma_count;
 	struct dpu_reg_dma_cfg dma_cfg;
@@ -681,9 +691,11 @@ struct dpu_mdss_cfg {
 	/* Add additional block data structures here */
 
 	struct dpu_perf_cfg perf;
-	struct dpu_format_extended *dma_formats;
-	struct dpu_format_extended *cursor_formats;
-	struct dpu_format_extended *vig_formats;
+	const struct dpu_format_extended *dma_formats;
+	const struct dpu_format_extended *cursor_formats;
+	const struct dpu_format_extended *vig_formats;
+
+	unsigned long mdss_irqs;
 };
 
 struct dpu_mdss_hw_cfg_handler {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
index bb6112c949ae..3766f0fd0bf0 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
@@ -6,8 +6,12 @@
 
 static const uint32_t qcom_compressed_supported_formats[] = {
 	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_ARGB8888,
 	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_BGR565,
+
+	DRM_FORMAT_NV12,
 };
 
 static const uint32_t plane_formats[] = {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
index 179e8d52cadb..831e5f7a9b7f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -22,14 +22,18 @@
 #define   CTL_PREPARE                   0x0d0
 #define   CTL_SW_RESET                  0x030
 #define   CTL_LAYER_EXTN_OFFSET         0x40
+#define   CTL_INTF_ACTIVE               0x0F4
+#define   CTL_INTF_FLUSH                0x110
+#define   CTL_INTF_MASTER               0x134
 
 #define CTL_MIXER_BORDER_OUT            BIT(24)
 #define CTL_FLUSH_MASK_CTL              BIT(17)
 
 #define DPU_REG_RESET_TIMEOUT_US        2000
+#define  INTF_IDX       31
 
-static struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl,
-		struct dpu_mdss_cfg *m,
+static const struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl,
+		const struct dpu_mdss_cfg *m,
 		void __iomem *addr,
 		struct dpu_hw_blk_reg_map *b)
 {
@@ -100,11 +104,27 @@ static inline void dpu_hw_ctl_update_pending_flush(struct dpu_hw_ctl *ctx,
 	ctx->pending_flush_mask |= flushbits;
 }
 
+static inline void dpu_hw_ctl_update_pending_intf_flush(struct dpu_hw_ctl *ctx,
+		u32 flushbits)
+{
+	ctx->pending_intf_flush_mask |= flushbits;
+}
+
 static u32 dpu_hw_ctl_get_pending_flush(struct dpu_hw_ctl *ctx)
 {
 	return ctx->pending_flush_mask;
 }
 
+static inline void dpu_hw_ctl_trigger_flush_v1(struct dpu_hw_ctl *ctx)
+{
+
+	if (ctx->pending_flush_mask & BIT(INTF_IDX))
+		DPU_REG_WRITE(&ctx->hw, CTL_INTF_FLUSH,
+				ctx->pending_intf_flush_mask);
+
+	DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask);
+}
+
 static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx)
 {
 	trace_dpu_hw_ctl_trigger_pending_flush(ctx->pending_flush_mask,
@@ -222,6 +242,36 @@ static int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx,
 	return 0;
 }
 
+static int dpu_hw_ctl_get_bitmask_intf_v1(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf intf)
+{
+	switch (intf) {
+	case INTF_0:
+	case INTF_1:
+		*flushbits |= BIT(31);
+		break;
+	default:
+		return 0;
+	}
+	return 0;
+}
+
+static int dpu_hw_ctl_active_get_bitmask_intf(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf intf)
+{
+	switch (intf) {
+	case INTF_0:
+		*flushbits |= BIT(0);
+		break;
+	case INTF_1:
+		*flushbits |= BIT(1);
+		break;
+	default:
+		return 0;
+	}
+	return 0;
+}
+
 static u32 dpu_hw_ctl_poll_reset_status(struct dpu_hw_ctl *ctx, u32 timeout_us)
 {
 	struct dpu_hw_blk_reg_map *c = &ctx->hw;
@@ -422,6 +472,24 @@ exit:
 	DPU_REG_WRITE(c, CTL_LAYER_EXT3(lm), mixercfg_ext3);
 }
 
+
+static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 intf_active = 0;
+	u32 mode_sel = 0;
+
+	if (cfg->intf_mode_sel == DPU_CTL_MODE_SEL_CMD)
+		mode_sel |= BIT(17);
+
+	intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE);
+	intf_active |= BIT(cfg->intf - INTF_0);
+
+	DPU_REG_WRITE(c, CTL_TOP, mode_sel);
+	DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active);
+}
+
 static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
 		struct dpu_hw_intf_cfg *cfg)
 {
@@ -455,31 +523,41 @@ static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
 static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops,
 		unsigned long cap)
 {
+	if (cap & BIT(DPU_CTL_ACTIVE_CFG)) {
+		ops->trigger_flush = dpu_hw_ctl_trigger_flush_v1;
+		ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg_v1;
+		ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf_v1;
+		ops->get_bitmask_active_intf =
+			dpu_hw_ctl_active_get_bitmask_intf;
+		ops->update_pending_intf_flush =
+			dpu_hw_ctl_update_pending_intf_flush;
+	} else {
+		ops->trigger_flush = dpu_hw_ctl_trigger_flush;
+		ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg;
+		ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf;
+	}
 	ops->clear_pending_flush = dpu_hw_ctl_clear_pending_flush;
 	ops->update_pending_flush = dpu_hw_ctl_update_pending_flush;
 	ops->get_pending_flush = dpu_hw_ctl_get_pending_flush;
-	ops->trigger_flush = dpu_hw_ctl_trigger_flush;
 	ops->get_flush_register = dpu_hw_ctl_get_flush_register;
 	ops->trigger_start = dpu_hw_ctl_trigger_start;
 	ops->trigger_pending = dpu_hw_ctl_trigger_pending;
-	ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg;
 	ops->reset = dpu_hw_ctl_reset_control;
 	ops->wait_reset_status = dpu_hw_ctl_wait_reset_status;
 	ops->clear_all_blendstages = dpu_hw_ctl_clear_all_blendstages;
 	ops->setup_blendstage = dpu_hw_ctl_setup_blendstage;
 	ops->get_bitmask_sspp = dpu_hw_ctl_get_bitmask_sspp;
 	ops->get_bitmask_mixer = dpu_hw_ctl_get_bitmask_mixer;
-	ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf;
 };
 
 static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m)
+		const struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_ctl *c;
-	struct dpu_ctl_cfg *cfg;
+	const struct dpu_ctl_cfg *cfg;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
index d3ae939ef9f8..09e1263c72e2 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
@@ -91,6 +91,15 @@ struct dpu_hw_ctl_ops {
 		u32 flushbits);
 
 	/**
+	 * OR in the given flushbits to the cached pending_intf_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @flushbits : module flushmask
+	 */
+	void (*update_pending_intf_flush)(struct dpu_hw_ctl *ctx,
+		u32 flushbits);
+
+	/**
 	 * Write the value of the pending_flush_mask to hardware
 	 * @ctx       : ctl path ctx pointer
 	 */
@@ -130,11 +139,24 @@ struct dpu_hw_ctl_ops {
 	uint32_t (*get_bitmask_mixer)(struct dpu_hw_ctl *ctx,
 		enum dpu_lm blk);
 
+	/**
+	 * Query the value of the intf flush mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
 	int (*get_bitmask_intf)(struct dpu_hw_ctl *ctx,
 		u32 *flushbits,
 		enum dpu_intf blk);
 
 	/**
+	 * Query the value of the intf active flush mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	int (*get_bitmask_active_intf)(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf blk);
+
+	/**
 	 * Set all blend stages to disabled
 	 * @ctx       : ctl path ctx pointer
 	 */
@@ -159,6 +181,7 @@ struct dpu_hw_ctl_ops {
  * @mixer_count: number of mixers
  * @mixer_hw_caps: mixer hardware capabilities
  * @pending_flush_mask: storage for pending ctl_flush managed via ops
+ * @pending_intf_flush_mask: pending INTF flush
  * @ops: operation list
  */
 struct dpu_hw_ctl {
@@ -171,6 +194,7 @@ struct dpu_hw_ctl {
 	int mixer_count;
 	const struct dpu_lm_cfg *mixer_hw_caps;
 	u32 pending_flush_mask;
+	u32 pending_intf_flush_mask;
 
 	/* ops */
 	struct dpu_hw_ctl_ops ops;
@@ -195,7 +219,7 @@ static inline struct dpu_hw_ctl *to_dpu_hw_ctl(struct dpu_hw_blk *hw)
  */
 struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m);
+		const struct dpu_mdss_cfg *m);
 
 /**
  * dpu_hw_ctl_destroy(): Destroys ctl driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
index 8bfa7d0eede6..d84a84f7fe1a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -800,8 +800,8 @@ static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr,
 		start_idx = reg_idx * 32;
 		end_idx = start_idx + 32;
 
-		if (start_idx >= ARRAY_SIZE(dpu_irq_map) ||
-				end_idx > ARRAY_SIZE(dpu_irq_map))
+		if (!test_bit(reg_idx, &intr->irq_mask) ||
+			start_idx >= ARRAY_SIZE(dpu_irq_map))
 			continue;
 
 		/*
@@ -955,8 +955,11 @@ static int dpu_hw_intr_clear_irqs(struct dpu_hw_intr *intr)
 	if (!intr)
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++)
-		DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off, 0xffffffff);
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		if (test_bit(i, &intr->irq_mask))
+			DPU_REG_WRITE(&intr->hw,
+					dpu_intr_set[i].clr_off, 0xffffffff);
+	}
 
 	/* ensure register writes go through */
 	wmb();
@@ -971,8 +974,11 @@ static int dpu_hw_intr_disable_irqs(struct dpu_hw_intr *intr)
 	if (!intr)
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++)
-		DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].en_off, 0x00000000);
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		if (test_bit(i, &intr->irq_mask))
+			DPU_REG_WRITE(&intr->hw,
+					dpu_intr_set[i].en_off, 0x00000000);
+	}
 
 	/* ensure register writes go through */
 	wmb();
@@ -991,6 +997,9 @@ static void dpu_hw_intr_get_interrupt_statuses(struct dpu_hw_intr *intr)
 
 	spin_lock_irqsave(&intr->irq_lock, irq_flags);
 	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		if (!test_bit(i, &intr->irq_mask))
+			continue;
+
 		/* Read interrupt status */
 		intr->save_irq_status[i] = DPU_REG_READ(&intr->hw,
 				dpu_intr_set[i].status_off);
@@ -1115,6 +1124,7 @@ struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	intr->irq_mask = m->mdss_irqs;
 	spin_lock_init(&intr->irq_lock);
 
 	return intr;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
index 4edcf402dc46..fc9c98617281 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
@@ -187,6 +187,7 @@ struct dpu_hw_intr {
 	u32 *save_irq_status;
 	u32 irq_idx_tbl_size;
 	spinlock_t irq_lock;
+	unsigned long irq_mask;
 };
 
 /**
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
index dcd87cda13fe..efe9a5719c6b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
@@ -56,8 +56,10 @@
 #define   INTF_FRAME_COUNT              0x0AC
 #define   INTF_LINE_COUNT               0x0B0
 
-static struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf,
-		struct dpu_mdss_cfg *m,
+#define   INTF_MUX                      0x25C
+
+static const struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf,
+		const struct dpu_mdss_cfg *m,
 		void __iomem *addr,
 		struct dpu_hw_blk_reg_map *b)
 {
@@ -218,6 +220,30 @@ static void dpu_hw_intf_setup_prg_fetch(
 	DPU_REG_WRITE(c, INTF_CONFIG, fetch_enable);
 }
 
+static void dpu_hw_intf_bind_pingpong_blk(
+		struct dpu_hw_intf *intf,
+		bool enable,
+		const enum dpu_pingpong pp)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 mux_cfg;
+
+	if (!intf)
+		return;
+
+	c = &intf->hw;
+
+	mux_cfg = DPU_REG_READ(c, INTF_MUX);
+	mux_cfg &= ~0xf;
+
+	if (enable)
+		mux_cfg |= (pp - PINGPONG_0) & 0x7;
+	else
+		mux_cfg |= 0xf;
+
+	DPU_REG_WRITE(c, INTF_MUX, mux_cfg);
+}
+
 static void dpu_hw_intf_get_status(
 		struct dpu_hw_intf *intf,
 		struct intf_status *s)
@@ -254,16 +280,18 @@ static void _setup_intf_ops(struct dpu_hw_intf_ops *ops,
 	ops->get_status = dpu_hw_intf_get_status;
 	ops->enable_timing = dpu_hw_intf_enable_timing_engine;
 	ops->get_line_count = dpu_hw_intf_get_line_count;
+	if (cap & BIT(DPU_CTL_ACTIVE_CFG))
+		ops->bind_pingpong_blk = dpu_hw_intf_bind_pingpong_blk;
 }
 
 static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m)
+		const struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_intf *c;
-	struct dpu_intf_cfg *cfg;
+	const struct dpu_intf_cfg *cfg;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
index b03acc225c9b..85468981632d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -52,6 +52,8 @@ struct intf_status {
  * @ enable_timing: enable/disable timing engine
  * @ get_status: returns if timing engine is enabled or not
  * @ get_line_count: reads current vertical line counter
+ * @bind_pingpong_blk: enable/disable the connection with pingpong which will
+ *                     feed pixels to this interface
  */
 struct dpu_hw_intf_ops {
 	void (*setup_timing_gen)(struct dpu_hw_intf *intf,
@@ -68,6 +70,10 @@ struct dpu_hw_intf_ops {
 			struct intf_status *status);
 
 	u32 (*get_line_count)(struct dpu_hw_intf *intf);
+
+	void (*bind_pingpong_blk)(struct dpu_hw_intf *intf,
+			bool enable,
+			const enum dpu_pingpong pp);
 };
 
 struct dpu_hw_intf {
@@ -92,7 +98,7 @@ struct dpu_hw_intf {
  */
 struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m);
+		const struct dpu_mdss_cfg *m);
 
 /**
  * dpu_hw_intf_destroy(): Destroys INTF driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
index 5bc39baa746a..37becd43bd54 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
@@ -24,8 +24,8 @@
 #define LM_BLEND0_FG_ALPHA               0x04
 #define LM_BLEND0_BG_ALPHA               0x08
 
-static struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
-		struct dpu_mdss_cfg *m,
+static const struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
+		const struct dpu_mdss_cfg *m,
 		void __iomem *addr,
 		struct dpu_hw_blk_reg_map *b)
 {
@@ -147,12 +147,13 @@ static void dpu_hw_lm_setup_color3(struct dpu_hw_mixer *ctx,
 	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
 }
 
-static void _setup_mixer_ops(struct dpu_mdss_cfg *m,
+static void _setup_mixer_ops(const struct dpu_mdss_cfg *m,
 		struct dpu_hw_lm_ops *ops,
 		unsigned long features)
 {
 	ops->setup_mixer_out = dpu_hw_lm_setup_out;
-	if (IS_SDM845_TARGET(m->hwversion) || IS_SDM670_TARGET(m->hwversion))
+	if (IS_SDM845_TARGET(m->hwversion) || IS_SDM670_TARGET(m->hwversion)
+	    || IS_SC7180_TARGET(m->hwversion))
 		ops->setup_blend_config = dpu_hw_lm_setup_blend_config_sdm845;
 	else
 		ops->setup_blend_config = dpu_hw_lm_setup_blend_config;
@@ -164,10 +165,10 @@ static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m)
+		const struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_mixer *c;
-	struct dpu_lm_cfg *cfg;
+	const struct dpu_lm_cfg *cfg;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
index 147ace31cfc2..4a6b2de19ef6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
@@ -91,7 +91,7 @@ static inline struct dpu_hw_mixer *to_dpu_hw_mixer(struct dpu_hw_blk *hw)
  */
 struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m);
+		const struct dpu_mdss_cfg *m);
 
 /**
  * dpu_hw_lm_destroy(): Destroys layer mixer driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
index 5dbaba9fd180..d110a40f0e73 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -28,8 +28,8 @@
 #define PP_FBC_BUDGET_CTL               0x038
 #define PP_FBC_LOSSY_MODE               0x03C
 
-static struct dpu_pingpong_cfg *_pingpong_offset(enum dpu_pingpong pp,
-		struct dpu_mdss_cfg *m,
+static const struct dpu_pingpong_cfg *_pingpong_offset(enum dpu_pingpong pp,
+		const struct dpu_mdss_cfg *m,
 		void __iomem *addr,
 		struct dpu_hw_blk_reg_map *b)
 {
@@ -195,10 +195,10 @@ static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m)
+		const struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_pingpong *c;
-	struct dpu_pingpong_cfg *cfg;
+	const struct dpu_pingpong_cfg *cfg;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
index 58bdb9279aa8..3d6f46b1db30 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -106,7 +106,7 @@ struct dpu_hw_pingpong {
  */
 struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m);
+		const struct dpu_mdss_cfg *m);
 
 /**
  * dpu_hw_pingpong_destroy - destroys pingpong driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
index 4f8b813aab81..82c5dbfdabc7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -132,6 +132,7 @@
 /* traffic shaper clock in Hz */
 #define TS_CLK			19200000
 
+
 static int _sspp_subblk_offset(struct dpu_hw_pipe *ctx,
 		int s_id,
 		u32 *idx)
@@ -657,7 +658,8 @@ static void _setup_layer_ops(struct dpu_hw_pipe *c,
 		test_bit(DPU_SSPP_SMART_DMA_V2, &c->cap->features))
 		c->ops.setup_multirect = dpu_hw_sspp_setup_multirect;
 
-	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features)) {
+	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features) ||
+			test_bit(DPU_SSPP_SCALER_QSEED4, &features)) {
 		c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3;
 		c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver;
 	}
@@ -666,7 +668,7 @@ static void _setup_layer_ops(struct dpu_hw_pipe *c,
 		c->ops.setup_cdp = dpu_hw_sspp_setup_cdp;
 }
 
-static struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp,
+static const struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp,
 		void __iomem *addr,
 		struct dpu_mdss_cfg *catalog,
 		struct dpu_hw_blk_reg_map *b)
@@ -696,7 +698,7 @@ struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
 		bool is_virtual_pipe)
 {
 	struct dpu_hw_pipe *hw_pipe;
-	struct dpu_sspp_cfg *cfg;
+	const struct dpu_sspp_cfg *cfg;
 
 	if (!addr || !catalog)
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
index a3680b482b41..85b018a9b03c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -27,7 +27,8 @@ struct dpu_hw_pipe;
  */
 #define DPU_SSPP_SCALER ((1UL << DPU_SSPP_SCALER_RGB) | \
 	(1UL << DPU_SSPP_SCALER_QSEED2) | \
-	(1UL << DPU_SSPP_SCALER_QSEED3))
+	 (1UL << DPU_SSPP_SCALER_QSEED3) | \
+	  (1UL << DPU_SSPP_SCALER_QSEED4))
 
 /**
  * Component indices
@@ -373,7 +374,7 @@ struct dpu_hw_pipe {
 	struct dpu_hw_blk base;
 	struct dpu_hw_blk_reg_map hw;
 	struct dpu_mdss_cfg *catalog;
-	struct dpu_mdp_cfg *mdp;
+	const struct dpu_mdp_cfg *mdp;
 
 	/* Pipe */
 	enum dpu_sspp idx;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
index 27fbeb504362..078afc5f5882 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
@@ -93,19 +93,12 @@ int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable)
 			DEV_DBG("%pS->%s: enable '%s'\n",
 				__builtin_return_address(0), __func__,
 				clk_arry[i].clk_name);
-			if (clk_arry[i].clk) {
-				rc = clk_prepare_enable(clk_arry[i].clk);
-				if (rc)
-					DEV_ERR("%pS->%s: %s en fail. rc=%d\n",
-						__builtin_return_address(0),
-						__func__,
-						clk_arry[i].clk_name, rc);
-			} else {
-				DEV_ERR("%pS->%s: '%s' is not available\n",
-					__builtin_return_address(0), __func__,
-					clk_arry[i].clk_name);
-				rc = -EPERM;
-			}
+			rc = clk_prepare_enable(clk_arry[i].clk);
+			if (rc)
+				DEV_ERR("%pS->%s: %s en fail. rc=%d\n",
+					__builtin_return_address(0),
+					__func__,
+					clk_arry[i].clk_name, rc);
 
 			if (rc && i) {
 				msm_dss_enable_clk(&clk_arry[i - 1],
@@ -119,12 +112,7 @@ int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable)
 				__builtin_return_address(0), __func__,
 				clk_arry[i].clk_name);
 
-			if (clk_arry[i].clk)
-				clk_disable_unprepare(clk_arry[i].clk);
-			else
-				DEV_ERR("%pS->%s: '%s' is not available\n",
-					__builtin_return_address(0), __func__,
-					clk_arry[i].clk_name);
+			clk_disable_unprepare(clk_arry[i].clk);
 		}
 	}
 
@@ -187,6 +175,7 @@ int msm_dss_parse_clock(struct platform_device *pdev,
 			continue;
 		mp->clk_config[i].rate = rate;
 		mp->clk_config[i].type = DSS_CLK_PCLK;
+		mp->clk_config[i].max_rate = rate;
 	}
 
 	mp->num_clk = num_clk;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 6c92f0fbeac9..cb08fafb1dc1 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1059,6 +1059,7 @@ static const struct dev_pm_ops dpu_pm_ops = {
 
 static const struct of_device_id dpu_dt_match[] = {
 	{ .compatible = "qcom,sdm845-dpu", },
+	{ .compatible = "qcom,sc7180-dpu", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dpu_dt_match);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 58d5acbcfc5c..3b9c33e694bf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -53,8 +53,13 @@ enum {
 	R_MAX
 };
 
+/*
+ * Default Preload Values
+ */
 #define DPU_QSEED3_DEFAULT_PRELOAD_H 0x4
 #define DPU_QSEED3_DEFAULT_PRELOAD_V 0x3
+#define DPU_QSEED4_DEFAULT_PRELOAD_V 0x2
+#define DPU_QSEED4_DEFAULT_PRELOAD_H 0x4
 
 #define DEFAULT_REFRESH_RATE	60
 
@@ -477,8 +482,16 @@ static void _dpu_plane_setup_scaler3(struct dpu_plane *pdpu,
 			scale_cfg->src_width[i] /= chroma_subsmpl_h;
 			scale_cfg->src_height[i] /= chroma_subsmpl_v;
 		}
-		scale_cfg->preload_x[i] = DPU_QSEED3_DEFAULT_PRELOAD_H;
-		scale_cfg->preload_y[i] = DPU_QSEED3_DEFAULT_PRELOAD_V;
+
+		if (pdpu->pipe_hw->cap->features &
+			BIT(DPU_SSPP_SCALER_QSEED4)) {
+			scale_cfg->preload_x[i] = DPU_QSEED4_DEFAULT_PRELOAD_H;
+			scale_cfg->preload_y[i] = DPU_QSEED4_DEFAULT_PRELOAD_V;
+		} else {
+			scale_cfg->preload_x[i] = DPU_QSEED3_DEFAULT_PRELOAD_H;
+			scale_cfg->preload_y[i] = DPU_QSEED3_DEFAULT_PRELOAD_V;
+		}
+
 		pstate->pixel_ext.num_ext_pxls_top[i] =
 			scale_cfg->src_height[i];
 		pstate->pixel_ext.num_ext_pxls_left[i] =
@@ -738,7 +751,7 @@ done:
 	} else {
 		pstate[R0]->multirect_index = DPU_SSPP_RECT_0;
 		pstate[R1]->multirect_index = DPU_SSPP_RECT_1;
-	};
+	}
 
 	DPU_DEBUG_PLANE(dpu_plane[R0], "R0: %d - %d\n",
 		pstate[R0]->multirect_mode, pstate[R0]->multirect_index);
@@ -858,7 +871,7 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 					  pdpu->pipe_sblk->maxupscale << 16,
 					  true, true);
 	if (ret) {
-		DPU_ERROR_PLANE(pdpu, "Check plane state failed (%d)\n", ret);
+		DPU_DEBUG_PLANE(pdpu, "Check plane state failed (%d)\n", ret);
 		return ret;
 	}
 	if (!state->visible)
@@ -884,13 +897,13 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 		(!(pdpu->features & DPU_SSPP_SCALER) ||
 		 !(pdpu->features & (BIT(DPU_SSPP_CSC)
 		 | BIT(DPU_SSPP_CSC_10BIT))))) {
-		DPU_ERROR_PLANE(pdpu,
+		DPU_DEBUG_PLANE(pdpu,
 				"plane doesn't have scaler/csc for yuv\n");
 		return -EINVAL;
 
 	/* check src bounds */
 	} else if (!dpu_plane_validate_src(&src, &fb_rect, min_src_size)) {
-		DPU_ERROR_PLANE(pdpu, "invalid source " DRM_RECT_FMT "\n",
+		DPU_DEBUG_PLANE(pdpu, "invalid source " DRM_RECT_FMT "\n",
 				DRM_RECT_ARG(&src));
 		return -E2BIG;
 
@@ -899,19 +912,19 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 		   (src.x1 & 0x1 || src.y1 & 0x1 ||
 		    drm_rect_width(&src) & 0x1 ||
 		    drm_rect_height(&src) & 0x1)) {
-		DPU_ERROR_PLANE(pdpu, "invalid yuv source " DRM_RECT_FMT "\n",
+		DPU_DEBUG_PLANE(pdpu, "invalid yuv source " DRM_RECT_FMT "\n",
 				DRM_RECT_ARG(&src));
 		return -EINVAL;
 
 	/* min dst support */
 	} else if (drm_rect_width(&dst) < 0x1 || drm_rect_height(&dst) < 0x1) {
-		DPU_ERROR_PLANE(pdpu, "invalid dest rect " DRM_RECT_FMT "\n",
+		DPU_DEBUG_PLANE(pdpu, "invalid dest rect " DRM_RECT_FMT "\n",
 				DRM_RECT_ARG(&dst));
 		return -EINVAL;
 
 	/* check decimated source width */
 	} else if (drm_rect_width(&src) > max_linewidth) {
-		DPU_ERROR_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n",
+		DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n",
 				DRM_RECT_ARG(&src), max_linewidth);
 		return -E2BIG;
 	}
@@ -1337,7 +1350,8 @@ static int _dpu_plane_init_debugfs(struct drm_plane *plane)
 			pdpu->debugfs_root, &pdpu->debugfs_src);
 
 	if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) ||
-			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2)) {
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED4)) {
 		dpu_debugfs_setup_regset32(&pdpu->debugfs_scaler,
 				sblk->scaler_blk.base + cfg->base,
 				sblk->scaler_blk.len,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index ddc8412731af..23f5b1433b35 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -141,11 +141,11 @@ int dpu_rm_destroy(struct dpu_rm *rm)
 
 static int _dpu_rm_hw_blk_create(
 		struct dpu_rm *rm,
-		struct dpu_mdss_cfg *cat,
+		const struct dpu_mdss_cfg *cat,
 		void __iomem *mmio,
 		enum dpu_hw_blk_type type,
 		uint32_t id,
-		void *hw_catalog_info)
+		const void *hw_catalog_info)
 {
 	struct dpu_rm_hw_blk *blk;
 	void *hw;
@@ -215,7 +215,7 @@ int dpu_rm_init(struct dpu_rm *rm,
 
 	/* Interrogate HW catalog and create tracking items for hw blocks */
 	for (i = 0; i < cat->mixer_count; i++) {
-		struct dpu_lm_cfg *lm = &cat->mixer[i];
+		const struct dpu_lm_cfg *lm = &cat->mixer[i];
 
 		if (lm->pingpong == PINGPONG_MAX) {
 			DPU_DEBUG("skip mixer %d without pingpong\n", lm->id);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
index 991f4c8f8a12..93ab36bd8df3 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -299,7 +299,7 @@ void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
 	entry = debugfs_create_dir("vbif", debugfs_root);
 
 	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
-		struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
+		const struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
 
 		snprintf(vbif_name, sizeof(vbif_name), "%d", vbif->id);
 
@@ -318,7 +318,7 @@ void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
 			(u32 *)&vbif->default_ot_wr_limit);
 
 		for (j = 0; j < vbif->dynamic_ot_rd_tbl.count; j++) {
-			struct dpu_vbif_dynamic_ot_cfg *cfg =
+			const struct dpu_vbif_dynamic_ot_cfg *cfg =
 					&vbif->dynamic_ot_rd_tbl.cfg[j];
 
 			snprintf(vbif_name, sizeof(vbif_name),
@@ -332,7 +332,7 @@ void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
 		}
 
 		for (j = 0; j < vbif->dynamic_ot_wr_tbl.count; j++) {
-			struct dpu_vbif_dynamic_ot_cfg *cfg =
+			const struct dpu_vbif_dynamic_ot_cfg *cfg =
 					&vbif->dynamic_ot_wr_tbl.cfg[j];
 
 			snprintf(vbif_name, sizeof(vbif_name),
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
index 772f0753ed38..aaf2f26f8505 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
@@ -121,7 +121,7 @@ static void mdp4_dsi_encoder_enable(struct drm_encoder *encoder)
 	if (mdp4_dsi_encoder->enabled)
 		return;
 
-	 mdp4_crtc_set_config(encoder->crtc,
+	mdp4_crtc_set_config(encoder->crtc,
 			MDP4_DMA_CONFIG_PACK_ALIGN_MSB |
 			MDP4_DMA_CONFIG_DEFLKR_EN |
 			MDP4_DMA_CONFIG_DITHER_EN |
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
index 9262ed2dc8c3..c7df71e2fafc 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -53,7 +53,7 @@ static int mdp4_lvds_connector_get_modes(struct drm_connector *connector)
 	if (panel) {
 		drm_panel_attach(panel, connector);
 
-		ret = panel->funcs->get_modes(panel);
+		ret = drm_panel_get_modes(panel, connector);
 
 		drm_panel_detach(panel);
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
index 1f48f64539a2..e3c4c250238b 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
@@ -902,7 +902,7 @@ struct mdp5_cfg_handler *mdp5_cfg_init(struct mdp5_kms *mdp5_kms,
 				major, minor);
 		ret = -ENXIO;
 		goto fail;
-	};
+	}
 
 	/* only after mdp5_cfg global pointer's init can we access the hw */
 	for (i = 0; i < num_handlers; i++) {
diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index eff1a4c61258..4de771d6f0be 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -178,6 +178,8 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 int msm_dsi_host_init(struct msm_dsi *msm_dsi);
 int msm_dsi_runtime_suspend(struct device *dev);
 int msm_dsi_runtime_resume(struct device *dev);
+int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host);
+int dsi_link_clk_set_rate_v2(struct msm_dsi_host *msm_host);
 int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host);
 int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host);
 void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 86ad3fdf207d..813d69deb5e8 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -153,6 +153,10 @@ static const char * const dsi_sdm845_bus_clk_names[] = {
 	"iface", "bus",
 };
 
+static const char * const dsi_sc7180_bus_clk_names[] = {
+	"iface", "bus",
+};
+
 static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
@@ -167,7 +171,22 @@ static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.num_dsi = 2,
 };
 
+static const struct msm_dsi_config sc7180_dsi_cfg = {
+	.io_offset = DSI_6G_REG_SHIFT,
+	.reg_cfg = {
+		.num = 1,
+		.regs = {
+			{"vdda", 21800, 4 },	/* 1.2 V */
+		},
+	},
+	.bus_clk_names = dsi_sc7180_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_sc7180_bus_clk_names),
+	.io_start = { 0xae94000 },
+	.num_dsi = 1,
+};
+
 static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
+	.link_clk_set_rate = dsi_link_clk_set_rate_v2,
 	.link_clk_enable = dsi_link_clk_enable_v2,
 	.link_clk_disable = dsi_link_clk_disable_v2,
 	.clk_init_ver = dsi_clk_init_v2,
@@ -179,6 +198,7 @@ static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
 };
 
 static const struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
+	.link_clk_set_rate = dsi_link_clk_set_rate_6g,
 	.link_clk_enable = dsi_link_clk_enable_6g,
 	.link_clk_disable = dsi_link_clk_disable_6g,
 	.clk_init_ver = NULL,
@@ -190,6 +210,7 @@ static const struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
 };
 
 static const struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
+	.link_clk_set_rate = dsi_link_clk_set_rate_6g,
 	.link_clk_enable = dsi_link_clk_enable_6g,
 	.link_clk_disable = dsi_link_clk_disable_6g,
 	.clk_init_ver = dsi_clk_init_6g_v2,
@@ -223,6 +244,9 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
 		&msm8998_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1,
 		&sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_1,
+		&sc7180_dsi_cfg, &msm_dsi_6g_v2_host_ops},
+
 };
 
 const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index 50a37ceb6a25..217e24a65178 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -20,6 +20,7 @@
 #define MSM_DSI_6G_VER_MINOR_V1_4_2	0x10040002
 #define MSM_DSI_6G_VER_MINOR_V2_2_0	0x20000000
 #define MSM_DSI_6G_VER_MINOR_V2_2_1	0x20020001
+#define MSM_DSI_6G_VER_MINOR_V2_4_1	0x20040001
 
 #define MSM_DSI_V2_VER_MINOR_8064	0x0
 
@@ -35,6 +36,7 @@ struct msm_dsi_config {
 };
 
 struct msm_dsi_host_cfg_ops {
+	int (*link_clk_set_rate)(struct msm_dsi_host *msm_host);
 	int (*link_clk_enable)(struct msm_dsi_host *msm_host);
 	void (*link_clk_disable)(struct msm_dsi_host *msm_host);
 	int (*clk_init_ver)(struct msm_dsi_host *msm_host);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 458cec82ae13..11ae5b8444c3 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -505,7 +505,7 @@ int msm_dsi_runtime_resume(struct device *dev)
 	return dsi_bus_clk_enable(msm_host);
 }
 
-int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
+int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -515,13 +515,13 @@ int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 	ret = clk_set_rate(msm_host->byte_clk, msm_host->byte_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate byte clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	if (msm_host->byte_intf_clk) {
@@ -530,10 +530,18 @@ int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 		if (ret) {
 			pr_err("%s: Failed to set rate byte intf clk, %d\n",
 			       __func__, ret);
-			goto error;
+			return ret;
 		}
 	}
 
+	return 0;
+}
+
+
+int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
+{
+	int ret;
+
 	ret = clk_prepare_enable(msm_host->esc_clk);
 	if (ret) {
 		pr_err("%s: Failed to enable dsi esc clk\n", __func__);
@@ -573,7 +581,7 @@ error:
 	return ret;
 }
 
-int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
+int dsi_link_clk_set_rate_v2(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -584,27 +592,34 @@ int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 	ret = clk_set_rate(msm_host->byte_clk, msm_host->byte_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate byte clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	ret = clk_set_rate(msm_host->esc_clk, msm_host->esc_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate esc clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	ret = clk_set_rate(msm_host->src_clk, msm_host->src_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate src clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
+	return 0;
+}
+
+int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
+{
+	int ret;
+
 	ret = clk_prepare_enable(msm_host->byte_clk);
 	if (ret) {
 		pr_err("%s: Failed to enable dsi byte clk\n", __func__);
@@ -818,7 +833,7 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	u32 flags = msm_host->mode_flags;
 	enum mipi_dsi_pixel_format mipi_fmt = msm_host->format;
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-	u32 data = 0;
+	u32 data = 0, lane_ctrl = 0;
 
 	if (!enable) {
 		dsi_write(msm_host, REG_DSI_CTRL, 0);
@@ -906,9 +921,11 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	dsi_write(msm_host, REG_DSI_LANE_SWAP_CTRL,
 		  DSI_LANE_SWAP_CTRL_DLN_SWAP_SEL(msm_host->dlane_swap));
 
-	if (!(flags & MIPI_DSI_CLOCK_NON_CONTINUOUS))
+	if (!(flags & MIPI_DSI_CLOCK_NON_CONTINUOUS)) {
+		lane_ctrl = dsi_read(msm_host, REG_DSI_LANE_CTRL);
 		dsi_write(msm_host, REG_DSI_LANE_CTRL,
-			DSI_LANE_CTRL_CLKLN_HS_FORCE_REQUEST);
+			lane_ctrl | DSI_LANE_CTRL_CLKLN_HS_FORCE_REQUEST);
+	}
 
 	data |= DSI_CTRL_ENABLE;
 
@@ -1996,6 +2013,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 	 * mdp clock need to be enabled to receive dsi interrupt
 	 */
 	pm_runtime_get_sync(&msm_host->pdev->dev);
+	cfg_hnd->ops->link_clk_set_rate(msm_host);
 	cfg_hnd->ops->link_clk_enable(msm_host);
 
 	/* TODO: vote for bus bandwidth */
@@ -2344,7 +2362,9 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 	}
 
 	pm_runtime_get_sync(&msm_host->pdev->dev);
-	ret = cfg_hnd->ops->link_clk_enable(msm_host);
+	ret = cfg_hnd->ops->link_clk_set_rate(msm_host);
+	if (!ret)
+		ret = cfg_hnd->ops->link_clk_enable(msm_host);
 	if (ret) {
 		pr_err("%s: failed to enable link clocks. ret=%d\n",
 		       __func__, ret);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 271aa7bbca92..104115d112eb 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -329,7 +329,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 	 * attached to the drm_panel.
 	 */
 	drm_panel_attach(panel, connector);
-	num = drm_panel_get_modes(panel);
+	num = drm_panel_get_modes(panel, connector);
 	if (!num)
 		return 0;
 
@@ -432,20 +432,8 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 		}
 	}
 
-	if (panel) {
-		ret = drm_panel_enable(panel);
-		if (ret) {
-			pr_err("%s: enable panel %d failed, %d\n", __func__, id,
-									ret);
-			goto panel_en_fail;
-		}
-	}
-
 	return;
 
-panel_en_fail:
-	if (is_dual_dsi && msm_dsi1)
-		msm_dsi_host_disable(msm_dsi1->host);
 host1_en_fail:
 	msm_dsi_host_disable(host);
 host_en_fail:
@@ -464,12 +452,51 @@ phy_en_fail:
 
 static void dsi_mgr_bridge_enable(struct drm_bridge *bridge)
 {
-	DBG("");
+	int id = dsi_mgr_bridge_get_id(bridge);
+	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
+	struct drm_panel *panel = msm_dsi->panel;
+	bool is_dual_dsi = IS_DUAL_DSI();
+	int ret;
+
+	DBG("id=%d", id);
+	if (!msm_dsi_device_connected(msm_dsi))
+		return;
+
+	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+		return;
+
+	if (panel) {
+		ret = drm_panel_enable(panel);
+		if (ret) {
+			pr_err("%s: enable panel %d failed, %d\n", __func__, id,
+									ret);
+		}
+	}
 }
 
 static void dsi_mgr_bridge_disable(struct drm_bridge *bridge)
 {
-	DBG("");
+	int id = dsi_mgr_bridge_get_id(bridge);
+	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
+	struct drm_panel *panel = msm_dsi->panel;
+	bool is_dual_dsi = IS_DUAL_DSI();
+	int ret;
+
+	DBG("id=%d", id);
+	if (!msm_dsi_device_connected(msm_dsi))
+		return;
+
+	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+		return;
+
+	if (panel) {
+		ret = drm_panel_disable(panel);
+		if (ret)
+			pr_err("%s: Panel %d OFF failed, %d\n", __func__, id,
+									ret);
+	}
 }
 
 static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
@@ -495,13 +522,6 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		goto disable_phy;
 
-	if (panel) {
-		ret = drm_panel_disable(panel);
-		if (ret)
-			pr_err("%s: Panel %d OFF failed, %d\n", __func__, id,
-									ret);
-	}
-
 	ret = msm_dsi_host_disable(host);
 	if (ret)
 		pr_err("%s: host %d disable failed, %d\n", __func__, id, ret);
diff --git a/drivers/gpu/drm/msm/edp/edp_bridge.c b/drivers/gpu/drm/msm/edp/edp_bridge.c
index 2950bba4aca9..b65b5cc2dba2 100644
--- a/drivers/gpu/drm/msm/edp/edp_bridge.c
+++ b/drivers/gpu/drm/msm/edp/edp_bridge.c
@@ -55,8 +55,14 @@ static void edp_bridge_mode_set(struct drm_bridge *bridge,
 	DBG("set mode: " DRM_MODE_FMT, DRM_MODE_ARG(mode));
 
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		if ((connector->encoder != NULL) &&
-			(connector->encoder->bridge == bridge)) {
+		struct drm_encoder *encoder = connector->encoder;
+		struct drm_bridge *first_bridge;
+
+		if (!connector->encoder)
+			continue;
+
+		first_bridge = drm_bridge_chain_get_first_bridge(encoder);
+		if (bridge == first_bridge) {
 			msm_edp_ctrl_timing_cfg(edp->ctrl,
 				adjusted_mode, &connector->display_info);
 			break;
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index 839822d894d0..58707a1f3878 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -101,7 +101,7 @@ static int gpio_config(struct hdmi *hdmi, bool on)
 
 				gpiod_set_value_cansleep(gpio.gpiod, value);
 			}
-		};
+		}
 
 		DBG("gpio off");
 	}
@@ -433,8 +433,10 @@ struct drm_connector *msm_hdmi_connector_init(struct hdmi *hdmi)
 
 	connector = &hdmi_connector->base;
 
-	drm_connector_init(hdmi->dev, connector, &hdmi_connector_funcs,
-			DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_init_with_ddc(hdmi->dev, connector,
+				    &hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    hdmi->i2c);
 	drm_connector_helper_add(connector, &msm_hdmi_connector_helper_funcs);
 
 	connector->polled = DRM_CONNECTOR_POLL_CONNECT |
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index ac678ace09a3..c26219c7a49f 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1192,7 +1192,8 @@ static int add_display_components(struct device *dev,
 	 * the interfaces to our components list.
 	 */
 	if (of_device_is_compatible(dev->of_node, "qcom,mdss") ||
-	    of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss")) {
+	    of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss") ||
+	    of_device_is_compatible(dev->of_node, "qcom,sc7180-mdss")) {
 		ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
 		if (ret) {
 			DRM_DEV_ERROR(dev, "failed to populate children devices\n");
@@ -1317,6 +1318,7 @@ static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
 	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
 	{ .compatible = "qcom,sdm845-mdss", .data = (void *)KMS_DPU },
+	{ .compatible = "qcom,sc7180-mdss", .data = (void *)KMS_DPU },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index cff198b2f470..db48867df47d 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -26,7 +26,7 @@ struct msm_fbdev {
 	struct drm_framebuffer *fb;
 };
 
-static struct fb_ops msm_fb_ops = {
+static const struct fb_ops msm_fb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index be5327af16fa..385d4965a8d0 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -54,7 +54,6 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 
 	INIT_LIST_HEAD(&submit->node);
 	INIT_LIST_HEAD(&submit->bo_list);
-	ww_acquire_init(&submit->ticket, &reservation_ww_class);
 
 	return submit;
 }
@@ -158,7 +157,7 @@ static void submit_unlock_unpin_bo(struct msm_gem_submit *submit,
 		msm_gem_unpin_iova(&msm_obj->base, submit->aspace);
 
 	if (submit->bos[i].flags & BO_LOCKED)
-		ww_mutex_unlock(&msm_obj->base.resv->lock);
+		dma_resv_unlock(msm_obj->base.resv);
 
 	if (backoff && !(submit->bos[i].flags & BO_VALID))
 		submit->bos[i].iova = 0;
@@ -181,8 +180,8 @@ retry:
 		contended = i;
 
 		if (!(submit->bos[i].flags & BO_LOCKED)) {
-			ret = ww_mutex_lock_interruptible(&msm_obj->base.resv->lock,
-					&submit->ticket);
+			ret = dma_resv_lock_interruptible(msm_obj->base.resv,
+							  &submit->ticket);
 			if (ret)
 				goto fail;
 			submit->bos[i].flags |= BO_LOCKED;
@@ -203,8 +202,8 @@ fail:
 	if (ret == -EDEADLK) {
 		struct msm_gem_object *msm_obj = submit->bos[contended].obj;
 		/* we lost out in a seqno race, lock and retry.. */
-		ret = ww_mutex_lock_slow_interruptible(&msm_obj->base.resv->lock,
-				&submit->ticket);
+		ret = dma_resv_lock_slow_interruptible(msm_obj->base.resv,
+						       &submit->ticket);
 		if (!ret) {
 			submit->bos[contended].flags |= BO_LOCKED;
 			slow_locked = contended;
@@ -390,8 +389,6 @@ static void submit_cleanup(struct msm_gem_submit *submit)
 		list_del_init(&msm_obj->submit_entry);
 		drm_gem_object_put(&msm_obj->base);
 	}
-
-	ww_acquire_fini(&submit->ticket);
 }
 
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
@@ -408,6 +405,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_ringbuffer *ring;
 	int out_fence_fd = -1;
 	struct pid *pid = get_pid(task_pid(current));
+	bool has_ww_ticket = false;
 	unsigned i;
 	int ret, submitid;
 	if (!gpu)
@@ -489,6 +487,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (ret)
 		goto out;
 
+	/* copy_*_user while holding a ww ticket upsets lockdep */
+	ww_acquire_init(&submit->ticket, &reservation_ww_class);
+	has_ww_ticket = true;
 	ret = submit_lock_objects(submit);
 	if (ret)
 		goto out;
@@ -588,6 +589,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 out:
 	submit_cleanup(submit);
+	if (has_ww_ticket)
+		ww_acquire_fini(&submit->ticket);
 	if (ret)
 		msm_gem_submit_free(submit);
 out_unlock:
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index ab8f0f9c9dc8..be5bc2e8425c 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -111,8 +111,15 @@ struct msm_gpu {
 	struct clk *ebi1_clk, *core_clk, *rbbmtimer_clk;
 	uint32_t fast_rate;
 
+	/* The gfx-mem interconnect path that's used by all GPU types. */
 	struct icc_path *icc_path;
 
+	/*
+	 * Second interconnect path for some A3xx and all A4xx GPUs to the
+	 * On Chip MEMory (OCMEM).
+	 */
+	struct icc_path *ocmem_icc_path;
+
 	/* Hang and Inactivity Detection:
 	 */
 #define DRM_MSM_INACTIVE_PERIOD   66 /* in ms (roughly four frames) */
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_out.c b/drivers/gpu/drm/mxsfb/mxsfb_out.c
index 4eb94744c526..9eca1605d11d 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_out.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_out.c
@@ -31,7 +31,7 @@ static int mxsfb_panel_get_modes(struct drm_connector *connector)
 			drm_connector_to_mxsfb_drm_private(connector);
 
 	if (mxsfb->panel)
-		return drm_panel_get_modes(mxsfb->panel);
+		return drm_panel_get_modes(mxsfb->panel, connector);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 3558df043592..d6e4ae1ef705 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -2,7 +2,8 @@
 config DRM_NOUVEAU
 	tristate "Nouveau (NVIDIA) cards"
 	depends on DRM && PCI && MMU
-        select FW_LOADER
+	select IOMMU_API
+	select FW_LOADER
 	select DRM_KMS_HELPER
 	select DRM_TTM
 	select BACKLIGHT_CLASS_DEVICE if DRM_NOUVEAU_BACKLIGHT
@@ -16,6 +17,7 @@ config DRM_NOUVEAU
 	select INPUT if ACPI && X86
 	select THERMAL if ACPI && X86
 	select ACPI_VIDEO if ACPI && X86
+	select SND_HDA_COMPONENT if SND_HDA_CORE
 	help
 	  Choose this option for open-source NVIDIA support.
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/arb.c b/drivers/gpu/drm/nouveau/dispnv04/arb.c
index 362495535e69..9d4a2d97507e 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/arb.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/arb.c
@@ -53,8 +53,8 @@ struct nv_sim_state {
 static void
 nv04_calc_arb(struct nv_fifo_info *fifo, struct nv_sim_state *arb)
 {
-	int pagemiss, cas, width, bpp;
-	int nvclks, mclks, pclks, crtpagemiss;
+	int pagemiss, cas, bpp;
+	int nvclks, mclks, crtpagemiss;
 	int found, mclk_extra, mclk_loop, cbs, m1, p1;
 	int mclk_freq, pclk_freq, nvclk_freq;
 	int us_m, us_n, us_p, crtc_drain_rate;
@@ -65,11 +65,9 @@ nv04_calc_arb(struct nv_fifo_info *fifo, struct nv_sim_state *arb)
 	nvclk_freq = arb->nvclk_khz;
 	pagemiss = arb->mem_page_miss;
 	cas = arb->mem_latency;
-	width = arb->memory_width >> 6;
 	bpp = arb->bpp;
 	cbs = 128;
 
-	pclks = 2;
 	nvclks = 10;
 	mclks = 13 + cas;
 	mclk_extra = 3;
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index 03466f04c741..3a9489ed6544 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -644,16 +644,13 @@ static int nv17_tv_create_resources(struct drm_encoder *encoder,
 	int i;
 
 	if (nouveau_tv_norm) {
-		for (i = 0; i < num_tv_norms; i++) {
-			if (!strcmp(nv17_tv_norm_names[i], nouveau_tv_norm)) {
-				tv_enc->tv_norm = i;
-				break;
-			}
-		}
-
-		if (i == num_tv_norms)
+		i = match_string(nv17_tv_norm_names, num_tv_norms,
+				 nouveau_tv_norm);
+		if (i < 0)
 			NV_WARN(drm, "Invalid TV norm setting \"%s\"\n",
 				nouveau_tv_norm);
+		else
+			tv_enc->tv_norm = i;
 	}
 
 	drm_mode_create_tv_properties(dev, num_tv_norms, nv17_tv_norm_names);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base907c.c b/drivers/gpu/drm/nouveau/dispnv50/base907c.c
index 5f2de77e0f32..224a34c340fe 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/base907c.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/base907c.c
@@ -75,12 +75,16 @@ base907c_xlut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	}
 }
 
-static void
-base907c_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+static bool
+base907c_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
 {
-	asyw->xlut.i.mode = 7;
+	if (size != 256 && size != 1024)
+		return false;
+
+	asyw->xlut.i.mode = size == 1024 ? 4 : 7;
 	asyw->xlut.i.enable = 2;
 	asyw->xlut.i.load = head907d_olut_load;
+	return true;
 }
 
 static inline u32
@@ -160,6 +164,7 @@ base907c = {
 	.csc_set = base907c_csc_set,
 	.csc_clr = base907c_csc_clr,
 	.olut_core = true,
+	.ilut_size = 1024,
 	.xlut_set = base907c_xlut_set,
 	.xlut_clr = base907c_xlut_clr,
 	.image_set = base907c_image_set,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 63425e246018..2f123082c85d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -29,6 +29,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/hdmi.h>
+#include <linux/component.h>
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_dp_helper.h>
@@ -476,12 +477,113 @@ nv50_dac_create(struct drm_connector *connector, struct dcb_output *dcbe)
 	return 0;
 }
 
+/*
+ * audio component binding for ELD notification
+ */
+static void
+nv50_audio_component_eld_notify(struct drm_audio_component *acomp, int port)
+{
+	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify)
+		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr,
+						 port, -1);
+}
+
+static int
+nv50_audio_component_get_eld(struct device *kdev, int port, int pipe,
+			     bool *enabled, unsigned char *buf, int max_bytes)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(kdev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct drm_encoder *encoder;
+	struct nouveau_encoder *nv_encoder;
+	struct nouveau_connector *nv_connector;
+	struct nouveau_crtc *nv_crtc;
+	int ret = 0;
+
+	*enabled = false;
+	drm_for_each_encoder(encoder, drm->dev) {
+		nv_encoder = nouveau_encoder(encoder);
+		nv_connector = nouveau_encoder_connector_get(nv_encoder);
+		nv_crtc = nouveau_crtc(encoder->crtc);
+		if (!nv_connector || !nv_crtc || nv_crtc->index != port)
+			continue;
+		*enabled = drm_detect_monitor_audio(nv_connector->edid);
+		if (*enabled) {
+			ret = drm_eld_size(nv_connector->base.eld);
+			memcpy(buf, nv_connector->base.eld,
+			       min(max_bytes, ret));
+		}
+		break;
+	}
+	return ret;
+}
+
+static const struct drm_audio_component_ops nv50_audio_component_ops = {
+	.get_eld = nv50_audio_component_get_eld,
+};
+
+static int
+nv50_audio_component_bind(struct device *kdev, struct device *hda_kdev,
+			  void *data)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(kdev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct drm_audio_component *acomp = data;
+
+	if (WARN_ON(!device_link_add(hda_kdev, kdev, DL_FLAG_STATELESS)))
+		return -ENOMEM;
+
+	drm_modeset_lock_all(drm_dev);
+	acomp->ops = &nv50_audio_component_ops;
+	acomp->dev = kdev;
+	drm->audio.component = acomp;
+	drm_modeset_unlock_all(drm_dev);
+	return 0;
+}
+
+static void
+nv50_audio_component_unbind(struct device *kdev, struct device *hda_kdev,
+			    void *data)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(kdev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct drm_audio_component *acomp = data;
+
+	drm_modeset_lock_all(drm_dev);
+	drm->audio.component = NULL;
+	acomp->ops = NULL;
+	acomp->dev = NULL;
+	drm_modeset_unlock_all(drm_dev);
+}
+
+static const struct component_ops nv50_audio_component_bind_ops = {
+	.bind   = nv50_audio_component_bind,
+	.unbind = nv50_audio_component_unbind,
+};
+
+static void
+nv50_audio_component_init(struct nouveau_drm *drm)
+{
+	if (!component_add(drm->dev->dev, &nv50_audio_component_bind_ops))
+		drm->audio.component_registered = true;
+}
+
+static void
+nv50_audio_component_fini(struct nouveau_drm *drm)
+{
+	if (drm->audio.component_registered) {
+		component_del(drm->dev->dev, &nv50_audio_component_bind_ops);
+		drm->audio.component_registered = false;
+	}
+}
+
 /******************************************************************************
  * Audio
  *****************************************************************************/
 static void
 nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 {
+	struct nouveau_drm *drm = nouveau_drm(encoder->dev);
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nv50_disp *disp = nv50_disp(encoder->dev);
 	struct {
@@ -496,11 +598,14 @@ nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 	};
 
 	nvif_mthd(&disp->disp->object, 0, &args, sizeof(args));
+
+	nv50_audio_component_eld_notify(drm->audio.component, nv_crtc->index);
 }
 
 static void
 nv50_audio_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
 {
+	struct nouveau_drm *drm = nouveau_drm(encoder->dev);
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
 	struct nouveau_connector *nv_connector;
@@ -527,6 +632,8 @@ nv50_audio_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
 
 	nvif_mthd(&disp->disp->object, 0, &args,
 		  sizeof(args.base) + drm_eld_size(args.data));
+
+	nv50_audio_component_eld_notify(drm->audio.component, nv_crtc->index);
 }
 
 /******************************************************************************
@@ -660,7 +767,6 @@ struct nv50_mstm {
 	struct nouveau_encoder *outp;
 
 	struct drm_dp_mst_topology_mgr mgr;
-	struct nv50_msto *msto[4];
 
 	bool modified;
 	bool disabled;
@@ -726,7 +832,6 @@ nv50_msto_cleanup(struct nv50_msto *msto)
 	drm_dp_mst_deallocate_vcpi(&mstm->mgr, mstc->port);
 
 	msto->mstc = NULL;
-	msto->head = NULL;
 	msto->disabled = false;
 }
 
@@ -806,11 +911,11 @@ nv50_msto_atomic_check(struct drm_encoder *encoder,
 		 * topology
 		 */
 		asyh->or.bpc = min(connector->display_info.bpc, 8U);
-		asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3);
+		asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3, false);
 	}
 
 	slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port,
-					      asyh->dp.pbn);
+					      asyh->dp.pbn, 0);
 	if (slots < 0)
 		return slots;
 
@@ -872,7 +977,6 @@ nv50_msto_enable(struct drm_encoder *encoder)
 	mstm->outp->update(mstm->outp, head->base.index, armh, proto,
 			   nv50_dp_bpc_to_depth(armh->or.bpc));
 
-	msto->head = head;
 	msto->mstc = mstc;
 	mstm->modified = true;
 }
@@ -913,45 +1017,40 @@ nv50_msto = {
 	.destroy = nv50_msto_destroy,
 };
 
-static int
-nv50_msto_new(struct drm_device *dev, u32 heads, const char *name, int id,
-	      struct nv50_msto **pmsto)
+static struct nv50_msto *
+nv50_msto_new(struct drm_device *dev, struct nv50_head *head, int id)
 {
 	struct nv50_msto *msto;
 	int ret;
 
-	if (!(msto = *pmsto = kzalloc(sizeof(*msto), GFP_KERNEL)))
-		return -ENOMEM;
+	msto = kzalloc(sizeof(*msto), GFP_KERNEL);
+	if (!msto)
+		return ERR_PTR(-ENOMEM);
 
 	ret = drm_encoder_init(dev, &msto->encoder, &nv50_msto,
-			       DRM_MODE_ENCODER_DPMST, "%s-mst-%d", name, id);
+			       DRM_MODE_ENCODER_DPMST, "mst-%d", id);
 	if (ret) {
-		kfree(*pmsto);
-		*pmsto = NULL;
-		return ret;
+		kfree(msto);
+		return ERR_PTR(ret);
 	}
 
 	drm_encoder_helper_add(&msto->encoder, &nv50_msto_help);
-	msto->encoder.possible_crtcs = heads;
-	return 0;
+	msto->encoder.possible_crtcs = drm_crtc_mask(&head->base.base);
+	msto->head = head;
+	return msto;
 }
 
 static struct drm_encoder *
 nv50_mstc_atomic_best_encoder(struct drm_connector *connector,
 			      struct drm_connector_state *connector_state)
 {
-	struct nv50_head *head = nv50_head(connector_state->crtc);
 	struct nv50_mstc *mstc = nv50_mstc(connector);
+	struct drm_crtc *crtc = connector_state->crtc;
 
-	return &mstc->mstm->msto[head->base.index]->encoder;
-}
-
-static struct drm_encoder *
-nv50_mstc_best_encoder(struct drm_connector *connector)
-{
-	struct nv50_mstc *mstc = nv50_mstc(connector);
+	if (!(mstc->mstm->outp->dcb->heads & drm_crtc_mask(crtc)))
+		return NULL;
 
-	return &mstc->mstm->msto[0]->encoder;
+	return &nv50_head(crtc)->msto->encoder;
 }
 
 static enum drm_mode_status
@@ -1038,7 +1137,6 @@ static const struct drm_connector_helper_funcs
 nv50_mstc_help = {
 	.get_modes = nv50_mstc_get_modes,
 	.mode_valid = nv50_mstc_mode_valid,
-	.best_encoder = nv50_mstc_best_encoder,
 	.atomic_best_encoder = nv50_mstc_atomic_best_encoder,
 	.atomic_check = nv50_mstc_atomic_check,
 	.detect_ctx = nv50_mstc_detect,
@@ -1071,8 +1169,9 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
 	      const char *path, struct nv50_mstc **pmstc)
 {
 	struct drm_device *dev = mstm->outp->base.base.dev;
+	struct drm_crtc *crtc;
 	struct nv50_mstc *mstc;
-	int ret, i;
+	int ret;
 
 	if (!(mstc = *pmstc = kzalloc(sizeof(*mstc), GFP_KERNEL)))
 		return -ENOMEM;
@@ -1092,8 +1191,13 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
 	mstc->connector.funcs->reset(&mstc->connector);
 	nouveau_conn_attach_properties(&mstc->connector);
 
-	for (i = 0; i < ARRAY_SIZE(mstm->msto) && mstm->msto[i]; i++)
-		drm_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
+	drm_for_each_crtc(crtc, dev) {
+		if (!(mstm->outp->dcb->heads & drm_crtc_mask(crtc)))
+			continue;
+
+		drm_connector_attach_encoder(&mstc->connector,
+					     &nv50_head(crtc)->msto->encoder);
+	}
 
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0);
@@ -1367,7 +1471,7 @@ nv50_mstm_new(struct nouveau_encoder *outp, struct drm_dp_aux *aux, int aux_max,
 	const int max_payloads = hweight8(outp->dcb->heads);
 	struct drm_device *dev = outp->base.base.dev;
 	struct nv50_mstm *mstm;
-	int ret, i;
+	int ret;
 	u8 dpcd;
 
 	/* This is a workaround for some monitors not functioning
@@ -1390,13 +1494,6 @@ nv50_mstm_new(struct nouveau_encoder *outp, struct drm_dp_aux *aux, int aux_max,
 	if (ret)
 		return ret;
 
-	for (i = 0; i < max_payloads; i++) {
-		ret = nv50_msto_new(dev, outp->dcb->heads, outp->base.base.name,
-				    i, &mstm->msto[i]);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
@@ -1569,17 +1666,24 @@ nv50_sor_func = {
 	.destroy = nv50_sor_destroy,
 };
 
+static bool nv50_has_mst(struct nouveau_drm *drm)
+{
+	struct nvkm_bios *bios = nvxx_bios(&drm->client.device);
+	u32 data;
+	u8 ver, hdr, cnt, len;
+
+	data = nvbios_dp_table(bios, &ver, &hdr, &cnt, &len);
+	return data && ver >= 0x40 && (nvbios_rd08(bios, data + 0x08) & 0x04);
+}
+
 static int
 nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 {
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_drm *drm = nouveau_drm(connector->dev);
-	struct nvkm_bios *bios = nvxx_bios(&drm->client.device);
 	struct nvkm_i2c *i2c = nvxx_i2c(&drm->client.device);
 	struct nouveau_encoder *nv_encoder;
 	struct drm_encoder *encoder;
-	u8 ver, hdr, cnt, len;
-	u32 data;
 	int type, ret;
 
 	switch (dcbe->type) {
@@ -1624,10 +1728,9 @@ nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 		}
 
 		if (nv_connector->type != DCB_CONNECTOR_eDP &&
-		    (data = nvbios_dp_table(bios, &ver, &hdr, &cnt, &len)) &&
-		    ver >= 0x40 && (nvbios_rd08(bios, data + 0x08) & 0x04)) {
-			ret = nv50_mstm_new(nv_encoder, &nv_connector->aux, 16,
-					    nv_connector->base.base.id,
+		    nv50_has_mst(drm)) {
+			ret = nv50_mstm_new(nv_encoder, &nv_connector->aux,
+					    16, nv_connector->base.base.id,
 					    &nv_encoder->dp.mstm);
 			if (ret)
 				return ret;
@@ -1673,7 +1776,6 @@ nv50_pior_enable(struct drm_encoder *encoder)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
-	struct nouveau_connector *nv_connector;
 	struct nv50_head_atom *asyh = nv50_head_atom(nv_crtc->base.state);
 	struct nv50_core *core = nv50_disp(encoder->dev)->core;
 	u8 owner = 1 << nv_crtc->index;
@@ -1681,7 +1783,6 @@ nv50_pior_enable(struct drm_encoder *encoder)
 
 	nv50_outp_acquire(nv_encoder);
 
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
 	switch (asyh->or.bpc) {
 	case 10: asyh->or.depth = 0x6; break;
 	case  8: asyh->or.depth = 0x5; break;
@@ -2302,6 +2403,8 @@ nv50_display_destroy(struct drm_device *dev)
 {
 	struct nv50_disp *disp = nv50_disp(dev);
 
+	nv50_audio_component_fini(nouveau_drm(dev));
+
 	nv50_core_del(&disp->core);
 
 	nouveau_bo_unmap(disp->sync);
@@ -2323,6 +2426,7 @@ nv50_display_create(struct drm_device *dev)
 	struct nv50_disp *disp;
 	struct dcb_output *dcbe;
 	int crtcs, ret, i;
+	bool has_mst = nv50_has_mst(drm);
 
 	disp = kzalloc(sizeof(*disp), GFP_KERNEL);
 	if (!disp)
@@ -2371,11 +2475,37 @@ nv50_display_create(struct drm_device *dev)
 		crtcs = 0x3;
 
 	for (i = 0; i < fls(crtcs); i++) {
+		struct nv50_head *head;
+
 		if (!(crtcs & (1 << i)))
 			continue;
-		ret = nv50_head_create(dev, i);
-		if (ret)
+
+		head = nv50_head_create(dev, i);
+		if (IS_ERR(head)) {
+			ret = PTR_ERR(head);
 			goto out;
+		}
+
+		if (has_mst) {
+			head->msto = nv50_msto_new(dev, head, i);
+			if (IS_ERR(head->msto)) {
+				ret = PTR_ERR(head->msto);
+				head->msto = NULL;
+				goto out;
+			}
+
+			/*
+			 * FIXME: This is a hack to workaround the following
+			 * issues:
+			 *
+			 * https://gitlab.gnome.org/GNOME/mutter/issues/759
+			 * https://gitlab.freedesktop.org/xorg/xserver/merge_requests/277
+			 *
+			 * Once these issues are closed, this should be
+			 * removed
+			 */
+			head->msto->encoder.possible_crtcs = crtcs;
+		}
 	}
 
 	/* create encoder/connector objects based on VBIOS DCB table */
@@ -2423,6 +2553,8 @@ nv50_display_create(struct drm_device *dev)
 	/* Disable vblank irqs aggressively for power-saving, safe on nv50+ */
 	dev->vblank_disable_immediate = true;
 
+	nv50_audio_component_init(drm);
+
 out:
 	if (ret)
 		nv50_display_destroy(dev);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 7c41b0599d1a..d54fe00ac3a3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -4,6 +4,8 @@
 
 #include "nouveau_display.h"
 
+struct nv50_msto;
+
 struct nv50_disp {
 	struct nvif_disp *disp;
 	struct nv50_core *core;
@@ -78,14 +80,14 @@ void evo_kick(u32 *, struct nv50_dmac *);
 
 #define evo_mthd(p, m, s) do {						\
 	const u32 _m = (m), _s = (s);					\
-	if (drm_debug & DRM_UT_KMS)					\
+	if (drm_debug_enabled(DRM_UT_KMS))				\
 		pr_err("%04x %d %s\n", _m, _s, __func__);		\
 	*((p)++) = ((_s << 18) | _m);					\
 } while(0)
 
 #define evo_data(p, d) do {						\
 	const u32 _d = (d);						\
-	if (drm_debug & DRM_UT_KMS)					\
+	if (drm_debug_enabled(DRM_UT_KMS))				\
 		pr_err("\t%08x\n", _d);					\
 	*((p)++) = _d;							\
 } while(0)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c
index c9692df2b76c..d9d64602947d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.c
@@ -213,6 +213,7 @@ nv50_head_atomic_check_lut(struct nv50_head *head,
 {
 	struct nv50_disp *disp = nv50_disp(head->base.base.dev);
 	struct drm_property_blob *olut = asyh->state.gamma_lut;
+	int size;
 
 	/* Determine whether core output LUT should be enabled. */
 	if (olut) {
@@ -229,14 +230,23 @@ nv50_head_atomic_check_lut(struct nv50_head *head,
 		}
 	}
 
-	if (!olut && !head->func->olut_identity) {
-		asyh->olut.handle = 0;
-		return 0;
+	if (!olut) {
+		if (!head->func->olut_identity) {
+			asyh->olut.handle = 0;
+			return 0;
+		}
+		size = 0;
+	} else {
+		size = drm_color_lut_size(olut);
 	}
 
+	if (!head->func->olut(head, asyh, size)) {
+		DRM_DEBUG_KMS("Invalid olut\n");
+		return -EINVAL;
+	}
 	asyh->olut.handle = disp->core->chan.vram.handle;
 	asyh->olut.buffer = !asyh->olut.buffer;
-	head->func->olut(head, asyh);
+
 	return 0;
 }
 
@@ -473,7 +483,7 @@ nv50_head_func = {
 	.atomic_destroy_state = nv50_head_atomic_destroy_state,
 };
 
-int
+struct nv50_head *
 nv50_head_create(struct drm_device *dev, int index)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
@@ -485,7 +495,7 @@ nv50_head_create(struct drm_device *dev, int index)
 
 	head = kzalloc(sizeof(*head), GFP_KERNEL);
 	if (!head)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	head->func = disp->core->func->head;
 	head->base.index = index;
@@ -503,27 +513,26 @@ nv50_head_create(struct drm_device *dev, int index)
 		ret = nv50_curs_new(drm, head->base.index, &curs);
 	if (ret) {
 		kfree(head);
-		return ret;
+		return ERR_PTR(ret);
 	}
 
 	crtc = &head->base.base;
 	drm_crtc_init_with_planes(dev, crtc, &base->plane, &curs->plane,
 				  &nv50_head_func, "head-%d", head->base.index);
 	drm_crtc_helper_add(crtc, &nv50_head_help);
+	/* Keep the legacy gamma size at 256 to avoid compatibility issues */
 	drm_mode_crtc_set_gamma_size(crtc, 256);
-	if (disp->disp->object.oclass >= GF110_DISP)
-		drm_crtc_enable_color_mgmt(crtc, 256, true, 256);
-	else
-		drm_crtc_enable_color_mgmt(crtc, 0, false, 256);
+	drm_crtc_enable_color_mgmt(crtc, base->func->ilut_size,
+				   disp->disp->object.oclass >= GF110_DISP,
+				   head->func->olut_size);
 
 	if (head->func->olut_set) {
 		ret = nv50_lut_init(disp, &drm->client.mmu, &head->olut);
-		if (ret)
-			goto out;
+		if (ret) {
+			nv50_head_destroy(crtc);
+			return ERR_PTR(ret);
+		}
 	}
 
-out:
-	if (ret)
-		nv50_head_destroy(crtc);
-	return ret;
+	return head;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.h b/drivers/gpu/drm/nouveau/dispnv50/head.h
index d1c002f534d4..c32b27cdaefc 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.h
@@ -11,17 +11,19 @@ struct nv50_head {
 	const struct nv50_head_func *func;
 	struct nouveau_crtc base;
 	struct nv50_lut olut;
+	struct nv50_msto *msto;
 };
 
-int nv50_head_create(struct drm_device *, int index);
+struct nv50_head *nv50_head_create(struct drm_device *, int index);
 void nv50_head_flush_set(struct nv50_head *, struct nv50_head_atom *);
 void nv50_head_flush_clr(struct nv50_head *, struct nv50_head_atom *, bool y);
 
 struct nv50_head_func {
 	void (*view)(struct nv50_head *, struct nv50_head_atom *);
 	void (*mode)(struct nv50_head *, struct nv50_head_atom *);
-	void (*olut)(struct nv50_head *, struct nv50_head_atom *);
+	bool (*olut)(struct nv50_head *, struct nv50_head_atom *, int);
 	bool olut_identity;
+	int  olut_size;
 	void (*olut_set)(struct nv50_head *, struct nv50_head_atom *);
 	void (*olut_clr)(struct nv50_head *);
 	void (*core_calc)(struct nv50_head *, struct nv50_head_atom *);
@@ -43,7 +45,7 @@ struct nv50_head_func {
 extern const struct nv50_head_func head507d;
 void head507d_view(struct nv50_head *, struct nv50_head_atom *);
 void head507d_mode(struct nv50_head *, struct nv50_head_atom *);
-void head507d_olut(struct nv50_head *, struct nv50_head_atom *);
+bool head507d_olut(struct nv50_head *, struct nv50_head_atom *, int);
 void head507d_core_calc(struct nv50_head *, struct nv50_head_atom *);
 void head507d_core_clr(struct nv50_head *);
 int head507d_curs_layout(struct nv50_head *, struct nv50_wndw_atom *,
@@ -60,7 +62,7 @@ extern const struct nv50_head_func head827d;
 extern const struct nv50_head_func head907d;
 void head907d_view(struct nv50_head *, struct nv50_head_atom *);
 void head907d_mode(struct nv50_head *, struct nv50_head_atom *);
-void head907d_olut(struct nv50_head *, struct nv50_head_atom *);
+bool head907d_olut(struct nv50_head *, struct nv50_head_atom *, int);
 void head907d_olut_set(struct nv50_head *, struct nv50_head_atom *);
 void head907d_olut_clr(struct nv50_head *);
 void head907d_core_set(struct nv50_head *, struct nv50_head_atom *);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head507d.c b/drivers/gpu/drm/nouveau/dispnv50/head507d.c
index 7561be5ca707..66ccf36b56a2 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head507d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head507d.c
@@ -271,15 +271,19 @@ head507d_olut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-void
-head507d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+bool
+head507d_olut(struct nv50_head *head, struct nv50_head_atom *asyh, int size)
 {
+	if (size != 256)
+		return false;
+
 	if (asyh->base.cpp == 1)
 		asyh->olut.mode = 0;
 	else
 		asyh->olut.mode = 1;
 
 	asyh->olut.load = head507d_olut_load;
+	return true;
 }
 
 void
@@ -328,6 +332,7 @@ head507d = {
 	.view = head507d_view,
 	.mode = head507d_mode,
 	.olut = head507d_olut,
+	.olut_size = 256,
 	.olut_set = head507d_olut_set,
 	.olut_clr = head507d_olut_clr,
 	.core_calc = head507d_core_calc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head827d.c b/drivers/gpu/drm/nouveau/dispnv50/head827d.c
index af5e7bd5978b..11877119eea4 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head827d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head827d.c
@@ -108,6 +108,7 @@ head827d = {
 	.view = head507d_view,
 	.mode = head507d_mode,
 	.olut = head507d_olut,
+	.olut_size = 256,
 	.olut_set = head827d_olut_set,
 	.olut_clr = head827d_olut_clr,
 	.core_calc = head507d_core_calc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head907d.c b/drivers/gpu/drm/nouveau/dispnv50/head907d.c
index c2d09dd97b1f..3002ec23d7a6 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head907d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head907d.c
@@ -230,11 +230,15 @@ head907d_olut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-void
-head907d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+bool
+head907d_olut(struct nv50_head *head, struct nv50_head_atom *asyh, int size)
 {
-	asyh->olut.mode = 7;
+	if (size != 256 && size != 1024)
+		return false;
+
+	asyh->olut.mode = size == 1024 ? 4 : 7;
 	asyh->olut.load = head907d_olut_load;
+	return true;
 }
 
 void
@@ -285,6 +289,7 @@ head907d = {
 	.view = head907d_view,
 	.mode = head907d_mode,
 	.olut = head907d_olut,
+	.olut_size = 1024,
 	.olut_set = head907d_olut_set,
 	.olut_clr = head907d_olut_clr,
 	.core_calc = head507d_core_calc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head917d.c b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
index 303df8459ca8..76958cedd51f 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head917d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
@@ -83,6 +83,7 @@ head917d = {
 	.view = head907d_view,
 	.mode = head907d_mode,
 	.olut = head907d_olut,
+	.olut_size = 1024,
 	.olut_set = head907d_olut_set,
 	.olut_clr = head907d_olut_clr,
 	.core_calc = head507d_core_calc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/headc37d.c b/drivers/gpu/drm/nouveau/dispnv50/headc37d.c
index ef6a99d95a9c..00011ce109a6 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/headc37d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/headc37d.c
@@ -148,14 +148,18 @@ headc37d_olut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 	}
 }
 
-static void
-headc37d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+static bool
+headc37d_olut(struct nv50_head *head, struct nv50_head_atom *asyh, int size)
 {
+	if (size != 256 && size != 1024)
+		return false;
+
 	asyh->olut.mode = 2;
-	asyh->olut.size = 0;
+	asyh->olut.size = size == 1024 ? 2 : 0;
 	asyh->olut.range = 0;
 	asyh->olut.output_mode = 1;
 	asyh->olut.load = head907d_olut_load;
+	return true;
 }
 
 static void
@@ -201,6 +205,7 @@ headc37d = {
 	.view = headc37d_view,
 	.mode = headc37d_mode,
 	.olut = headc37d_olut,
+	.olut_size = 1024,
 	.olut_set = headc37d_olut_set,
 	.olut_clr = headc37d_olut_clr,
 	.curs_layout = head917d_curs_layout,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/headc57d.c b/drivers/gpu/drm/nouveau/dispnv50/headc57d.c
index 32a7f9e85fb0..938d910a1b1e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/headc57d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/headc57d.c
@@ -151,17 +151,20 @@ headc57d_olut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-void
-headc57d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+bool
+headc57d_olut(struct nv50_head *head, struct nv50_head_atom *asyh, int size)
 {
+	if (size != 0 && size != 256 && size != 1024)
+		return false;
+
 	asyh->olut.mode = 2; /* DIRECT10 */
 	asyh->olut.size = 4 /* VSS header. */ + 1024 + 1 /* Entries. */;
 	asyh->olut.output_mode = 1; /* INTERPOLATE_ENABLE. */
-	if (asyh->state.gamma_lut &&
-	    asyh->state.gamma_lut->length / sizeof(struct drm_color_lut) == 256)
+	if (size == 256)
 		asyh->olut.load = headc57d_olut_load_8;
 	else
 		asyh->olut.load = headc57d_olut_load;
+	return true;
 }
 
 static void
@@ -194,6 +197,7 @@ headc57d = {
 	.mode = headc57d_mode,
 	.olut = headc57d_olut,
 	.olut_identity = true,
+	.olut_size = 1024,
 	.olut_set = headc57d_olut_set,
 	.olut_clr = headc57d_olut_clr,
 	.curs_layout = head917d_curs_layout,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/lut.c b/drivers/gpu/drm/nouveau/dispnv50/lut.c
index 994def4fd51a..4e95ca5604ab 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/lut.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/lut.c
@@ -49,7 +49,7 @@ nv50_lut_load(struct nv50_lut *lut, int buffer, struct drm_property_blob *blob,
 			kvfree(in);
 		}
 	} else {
-		load(in, blob->length / sizeof(*in), mem);
+		load(in, drm_color_lut_size(blob), mem);
 	}
 
 	return addr;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 5193b6257061..890315291b01 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -318,7 +318,7 @@ nv50_wndw_atomic_check_acquire(struct nv50_wndw *wndw, bool modeset,
 	return wndw->func->acquire(wndw, asyw, asyh);
 }
 
-static void
+static int
 nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 			   struct nv50_wndw_atom *armw,
 			   struct nv50_wndw_atom *asyw,
@@ -340,7 +340,7 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 		 */
 		if (!(ilut = asyh->state.gamma_lut)) {
 			asyw->visible = false;
-			return;
+			return 0;
 		}
 
 		if (wndw->func->ilut)
@@ -359,7 +359,10 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 	/* Recalculate LUT state. */
 	memset(&asyw->xlut, 0x00, sizeof(asyw->xlut));
 	if ((asyw->ilut = wndw->func->ilut ? ilut : NULL)) {
-		wndw->func->ilut(wndw, asyw);
+		if (!wndw->func->ilut(wndw, asyw, drm_color_lut_size(ilut))) {
+			DRM_DEBUG_KMS("Invalid ilut\n");
+			return -EINVAL;
+		}
 		asyw->xlut.handle = wndw->wndw.vram.handle;
 		asyw->xlut.i.buffer = !asyw->xlut.i.buffer;
 		asyw->set.xlut = true;
@@ -384,6 +387,7 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 
 	/* Can't do an immediate flip while changing the LUT. */
 	asyh->state.async_flip = false;
+	return 0;
 }
 
 static int
@@ -424,8 +428,11 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state)
 	    (!armw->visible ||
 	     asyh->state.color_mgmt_changed ||
 	     asyw->state.fb->format->format !=
-	     armw->state.fb->format->format))
-		nv50_wndw_atomic_check_lut(wndw, armw, asyw, asyh);
+	     armw->state.fb->format->format)) {
+		ret = nv50_wndw_atomic_check_lut(wndw, armw, asyw, asyh);
+		if (ret)
+			return ret;
+	}
 
 	/* Calculate new window state. */
 	if (asyw->visible) {
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
index c63bd3bdaf06..caf397475918 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
@@ -64,12 +64,13 @@ struct nv50_wndw_func {
 	void (*ntfy_clr)(struct nv50_wndw *);
 	int (*ntfy_wait_begun)(struct nouveau_bo *, u32 offset,
 			       struct nvif_device *);
-	void (*ilut)(struct nv50_wndw *, struct nv50_wndw_atom *);
+	bool (*ilut)(struct nv50_wndw *, struct nv50_wndw_atom *, int);
 	void (*csc)(struct nv50_wndw *, struct nv50_wndw_atom *,
 		    const struct drm_color_ctm *);
 	void (*csc_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
 	void (*csc_clr)(struct nv50_wndw *);
 	bool ilut_identity;
+	int  ilut_size;
 	bool olut_core;
 	void (*xlut_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
 	void (*xlut_clr)(struct nv50_wndw *);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c
index 0f9402162bde..b92dc3461bbd 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c
@@ -71,14 +71,18 @@ wndwc37e_ilut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	}
 }
 
-static void
-wndwc37e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+static bool
+wndwc37e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
 {
+	if (size != 256 && size != 1024)
+		return false;
+
 	asyw->xlut.i.mode = 2;
-	asyw->xlut.i.size = 0;
+	asyw->xlut.i.size = size == 1024 ? 2 : 0;
 	asyw->xlut.i.range = 0;
 	asyw->xlut.i.output_mode = 1;
 	asyw->xlut.i.load = head907d_olut_load;
+	return true;
 }
 
 void
@@ -261,6 +265,7 @@ wndwc37e = {
 	.ntfy_reset = corec37d_ntfy_init,
 	.ntfy_wait_begun = base507c_ntfy_wait_begun,
 	.ilut = wndwc37e_ilut,
+	.ilut_size = 1024,
 	.xlut_set = wndwc37e_ilut_set,
 	.xlut_clr = wndwc37e_ilut_clr,
 	.csc = base907c_csc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
index a311c79e5295..35c9c52fab26 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
@@ -156,19 +156,21 @@ wndwc57e_ilut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-static void
-wndwc57e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+static bool
+wndwc57e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
 {
-	u16 size = asyw->ilut->length / sizeof(struct drm_color_lut);
+	if (size = size ? size : 1024, size != 256 && size != 1024)
+		return false;
+
 	if (size == 256) {
 		asyw->xlut.i.mode = 1; /* DIRECT8. */
 	} else {
 		asyw->xlut.i.mode = 2; /* DIRECT10. */
-		size = 1024;
 	}
 	asyw->xlut.i.size = 4 /* VSS header. */ + size + 1 /* Entries. */;
 	asyw->xlut.i.output_mode = 0; /* INTERPOLATE_DISABLE. */
 	asyw->xlut.i.load = wndwc57e_ilut_load;
+	return true;
 }
 
 static const struct nv50_wndw_func
@@ -183,6 +185,7 @@ wndwc57e = {
 	.ntfy_wait_begun = base507c_ntfy_wait_begun,
 	.ilut = wndwc57e_ilut,
 	.ilut_identity = true,
+	.ilut_size = 1024,
 	.xlut_set = wndwc57e_ilut_set,
 	.xlut_clr = wndwc57e_ilut_clr,
 	.csc = base907c_csc,
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/acr.h b/drivers/gpu/drm/nouveau/include/nvfw/acr.h
new file mode 100644
index 000000000000..e65d6a8db104
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/acr.h
@@ -0,0 +1,152 @@
+#ifndef __NVFW_ACR_H__
+#define __NVFW_ACR_H__
+
+struct wpr_header {
+#define WPR_HEADER_V0_FALCON_ID_INVALID                              0xffffffff
+	u32 falcon_id;
+	u32 lsb_offset;
+	u32 bootstrap_owner;
+	u32 lazy_bootstrap;
+#define WPR_HEADER_V0_STATUS_NONE                                             0
+#define WPR_HEADER_V0_STATUS_COPY                                             1
+#define WPR_HEADER_V0_STATUS_VALIDATION_CODE_FAILED                           2
+#define WPR_HEADER_V0_STATUS_VALIDATION_DATA_FAILED                           3
+#define WPR_HEADER_V0_STATUS_VALIDATION_DONE                                  4
+#define WPR_HEADER_V0_STATUS_VALIDATION_SKIPPED                               5
+#define WPR_HEADER_V0_STATUS_BOOTSTRAP_READY                                  6
+	u32 status;
+};
+
+void wpr_header_dump(struct nvkm_subdev *, const struct wpr_header *);
+
+struct wpr_header_v1 {
+#define WPR_HEADER_V1_FALCON_ID_INVALID                              0xffffffff
+	u32 falcon_id;
+	u32 lsb_offset;
+	u32 bootstrap_owner;
+	u32 lazy_bootstrap;
+	u32 bin_version;
+#define WPR_HEADER_V1_STATUS_NONE                                             0
+#define WPR_HEADER_V1_STATUS_COPY                                             1
+#define WPR_HEADER_V1_STATUS_VALIDATION_CODE_FAILED                           2
+#define WPR_HEADER_V1_STATUS_VALIDATION_DATA_FAILED                           3
+#define WPR_HEADER_V1_STATUS_VALIDATION_DONE                                  4
+#define WPR_HEADER_V1_STATUS_VALIDATION_SKIPPED                               5
+#define WPR_HEADER_V1_STATUS_BOOTSTRAP_READY                                  6
+#define WPR_HEADER_V1_STATUS_REVOCATION_CHECK_FAILED                          7
+	u32 status;
+};
+
+void wpr_header_v1_dump(struct nvkm_subdev *, const struct wpr_header_v1 *);
+
+struct lsf_signature {
+	u8 prd_keys[2][16];
+	u8 dbg_keys[2][16];
+	u32 b_prd_present;
+	u32 b_dbg_present;
+	u32 falcon_id;
+};
+
+struct lsf_signature_v1 {
+	u8 prd_keys[2][16];
+	u8 dbg_keys[2][16];
+	u32 b_prd_present;
+	u32 b_dbg_present;
+	u32 falcon_id;
+	u32 supports_versioning;
+	u32 version;
+	u32 depmap_count;
+	u8 depmap[11/*LSF_LSB_DEPMAP_SIZE*/ * 2 * 4];
+	u8 kdf[16];
+};
+
+struct lsb_header_tail {
+	u32 ucode_off;
+	u32 ucode_size;
+	u32 data_size;
+	u32 bl_code_size;
+	u32 bl_imem_off;
+	u32 bl_data_off;
+	u32 bl_data_size;
+	u32 app_code_off;
+	u32 app_code_size;
+	u32 app_data_off;
+	u32 app_data_size;
+	u32 flags;
+};
+
+struct lsb_header {
+	struct lsf_signature signature;
+	struct lsb_header_tail tail;
+};
+
+void lsb_header_dump(struct nvkm_subdev *, struct lsb_header *);
+
+struct lsb_header_v1 {
+	struct lsf_signature_v1 signature;
+	struct lsb_header_tail tail;
+};
+
+void lsb_header_v1_dump(struct nvkm_subdev *, struct lsb_header_v1 *);
+
+struct flcn_acr_desc {
+	union {
+		u8 reserved_dmem[0x200];
+		u32 signatures[4];
+	} ucode_reserved_space;
+	u32 wpr_region_id;
+	u32 wpr_offset;
+	u32 mmu_mem_range;
+	struct {
+		u32 no_regions;
+		struct {
+			u32 start_addr;
+			u32 end_addr;
+			u32 region_id;
+			u32 read_mask;
+			u32 write_mask;
+			u32 client_mask;
+		} region_props[2];
+	} regions;
+	u32 ucode_blob_size;
+	u64 ucode_blob_base __aligned(8);
+	struct {
+		u32 vpr_enabled;
+		u32 vpr_start;
+		u32 vpr_end;
+		u32 hdcp_policies;
+	} vpr_desc;
+};
+
+void flcn_acr_desc_dump(struct nvkm_subdev *, struct flcn_acr_desc *);
+
+struct flcn_acr_desc_v1 {
+	u8 reserved_dmem[0x200];
+	u32 signatures[4];
+	u32 wpr_region_id;
+	u32 wpr_offset;
+	u32 mmu_memory_range;
+	struct {
+		u32 no_regions;
+		struct {
+			u32 start_addr;
+			u32 end_addr;
+			u32 region_id;
+			u32 read_mask;
+			u32 write_mask;
+			u32 client_mask;
+			u32 shadow_mem_start_addr;
+		} region_props[2];
+	} regions;
+	u32 ucode_blob_size;
+	u64 ucode_blob_base __aligned(8);
+	struct {
+		u32 vpr_enabled;
+		u32 vpr_start;
+		u32 vpr_end;
+		u32 hdcp_policies;
+	} vpr_desc;
+};
+
+void flcn_acr_desc_v1_dump(struct nvkm_subdev *, struct flcn_acr_desc_v1 *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/flcn.h b/drivers/gpu/drm/nouveau/include/nvfw/flcn.h
new file mode 100644
index 000000000000..e090f347d220
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/flcn.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVFW_FLCN_H__
+#define __NVFW_FLCN_H__
+#include <core/os.h>
+struct nvkm_subdev;
+
+struct loader_config {
+	u32 dma_idx;
+	u32 code_dma_base;
+	u32 code_size_total;
+	u32 code_size_to_load;
+	u32 code_entry_point;
+	u32 data_dma_base;
+	u32 data_size;
+	u32 overlay_dma_base;
+	u32 argc;
+	u32 argv;
+	u32 code_dma_base1;
+	u32 data_dma_base1;
+	u32 overlay_dma_base1;
+};
+
+void
+loader_config_dump(struct nvkm_subdev *, const struct loader_config *);
+
+struct loader_config_v1 {
+	u32 reserved;
+	u32 dma_idx;
+	u64 code_dma_base;
+	u32 code_size_total;
+	u32 code_size_to_load;
+	u32 code_entry_point;
+	u64 data_dma_base;
+	u32 data_size;
+	u64 overlay_dma_base;
+	u32 argc;
+	u32 argv;
+} __packed;
+
+void
+loader_config_v1_dump(struct nvkm_subdev *, const struct loader_config_v1 *);
+
+struct flcn_bl_dmem_desc {
+	u32 reserved[4];
+	u32 signature[4];
+	u32 ctx_dma;
+	u32 code_dma_base;
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 sec_code_off;
+	u32 sec_code_size;
+	u32 code_entry_point;
+	u32 data_dma_base;
+	u32 data_size;
+	u32 code_dma_base1;
+	u32 data_dma_base1;
+};
+
+void
+flcn_bl_dmem_desc_dump(struct nvkm_subdev *, const struct flcn_bl_dmem_desc *);
+
+struct flcn_bl_dmem_desc_v1 {
+	u32 reserved[4];
+	u32 signature[4];
+	u32 ctx_dma;
+	u64 code_dma_base;
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 sec_code_off;
+	u32 sec_code_size;
+	u32 code_entry_point;
+	u64 data_dma_base;
+	u32 data_size;
+} __packed;
+
+void flcn_bl_dmem_desc_v1_dump(struct nvkm_subdev *,
+			       const struct flcn_bl_dmem_desc_v1 *);
+
+struct flcn_bl_dmem_desc_v2 {
+	u32 reserved[4];
+	u32 signature[4];
+	u32 ctx_dma;
+	u64 code_dma_base;
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 sec_code_off;
+	u32 sec_code_size;
+	u32 code_entry_point;
+	u64 data_dma_base;
+	u32 data_size;
+	u32 argc;
+	u32 argv;
+} __packed;
+
+void flcn_bl_dmem_desc_v2_dump(struct nvkm_subdev *,
+			       const struct flcn_bl_dmem_desc_v2 *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/fw.h b/drivers/gpu/drm/nouveau/include/nvfw/fw.h
new file mode 100644
index 000000000000..a7cf1188c9d6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/fw.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVFW_FW_H__
+#define __NVFW_FW_H__
+#include <core/os.h>
+struct nvkm_subdev;
+
+struct nvfw_bin_hdr {
+	u32 bin_magic;
+	u32 bin_ver;
+	u32 bin_size;
+	u32 header_offset;
+	u32 data_offset;
+	u32 data_size;
+};
+
+const struct nvfw_bin_hdr *nvfw_bin_hdr(struct nvkm_subdev *, const void *);
+
+struct nvfw_bl_desc {
+	u32 start_tag;
+	u32 dmem_load_off;
+	u32 code_off;
+	u32 code_size;
+	u32 data_off;
+	u32 data_size;
+};
+
+const struct nvfw_bl_desc *nvfw_bl_desc(struct nvkm_subdev *, const void *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/hs.h b/drivers/gpu/drm/nouveau/include/nvfw/hs.h
new file mode 100644
index 000000000000..64d0d32200c2
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/hs.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVFW_HS_H__
+#define __NVFW_HS_H__
+#include <core/os.h>
+struct nvkm_subdev;
+
+struct nvfw_hs_header {
+	u32 sig_dbg_offset;
+	u32 sig_dbg_size;
+	u32 sig_prod_offset;
+	u32 sig_prod_size;
+	u32 patch_loc;
+	u32 patch_sig;
+	u32 hdr_offset;
+	u32 hdr_size;
+};
+
+const struct nvfw_hs_header *nvfw_hs_header(struct nvkm_subdev *, const void *);
+
+struct nvfw_hs_load_header {
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 data_dma_base;
+	u32 data_size;
+	u32 num_apps;
+	u32 apps[0];
+};
+
+const struct nvfw_hs_load_header *
+nvfw_hs_load_header(struct nvkm_subdev *, const void *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/ls.h b/drivers/gpu/drm/nouveau/include/nvfw/ls.h
new file mode 100644
index 000000000000..f63692a2a16c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/ls.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVFW_LS_H__
+#define __NVFW_LS_H__
+#include <core/os.h>
+struct nvkm_subdev;
+
+struct nvfw_ls_desc_head {
+	u32 descriptor_size;
+	u32 image_size;
+	u32 tools_version;
+	u32 app_version;
+	char date[64];
+	u32 bootloader_start_offset;
+	u32 bootloader_size;
+	u32 bootloader_imem_offset;
+	u32 bootloader_entry_point;
+	u32 app_start_offset;
+	u32 app_size;
+	u32 app_imem_offset;
+	u32 app_imem_entry;
+	u32 app_dmem_offset;
+	u32 app_resident_code_offset;
+	u32 app_resident_code_size;
+	u32 app_resident_data_offset;
+	u32 app_resident_data_size;
+};
+
+struct nvfw_ls_desc {
+	struct nvfw_ls_desc_head head;
+	u32 nb_overlays;
+	struct {
+		u32 start;
+		u32 size;
+	} load_ovl[64];
+	u32 compressed;
+};
+
+const struct nvfw_ls_desc *nvfw_ls_desc(struct nvkm_subdev *, const void *);
+
+struct nvfw_ls_desc_v1 {
+	struct nvfw_ls_desc_head head;
+	u32 nb_imem_overlays;
+	u32 nb_dmem_overlays;
+	struct {
+		u32 start;
+		u32 size;
+	} load_ovl[64];
+	u32 compressed;
+};
+
+const struct nvfw_ls_desc_v1 *
+nvfw_ls_desc_v1(struct nvkm_subdev *, const void *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/pmu.h b/drivers/gpu/drm/nouveau/include/nvfw/pmu.h
new file mode 100644
index 000000000000..452ed7d03827
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/pmu.h
@@ -0,0 +1,98 @@
+#ifndef __NVFW_PMU_H__
+#define __NVFW_PMU_H__
+
+struct nv_pmu_args {
+	u32 reserved;
+	u32 freq_hz;
+	u32 trace_size;
+	u32 trace_dma_base;
+	u16 trace_dma_base1;
+	u8 trace_dma_offset;
+	u32 trace_dma_idx;
+	bool secure_mode;
+	bool raise_priv_sec;
+	struct {
+		u32 dma_base;
+		u16 dma_base1;
+		u8 dma_offset;
+		u16 fb_size;
+		u8 dma_idx;
+	} gc6_ctx;
+	u8 pad;
+};
+
+#define NV_PMU_UNIT_INIT                                                   0x07
+#define NV_PMU_UNIT_ACR                                                    0x0a
+
+struct nv_pmu_init_msg {
+	struct nv_falcon_msg hdr;
+#define NV_PMU_INIT_MSG_INIT                                               0x00
+	u8 msg_type;
+
+	u8 pad;
+	u16 os_debug_entry_point;
+
+	struct {
+		u16 size;
+		u16 offset;
+		u8 index;
+		u8 pad;
+	} queue_info[5];
+
+	u16 sw_managed_area_offset;
+	u16 sw_managed_area_size;
+};
+
+struct nv_pmu_acr_cmd {
+	struct nv_falcon_cmd hdr;
+#define NV_PMU_ACR_CMD_INIT_WPR_REGION                                     0x00
+#define NV_PMU_ACR_CMD_BOOTSTRAP_FALCON                                    0x01
+#define NV_PMU_ACR_CMD_BOOTSTRAP_MULTIPLE_FALCONS                          0x03
+	u8 cmd_type;
+};
+
+struct nv_pmu_acr_msg {
+	struct nv_falcon_cmd hdr;
+	u8 msg_type;
+};
+
+struct nv_pmu_acr_init_wpr_region_cmd {
+	struct nv_pmu_acr_cmd cmd;
+	u32 region_id;
+	u32 wpr_offset;
+};
+
+struct nv_pmu_acr_init_wpr_region_msg {
+	struct nv_pmu_acr_msg msg;
+	u32 error_code;
+};
+
+struct nv_pmu_acr_bootstrap_falcon_cmd {
+	struct nv_pmu_acr_cmd cmd;
+#define NV_PMU_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_YES                  0x00000000
+#define NV_PMU_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_NO                   0x00000001
+	u32 flags;
+	u32 falcon_id;
+};
+
+struct nv_pmu_acr_bootstrap_falcon_msg {
+	struct nv_pmu_acr_msg msg;
+	u32 falcon_id;
+};
+
+struct nv_pmu_acr_bootstrap_multiple_falcons_cmd {
+	struct nv_pmu_acr_cmd cmd;
+#define NV_PMU_ACR_BOOTSTRAP_MULTIPLE_FALCONS_FLAGS_RESET_YES        0x00000000
+#define NV_PMU_ACR_BOOTSTRAP_MULTIPLE_FALCONS_FLAGS_RESET_NO         0x00000001
+	u32 flags;
+	u32 falcon_mask;
+	u32 use_va_mask;
+	u32 wpr_lo;
+	u32 wpr_hi;
+};
+
+struct nv_pmu_acr_bootstrap_multiple_falcons_msg {
+	struct nv_pmu_acr_msg msg;
+	u32 falcon_mask;
+};
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/sec2.h b/drivers/gpu/drm/nouveau/include/nvfw/sec2.h
new file mode 100644
index 000000000000..03496558b775
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/sec2.h
@@ -0,0 +1,60 @@
+#ifndef __NVFW_SEC2_H__
+#define __NVFW_SEC2_H__
+
+struct nv_sec2_args {
+	u32 freq_hz;
+	u32 falc_trace_size;
+	u32 falc_trace_dma_base;
+	u32 falc_trace_dma_idx;
+	bool secure_mode;
+};
+
+#define NV_SEC2_UNIT_INIT                                                  0x01
+#define NV_SEC2_UNIT_ACR                                                   0x08
+
+struct nv_sec2_init_msg {
+	struct nv_falcon_msg hdr;
+#define NV_SEC2_INIT_MSG_INIT                                              0x00
+	u8 msg_type;
+
+	u8 num_queues;
+	u16 os_debug_entry_point;
+
+	struct {
+		u32 offset;
+		u16 size;
+		u8 index;
+#define NV_SEC2_INIT_MSG_QUEUE_ID_CMDQ                                     0x00
+#define NV_SEC2_INIT_MSG_QUEUE_ID_MSGQ                                     0x01
+		u8 id;
+	} queue_info[2];
+
+	u32 sw_managed_area_offset;
+	u16 sw_managed_area_size;
+};
+
+struct nv_sec2_acr_cmd {
+	struct nv_falcon_cmd hdr;
+#define NV_SEC2_ACR_CMD_BOOTSTRAP_FALCON                                   0x00
+	u8 cmd_type;
+};
+
+struct nv_sec2_acr_msg {
+	struct nv_falcon_cmd hdr;
+	u8 msg_type;
+};
+
+struct nv_sec2_acr_bootstrap_falcon_cmd {
+	struct nv_sec2_acr_cmd cmd;
+#define NV_SEC2_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_YES                 0x00000000
+#define NV_SEC2_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_NO                  0x00000001
+	u32 flags;
+	u32 falcon_id;
+};
+
+struct nv_sec2_acr_bootstrap_falcon_msg {
+	struct nv_sec2_acr_msg msg;
+	u32 error_code;
+	u32 falcon_id;
+};
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index f704ae600e94..30659747ffe8 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -166,6 +166,8 @@
 
 #define VOLTA_A                                       /* cl9097.h */ 0x0000c397
 
+#define TURING_A                                      /* cl9097.h */ 0x0000c597
+
 #define NV74_BSP                                                     0x000074b0
 
 #define GT212_MSVLD                                                  0x000085b1
@@ -207,6 +209,7 @@
 #define PASCAL_COMPUTE_A                                             0x0000c0c0
 #define PASCAL_COMPUTE_B                                             0x0000c1c0
 #define VOLTA_COMPUTE_A                                              0x0000c3c0
+#define TURING_COMPUTE_A                                             0x0000c5c0
 
 #define NV74_CIPHER                                                  0x000074c1
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/if0008.h b/drivers/gpu/drm/nouveau/include/nvif/if0008.h
index 8450127420f5..c21d09f04f1d 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/if0008.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/if0008.h
@@ -35,7 +35,7 @@ struct nvif_mmu_type_v0 {
 
 struct nvif_mmu_kind_v0 {
 	__u8  version;
-	__u8  pad01[1];
+	__u8  kind_inv;
 	__u16 count;
 	__u8  data[];
 };
diff --git a/drivers/gpu/drm/nouveau/include/nvif/mmu.h b/drivers/gpu/drm/nouveau/include/nvif/mmu.h
index 747ecf67e403..cec1e88a0a05 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/mmu.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/mmu.h
@@ -7,6 +7,7 @@ struct nvif_mmu {
 	u8  dmabits;
 	u8  heap_nr;
 	u8  type_nr;
+	u8  kind_inv;
 	u16 kind_nr;
 	s32 mem;
 
@@ -36,9 +37,8 @@ void nvif_mmu_fini(struct nvif_mmu *);
 static inline bool
 nvif_mmu_kind_valid(struct nvif_mmu *mmu, u8 kind)
 {
-	const u8 invalid = mmu->kind_nr - 1;
 	if (kind) {
-		if (kind >= mmu->kind_nr || mmu->kind[kind] == invalid)
+		if (kind >= mmu->kind_nr || mmu->kind[kind] == mmu->kind_inv)
 			return false;
 	}
 	return true;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 6d55cd0476aa..5c007ce62fc3 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -23,13 +23,13 @@ enum nvkm_devidx {
 	NVKM_SUBDEV_MMU,
 	NVKM_SUBDEV_BAR,
 	NVKM_SUBDEV_FAULT,
+	NVKM_SUBDEV_ACR,
 	NVKM_SUBDEV_PMU,
 	NVKM_SUBDEV_VOLT,
 	NVKM_SUBDEV_ICCSENSE,
 	NVKM_SUBDEV_THERM,
 	NVKM_SUBDEV_CLK,
 	NVKM_SUBDEV_GSP,
-	NVKM_SUBDEV_SECBOOT,
 
 	NVKM_ENGINE_BSP,
 
@@ -129,6 +129,7 @@ struct nvkm_device {
 		struct notifier_block nb;
 	} acpi;
 
+	struct nvkm_acr *acr;
 	struct nvkm_bar *bar;
 	struct nvkm_bios *bios;
 	struct nvkm_bus *bus;
@@ -149,7 +150,6 @@ struct nvkm_device {
 	struct nvkm_subdev *mxm;
 	struct nvkm_pci *pci;
 	struct nvkm_pmu *pmu;
-	struct nvkm_secboot *secboot;
 	struct nvkm_therm *therm;
 	struct nvkm_timer *timer;
 	struct nvkm_top *top;
@@ -169,7 +169,7 @@ struct nvkm_device {
 	struct nvkm_engine *mspdec;
 	struct nvkm_engine *msppp;
 	struct nvkm_engine *msvld;
-	struct nvkm_engine *nvenc[3];
+	struct nvkm_nvenc *nvenc[3];
 	struct nvkm_nvdec *nvdec[3];
 	struct nvkm_pm *pm;
 	struct nvkm_engine *sec;
@@ -202,6 +202,7 @@ struct nvkm_device_quirk {
 struct nvkm_device_chip {
 	const char *name;
 
+	int (*acr     )(struct nvkm_device *, int idx, struct nvkm_acr **);
 	int (*bar     )(struct nvkm_device *, int idx, struct nvkm_bar **);
 	int (*bios    )(struct nvkm_device *, int idx, struct nvkm_bios **);
 	int (*bus     )(struct nvkm_device *, int idx, struct nvkm_bus **);
@@ -222,7 +223,6 @@ struct nvkm_device_chip {
 	int (*mxm     )(struct nvkm_device *, int idx, struct nvkm_subdev **);
 	int (*pci     )(struct nvkm_device *, int idx, struct nvkm_pci **);
 	int (*pmu     )(struct nvkm_device *, int idx, struct nvkm_pmu **);
-	int (*secboot )(struct nvkm_device *, int idx, struct nvkm_secboot **);
 	int (*therm   )(struct nvkm_device *, int idx, struct nvkm_therm **);
 	int (*timer   )(struct nvkm_device *, int idx, struct nvkm_timer **);
 	int (*top     )(struct nvkm_device *, int idx, struct nvkm_top **);
@@ -242,7 +242,7 @@ struct nvkm_device_chip {
 	int (*mspdec  )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*msppp   )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*msvld   )(struct nvkm_device *, int idx, struct nvkm_engine **);
-	int (*nvenc[3])(struct nvkm_device *, int idx, struct nvkm_engine **);
+	int (*nvenc[3])(struct nvkm_device *, int idx, struct nvkm_nvenc **);
 	int (*nvdec[3])(struct nvkm_device *, int idx, struct nvkm_nvdec **);
 	int (*pm      )(struct nvkm_device *, int idx, struct nvkm_pm **);
 	int (*sec     )(struct nvkm_device *, int idx, struct nvkm_engine **);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/falcon.h b/drivers/gpu/drm/nouveau/include/nvkm/core/falcon.h
new file mode 100644
index 000000000000..daa8e4bfb6bf
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/falcon.h
@@ -0,0 +1,77 @@
+#ifndef __NVKM_FALCON_H__
+#define __NVKM_FALCON_H__
+#include <engine/falcon.h>
+
+int nvkm_falcon_ctor(const struct nvkm_falcon_func *, struct nvkm_subdev *owner,
+		     const char *name, u32 addr, struct nvkm_falcon *);
+void nvkm_falcon_dtor(struct nvkm_falcon *);
+
+void nvkm_falcon_v1_load_imem(struct nvkm_falcon *,
+			      void *, u32, u32, u16, u8, bool);
+void nvkm_falcon_v1_load_dmem(struct nvkm_falcon *, void *, u32, u32, u8);
+void nvkm_falcon_v1_read_dmem(struct nvkm_falcon *, u32, u32, u8, void *);
+void nvkm_falcon_v1_bind_context(struct nvkm_falcon *, struct nvkm_memory *);
+int nvkm_falcon_v1_wait_for_halt(struct nvkm_falcon *, u32);
+int nvkm_falcon_v1_clear_interrupt(struct nvkm_falcon *, u32);
+void nvkm_falcon_v1_set_start_addr(struct nvkm_falcon *, u32 start_addr);
+void nvkm_falcon_v1_start(struct nvkm_falcon *);
+int nvkm_falcon_v1_enable(struct nvkm_falcon *);
+void nvkm_falcon_v1_disable(struct nvkm_falcon *);
+
+void gp102_sec2_flcn_bind_context(struct nvkm_falcon *, struct nvkm_memory *);
+int gp102_sec2_flcn_enable(struct nvkm_falcon *);
+
+#define FLCN_PRINTK(t,f,fmt,a...) do {                                         \
+	if (nvkm_subdev_name[(f)->owner->index] != (f)->name)                  \
+		nvkm_##t((f)->owner, "%s: "fmt"\n", (f)->name, ##a);           \
+	else                                                                   \
+		nvkm_##t((f)->owner, fmt"\n", ##a);                            \
+} while(0)
+#define FLCN_DBG(f,fmt,a...) FLCN_PRINTK(debug, (f), fmt, ##a)
+#define FLCN_ERR(f,fmt,a...) FLCN_PRINTK(error, (f), fmt, ##a)
+
+/**
+ * struct nv_falcon_msg - header for all messages
+ *
+ * @unit_id:	id of firmware process that sent the message
+ * @size:	total size of message
+ * @ctrl_flags:	control flags
+ * @seq_id:	used to match a message from its corresponding command
+ */
+struct nv_falcon_msg {
+	u8 unit_id;
+	u8 size;
+	u8 ctrl_flags;
+	u8 seq_id;
+};
+
+#define nv_falcon_cmd nv_falcon_msg
+#define NV_FALCON_CMD_UNIT_ID_REWIND                                       0x00
+
+struct nvkm_falcon_qmgr;
+int nvkm_falcon_qmgr_new(struct nvkm_falcon *, struct nvkm_falcon_qmgr **);
+void nvkm_falcon_qmgr_del(struct nvkm_falcon_qmgr **);
+
+typedef int
+(*nvkm_falcon_qmgr_callback)(void *priv, struct nv_falcon_msg *);
+
+struct nvkm_falcon_cmdq;
+int nvkm_falcon_cmdq_new(struct nvkm_falcon_qmgr *, const char *name,
+			 struct nvkm_falcon_cmdq **);
+void nvkm_falcon_cmdq_del(struct nvkm_falcon_cmdq **);
+void nvkm_falcon_cmdq_init(struct nvkm_falcon_cmdq *,
+			   u32 index, u32 offset, u32 size);
+void nvkm_falcon_cmdq_fini(struct nvkm_falcon_cmdq *);
+int nvkm_falcon_cmdq_send(struct nvkm_falcon_cmdq *, struct nv_falcon_cmd *,
+			  nvkm_falcon_qmgr_callback, void *priv,
+			  unsigned long timeout_jiffies);
+
+struct nvkm_falcon_msgq;
+int nvkm_falcon_msgq_new(struct nvkm_falcon_qmgr *, const char *name,
+			 struct nvkm_falcon_msgq **);
+void nvkm_falcon_msgq_del(struct nvkm_falcon_msgq **);
+void nvkm_falcon_msgq_init(struct nvkm_falcon_msgq *,
+			   u32 index, u32 offset, u32 size);
+int nvkm_falcon_msgq_recv_initmsg(struct nvkm_falcon_msgq *, void *, u32 size);
+void nvkm_falcon_msgq_recv(struct nvkm_falcon_msgq *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/firmware.h b/drivers/gpu/drm/nouveau/include/nvkm/core/firmware.h
index 383370c32428..d14b7fb07368 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/firmware.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/firmware.h
@@ -1,12 +1,55 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_FIRMWARE_H__
 #define __NVKM_FIRMWARE_H__
+#include <core/option.h>
 #include <core/subdev.h>
 
-int nvkm_firmware_get_version(const struct nvkm_subdev *, const char *fwname,
-			      int min_version, int max_version,
-			      const struct firmware **);
-int nvkm_firmware_get(const struct nvkm_subdev *, const char *fwname,
+int nvkm_firmware_get(const struct nvkm_subdev *, const char *fwname, int ver,
 		      const struct firmware **);
 void nvkm_firmware_put(const struct firmware *);
+
+int nvkm_firmware_load_blob(const struct nvkm_subdev *subdev, const char *path,
+			    const char *name, int ver, struct nvkm_blob *);
+int nvkm_firmware_load_name(const struct nvkm_subdev *subdev, const char *path,
+			    const char *name, int ver,
+			    const struct firmware **);
+
+#define nvkm_firmware_load(s,l,o,p...) ({                                      \
+	struct nvkm_subdev *_s = (s);                                          \
+	const char *_opts = (o);                                               \
+	char _option[32];                                                      \
+	typeof(l[0]) *_list = (l), *_next, *_fwif = NULL;                      \
+	int _ver, _fwv, _ret = 0;                                              \
+                                                                               \
+	snprintf(_option, sizeof(_option), "Nv%sFw", _opts);                   \
+	_ver = nvkm_longopt(_s->device->cfgopt, _option, -2);                  \
+	if (_ver >= -1) {                                                      \
+		for (_next = _list; !_fwif && _next->load; _next++) {          \
+			if (_next->version == _ver)                            \
+				_fwif = _next;                                 \
+		}                                                              \
+		_ret = _fwif ? 0 : -EINVAL;                                    \
+	}                                                                      \
+                                                                               \
+	if (_ret == 0) {                                                       \
+		snprintf(_option, sizeof(_option), "Nv%sFwVer", _opts);        \
+		_fwv = _fwif ? _fwif->version : -1;                            \
+		_ver = nvkm_longopt(_s->device->cfgopt, _option, _fwv);        \
+		for (_next = _fwif ? _fwif : _list; _next->load; _next++) {    \
+			_fwv = (_ver >= 0) ? _ver : _next->version;            \
+			_ret = _next->load(p, _fwv, _next);                    \
+			if (_ret == 0 || _ver >= 0) {                          \
+				_fwif = _next;                                 \
+				break;                                         \
+			}                                                      \
+		}                                                              \
+	}                                                                      \
+                                                                               \
+	if (_ret) {                                                            \
+		nvkm_error(_s, "failed to load firmware\n");                   \
+		_fwif = ERR_PTR(_ret);                                         \
+	}                                                                      \
+	                                                                       \
+	_fwif;                                                                 \
+})
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/memory.h b/drivers/gpu/drm/nouveau/include/nvkm/core/memory.h
index b23bf6109f2d..74d3f1a809d7 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/memory.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/memory.h
@@ -84,6 +84,22 @@ void nvkm_memory_tags_put(struct nvkm_memory *, struct nvkm_device *,
 	nvkm_wo32((o), __a + 4, upper_32_bits(__d));                           \
 } while(0)
 
+#define nvkm_robj(o,a,p,s) do {                                                \
+	u32 _addr = (a), _size = (s) >> 2, *_data = (void *)(p);               \
+	while (_size--) {                                                      \
+		*(_data++) = nvkm_ro32((o), _addr);                            \
+		_addr += 4;                                                    \
+	}                                                                      \
+} while(0)
+
+#define nvkm_wobj(o,a,p,s) do {                                                \
+	u32 _addr = (a), _size = (s) >> 2, *_data = (void *)(p);               \
+	while (_size--) {                                                      \
+		nvkm_wo32((o), _addr, *(_data++));                             \
+		_addr += 4;                                                    \
+	}                                                                      \
+} while(0)
+
 #define nvkm_fill(t,s,o,a,d,c) do {                                            \
 	u64 _a = (a), _c = (c), _d = (d), _o = _a >> s, _s = _c << s;          \
 	u##t __iomem *_m = nvkm_kmap(o);                                       \
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/os.h b/drivers/gpu/drm/nouveau/include/nvkm/core/os.h
index 029a416197db..d7ba3205207f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/os.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/os.h
@@ -21,4 +21,17 @@
 	iowrite32_native(lower_32_bits(_v), &_p[0]);			       \
 	iowrite32_native(upper_32_bits(_v), &_p[1]);			       \
 } while(0)
+
+struct nvkm_blob {
+	void *data;
+	u32 size;
+};
+
+static inline void
+nvkm_blob_dtor(struct nvkm_blob *blob)
+{
+	kfree(blob->data);
+	blob->data = NULL;
+	blob->size = 0;
+}
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h
index 23b582d696c6..27c1f868552c 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: MIT */
-#ifndef __NVKM_FALCON_H__
-#define __NVKM_FALCON_H__
+#ifndef __NVKM_FLCNEN_H__
+#define __NVKM_FLCNEN_H__
 #define nvkm_falcon(p) container_of((p), struct nvkm_falcon, engine)
 #include <core/engine.h>
 struct nvkm_fifo_chan;
@@ -23,12 +23,13 @@ struct nvkm_falcon {
 
 	struct mutex mutex;
 	struct mutex dmem_mutex;
+	bool oneinit;
+
 	const struct nvkm_subdev *user;
 
 	u8 version;
 	u8 secret;
 	bool debug;
-	bool has_emem;
 
 	struct nvkm_memory *core;
 	bool external;
@@ -76,9 +77,14 @@ struct nvkm_falcon_func {
 	} data;
 	void (*init)(struct nvkm_falcon *);
 	void (*intr)(struct nvkm_falcon *, struct nvkm_fifo_chan *);
+
+	u32 debug;
+	u32 fbif;
+
 	void (*load_imem)(struct nvkm_falcon *, void *, u32, u32, u16, u8, bool);
 	void (*load_dmem)(struct nvkm_falcon *, void *, u32, u32, u8);
 	void (*read_dmem)(struct nvkm_falcon *, u32, u32, u8, void *);
+	u32 emem_addr;
 	void (*bind_context)(struct nvkm_falcon *, struct nvkm_memory *);
 	int (*wait_for_halt)(struct nvkm_falcon *, u32);
 	int (*clear_interrupt)(struct nvkm_falcon *, u32);
@@ -86,6 +92,13 @@ struct nvkm_falcon_func {
 	void (*start)(struct nvkm_falcon *);
 	int (*enable)(struct nvkm_falcon *falcon);
 	void (*disable)(struct nvkm_falcon *falcon);
+	int (*reset)(struct nvkm_falcon *);
+
+	struct {
+		u32 head;
+		u32 tail;
+		u32 stride;
+	} cmdq, msgq;
 
 	struct nvkm_sclass sclass[];
 };
@@ -122,5 +135,4 @@ int nvkm_falcon_clear_interrupt(struct nvkm_falcon *, u32);
 int nvkm_falcon_enable(struct nvkm_falcon *);
 void nvkm_falcon_disable(struct nvkm_falcon *);
 int nvkm_falcon_reset(struct nvkm_falcon *);
-
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
index 2cde36f3c064..1530c81f86a2 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
@@ -50,6 +50,8 @@ int gp100_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp102_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp104_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp107_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
+int gp108_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp10b_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gv100_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
+int tu102_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/nvdec.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/nvdec.h
index 7c7d7f0abfcc..1b3183e31606 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/nvdec.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/nvdec.h
@@ -3,13 +3,13 @@
 #define __NVKM_NVDEC_H__
 #define nvkm_nvdec(p) container_of((p), struct nvkm_nvdec, engine)
 #include <core/engine.h>
+#include <core/falcon.h>
 
 struct nvkm_nvdec {
+	const struct nvkm_nvdec_func *func;
 	struct nvkm_engine engine;
-	u32 addr;
-
-	struct nvkm_falcon *falcon;
+	struct nvkm_falcon falcon;
 };
 
-int gp102_nvdec_new(struct nvkm_device *, int, struct nvkm_nvdec **);
+int gm107_nvdec_new(struct nvkm_device *, int, struct nvkm_nvdec **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/nvenc.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/nvenc.h
index 21624046d0a1..33e6ba8adc8d 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/nvenc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/nvenc.h
@@ -1,5 +1,15 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_NVENC_H__
 #define __NVKM_NVENC_H__
+#define nvkm_nvenc(p) container_of((p), struct nvkm_nvenc, engine)
 #include <core/engine.h>
+#include <core/falcon.h>
+
+struct nvkm_nvenc {
+	const struct nvkm_nvenc_func *func;
+	struct nvkm_engine engine;
+	struct nvkm_falcon falcon;
+};
+
+int gm107_nvenc_new(struct nvkm_device *, int, struct nvkm_nvenc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/sec2.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/sec2.h
index 33078f86c779..34dc765648d5 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/sec2.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/sec2.h
@@ -1,17 +1,24 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_SEC2_H__
 #define __NVKM_SEC2_H__
+#define nvkm_sec2(p) container_of((p), struct nvkm_sec2, engine)
 #include <core/engine.h>
+#include <core/falcon.h>
 
 struct nvkm_sec2 {
+	const struct nvkm_sec2_func *func;
 	struct nvkm_engine engine;
-	u32 addr;
+	struct nvkm_falcon falcon;
+
+	struct nvkm_falcon_qmgr *qmgr;
+	struct nvkm_falcon_cmdq *cmdq;
+	struct nvkm_falcon_msgq *msgq;
 
-	struct nvkm_falcon *falcon;
-	struct nvkm_msgqueue *queue;
 	struct work_struct work;
+	bool initmsg_received;
 };
 
 int gp102_sec2_new(struct nvkm_device *, int, struct nvkm_sec2 **);
+int gp108_sec2_new(struct nvkm_device *, int, struct nvkm_sec2 **);
 int tu102_sec2_new(struct nvkm_device *, int, struct nvkm_sec2 **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/acr.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/acr.h
new file mode 100644
index 000000000000..5d9c3a966de6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/acr.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVKM_ACR_H__
+#define __NVKM_ACR_H__
+#define nvkm_acr(p) container_of((p), struct nvkm_acr, subdev)
+#include <core/subdev.h>
+#include <core/falcon.h>
+
+enum nvkm_acr_lsf_id {
+	NVKM_ACR_LSF_PMU = 0,
+	NVKM_ACR_LSF_GSPLITE = 1,
+	NVKM_ACR_LSF_FECS = 2,
+	NVKM_ACR_LSF_GPCCS = 3,
+	NVKM_ACR_LSF_NVDEC = 4,
+	NVKM_ACR_LSF_SEC2 = 7,
+	NVKM_ACR_LSF_MINION = 10,
+	NVKM_ACR_LSF_NUM
+};
+
+static inline const char *
+nvkm_acr_lsf_id(enum nvkm_acr_lsf_id id)
+{
+	switch (id) {
+	case NVKM_ACR_LSF_PMU    : return "pmu";
+	case NVKM_ACR_LSF_GSPLITE: return "gsplite";
+	case NVKM_ACR_LSF_FECS   : return "fecs";
+	case NVKM_ACR_LSF_GPCCS  : return "gpccs";
+	case NVKM_ACR_LSF_NVDEC  : return "nvdec";
+	case NVKM_ACR_LSF_SEC2   : return "sec2";
+	case NVKM_ACR_LSF_MINION : return "minion";
+	default:
+		return "unknown";
+	}
+}
+
+struct nvkm_acr {
+	const struct nvkm_acr_func *func;
+	struct nvkm_subdev subdev;
+
+	struct list_head hsfw, hsf;
+	struct list_head lsfw, lsf;
+
+	struct nvkm_memory *wpr;
+	u64 wpr_start;
+	u64 wpr_end;
+	u64 shadow_start;
+
+	struct nvkm_memory *inst;
+	struct nvkm_vmm *vmm;
+
+	bool done;
+
+	const struct firmware *wpr_fw;
+	bool wpr_comp;
+	u64 wpr_prev;
+};
+
+bool nvkm_acr_managed_falcon(struct nvkm_device *, enum nvkm_acr_lsf_id);
+int nvkm_acr_bootstrap_falcons(struct nvkm_device *, unsigned long mask);
+
+int gm200_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int gm20b_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int gp102_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int gp108_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int gp10b_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int tu102_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+
+struct nvkm_acr_lsfw {
+	const struct nvkm_acr_lsf_func *func;
+	struct nvkm_falcon *falcon;
+	enum nvkm_acr_lsf_id id;
+
+	struct list_head head;
+
+	struct nvkm_blob img;
+
+	const struct firmware *sig;
+
+	u32 bootloader_size;
+	u32 bootloader_imem_offset;
+
+	u32 app_size;
+	u32 app_start_offset;
+	u32 app_imem_entry;
+	u32 app_resident_code_offset;
+	u32 app_resident_code_size;
+	u32 app_resident_data_offset;
+	u32 app_resident_data_size;
+
+	u32 ucode_size;
+	u32 data_size;
+
+	struct {
+		u32 lsb;
+		u32 img;
+		u32 bld;
+	} offset;
+	u32 bl_data_size;
+};
+
+struct nvkm_acr_lsf_func {
+/* The (currently) map directly to LSB header flags. */
+#define NVKM_ACR_LSF_LOAD_CODE_AT_0                                  0x00000001
+#define NVKM_ACR_LSF_DMACTL_REQ_CTX                                  0x00000004
+#define NVKM_ACR_LSF_FORCE_PRIV_LOAD                                 0x00000008
+	u32 flags;
+	u32 bld_size;
+	void (*bld_write)(struct nvkm_acr *, u32 bld, struct nvkm_acr_lsfw *);
+	void (*bld_patch)(struct nvkm_acr *, u32 bld, s64 adjust);
+	int (*boot)(struct nvkm_falcon *);
+	int (*bootstrap_falcon)(struct nvkm_falcon *, enum nvkm_acr_lsf_id);
+	int (*bootstrap_multiple_falcons)(struct nvkm_falcon *, u32 mask);
+};
+
+int
+nvkm_acr_lsfw_load_sig_image_desc(struct nvkm_subdev *, struct nvkm_falcon *,
+				  enum nvkm_acr_lsf_id, const char *path,
+				  int ver, const struct nvkm_acr_lsf_func *);
+int
+nvkm_acr_lsfw_load_sig_image_desc_v1(struct nvkm_subdev *, struct nvkm_falcon *,
+				     enum nvkm_acr_lsf_id, const char *path,
+				     int ver, const struct nvkm_acr_lsf_func *);
+int
+nvkm_acr_lsfw_load_bl_inst_data_sig(struct nvkm_subdev *, struct nvkm_falcon *,
+				    enum nvkm_acr_lsf_id, const char *path,
+				    int ver, const struct nvkm_acr_lsf_func *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h
index 97322f95b3ee..a513c16ab105 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h
@@ -31,6 +31,7 @@ struct nvkm_fault_data {
 };
 
 int gp100_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
+int gp10b_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
 int gv100_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
 int tu102_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
index 239ad222b95a..34b56b10218a 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
@@ -33,6 +33,8 @@ struct nvkm_fb {
 	const struct nvkm_fb_func *func;
 	struct nvkm_subdev subdev;
 
+	struct nvkm_blob vpr_scrubber;
+
 	struct nvkm_ram *ram;
 	struct nvkm_mm tags;
 
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 4c672a5c4cd5..06db67610a50 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -2,12 +2,11 @@
 #define __NVKM_GSP_H__
 #define nvkm_gsp(p) container_of((p), struct nvkm_gsp, subdev)
 #include <core/subdev.h>
+#include <core/falcon.h>
 
 struct nvkm_gsp {
 	struct nvkm_subdev subdev;
-	u32 addr;
-
-	struct nvkm_falcon *falcon;
+	struct nvkm_falcon falcon;
 };
 
 int gv100_gsp_new(struct nvkm_device *, int, struct nvkm_gsp **);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
index 644d527c3b96..d76f60d7d29a 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
@@ -40,4 +40,5 @@ int gm107_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gm200_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gp100_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gp102_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
+int gp10b_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/pmu.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/pmu.h
index 4752006880f3..da553089d2d8 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/pmu.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/pmu.h
@@ -2,13 +2,20 @@
 #ifndef __NVKM_PMU_H__
 #define __NVKM_PMU_H__
 #include <core/subdev.h>
-#include <engine/falcon.h>
+#include <core/falcon.h>
 
 struct nvkm_pmu {
 	const struct nvkm_pmu_func *func;
 	struct nvkm_subdev subdev;
-	struct nvkm_falcon *falcon;
-	struct nvkm_msgqueue *queue;
+	struct nvkm_falcon falcon;
+
+	struct nvkm_falcon_qmgr *qmgr;
+	struct nvkm_falcon_cmdq *hpq;
+	struct nvkm_falcon_cmdq *lpq;
+	struct nvkm_falcon_msgq *msgq;
+	bool initmsg_received;
+
+	struct completion wpr_ready;
 
 	struct {
 		u32 base;
@@ -43,6 +50,7 @@ int gm107_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
 int gm20b_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
 int gp100_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
 int gp102_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
+int gp10b_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
 
 /* interface to MEMX process running on PMU */
 struct nvkm_memx;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index f8015e0318d7..1b62ccc57aef 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1162,7 +1162,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 void
 nouveau_bo_move_init(struct nouveau_drm *drm)
 {
-	static const struct {
+	static const struct _method_table {
 		const char *name;
 		int engine;
 		s32 oclass;
@@ -1192,7 +1192,8 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 		{  "M2MF", 0, 0x0039, nv04_bo_move_m2mf, nv04_bo_move_init },
 		{},
 		{ "CRYPT", 0, 0x88b4, nv98_bo_move_exec, nv50_bo_move_init },
-	}, *mthd = _methods;
+	};
+	const struct _method_table *mthd = _methods;
 	const char *name = "CPU";
 	int ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index 282fd90b65e1..d9381a053169 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -55,6 +55,8 @@ nouveau_channel_killed(struct nvif_notify *ntfy)
 	struct nouveau_cli *cli = (void *)chan->user.client;
 	NV_PRINTK(warn, cli, "channel %d killed!\n", chan->chid);
 	atomic_set(&chan->killed, 1);
+	if (chan->fence)
+		nouveau_fence_context_kill(chan->fence, -ENODEV);
 	return NVIF_NOTIFY_DROP;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index fa1439941596..0ad5d87b5a8e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -635,10 +635,10 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 	unsigned long c, i;
 	int ret = -ENOMEM;
 
-	args.src = kcalloc(max, sizeof(args.src), GFP_KERNEL);
+	args.src = kcalloc(max, sizeof(*args.src), GFP_KERNEL);
 	if (!args.src)
 		goto out;
-	args.dst = kcalloc(max, sizeof(args.dst), GFP_KERNEL);
+	args.dst = kcalloc(max, sizeof(*args.dst), GFP_KERNEL);
 	if (!args.dst)
 		goto out_free_src;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 2cd83849600f..b65ae817eabf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -715,7 +715,6 @@ fail_nvkm:
 void
 nouveau_drm_device_remove(struct drm_device *dev)
 {
-	struct pci_dev *pdev = dev->pdev;
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvkm_client *client;
 	struct nvkm_device *device;
@@ -727,7 +726,6 @@ nouveau_drm_device_remove(struct drm_device *dev)
 	device = nvkm_device_find(client->device);
 
 	nouveau_drm_device_fini(dev);
-	pci_disable_device(pdev);
 	drm_dev_put(dev);
 	nvkm_device_del(&device);
 }
@@ -738,6 +736,7 @@ nouveau_drm_remove(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
 	nouveau_drm_device_remove(dev);
+	pci_disable_device(pdev);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 70f34cacc552..c2c332fbde97 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -58,6 +58,8 @@
 #include <drm/ttm/ttm_module.h>
 #include <drm/ttm/ttm_page_alloc.h>
 
+#include <drm/drm_audio_component.h>
+
 #include "uapi/drm/nouveau_drm.h"
 
 struct nouveau_channel;
@@ -211,6 +213,11 @@ struct nouveau_drm {
 	struct nouveau_svm *svm;
 
 	struct nouveau_dmem *dmem;
+
+	struct {
+		struct drm_audio_component *component;
+		bool component_registered;
+	} audio;
 };
 
 static inline struct nouveau_drm *
@@ -248,11 +255,11 @@ void nouveau_drm_device_remove(struct drm_device *dev);
 #define NV_INFO(drm,f,a...) NV_PRINTK(info, &(drm)->client, f, ##a)
 
 #define NV_DEBUG(drm,f,a...) do {                                              \
-	if (unlikely(drm_debug & DRM_UT_DRIVER))                               \
+	if (drm_debug_enabled(DRM_UT_DRIVER))                                  \
 		NV_PRINTK(info, &(drm)->client, f, ##a);                       \
 } while(0)
 #define NV_ATOMIC(drm,f,a...) do {                                             \
-	if (unlikely(drm_debug & DRM_UT_ATOMIC))                               \
+	if (drm_debug_enabled(DRM_UT_ATOMIC))                                  \
 		NV_PRINTK(info, &(drm)->client, f, ##a);                       \
 } while(0)
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index f439f0a5b43a..0c5cdda3c336 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -203,7 +203,7 @@ nouveau_fbcon_release(struct fb_info *info, int user)
 	return 0;
 }
 
-static struct fb_ops nouveau_fbcon_ops = {
+static const struct fb_ops nouveau_fbcon_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open = nouveau_fbcon_open,
@@ -214,7 +214,7 @@ static struct fb_ops nouveau_fbcon_ops = {
 	.fb_sync = nouveau_fbcon_sync,
 };
 
-static struct fb_ops nouveau_fbcon_sw_ops = {
+static const struct fb_ops nouveau_fbcon_sw_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open = nouveau_fbcon_open,
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 9118df035b28..666f2090d92b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -87,7 +87,7 @@ nouveau_local_fence(struct dma_fence *fence, struct nouveau_drm *drm)
 }
 
 void
-nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
+nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 {
 	struct nouveau_fence *fence;
 
@@ -95,11 +95,19 @@ nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 	while (!list_empty(&fctx->pending)) {
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 
+		if (error)
+			dma_fence_set_error(&fence->base, error);
+
 		if (nouveau_fence_signal(fence))
 			nvif_notify_put(&fctx->notify);
 	}
 	spin_unlock_irq(&fctx->lock);
+}
 
+void
+nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
+{
+	nouveau_fence_context_kill(fctx, 0);
 	nvif_notify_fini(&fctx->notify);
 	fctx->dead = 1;
 
@@ -156,7 +164,7 @@ nouveau_fence_wait_uevent_handler(struct nvif_notify *notify)
 
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
-		if (nouveau_fence_update(fence->channel, fctx))
+		if (nouveau_fence_update(chan, fctx))
 			ret = NVIF_NOTIFY_DROP;
 	}
 	spin_unlock_irqrestore(&fctx->lock, flags);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index c9e24baaaa4f..4887caa69c65 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -63,6 +63,7 @@ struct nouveau_fence_priv {
 void nouveau_fence_context_new(struct nouveau_channel *, struct nouveau_fence_chan *);
 void nouveau_fence_context_del(struct nouveau_fence_chan *);
 void nouveau_fence_context_free(struct nouveau_fence_chan *);
+void nouveau_fence_context_kill(struct nouveau_fence_chan *, int error);
 
 int nv04_fence_create(struct nouveau_drm *);
 int nv04_fence_mthd(struct nouveau_channel *, u32, u32, u32);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 1324c19f4e5c..f5ece1f94973 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -484,12 +484,9 @@ retry:
 
 static int
 validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli,
-	      struct list_head *list, struct drm_nouveau_gem_pushbuf_bo *pbbo,
-	      uint64_t user_pbbo_ptr)
+	      struct list_head *list, struct drm_nouveau_gem_pushbuf_bo *pbbo)
 {
 	struct nouveau_drm *drm = chan->drm;
-	struct drm_nouveau_gem_pushbuf_bo __user *upbbo =
-				(void __force __user *)(uintptr_t)user_pbbo_ptr;
 	struct nouveau_bo *nvbo;
 	int ret, relocs = 0;
 
@@ -533,10 +530,6 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli,
 			b->presumed.offset = nvbo->bo.offset;
 			b->presumed.valid = 0;
 			relocs++;
-
-			if (copy_to_user(&upbbo[nvbo->pbbo_index].presumed,
-					     &b->presumed, sizeof(b->presumed)))
-				return -EFAULT;
 		}
 	}
 
@@ -547,8 +540,8 @@ static int
 nouveau_gem_pushbuf_validate(struct nouveau_channel *chan,
 			     struct drm_file *file_priv,
 			     struct drm_nouveau_gem_pushbuf_bo *pbbo,
-			     uint64_t user_buffers, int nr_buffers,
-			     struct validate_op *op, int *apply_relocs)
+			     int nr_buffers,
+			     struct validate_op *op, bool *apply_relocs)
 {
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	int ret;
@@ -565,7 +558,7 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan,
 		return ret;
 	}
 
-	ret = validate_list(chan, cli, &op->list, pbbo, user_buffers);
+	ret = validate_list(chan, cli, &op->list, pbbo);
 	if (unlikely(ret < 0)) {
 		if (ret != -ERESTARTSYS)
 			NV_PRINTK(err, cli, "validating bo list\n");
@@ -605,16 +598,12 @@ u_memcpya(uint64_t user, unsigned nmemb, unsigned size)
 static int
 nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				struct drm_nouveau_gem_pushbuf *req,
+				struct drm_nouveau_gem_pushbuf_reloc *reloc,
 				struct drm_nouveau_gem_pushbuf_bo *bo)
 {
-	struct drm_nouveau_gem_pushbuf_reloc *reloc = NULL;
 	int ret = 0;
 	unsigned i;
 
-	reloc = u_memcpya(req->relocs, req->nr_relocs, sizeof(*reloc));
-	if (IS_ERR(reloc))
-		return PTR_ERR(reloc);
-
 	for (i = 0; i < req->nr_relocs; i++) {
 		struct drm_nouveau_gem_pushbuf_reloc *r = &reloc[i];
 		struct drm_nouveau_gem_pushbuf_bo *b;
@@ -693,11 +682,13 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct drm_nouveau_gem_pushbuf *req = data;
 	struct drm_nouveau_gem_pushbuf_push *push;
+	struct drm_nouveau_gem_pushbuf_reloc *reloc = NULL;
 	struct drm_nouveau_gem_pushbuf_bo *bo;
 	struct nouveau_channel *chan = NULL;
 	struct validate_op op;
 	struct nouveau_fence *fence = NULL;
-	int i, j, ret = 0, do_reloc = 0;
+	int i, j, ret = 0;
+	bool do_reloc = false, sync = false;
 
 	if (unlikely(!abi16))
 		return -ENOMEM;
@@ -711,6 +702,10 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 
 	if (!chan)
 		return nouveau_abi16_put(abi16, -ENOENT);
+	if (unlikely(atomic_read(&chan->killed)))
+		return nouveau_abi16_put(abi16, -ENODEV);
+
+	sync = req->vram_available & NOUVEAU_GEM_PUSHBUF_SYNC;
 
 	req->vram_available = drm->gem.vram_available;
 	req->gart_available = drm->gem.gart_available;
@@ -755,7 +750,8 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 	}
 
 	/* Validate buffer list */
-	ret = nouveau_gem_pushbuf_validate(chan, file_priv, bo, req->buffers,
+revalidate:
+	ret = nouveau_gem_pushbuf_validate(chan, file_priv, bo,
 					   req->nr_buffers, &op, &do_reloc);
 	if (ret) {
 		if (ret != -ERESTARTSYS)
@@ -765,7 +761,18 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 
 	/* Apply any relocations that are required */
 	if (do_reloc) {
-		ret = nouveau_gem_pushbuf_reloc_apply(cli, req, bo);
+		if (!reloc) {
+			validate_fini(&op, chan, NULL, bo);
+			reloc = u_memcpya(req->relocs, req->nr_relocs, sizeof(*reloc));
+			if (IS_ERR(reloc)) {
+				ret = PTR_ERR(reloc);
+				goto out_prevalid;
+			}
+
+			goto revalidate;
+		}
+
+		ret = nouveau_gem_pushbuf_reloc_apply(cli, req, reloc, bo);
 		if (ret) {
 			NV_PRINTK(err, cli, "reloc apply: %d\n", ret);
 			goto out;
@@ -847,10 +854,33 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 		goto out;
 	}
 
+	if (sync) {
+		if (!(ret = nouveau_fence_wait(fence, false, false))) {
+			if ((ret = dma_fence_get_status(&fence->base)) == 1)
+				ret = 0;
+		}
+	}
+
 out:
 	validate_fini(&op, chan, fence, bo);
 	nouveau_fence_unref(&fence);
 
+	if (do_reloc) {
+		struct drm_nouveau_gem_pushbuf_bo __user *upbbo =
+			u64_to_user_ptr(req->buffers);
+
+		for (i = 0; i < req->nr_buffers; i++) {
+			if (bo[i].presumed.valid)
+				continue;
+
+			if (copy_to_user(&upbbo[i].presumed, &bo[i].presumed,
+					 sizeof(bo[i].presumed))) {
+				ret = -EFAULT;
+				break;
+			}
+		}
+		u_free(reloc);
+	}
 out_prevalid:
 	u_free(bo);
 	u_free(push);
diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
index d445c6f3fece..1c3104d20571 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hwmon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
@@ -741,7 +741,7 @@ nouveau_hwmon_init(struct drm_device *dev)
 			special_groups[i++] = &pwm_fan_sensor_group;
 	}
 
-	special_groups[i] = 0;
+	special_groups[i] = NULL;
 	hwmon_dev = hwmon_device_register_with_info(dev->dev, "nouveau", dev,
 							&nouveau_chip_info,
 							special_groups);
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 77a0c6ad3cef..7ca0a2498532 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -63,14 +63,12 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_mem *mem;
 	int ret;
 
 	if (drm->client.device.info.ram_size == 0)
 		return -ENOMEM;
 
 	ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg);
-	mem = nouveau_mem(reg);
 	if (ret)
 		return ret;
 
@@ -103,11 +101,9 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_mem *mem;
 	int ret;
 
 	ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg);
-	mem = nouveau_mem(reg);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c
index 77061182a1cf..b28c7dc13ad6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c
@@ -69,8 +69,8 @@ nouveau_vma_del(struct nouveau_vma **pvma)
 		}
 		list_del(&vma->head);
 		kfree(*pvma);
-		*pvma = NULL;
 	}
+	*pvma = NULL;
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvif/mmu.c b/drivers/gpu/drm/nouveau/nvif/mmu.c
index 5641bda2046d..47efc408efa6 100644
--- a/drivers/gpu/drm/nouveau/nvif/mmu.c
+++ b/drivers/gpu/drm/nouveau/nvif/mmu.c
@@ -121,6 +121,7 @@ nvif_mmu_init(struct nvif_object *parent, s32 oclass, struct nvif_mmu *mmu)
 				       kind, argc);
 		if (ret == 0)
 			memcpy(mmu->kind, kind->data, kind->count);
+		mmu->kind_inv = kind->kind_inv;
 		kfree(kind);
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/Kbuild b/drivers/gpu/drm/nouveau/nvkm/Kbuild
index b53de9ba8c73..db3ade125fa9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/Kbuild
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: MIT
 include $(src)/nvkm/core/Kbuild
+include $(src)/nvkm/nvfw/Kbuild
 include $(src)/nvkm/falcon/Kbuild
 include $(src)/nvkm/subdev/Kbuild
 include $(src)/nvkm/engine/Kbuild
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
index 092acdec2c39..8b25367917ca 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
@@ -22,6 +22,40 @@
 #include <core/device.h>
 #include <core/firmware.h>
 
+int
+nvkm_firmware_load_name(const struct nvkm_subdev *subdev, const char *base,
+			const char *name, int ver, const struct firmware **pfw)
+{
+	char path[64];
+	int ret;
+
+	snprintf(path, sizeof(path), "%s%s", base, name);
+	ret = nvkm_firmware_get(subdev, path, ver, pfw);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+int
+nvkm_firmware_load_blob(const struct nvkm_subdev *subdev, const char *base,
+			const char *name, int ver, struct nvkm_blob *blob)
+{
+	const struct firmware *fw;
+	int ret;
+
+	ret = nvkm_firmware_load_name(subdev, base, name, ver, &fw);
+	if (ret == 0) {
+		blob->data = kmemdup(fw->data, fw->size, GFP_KERNEL);
+		blob->size = fw->size;
+		nvkm_firmware_put(fw);
+		if (!blob->data)
+			return -ENOMEM;
+	}
+
+	return ret;
+}
+
 /**
  * nvkm_firmware_get - load firmware from the official nvidia/chip/ directory
  * @subdev	subdevice that will use that firmware
@@ -32,9 +66,8 @@
  * Firmware files released by NVIDIA will always follow this format.
  */
 int
-nvkm_firmware_get_version(const struct nvkm_subdev *subdev, const char *fwname,
-			  int min_version, int max_version,
-			  const struct firmware **fw)
+nvkm_firmware_get(const struct nvkm_subdev *subdev, const char *fwname, int ver,
+		  const struct firmware **fw)
 {
 	struct nvkm_device *device = subdev->device;
 	char f[64];
@@ -50,31 +83,21 @@ nvkm_firmware_get_version(const struct nvkm_subdev *subdev, const char *fwname,
 		cname[i] = tolower(cname[i]);
 	}
 
-	for (i = max_version; i >= min_version; i--) {
-		if (i != 0)
-			snprintf(f, sizeof(f), "nvidia/%s/%s-%d.bin", cname, fwname, i);
-		else
-			snprintf(f, sizeof(f), "nvidia/%s/%s.bin", cname, fwname);
-
-		if (!firmware_request_nowarn(fw, f, device->dev)) {
-			nvkm_debug(subdev, "firmware \"%s\" loaded\n", f);
-			return i;
-		}
+	if (ver != 0)
+		snprintf(f, sizeof(f), "nvidia/%s/%s-%d.bin", cname, fwname, ver);
+	else
+		snprintf(f, sizeof(f), "nvidia/%s/%s.bin", cname, fwname);
 
-		nvkm_debug(subdev, "firmware \"%s\" unavailable\n", f);
+	if (!firmware_request_nowarn(fw, f, device->dev)) {
+		nvkm_debug(subdev, "firmware \"%s\" loaded - %zu byte(s)\n",
+			   f, (*fw)->size);
+		return 0;
 	}
 
-	nvkm_error(subdev, "failed to load firmware \"%s\"", fwname);
+	nvkm_debug(subdev, "firmware \"%s\" unavailable\n", f);
 	return -ENOENT;
 }
 
-int
-nvkm_firmware_get(const struct nvkm_subdev *subdev, const char *fwname,
-		  const struct firmware **fw)
-{
-	return nvkm_firmware_get_version(subdev, fwname, 0, 0, fw);
-}
-
 /**
  * nvkm_firmware_put - release firmware loaded with nvkm_firmware_get
  */
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/memory.c b/drivers/gpu/drm/nouveau/nvkm/core/memory.c
index e85a08ecd9da..4cc186262d34 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/memory.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/memory.c
@@ -91,8 +91,8 @@ nvkm_memory_tags_get(struct nvkm_memory *memory, struct nvkm_device *device,
 	}
 
 	refcount_set(&tags->refcount, 1);
+	*ptags = memory->tags = tags;
 	mutex_unlock(&fb->subdev.mutex);
-	*ptags = tags;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
index 245990de1e90..79a8f9d305c5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
@@ -30,6 +30,7 @@ static struct lock_class_key nvkm_subdev_lock_class[NVKM_SUBDEV_NR];
 
 const char *
 nvkm_subdev_name[NVKM_SUBDEV_NR] = {
+	[NVKM_SUBDEV_ACR     ] = "acr",
 	[NVKM_SUBDEV_BAR     ] = "bar",
 	[NVKM_SUBDEV_VBIOS   ] = "bios",
 	[NVKM_SUBDEV_BUS     ] = "bus",
@@ -50,7 +51,6 @@ nvkm_subdev_name[NVKM_SUBDEV_NR] = {
 	[NVKM_SUBDEV_MXM     ] = "mxm",
 	[NVKM_SUBDEV_PCI     ] = "pci",
 	[NVKM_SUBDEV_PMU     ] = "pmu",
-	[NVKM_SUBDEV_SECBOOT ] = "secboot",
 	[NVKM_SUBDEV_THERM   ] = "therm",
 	[NVKM_SUBDEV_TIMER   ] = "tmr",
 	[NVKM_SUBDEV_TOP     ] = "top",
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index c3c7159f3411..c7d700916eae 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -1987,6 +1987,8 @@ nv117_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gm107_fifo_new,
 	.gr = gm107_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
@@ -2027,6 +2029,7 @@ nv118_chipset = {
 static const struct nvkm_device_chip
 nv120_chipset = {
 	.name = "GM200",
+	.acr = gm200_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2045,7 +2048,6 @@ nv120_chipset = {
 	.pci = gk104_pci_new,
 	.pmu = gm107_pmu_new,
 	.therm = gm200_therm_new,
-	.secboot = gm200_secboot_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -2056,12 +2058,16 @@ nv120_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gm200_fifo_new,
 	.gr = gm200_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv124_chipset = {
 	.name = "GM204",
+	.acr = gm200_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2080,7 +2086,6 @@ nv124_chipset = {
 	.pci = gk104_pci_new,
 	.pmu = gm107_pmu_new,
 	.therm = gm200_therm_new,
-	.secboot = gm200_secboot_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -2091,12 +2096,16 @@ nv124_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gm200_fifo_new,
 	.gr = gm200_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv126_chipset = {
 	.name = "GM206",
+	.acr = gm200_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2115,7 +2124,6 @@ nv126_chipset = {
 	.pci = gk104_pci_new,
 	.pmu = gm107_pmu_new,
 	.therm = gm200_therm_new,
-	.secboot = gm200_secboot_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -2126,12 +2134,15 @@ nv126_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gm200_fifo_new,
 	.gr = gm200_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv12b_chipset = {
 	.name = "GM20B",
+	.acr = gm20b_acr_new,
 	.bar = gm20b_bar_new,
 	.bus = gf100_bus_new,
 	.clk = gm20b_clk_new,
@@ -2143,7 +2154,6 @@ nv12b_chipset = {
 	.mc = gk20a_mc_new,
 	.mmu = gm20b_mmu_new,
 	.pmu = gm20b_pmu_new,
-	.secboot = gm20b_secboot_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
 	.ce[2] = gm200_ce_new,
@@ -2157,6 +2167,7 @@ nv12b_chipset = {
 static const struct nvkm_device_chip
 nv130_chipset = {
 	.name = "GP100",
+	.acr = gm200_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2172,7 +2183,6 @@ nv130_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gm200_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp100_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2187,12 +2197,17 @@ nv130_chipset = {
 	.disp = gp100_disp_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp100_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
+	.nvenc[2] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv132_chipset = {
 	.name = "GP102",
+	.acr = gp102_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2208,7 +2223,6 @@ nv132_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp102_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2221,7 +2235,9 @@ nv132_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp102_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
 };
@@ -2229,6 +2245,7 @@ nv132_chipset = {
 static const struct nvkm_device_chip
 nv134_chipset = {
 	.name = "GP104",
+	.acr = gp102_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2244,7 +2261,6 @@ nv134_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp102_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2257,7 +2273,9 @@ nv134_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp104_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
 };
@@ -2265,6 +2283,7 @@ nv134_chipset = {
 static const struct nvkm_device_chip
 nv136_chipset = {
 	.name = "GP106",
+	.acr = gp102_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2280,7 +2299,6 @@ nv136_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp102_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2293,7 +2311,8 @@ nv136_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp104_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
 };
@@ -2301,6 +2320,7 @@ nv136_chipset = {
 static const struct nvkm_device_chip
 nv137_chipset = {
 	.name = "GP107",
+	.acr = gp102_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2316,7 +2336,6 @@ nv137_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp102_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2329,7 +2348,9 @@ nv137_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp107_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
 };
@@ -2337,6 +2358,7 @@ nv137_chipset = {
 static const struct nvkm_device_chip
 nv138_chipset = {
 	.name = "GP108",
+	.acr = gp108_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2352,7 +2374,6 @@ nv138_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp108_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2364,30 +2385,30 @@ nv138_chipset = {
 	.disp = gp102_disp_new,
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
-	.gr = gp107_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
-	.sec2 = gp102_sec2_new,
+	.gr = gp108_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.sec2 = gp108_sec2_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv13b_chipset = {
 	.name = "GP10B",
+	.acr = gp10b_acr_new,
 	.bar = gm20b_bar_new,
 	.bus = gf100_bus_new,
-	.fault = gp100_fault_new,
+	.fault = gp10b_fault_new,
 	.fb = gp10b_fb_new,
 	.fuse = gm107_fuse_new,
 	.ibus = gp10b_ibus_new,
 	.imem = gk20a_instmem_new,
-	.ltc = gp102_ltc_new,
+	.ltc = gp10b_ltc_new,
 	.mc = gp10b_mc_new,
 	.mmu = gp10b_mmu_new,
-	.secboot = gp10b_secboot_new,
-	.pmu = gm20b_pmu_new,
+	.pmu = gp10b_pmu_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
-	.ce[2] = gp102_ce_new,
+	.ce[0] = gp100_ce_new,
 	.dma = gf119_dma_new,
 	.fifo = gp10b_fifo_new,
 	.gr = gp10b_gr_new,
@@ -2397,6 +2418,7 @@ nv13b_chipset = {
 static const struct nvkm_device_chip
 nv140_chipset = {
 	.name = "GV100",
+	.acr = gp108_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2414,7 +2436,6 @@ nv140_chipset = {
 	.mmu = gv100_mmu_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
-	.secboot = gp108_secboot_new,
 	.therm = gp100_therm_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
@@ -2431,13 +2452,17 @@ nv140_chipset = {
 	.dma = gv100_dma_new,
 	.fifo = gv100_fifo_new,
 	.gr = gv100_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
-	.sec2 = gp102_sec2_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
+	.nvenc[2] = gm107_nvenc_new,
+	.sec2 = gp108_sec2_new,
 };
 
 static const struct nvkm_device_chip
 nv162_chipset = {
 	.name = "TU102",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2466,13 +2491,16 @@ nv162_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.gr = tu102_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
 static const struct nvkm_device_chip
 nv164_chipset = {
 	.name = "TU104",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2501,13 +2529,17 @@ nv164_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.gr = tu102_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvdec[1] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
 static const struct nvkm_device_chip
 nv166_chipset = {
 	.name = "TU106",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2536,7 +2568,11 @@ nv166_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.gr = tu102_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvdec[1] = gm107_nvdec_new,
+	.nvdec[2] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
@@ -2571,7 +2607,8 @@ nv167_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
@@ -2606,7 +2643,8 @@ nv168_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
@@ -2638,6 +2676,7 @@ nvkm_device_subdev(struct nvkm_device *device, int index)
 
 	switch (index) {
 #define _(n,p,m) case NVKM_SUBDEV_##n: if (p) return (m); break
+	_(ACR     , device->acr     , &device->acr->subdev);
 	_(BAR     , device->bar     , &device->bar->subdev);
 	_(VBIOS   , device->bios    , &device->bios->subdev);
 	_(BUS     , device->bus     , &device->bus->subdev);
@@ -2658,7 +2697,6 @@ nvkm_device_subdev(struct nvkm_device *device, int index)
 	_(MXM     , device->mxm     ,  device->mxm);
 	_(PCI     , device->pci     , &device->pci->subdev);
 	_(PMU     , device->pmu     , &device->pmu->subdev);
-	_(SECBOOT , device->secboot , &device->secboot->subdev);
 	_(THERM   , device->therm   , &device->therm->subdev);
 	_(TIMER   , device->timer   , &device->timer->subdev);
 	_(TOP     , device->top     , &device->top->subdev);
@@ -2703,9 +2741,9 @@ nvkm_device_engine(struct nvkm_device *device, int index)
 	_(MSPDEC , device->mspdec  ,  device->mspdec);
 	_(MSPPP  , device->msppp   ,  device->msppp);
 	_(MSVLD  , device->msvld   ,  device->msvld);
-	_(NVENC0 , device->nvenc[0],  device->nvenc[0]);
-	_(NVENC1 , device->nvenc[1],  device->nvenc[1]);
-	_(NVENC2 , device->nvenc[2],  device->nvenc[2]);
+	_(NVENC0 , device->nvenc[0], &device->nvenc[0]->engine);
+	_(NVENC1 , device->nvenc[1], &device->nvenc[1]->engine);
+	_(NVENC2 , device->nvenc[2], &device->nvenc[2]->engine);
 	_(NVDEC0 , device->nvdec[0], &device->nvdec[0]->engine);
 	_(NVDEC1 , device->nvdec[1], &device->nvdec[1]->engine);
 	_(NVDEC2 , device->nvdec[2], &device->nvdec[2]->engine);
@@ -3144,6 +3182,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 	}                                                                      \
 	break
 		switch (i) {
+		_(NVKM_SUBDEV_ACR     ,      acr);
 		_(NVKM_SUBDEV_BAR     ,      bar);
 		_(NVKM_SUBDEV_VBIOS   ,     bios);
 		_(NVKM_SUBDEV_BUS     ,      bus);
@@ -3164,7 +3203,6 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		_(NVKM_SUBDEV_MXM     ,      mxm);
 		_(NVKM_SUBDEV_PCI     ,      pci);
 		_(NVKM_SUBDEV_PMU     ,      pmu);
-		_(NVKM_SUBDEV_SECBOOT ,  secboot);
 		_(NVKM_SUBDEV_THERM   ,    therm);
 		_(NVKM_SUBDEV_TIMER   ,    timer);
 		_(NVKM_SUBDEV_TOP     ,      top);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
index d8be2f77ac66..54eab5e04230 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
@@ -3,6 +3,7 @@
 #define __NVKM_DEVICE_PRIV_H__
 #include <core/device.h>
 
+#include <subdev/acr.h>
 #include <subdev/bar.h>
 #include <subdev/bios.h>
 #include <subdev/bus.h>
@@ -27,7 +28,6 @@
 #include <subdev/timer.h>
 #include <subdev/top.h>
 #include <subdev/volt.h>
-#include <subdev/secboot.h>
 
 #include <engine/bsp.h>
 #include <engine/ce.h>
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index 0e372a190d3f..d0d52c1d4aee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -52,18 +52,18 @@ nvkm_device_tegra_power_up(struct nvkm_device_tegra *tdev)
 	clk_set_rate(tdev->clk_pwr, 204000000);
 	udelay(10);
 
-	reset_control_assert(tdev->rst);
-	udelay(10);
-
 	if (!tdev->pdev->dev.pm_domain) {
+		reset_control_assert(tdev->rst);
+		udelay(10);
+
 		ret = tegra_powergate_remove_clamping(TEGRA_POWERGATE_3D);
 		if (ret)
 			goto err_clamp;
 		udelay(10);
-	}
 
-	reset_control_deassert(tdev->rst);
-	udelay(10);
+		reset_control_deassert(tdev->rst);
+		udelay(10);
+	}
 
 	return 0;
 
@@ -279,6 +279,7 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 		      struct nvkm_device **pdevice)
 {
 	struct nvkm_device_tegra *tdev;
+	unsigned long rate;
 	int ret;
 
 	if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL)))
@@ -307,6 +308,17 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 		goto free;
 	}
 
+	rate = clk_get_rate(tdev->clk);
+	if (rate == 0) {
+		ret = clk_set_rate(tdev->clk, ULONG_MAX);
+		if (ret < 0)
+			goto free;
+
+		rate = clk_get_rate(tdev->clk);
+
+		dev_dbg(&pdev->dev, "GPU clock set to %lu\n", rate);
+	}
+
 	if (func->require_ref_clk)
 		tdev->clk_ref = devm_clk_get(&pdev->dev, "ref");
 	if (IS_ERR(tdev->clk_ref)) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index bcf32d92ee5a..50e3539f33d2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -74,6 +74,8 @@ nv50_disp_chan_mthd(struct nv50_disp_chan *chan, int debug)
 
 	if (debug > subdev->debug)
 		return;
+	if (!mthd)
+		return;
 
 	for (i = 0; (list = mthd->data[i].mthd) != NULL; i++) {
 		u32 base = chan->head * mthd->addr;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
index 818d21bd28d3..3800aeb507d0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
@@ -365,7 +365,7 @@ nvkm_dp_train(struct nvkm_dp *dp, u32 dataKBps)
 	 * and it's better to have a failed modeset than that.
 	 */
 	for (cfg = nvkm_dp_rates; cfg->rate; cfg++) {
-		if (cfg->nr <= outp_nr && cfg->nr <= outp_bw) {
+		if (cfg->nr <= outp_nr && cfg->bw <= outp_bw) {
 			/* Try to respect sink limits too when selecting
 			 * lowest link configuration.
 			 */
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c
index 892be6c9b76c..3aa2cc3af1e2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c
@@ -101,15 +101,26 @@ gv100_disp_exception(struct nv50_disp *disp, int chid)
 	u32 stat = nvkm_rd32(device, 0x611020 + (chid * 12));
 	u32 type = (stat & 0x00007000) >> 12;
 	u32 mthd = (stat & 0x00000fff) << 2;
-	u32 data = nvkm_rd32(device, 0x611024 + (chid * 12));
-	u32 code = nvkm_rd32(device, 0x611028 + (chid * 12));
 	const struct nvkm_enum *reason =
 		nvkm_enum_find(nv50_disp_intr_error_type, type);
 
-	nvkm_error(subdev, "chid %d stat %08x reason %d [%s] mthd %04x "
-			   "data %08x code %08x\n",
-		   chid, stat, type, reason ? reason->name : "",
-		   mthd, data, code);
+	/*TODO: Suspect 33->41 are for WRBK channel exceptions, but we
+	 *      don't support those currently.
+	 *
+	 *      CORE+WIN CHIDs map directly to the FE_EXCEPT() slots.
+	 */
+	if (chid <= 32) {
+		u32 data = nvkm_rd32(device, 0x611024 + (chid * 12));
+		u32 code = nvkm_rd32(device, 0x611028 + (chid * 12));
+		nvkm_error(subdev, "chid %d stat %08x reason %d [%s] "
+				   "mthd %04x data %08x code %08x\n",
+			   chid, stat, type, reason ? reason->name : "",
+			   mthd, data, code);
+	} else {
+		nvkm_error(subdev, "chid %d stat %08x reason %d [%s] "
+				   "mthd %04x\n",
+			   chid, stat, type, reason ? reason->name : "", mthd);
+	}
 
 	if (chid < ARRAY_SIZE(disp->chan) && disp->chan[chid]) {
 		switch (mthd) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
index 73724a8cb861..558c86fd8e82 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
@@ -36,8 +36,10 @@ nvkm-y += nvkm/engine/gr/gp100.o
 nvkm-y += nvkm/engine/gr/gp102.o
 nvkm-y += nvkm/engine/gr/gp104.o
 nvkm-y += nvkm/engine/gr/gp107.o
+nvkm-y += nvkm/engine/gr/gp108.o
 nvkm-y += nvkm/engine/gr/gp10b.o
 nvkm-y += nvkm/engine/gr/gv100.o
+nvkm-y += nvkm/engine/gr/tu102.o
 
 nvkm-y += nvkm/engine/gr/ctxnv40.o
 nvkm-y += nvkm/engine/gr/ctxnv50.o
@@ -60,3 +62,4 @@ nvkm-y += nvkm/engine/gr/ctxgp102.o
 nvkm-y += nvkm/engine/gr/ctxgp104.o
 nvkm-y += nvkm/engine/gr/ctxgp107.o
 nvkm-y += nvkm/engine/gr/ctxgv100.o
+nvkm-y += nvkm/engine/gr/ctxtu102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
index 85f2d1e950e8..297915719bf2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
@@ -1324,10 +1324,8 @@ gf100_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
 void
 gf100_grctx_generate_floorsweep(struct gf100_gr *gr)
 {
-	struct nvkm_device *device = gr->base.engine.subdev.device;
 	const struct gf100_grctx_func *func = gr->func->grctx;
-	int gpc, sm, i, j;
-	u32 data;
+	int sm;
 
 	for (sm = 0; sm < gr->sm_nr; sm++) {
 		func->sm_id(gr, gr->sm[sm].gpc, gr->sm[sm].tpc, sm);
@@ -1335,12 +1333,9 @@ gf100_grctx_generate_floorsweep(struct gf100_gr *gr)
 			func->tpc_nr(gr, gr->sm[sm].gpc);
 	}
 
-	for (gpc = 0, i = 0; i < 4; i++) {
-		for (data = 0, j = 0; j < 8 && gpc < gr->gpc_nr; j++, gpc++)
-			data |= gr->tpc_nr[gpc] << (j * 4);
-		nvkm_wr32(device, 0x406028 + (i * 4), data);
-		nvkm_wr32(device, 0x405870 + (i * 4), data);
-	}
+	gf100_gr_init_num_tpc_per_gpc(gr, false, true);
+	if (!func->skip_pd_num_tpc_per_gpc)
+		gf100_gr_init_num_tpc_per_gpc(gr, true, false);
 
 	if (func->r4060a8)
 		func->r4060a8(gr);
@@ -1374,7 +1369,7 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 
 	nvkm_mc_unk260(device, 0);
 
-	if (!gr->fuc_sw_ctx) {
+	if (!gr->sw_ctx) {
 		gf100_gr_mmio(gr, grctx->hub);
 		gf100_gr_mmio(gr, grctx->gpc_0);
 		gf100_gr_mmio(gr, grctx->zcull);
@@ -1382,7 +1377,7 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 		gf100_gr_mmio(gr, grctx->tpc);
 		gf100_gr_mmio(gr, grctx->ppc);
 	} else {
-		gf100_gr_mmio(gr, gr->fuc_sw_ctx);
+		gf100_gr_mmio(gr, gr->sw_ctx);
 	}
 
 	gf100_gr_wait_idle(gr);
@@ -1401,8 +1396,8 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	gf100_gr_wait_idle(gr);
 
 	if (grctx->r400088) grctx->r400088(gr, false);
-	if (gr->fuc_bundle)
-		gf100_gr_icmd(gr, gr->fuc_bundle);
+	if (gr->bundle)
+		gf100_gr_icmd(gr, gr->bundle);
 	else
 		gf100_gr_icmd(gr, grctx->icmd);
 	if (grctx->sw_veid_bundle_init)
@@ -1411,8 +1406,8 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 
 	nvkm_wr32(device, 0x404154, idle_timeout);
 
-	if (gr->fuc_method)
-		gf100_gr_mthd(gr, gr->fuc_method);
+	if (gr->method)
+		gf100_gr_mthd(gr, gr->method);
 	else
 		gf100_gr_mthd(gr, grctx->mthd);
 	nvkm_mc_unk260(device, 1);
@@ -1431,6 +1426,8 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 		grctx->r419a3c(gr);
 	if (grctx->r408840)
 		grctx->r408840(gr);
+	if (grctx->r419c0c)
+		grctx->r419c0c(gr);
 }
 
 #define CB_RESERVED 0x80000
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
index 478b4723d0f9..32bbddc0993e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
@@ -57,6 +57,7 @@ struct gf100_grctx_func {
 	/* floorsweeping */
 	void (*sm_id)(struct gf100_gr *, int gpc, int tpc, int sm);
 	void (*tpc_nr)(struct gf100_gr *, int gpc);
+	bool skip_pd_num_tpc_per_gpc;
 	void (*r4060a8)(struct gf100_gr *);
 	void (*rop_mapping)(struct gf100_gr *);
 	void (*alpha_beta_tables)(struct gf100_gr *);
@@ -76,6 +77,7 @@ struct gf100_grctx_func {
 	void (*r418e94)(struct gf100_gr *);
 	void (*r419a3c)(struct gf100_gr *);
 	void (*r408840)(struct gf100_gr *);
+	void (*r419c0c)(struct gf100_gr *);
 };
 
 extern const struct gf100_grctx_func gf100_grctx;
@@ -153,6 +155,14 @@ extern const struct gf100_grctx_func gp107_grctx;
 
 extern const struct gf100_grctx_func gv100_grctx;
 
+extern const struct gf100_grctx_func tu102_grctx;
+void gv100_grctx_unkn88c(struct gf100_gr *, bool);
+void gv100_grctx_generate_unkn(struct gf100_gr *);
+extern const struct gf100_gr_init gv100_grctx_init_sw_veid_bundle_init_0[];
+void gv100_grctx_generate_attrib(struct gf100_grctx *);
+void gv100_grctx_generate_rop_mapping(struct gf100_gr *);
+void gv100_grctx_generate_r400088(struct gf100_gr *, bool);
+
 /* context init value lists */
 
 extern const struct gf100_gr_pack gf100_grctx_pack_icmd[];
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
index 896d473dcc0f..c0d36bc601f9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
@@ -32,7 +32,7 @@ gk20a_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	u32 idle_timeout;
 	int i;
 
-	gf100_gr_mmio(gr, gr->fuc_sw_ctx);
+	gf100_gr_mmio(gr, gr->sw_ctx);
 
 	gf100_gr_wait_idle(gr);
 
@@ -56,10 +56,10 @@ gk20a_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	nvkm_wr32(device, 0x404154, idle_timeout);
 	gf100_gr_wait_idle(gr);
 
-	gf100_gr_mthd(gr, gr->fuc_method);
+	gf100_gr_mthd(gr, gr->method);
 	gf100_gr_wait_idle(gr);
 
-	gf100_gr_icmd(gr, gr->fuc_bundle);
+	gf100_gr_icmd(gr, gr->bundle);
 	grctx->pagepool(info);
 	grctx->bundle(info);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
index a1d9e114ebeb..6b92f8aa18a3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
@@ -29,7 +29,7 @@ gm20b_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	u32 idle_timeout;
 	int i, tmp;
 
-	gf100_gr_mmio(gr, gr->fuc_sw_ctx);
+	gf100_gr_mmio(gr, gr->sw_ctx);
 
 	gf100_gr_wait_idle(gr);
 
@@ -59,10 +59,10 @@ gm20b_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	nvkm_wr32(device, 0x404154, idle_timeout);
 	gf100_gr_wait_idle(gr);
 
-	gf100_gr_mthd(gr, gr->fuc_method);
+	gf100_gr_mthd(gr, gr->method);
 	gf100_gr_wait_idle(gr);
 
-	gf100_gr_icmd(gr, gr->fuc_bundle);
+	gf100_gr_icmd(gr, gr->bundle);
 	grctx->pagepool(info);
 	grctx->bundle(info);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c
index 0990765ef191..39553d55d3f3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c
@@ -25,7 +25,7 @@
  * PGRAPH context implementation
  ******************************************************************************/
 
-static const struct gf100_gr_init
+const struct gf100_gr_init
 gv100_grctx_init_sw_veid_bundle_init_0[] = {
 	{ 0x00001000, 64, 0x00100000, 0x00000008 },
 	{ 0x00000941, 64, 0x00100000, 0x00000000 },
@@ -58,7 +58,7 @@ gv100_grctx_pack_sw_veid_bundle_init[] = {
 	{}
 };
 
-static void
+void
 gv100_grctx_generate_attrib(struct gf100_grctx *info)
 {
 	struct gf100_gr *gr = info->gr;
@@ -67,14 +67,14 @@ gv100_grctx_generate_attrib(struct gf100_grctx *info)
 	const u32 attrib = grctx->attrib_nr;
 	const u32   gfxp = grctx->gfxp_nr;
 	const int s = 12;
-	const int max_batches = 0xffff;
 	u32 size = grctx->alpha_nr_max * gr->tpc_total;
 	u32 ao = 0;
 	u32 bo = ao + size;
 	int gpc, ppc, b, n = 0;
 
-	size += grctx->gfxp_nr * gr->tpc_total;
-	size = ((size * 0x20) + 128) & ~127;
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++)
+		size += grctx->gfxp_nr * gr->ppc_nr[gpc] * gr->ppc_tpc_max;
+	size = ((size * 0x20) + 127) & ~127;
 	b = mmio_vram(info, size, (1 << s), false);
 
 	mmio_refn(info, 0x418810, 0x80000000, s, b);
@@ -84,13 +84,12 @@ gv100_grctx_generate_attrib(struct gf100_grctx *info)
 	mmio_wr32(info, 0x419e04, 0x80000000 | size >> 7);
 	mmio_wr32(info, 0x405830, attrib);
 	mmio_wr32(info, 0x40585c, alpha);
-	mmio_wr32(info, 0x4064c4, ((alpha / 4) << 16) | max_batches);
 
 	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
 		for (ppc = 0; ppc < gr->ppc_nr[gpc]; ppc++, n++) {
 			const u32 as =  alpha * gr->ppc_tpc_nr[gpc][ppc];
-			const u32 bs = attrib * gr->ppc_tpc_nr[gpc][ppc];
-			const u32 gs =   gfxp * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 bs = attrib * gr->ppc_tpc_max;
+			const u32 gs =   gfxp * gr->ppc_tpc_max;
 			const u32 u = 0x418ea0 + (n * 0x04);
 			const u32 o = PPC_UNIT(gpc, ppc, 0);
 			if (!(gr->ppc_mask[gpc] & (1 << ppc)))
@@ -110,7 +109,7 @@ gv100_grctx_generate_attrib(struct gf100_grctx *info)
 	mmio_wr32(info, 0x41befc, 0x00000100);
 }
 
-static void
+void
 gv100_grctx_generate_rop_mapping(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -147,7 +146,7 @@ gv100_grctx_generate_rop_mapping(struct gf100_gr *gr)
 				     gr->screen_tile_row_offset);
 }
 
-static void
+void
 gv100_grctx_generate_r400088(struct gf100_gr *gr, bool on)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -163,7 +162,7 @@ gv100_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
 	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), sm);
 }
 
-static void
+void
 gv100_grctx_generate_unkn(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -174,7 +173,7 @@ gv100_grctx_generate_unkn(struct gf100_gr *gr)
 	nvkm_mask(device, 0x419c00, 0x00000008, 0x00000008);
 }
 
-static void
+void
 gv100_grctx_unkn88c(struct gf100_gr *gr, bool on)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxtu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxtu102.c
new file mode 100644
index 000000000000..2299ca07d04a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxtu102.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2019 Red Hat 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 "ctxgf100.h"
+
+static void
+tu102_grctx_generate_r419c0c(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x419c0c, 0x80000000, 0x80000000);
+	nvkm_mask(device, 0x40584c, 0x00000008, 0x00000000);
+	nvkm_mask(device, 0x400080, 0x00000000, 0x00000000);
+}
+
+static void
+tu102_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x608), sm);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), sm);
+}
+
+static const struct gf100_gr_init
+tu102_grctx_init_unknown_bundle_init_0[] = {
+	{ 0x00001000,  1, 0x00000001, 0x00000004 },
+	{ 0x00002020, 64, 0x00000001, 0x00000000 },
+	{ 0x0001e100,  1, 0x00000001, 0x00000001 },
+	{}
+};
+
+static const struct gf100_gr_pack
+tu102_grctx_pack_sw_veid_bundle_init[] = {
+	{ gv100_grctx_init_sw_veid_bundle_init_0 },
+	{ tu102_grctx_init_unknown_bundle_init_0 },
+	{}
+};
+
+static void
+tu102_grctx_generate_attrib(struct gf100_grctx *info)
+{
+	const u64 size = 0x80000; /*XXX: educated guess */
+	const int s = 8;
+	const int b = mmio_vram(info, size, (1 << s), true);
+
+	gv100_grctx_generate_attrib(info);
+
+	mmio_refn(info, 0x408070, 0x00000000, s, b);
+	mmio_wr32(info, 0x408074, size >> s); /*XXX: guess */
+	mmio_refn(info, 0x419034, 0x00000000, s, b);
+	mmio_wr32(info, 0x408078, 0x00000000);
+}
+
+const struct gf100_grctx_func
+tu102_grctx = {
+	.unkn88c = gv100_grctx_unkn88c,
+	.main = gf100_grctx_generate_main,
+	.unkn = gv100_grctx_generate_unkn,
+	.sw_veid_bundle_init = tu102_grctx_pack_sw_veid_bundle_init,
+	.bundle = gm107_grctx_generate_bundle,
+	.bundle_size = 0x3000,
+	.bundle_min_gpm_fifo_depth = 0x180,
+	.bundle_token_limit = 0xa80,
+	.pagepool = gp100_grctx_generate_pagepool,
+	.pagepool_size = 0x20000,
+	.attrib = tu102_grctx_generate_attrib,
+	.attrib_nr_max = 0x800,
+	.attrib_nr = 0x700,
+	.alpha_nr_max = 0xc00,
+	.alpha_nr = 0x800,
+	.gfxp_nr = 0xfa8,
+	.sm_id = tu102_grctx_generate_sm_id,
+	.skip_pd_num_tpc_per_gpc = true,
+	.rop_mapping = gv100_grctx_generate_rop_mapping,
+	.r406500 = gm200_grctx_generate_r406500,
+	.r400088 = gv100_grctx_generate_r400088,
+	.r419c0c = tu102_grctx_generate_r419c0c,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgk208.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgk208.fuc5.h
index c24f35ad56a6..ae2d5b6891cb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgk208.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgk208.fuc5.h
@@ -441,7 +441,7 @@ static uint32_t gk208_grhub_code[] = {
 	0x020014fe,
 	0x12004002,
 	0xbd0002f6,
-	0x05c94104,
+	0x05ca4104,
 	0xbd0010fe,
 	0x07004024,
 	0xbd0002f6,
@@ -460,423 +460,423 @@ static uint32_t gk208_grhub_code[] = {
 	0x01039204,
 	0x03090080,
 	0xbd0003f6,
-	0x87044204,
-	0xf6040040,
-	0x04bd0002,
-	0x00400402,
-	0x0002f603,
-	0x31f404bd,
-	0x96048e10,
-	0x00657e40,
-	0xc7feb200,
-	0x01b590f1,
-	0x1ff4f003,
-	0x01020fb5,
-	0x041fbb01,
-	0x800112b6,
-	0xf6010300,
-	0x04bd0001,
-	0x01040080,
+	0x87048204,
+	0x04004000,
+	0xbd0002f6,
+	0x40040204,
+	0x02f60300,
+	0xf404bd00,
+	0x048e1031,
+	0x657e4096,
+	0xfeb20000,
+	0xb590f1c7,
+	0xf4f00301,
+	0x020fb51f,
+	0x1fbb0101,
+	0x0112b604,
+	0x01030080,
 	0xbd0001f6,
-	0x01004104,
-	0xac7e020f,
-	0xbb7e0006,
-	0x100f0006,
-	0x0006fd7e,
-	0x98000e98,
-	0x207e010f,
-	0x14950001,
-	0xc0008008,
-	0x0004f601,
-	0x008004bd,
-	0x04f601c1,
-	0xb704bd00,
-	0xbb130030,
-	0xf5b6001f,
-	0xd3008002,
-	0x000ff601,
-	0x15b604bd,
-	0x0110b608,
-	0xb20814b6,
-	0x02687e1f,
-	0x001fbb00,
-	0x84020398,
-/* 0x041f: init_gpc */
-	0xb8502000,
-	0x0008044e,
-	0x8f7e1fb2,
+	0x04008004,
+	0x0001f601,
+	0x004104bd,
+	0x7e020f01,
+	0x7e0006ad,
+	0x0f0006bc,
+	0x06fe7e10,
+	0x000e9800,
+	0x7e010f98,
+	0x95000120,
+	0x00800814,
+	0x04f601c0,
+	0x8004bd00,
+	0xf601c100,
+	0x04bd0004,
+	0x130030b7,
+	0xb6001fbb,
+	0x008002f5,
+	0x0ff601d3,
+	0xb604bd00,
+	0x10b60815,
+	0x0814b601,
+	0x687e1fb2,
+	0x1fbb0002,
+	0x02039800,
+	0x50200084,
+/* 0x0420: init_gpc */
+	0x08044eb8,
+	0x7e1fb200,
+	0xb800008f,
+	0x00010c4e,
+	0x8f7ef4bd,
 	0x4eb80000,
-	0xbd00010c,
-	0x008f7ef4,
-	0x044eb800,
-	0x8f7e0001,
+	0x7e000104,
+	0xb800008f,
+	0x0001004e,
+	0x8f7e020f,
 	0x4eb80000,
-	0x0f000100,
-	0x008f7e02,
-	0x004eb800,
-/* 0x044e: init_gpc_wait */
+/* 0x044f: init_gpc_wait */
+	0x7e000800,
+	0xc8000065,
+	0x0bf41fff,
+	0x044eb8f9,
 	0x657e0008,
-	0xffc80000,
-	0xf90bf41f,
-	0x08044eb8,
-	0x00657e00,
-	0x001fbb00,
-	0x800040b7,
-	0xf40132b6,
-	0x000fb41b,
-	0x0006fd7e,
-	0xac7e000f,
-	0x00800006,
-	0x01f60201,
-	0xbd04bd00,
-	0x1f19f014,
-	0x02300080,
-	0xbd0001f6,
-/* 0x0491: wait */
-	0x0028f404,
-/* 0x0497: main */
-	0x0d0031f4,
-	0x00377e10,
-	0xf401f400,
-	0x4001e4b1,
-	0x00c71bf5,
-	0x99f094bd,
-	0x37008004,
-	0x0009f602,
-	0x008104bd,
-	0x11cf02c0,
-	0xc1008200,
-	0x0022cf02,
-	0xf41f13c8,
-	0x23c8770b,
-	0x550bf41f,
-	0x12b220f9,
-	0x99f094bd,
-	0x37008007,
-	0x0009f602,
-	0x32f404bd,
-	0x0231f401,
-	0x0008807e,
-	0x99f094bd,
-	0x17008007,
-	0x0009f602,
-	0x20fc04bd,
-	0x99f094bd,
-	0x37008006,
-	0x0009f602,
-	0x31f404bd,
-	0x08807e01,
+	0x1fbb0000,
+	0x0040b700,
+	0x0132b680,
+	0x0fb41bf4,
+	0x06fe7e00,
+	0x7e000f00,
+	0x800006ad,
+	0xf6020100,
+	0x04bd0001,
+	0x19f014bd,
+	0x3000801f,
+	0x0001f602,
+/* 0x0492: wait */
+	0x28f404bd,
+	0x0031f400,
+/* 0x0498: main */
+	0x377e100d,
+	0x01f40000,
+	0x01e4b1f4,
+	0xc71bf540,
 	0xf094bd00,
-	0x00800699,
+	0x00800499,
+	0x09f60237,
+	0x8104bd00,
+	0xcf02c000,
+	0x00820011,
+	0x22cf02c1,
+	0x1f13c800,
+	0xc8770bf4,
+	0x0bf41f23,
+	0xb220f955,
+	0xf094bd12,
+	0x00800799,
+	0x09f60237,
+	0xf404bd00,
+	0x31f40132,
+	0x08817e02,
+	0xf094bd00,
+	0x00800799,
 	0x09f60217,
+	0xfc04bd00,
+	0xf094bd20,
+	0x00800699,
+	0x09f60237,
 	0xf404bd00,
-/* 0x0522: chsw_prev_no_next */
-	0x20f92f0e,
-	0x32f412b2,
-	0x0232f401,
-	0x0008807e,
-	0x008020fc,
-	0x02f602c0,
+	0x817e0131,
+	0x94bd0008,
+	0x800699f0,
+	0xf6021700,
+	0x04bd0009,
+/* 0x0523: chsw_prev_no_next */
+	0xf92f0ef4,
+	0xf412b220,
+	0x32f40132,
+	0x08817e02,
+	0x8020fc00,
+	0xf602c000,
+	0x04bd0002,
+/* 0x053f: chsw_no_prev */
+	0xc8130ef4,
+	0x0bf41f23,
+	0x0131f40d,
+	0x7e0232f4,
+/* 0x054f: chsw_done */
+	0x02000881,
+	0xc3008001,
+	0x0002f602,
+	0x94bd04bd,
+	0x800499f0,
+	0xf6021700,
+	0x04bd0009,
+	0xff300ef5,
+/* 0x056c: main_not_ctx_switch */
+	0xf401e4b0,
+	0xf2b20c1b,
+	0x0008217e,
+/* 0x057b: main_not_ctx_chan */
+	0xb0400ef4,
+	0x1bf402e4,
+	0xf094bd2c,
+	0x00800799,
+	0x09f60237,
 	0xf404bd00,
-/* 0x053e: chsw_no_prev */
-	0x23c8130e,
-	0x0d0bf41f,
-	0xf40131f4,
-	0x807e0232,
-/* 0x054e: chsw_done */
-	0x01020008,
-	0x02c30080,
-	0xbd0002f6,
-	0xf094bd04,
-	0x00800499,
+	0x32f40132,
+	0x08817e02,
+	0xf094bd00,
+	0x00800799,
 	0x09f60217,
-	0xf504bd00,
-/* 0x056b: main_not_ctx_switch */
-	0xb0ff300e,
-	0x1bf401e4,
-	0x7ef2b20c,
-	0xf4000820,
-/* 0x057a: main_not_ctx_chan */
-	0xe4b0400e,
-	0x2c1bf402,
-	0x99f094bd,
-	0x37008007,
-	0x0009f602,
-	0x32f404bd,
-	0x0232f401,
-	0x0008807e,
-	0x99f094bd,
-	0x17008007,
-	0x0009f602,
-	0x0ef404bd,
-/* 0x05a9: main_not_ctx_save */
-	0x10ef9411,
-	0x7e01f5f0,
-	0xf50002f8,
-/* 0x05b7: main_done */
-	0xbdfee40e,
-	0x1f29f024,
-	0x02300080,
-	0xbd0002f6,
-	0xd20ef504,
-/* 0x05c9: ih */
-	0xf900f9fe,
-	0x0188fe80,
-	0x90f980f9,
-	0xb0f9a0f9,
-	0xe0f9d0f9,
-	0x04bdf0f9,
-	0xcf02004a,
-	0xabc400aa,
-	0x230bf404,
-	0x004e100d,
-	0x00eecf1a,
-	0xcf19004f,
-	0x047e00ff,
-	0xb0b70000,
-	0x010e0400,
-	0xf61d0040,
-	0x04bd000e,
-/* 0x060c: ih_no_fifo */
-	0x0100abe4,
-	0x0d0c0bf4,
-	0x40014e10,
-	0x0000047e,
-/* 0x061c: ih_no_ctxsw */
-	0x0400abe4,
-	0x8e560bf4,
-	0x7e400708,
+	0xf404bd00,
+/* 0x05aa: main_not_ctx_save */
+	0xef94110e,
+	0x01f5f010,
+	0x0002f87e,
+	0xfee40ef5,
+/* 0x05b8: main_done */
+	0x29f024bd,
+	0x3000801f,
+	0x0002f602,
+	0x0ef504bd,
+/* 0x05ca: ih */
+	0x00f9fed2,
+	0x88fe80f9,
+	0xf980f901,
+	0xf9a0f990,
+	0xf9d0f9b0,
+	0xbdf0f9e0,
+	0x02004a04,
+	0xc400aacf,
+	0x0bf404ab,
+	0x4e100d23,
+	0xeecf1a00,
+	0x19004f00,
+	0x7e00ffcf,
+	0xb7000004,
+	0x0e0400b0,
+	0x1d004001,
+	0xbd000ef6,
+/* 0x060d: ih_no_fifo */
+	0x00abe404,
+	0x0c0bf401,
+	0x014e100d,
+	0x00047e40,
+/* 0x061d: ih_no_ctxsw */
+	0x00abe400,
+	0x560bf404,
+	0x4007088e,
+	0x0000657e,
+	0x0080ffb2,
+	0x0ff60204,
+	0x8e04bd00,
+	0x7e400704,
 	0xb2000065,
-	0x040080ff,
+	0x030080ff,
 	0x000ff602,
-	0x048e04bd,
-	0x657e4007,
-	0xffb20000,
-	0x02030080,
-	0xbd000ff6,
-	0x50fec704,
-	0x8f02ee94,
-	0xbb400700,
-	0x657e00ef,
-	0x00800000,
-	0x0ff60202,
+	0xfec704bd,
+	0x02ee9450,
+	0x4007008f,
+	0x7e00efbb,
+	0x80000065,
+	0xf6020200,
+	0x04bd000f,
+	0xf87e030f,
+	0x004b0002,
+	0x8ebfb201,
+	0x7e400144,
+/* 0x0677: ih_no_fwmthd */
+	0x4b00008f,
+	0xb0bd0504,
+	0xf4b4abff,
+	0x00800c0b,
+	0x0bf60307,
+/* 0x068b: ih_no_other */
+	0x4004bd00,
+	0x0af60100,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x00fc80fc,
+	0xf80032f4,
+/* 0x06ad: ctx_4170s */
+	0x10f5f001,
+	0x708effb2,
+	0x8f7e4041,
+	0x00f80000,
+/* 0x06bc: ctx_4170w */
+	0x4041708e,
+	0x0000657e,
+	0xf4f0ffb2,
+	0xf31bf410,
+/* 0x06ce: ctx_redswitch */
+	0x004e00f8,
+	0x40e5f002,
+	0xf020e5f0,
+	0x008010e5,
+	0x0ef60185,
 	0x0f04bd00,
-	0x02f87e03,
-	0x01004b00,
-	0x448ebfb2,
-	0x8f7e4001,
-/* 0x0676: ih_no_fwmthd */
-	0x044b0000,
-	0xffb0bd05,
-	0x0bf4b4ab,
-	0x0700800c,
-	0x000bf603,
-/* 0x068a: ih_no_other */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0xf400fc80,
-	0x01f80032,
-/* 0x06ac: ctx_4170s */
-	0xb210f5f0,
-	0x41708eff,
+/* 0x06e5: ctx_redswitch_delay */
+	0x01f2b608,
+	0xf1fd1bf4,
+	0xf10400e5,
+	0x800100e5,
+	0xf6018500,
+	0x04bd000e,
+/* 0x06fe: ctx_86c */
+	0x008000f8,
+	0x0ff60223,
+	0xb204bd00,
+	0x8a148eff,
 	0x008f7e40,
-/* 0x06bb: ctx_4170w */
-	0x8e00f800,
-	0x7e404170,
-	0xb2000065,
-	0x10f4f0ff,
-	0xf8f31bf4,
-/* 0x06cd: ctx_redswitch */
-	0x02004e00,
-	0xf040e5f0,
-	0xe5f020e5,
-	0x85008010,
-	0x000ef601,
-	0x080f04bd,
-/* 0x06e4: ctx_redswitch_delay */
-	0xf401f2b6,
-	0xe5f1fd1b,
-	0xe5f10400,
-	0x00800100,
-	0x0ef60185,
-	0xf804bd00,
-/* 0x06fd: ctx_86c */
-	0x23008000,
+	0x8effb200,
+	0x7e41a88c,
+	0xf800008f,
+/* 0x071d: ctx_mem */
+	0x84008000,
 	0x000ff602,
-	0xffb204bd,
-	0x408a148e,
-	0x00008f7e,
-	0x8c8effb2,
-	0x8f7e41a8,
-	0x00f80000,
-/* 0x071c: ctx_mem */
-	0x02840080,
-	0xbd000ff6,
-/* 0x0725: ctx_mem_wait */
-	0x84008f04,
-	0x00ffcf02,
-	0xf405fffd,
-	0x00f8f61b,
-/* 0x0734: ctx_load */
-	0x99f094bd,
-	0x37008005,
-	0x0009f602,
-	0x0c0a04bd,
-	0x0000b87e,
-	0x0080f4bd,
-	0x0ff60289,
-	0x8004bd00,
-	0xf602c100,
-	0x04bd0002,
-	0x02830080,
+/* 0x0726: ctx_mem_wait */
+	0x008f04bd,
+	0xffcf0284,
+	0x05fffd00,
+	0xf8f61bf4,
+/* 0x0735: ctx_load */
+	0xf094bd00,
+	0x00800599,
+	0x09f60237,
+	0x0a04bd00,
+	0x00b87e0c,
+	0x80f4bd00,
+	0xf6028900,
+	0x04bd000f,
+	0x02c10080,
 	0xbd0002f6,
-	0x7e070f04,
-	0x8000071c,
-	0xf602c000,
-	0x04bd0002,
-	0xf0000bfe,
-	0x24b61f2a,
-	0x0220b604,
-	0x99f094bd,
-	0x37008008,
-	0x0009f602,
-	0x008004bd,
-	0x02f60281,
-	0xd204bd00,
-	0x80000000,
-	0x800225f0,
-	0xf6028800,
-	0x04bd0002,
-	0x00421001,
-	0x0223f002,
-	0xf80512fa,
-	0xf094bd03,
+	0x83008004,
+	0x0002f602,
+	0x070f04bd,
+	0x00071d7e,
+	0x02c00080,
+	0xbd0002f6,
+	0x000bfe04,
+	0xb61f2af0,
+	0x20b60424,
+	0xf094bd02,
 	0x00800899,
-	0x09f60217,
-	0x9804bd00,
-	0x14b68101,
-	0x80029818,
-	0xfd0825b6,
-	0x01b50512,
-	0xf094bd16,
-	0x00800999,
 	0x09f60237,
 	0x8004bd00,
 	0xf6028100,
-	0x04bd0001,
-	0x00800102,
-	0x02f60288,
-	0x4104bd00,
-	0x13f00100,
-	0x0501fa06,
+	0x04bd0002,
+	0x000000d2,
+	0x0225f080,
+	0x02880080,
+	0xbd0002f6,
+	0x42100104,
+	0x23f00200,
+	0x0512fa02,
 	0x94bd03f8,
-	0x800999f0,
+	0x800899f0,
 	0xf6021700,
 	0x04bd0009,
-	0x99f094bd,
-	0x17008005,
-	0x0009f602,
-	0x00f804bd,
-/* 0x0820: ctx_chan */
-	0x0007347e,
-	0xb87e0c0a,
-	0x050f0000,
-	0x00071c7e,
-/* 0x0832: ctx_mmio_exec */
-	0x039800f8,
-	0x81008041,
-	0x0003f602,
-	0x34bd04bd,
-/* 0x0840: ctx_mmio_loop */
-	0xf4ff34c4,
-	0x00450e1b,
-	0x0653f002,
-	0xf80535fa,
-/* 0x0851: ctx_mmio_pull */
-	0x804e9803,
-	0x7e814f98,
-	0xb600008f,
-	0x12b60830,
-	0xdf1bf401,
-/* 0x0864: ctx_mmio_done */
-	0x80160398,
-	0xf6028100,
-	0x04bd0003,
-	0x414000b5,
-	0x13f00100,
-	0x0601fa06,
-	0x00f803f8,
-/* 0x0880: ctx_xfer */
-	0x0080040e,
-	0x0ef60302,
-/* 0x088b: ctx_xfer_idle */
-	0x8e04bd00,
-	0xcf030000,
-	0xe4f100ee,
-	0x1bf42000,
-	0x0611f4f5,
-/* 0x089f: ctx_xfer_pre */
-	0x0f0c02f4,
-	0x06fd7e10,
-	0x1b11f400,
-/* 0x08a8: ctx_xfer_pre_load */
-	0xac7e020f,
-	0xbb7e0006,
-	0xcd7e0006,
-	0xf4bd0006,
-	0x0006ac7e,
-	0x0007347e,
-/* 0x08c0: ctx_xfer_exec */
-	0xbd160198,
-	0x05008024,
-	0x0002f601,
-	0x1fb204bd,
-	0x41a5008e,
-	0x00008f7e,
-	0xf001fcf0,
-	0x24b6022c,
-	0x05f2fd01,
-	0x048effb2,
-	0x8f7e41a5,
-	0x167e0000,
-	0x24bd0002,
-	0x0247fc80,
-	0xbd0002f6,
-	0x012cf004,
-	0x800320b6,
-	0xf6024afc,
+	0xb6810198,
+	0x02981814,
+	0x0825b680,
+	0xb50512fd,
+	0x94bd1601,
+	0x800999f0,
+	0xf6023700,
+	0x04bd0009,
+	0x02810080,
+	0xbd0001f6,
+	0x80010204,
+	0xf6028800,
 	0x04bd0002,
-	0xf001acf0,
-	0x000b06a5,
-	0x98000c98,
-	0x000e010d,
-	0x00013d7e,
-	0xec7e080a,
-	0x0a7e0000,
-	0x01f40002,
-	0x7e0c0a12,
+	0xf0010041,
+	0x01fa0613,
+	0xbd03f805,
+	0x0999f094,
+	0x02170080,
+	0xbd0009f6,
+	0xf094bd04,
+	0x00800599,
+	0x09f60217,
+	0xf804bd00,
+/* 0x0821: ctx_chan */
+	0x07357e00,
+	0x7e0c0a00,
 	0x0f0000b8,
-	0x071c7e05,
-	0x2d02f400,
-/* 0x093c: ctx_xfer_post */
-	0xac7e020f,
-	0xf4bd0006,
-	0x0006fd7e,
-	0x0002277e,
-	0x0006bb7e,
-	0xac7ef4bd,
+	0x071d7e05,
+/* 0x0833: ctx_mmio_exec */
+	0x9800f800,
+	0x00804103,
+	0x03f60281,
+	0xbd04bd00,
+/* 0x0841: ctx_mmio_loop */
+	0xff34c434,
+	0x450e1bf4,
+	0x53f00200,
+	0x0535fa06,
+/* 0x0852: ctx_mmio_pull */
+	0x4e9803f8,
+	0x814f9880,
+	0x00008f7e,
+	0xb60830b6,
+	0x1bf40112,
+/* 0x0865: ctx_mmio_done */
+	0x160398df,
+	0x02810080,
+	0xbd0003f6,
+	0x4000b504,
+	0xf0010041,
+	0x01fa0613,
+	0xf803f806,
+/* 0x0881: ctx_xfer */
+	0x80040e00,
+	0xf6030200,
+	0x04bd000e,
+/* 0x088c: ctx_xfer_idle */
+	0x0300008e,
+	0xf100eecf,
+	0xf42000e4,
+	0x11f4f51b,
+	0x0c02f406,
+/* 0x08a0: ctx_xfer_pre */
+	0xfe7e100f,
 	0x11f40006,
-	0x40019810,
-	0xf40511fd,
-	0x327e070b,
-/* 0x0966: ctx_xfer_no_post_mmio */
-/* 0x0966: ctx_xfer_done */
-	0x00f80008,
+/* 0x08a9: ctx_xfer_pre_load */
+	0x7e020f1b,
+	0x7e0006ad,
+	0x7e0006bc,
+	0xbd0006ce,
+	0x06ad7ef4,
+	0x07357e00,
+/* 0x08c1: ctx_xfer_exec */
+	0x16019800,
+	0x008024bd,
+	0x02f60105,
+	0xb204bd00,
+	0xa5008e1f,
+	0x008f7e41,
+	0x01fcf000,
+	0xb6022cf0,
+	0xf2fd0124,
+	0x8effb205,
+	0x7e41a504,
+	0x7e00008f,
+	0xbd000216,
+	0x47fc8024,
+	0x0002f602,
+	0x2cf004bd,
+	0x0320b601,
+	0x024afc80,
+	0xbd0002f6,
+	0x01acf004,
+	0x0b06a5f0,
+	0x000c9800,
+	0x0e010d98,
+	0x013d7e00,
+	0x7e080a00,
+	0x7e0000ec,
+	0xf400020a,
+	0x0c0a1201,
+	0x0000b87e,
+	0x1d7e050f,
+	0x02f40007,
+/* 0x093d: ctx_xfer_post */
+	0x7e020f2d,
+	0xbd0006ad,
+	0x06fe7ef4,
+	0x02277e00,
+	0x06bc7e00,
+	0x7ef4bd00,
+	0xf40006ad,
+	0x01981011,
+	0x0511fd40,
+	0x7e070bf4,
+/* 0x0967: ctx_xfer_no_post_mmio */
+/* 0x0967: ctx_xfer_done */
+	0xf8000833,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgm107.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgm107.fuc5.h
index 649a442b4390..449dae753203 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgm107.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgm107.fuc5.h
@@ -441,7 +441,7 @@ static uint32_t gm107_grhub_code[] = {
 	0x020014fe,
 	0x12004002,
 	0xbd0002f6,
-	0x05c94104,
+	0x05ca4104,
 	0xbd0010fe,
 	0x07004024,
 	0xbd0002f6,
@@ -460,423 +460,423 @@ static uint32_t gm107_grhub_code[] = {
 	0x01039204,
 	0x03090080,
 	0xbd0003f6,
-	0x87044204,
-	0xf6040040,
-	0x04bd0002,
-	0x00400402,
-	0x0002f603,
-	0x31f404bd,
-	0x96048e10,
-	0x00657e40,
-	0xc7feb200,
-	0x01b590f1,
-	0x1ff4f003,
-	0x01020fb5,
-	0x041fbb01,
-	0x800112b6,
-	0xf6010300,
-	0x04bd0001,
-	0x01040080,
+	0x87048204,
+	0x04004000,
+	0xbd0002f6,
+	0x40040204,
+	0x02f60300,
+	0xf404bd00,
+	0x048e1031,
+	0x657e4096,
+	0xfeb20000,
+	0xb590f1c7,
+	0xf4f00301,
+	0x020fb51f,
+	0x1fbb0101,
+	0x0112b604,
+	0x01030080,
 	0xbd0001f6,
-	0x01004104,
-	0xac7e020f,
-	0xbb7e0006,
-	0x100f0006,
-	0x0006fd7e,
-	0x98000e98,
-	0x207e010f,
-	0x14950001,
-	0xc0008008,
-	0x0004f601,
-	0x008004bd,
-	0x04f601c1,
-	0xb704bd00,
-	0xbb130030,
-	0xf5b6001f,
-	0xd3008002,
-	0x000ff601,
-	0x15b604bd,
-	0x0110b608,
-	0xb20814b6,
-	0x02687e1f,
-	0x001fbb00,
-	0x84020398,
-/* 0x041f: init_gpc */
-	0xb8502000,
-	0x0008044e,
-	0x8f7e1fb2,
+	0x04008004,
+	0x0001f601,
+	0x004104bd,
+	0x7e020f01,
+	0x7e0006ad,
+	0x0f0006bc,
+	0x06fe7e10,
+	0x000e9800,
+	0x7e010f98,
+	0x95000120,
+	0x00800814,
+	0x04f601c0,
+	0x8004bd00,
+	0xf601c100,
+	0x04bd0004,
+	0x130030b7,
+	0xb6001fbb,
+	0x008002f5,
+	0x0ff601d3,
+	0xb604bd00,
+	0x10b60815,
+	0x0814b601,
+	0x687e1fb2,
+	0x1fbb0002,
+	0x02039800,
+	0x50200084,
+/* 0x0420: init_gpc */
+	0x08044eb8,
+	0x7e1fb200,
+	0xb800008f,
+	0x00010c4e,
+	0x8f7ef4bd,
 	0x4eb80000,
-	0xbd00010c,
-	0x008f7ef4,
-	0x044eb800,
-	0x8f7e0001,
+	0x7e000104,
+	0xb800008f,
+	0x0001004e,
+	0x8f7e020f,
 	0x4eb80000,
-	0x0f000100,
-	0x008f7e02,
-	0x004eb800,
-/* 0x044e: init_gpc_wait */
+/* 0x044f: init_gpc_wait */
+	0x7e000800,
+	0xc8000065,
+	0x0bf41fff,
+	0x044eb8f9,
 	0x657e0008,
-	0xffc80000,
-	0xf90bf41f,
-	0x08044eb8,
-	0x00657e00,
-	0x001fbb00,
-	0x800040b7,
-	0xf40132b6,
-	0x000fb41b,
-	0x0006fd7e,
-	0xac7e000f,
-	0x00800006,
-	0x01f60201,
-	0xbd04bd00,
-	0x1f19f014,
-	0x02300080,
-	0xbd0001f6,
-/* 0x0491: wait */
-	0x0028f404,
-/* 0x0497: main */
-	0x0d0031f4,
-	0x00377e10,
-	0xf401f400,
-	0x4001e4b1,
-	0x00c71bf5,
-	0x99f094bd,
-	0x37008004,
-	0x0009f602,
-	0x008104bd,
-	0x11cf02c0,
-	0xc1008200,
-	0x0022cf02,
-	0xf41f13c8,
-	0x23c8770b,
-	0x550bf41f,
-	0x12b220f9,
-	0x99f094bd,
-	0x37008007,
-	0x0009f602,
-	0x32f404bd,
-	0x0231f401,
-	0x0008807e,
-	0x99f094bd,
-	0x17008007,
-	0x0009f602,
-	0x20fc04bd,
-	0x99f094bd,
-	0x37008006,
-	0x0009f602,
-	0x31f404bd,
-	0x08807e01,
+	0x1fbb0000,
+	0x0040b700,
+	0x0132b680,
+	0x0fb41bf4,
+	0x06fe7e00,
+	0x7e000f00,
+	0x800006ad,
+	0xf6020100,
+	0x04bd0001,
+	0x19f014bd,
+	0x3000801f,
+	0x0001f602,
+/* 0x0492: wait */
+	0x28f404bd,
+	0x0031f400,
+/* 0x0498: main */
+	0x377e100d,
+	0x01f40000,
+	0x01e4b1f4,
+	0xc71bf540,
 	0xf094bd00,
-	0x00800699,
+	0x00800499,
+	0x09f60237,
+	0x8104bd00,
+	0xcf02c000,
+	0x00820011,
+	0x22cf02c1,
+	0x1f13c800,
+	0xc8770bf4,
+	0x0bf41f23,
+	0xb220f955,
+	0xf094bd12,
+	0x00800799,
+	0x09f60237,
+	0xf404bd00,
+	0x31f40132,
+	0x08817e02,
+	0xf094bd00,
+	0x00800799,
 	0x09f60217,
+	0xfc04bd00,
+	0xf094bd20,
+	0x00800699,
+	0x09f60237,
 	0xf404bd00,
-/* 0x0522: chsw_prev_no_next */
-	0x20f92f0e,
-	0x32f412b2,
-	0x0232f401,
-	0x0008807e,
-	0x008020fc,
-	0x02f602c0,
+	0x817e0131,
+	0x94bd0008,
+	0x800699f0,
+	0xf6021700,
+	0x04bd0009,
+/* 0x0523: chsw_prev_no_next */
+	0xf92f0ef4,
+	0xf412b220,
+	0x32f40132,
+	0x08817e02,
+	0x8020fc00,
+	0xf602c000,
+	0x04bd0002,
+/* 0x053f: chsw_no_prev */
+	0xc8130ef4,
+	0x0bf41f23,
+	0x0131f40d,
+	0x7e0232f4,
+/* 0x054f: chsw_done */
+	0x02000881,
+	0xc3008001,
+	0x0002f602,
+	0x94bd04bd,
+	0x800499f0,
+	0xf6021700,
+	0x04bd0009,
+	0xff300ef5,
+/* 0x056c: main_not_ctx_switch */
+	0xf401e4b0,
+	0xf2b20c1b,
+	0x0008217e,
+/* 0x057b: main_not_ctx_chan */
+	0xb0400ef4,
+	0x1bf402e4,
+	0xf094bd2c,
+	0x00800799,
+	0x09f60237,
 	0xf404bd00,
-/* 0x053e: chsw_no_prev */
-	0x23c8130e,
-	0x0d0bf41f,
-	0xf40131f4,
-	0x807e0232,
-/* 0x054e: chsw_done */
-	0x01020008,
-	0x02c30080,
-	0xbd0002f6,
-	0xf094bd04,
-	0x00800499,
+	0x32f40132,
+	0x08817e02,
+	0xf094bd00,
+	0x00800799,
 	0x09f60217,
-	0xf504bd00,
-/* 0x056b: main_not_ctx_switch */
-	0xb0ff300e,
-	0x1bf401e4,
-	0x7ef2b20c,
-	0xf4000820,
-/* 0x057a: main_not_ctx_chan */
-	0xe4b0400e,
-	0x2c1bf402,
-	0x99f094bd,
-	0x37008007,
-	0x0009f602,
-	0x32f404bd,
-	0x0232f401,
-	0x0008807e,
-	0x99f094bd,
-	0x17008007,
-	0x0009f602,
-	0x0ef404bd,
-/* 0x05a9: main_not_ctx_save */
-	0x10ef9411,
-	0x7e01f5f0,
-	0xf50002f8,
-/* 0x05b7: main_done */
-	0xbdfee40e,
-	0x1f29f024,
-	0x02300080,
-	0xbd0002f6,
-	0xd20ef504,
-/* 0x05c9: ih */
-	0xf900f9fe,
-	0x0188fe80,
-	0x90f980f9,
-	0xb0f9a0f9,
-	0xe0f9d0f9,
-	0x04bdf0f9,
-	0xcf02004a,
-	0xabc400aa,
-	0x230bf404,
-	0x004e100d,
-	0x00eecf1a,
-	0xcf19004f,
-	0x047e00ff,
-	0xb0b70000,
-	0x010e0400,
-	0xf61d0040,
-	0x04bd000e,
-/* 0x060c: ih_no_fifo */
-	0x0100abe4,
-	0x0d0c0bf4,
-	0x40014e10,
-	0x0000047e,
-/* 0x061c: ih_no_ctxsw */
-	0x0400abe4,
-	0x8e560bf4,
-	0x7e400708,
+	0xf404bd00,
+/* 0x05aa: main_not_ctx_save */
+	0xef94110e,
+	0x01f5f010,
+	0x0002f87e,
+	0xfee40ef5,
+/* 0x05b8: main_done */
+	0x29f024bd,
+	0x3000801f,
+	0x0002f602,
+	0x0ef504bd,
+/* 0x05ca: ih */
+	0x00f9fed2,
+	0x88fe80f9,
+	0xf980f901,
+	0xf9a0f990,
+	0xf9d0f9b0,
+	0xbdf0f9e0,
+	0x02004a04,
+	0xc400aacf,
+	0x0bf404ab,
+	0x4e100d23,
+	0xeecf1a00,
+	0x19004f00,
+	0x7e00ffcf,
+	0xb7000004,
+	0x0e0400b0,
+	0x1d004001,
+	0xbd000ef6,
+/* 0x060d: ih_no_fifo */
+	0x00abe404,
+	0x0c0bf401,
+	0x014e100d,
+	0x00047e40,
+/* 0x061d: ih_no_ctxsw */
+	0x00abe400,
+	0x560bf404,
+	0x4007088e,
+	0x0000657e,
+	0x0080ffb2,
+	0x0ff60204,
+	0x8e04bd00,
+	0x7e400704,
 	0xb2000065,
-	0x040080ff,
+	0x030080ff,
 	0x000ff602,
-	0x048e04bd,
-	0x657e4007,
-	0xffb20000,
-	0x02030080,
-	0xbd000ff6,
-	0x50fec704,
-	0x8f02ee94,
-	0xbb400700,
-	0x657e00ef,
-	0x00800000,
-	0x0ff60202,
+	0xfec704bd,
+	0x02ee9450,
+	0x4007008f,
+	0x7e00efbb,
+	0x80000065,
+	0xf6020200,
+	0x04bd000f,
+	0xf87e030f,
+	0x004b0002,
+	0x8ebfb201,
+	0x7e400144,
+/* 0x0677: ih_no_fwmthd */
+	0x4b00008f,
+	0xb0bd0504,
+	0xf4b4abff,
+	0x00800c0b,
+	0x0bf60307,
+/* 0x068b: ih_no_other */
+	0x4004bd00,
+	0x0af60100,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x00fc80fc,
+	0xf80032f4,
+/* 0x06ad: ctx_4170s */
+	0x10f5f001,
+	0x708effb2,
+	0x8f7e4041,
+	0x00f80000,
+/* 0x06bc: ctx_4170w */
+	0x4041708e,
+	0x0000657e,
+	0xf4f0ffb2,
+	0xf31bf410,
+/* 0x06ce: ctx_redswitch */
+	0x004e00f8,
+	0x40e5f002,
+	0xf020e5f0,
+	0x008010e5,
+	0x0ef60185,
 	0x0f04bd00,
-	0x02f87e03,
-	0x01004b00,
-	0x448ebfb2,
-	0x8f7e4001,
-/* 0x0676: ih_no_fwmthd */
-	0x044b0000,
-	0xffb0bd05,
-	0x0bf4b4ab,
-	0x0700800c,
-	0x000bf603,
-/* 0x068a: ih_no_other */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0xf400fc80,
-	0x01f80032,
-/* 0x06ac: ctx_4170s */
-	0xb210f5f0,
-	0x41708eff,
+/* 0x06e5: ctx_redswitch_delay */
+	0x01f2b608,
+	0xf1fd1bf4,
+	0xf10400e5,
+	0x800100e5,
+	0xf6018500,
+	0x04bd000e,
+/* 0x06fe: ctx_86c */
+	0x008000f8,
+	0x0ff60223,
+	0xb204bd00,
+	0x8a148eff,
 	0x008f7e40,
-/* 0x06bb: ctx_4170w */
-	0x8e00f800,
-	0x7e404170,
-	0xb2000065,
-	0x10f4f0ff,
-	0xf8f31bf4,
-/* 0x06cd: ctx_redswitch */
-	0x02004e00,
-	0xf040e5f0,
-	0xe5f020e5,
-	0x85008010,
-	0x000ef601,
-	0x080f04bd,
-/* 0x06e4: ctx_redswitch_delay */
-	0xf401f2b6,
-	0xe5f1fd1b,
-	0xe5f10400,
-	0x00800100,
-	0x0ef60185,
-	0xf804bd00,
-/* 0x06fd: ctx_86c */
-	0x23008000,
+	0x8effb200,
+	0x7e41a88c,
+	0xf800008f,
+/* 0x071d: ctx_mem */
+	0x84008000,
 	0x000ff602,
-	0xffb204bd,
-	0x408a148e,
-	0x00008f7e,
-	0x8c8effb2,
-	0x8f7e41a8,
-	0x00f80000,
-/* 0x071c: ctx_mem */
-	0x02840080,
-	0xbd000ff6,
-/* 0x0725: ctx_mem_wait */
-	0x84008f04,
-	0x00ffcf02,
-	0xf405fffd,
-	0x00f8f61b,
-/* 0x0734: ctx_load */
-	0x99f094bd,
-	0x37008005,
-	0x0009f602,
-	0x0c0a04bd,
-	0x0000b87e,
-	0x0080f4bd,
-	0x0ff60289,
-	0x8004bd00,
-	0xf602c100,
-	0x04bd0002,
-	0x02830080,
+/* 0x0726: ctx_mem_wait */
+	0x008f04bd,
+	0xffcf0284,
+	0x05fffd00,
+	0xf8f61bf4,
+/* 0x0735: ctx_load */
+	0xf094bd00,
+	0x00800599,
+	0x09f60237,
+	0x0a04bd00,
+	0x00b87e0c,
+	0x80f4bd00,
+	0xf6028900,
+	0x04bd000f,
+	0x02c10080,
 	0xbd0002f6,
-	0x7e070f04,
-	0x8000071c,
-	0xf602c000,
-	0x04bd0002,
-	0xf0000bfe,
-	0x24b61f2a,
-	0x0220b604,
-	0x99f094bd,
-	0x37008008,
-	0x0009f602,
-	0x008004bd,
-	0x02f60281,
-	0xd204bd00,
-	0x80000000,
-	0x800225f0,
-	0xf6028800,
-	0x04bd0002,
-	0x00421001,
-	0x0223f002,
-	0xf80512fa,
-	0xf094bd03,
+	0x83008004,
+	0x0002f602,
+	0x070f04bd,
+	0x00071d7e,
+	0x02c00080,
+	0xbd0002f6,
+	0x000bfe04,
+	0xb61f2af0,
+	0x20b60424,
+	0xf094bd02,
 	0x00800899,
-	0x09f60217,
-	0x9804bd00,
-	0x14b68101,
-	0x80029818,
-	0xfd0825b6,
-	0x01b50512,
-	0xf094bd16,
-	0x00800999,
 	0x09f60237,
 	0x8004bd00,
 	0xf6028100,
-	0x04bd0001,
-	0x00800102,
-	0x02f60288,
-	0x4104bd00,
-	0x13f00100,
-	0x0501fa06,
+	0x04bd0002,
+	0x000000d2,
+	0x0225f080,
+	0x02880080,
+	0xbd0002f6,
+	0x42100104,
+	0x23f00200,
+	0x0512fa02,
 	0x94bd03f8,
-	0x800999f0,
+	0x800899f0,
 	0xf6021700,
 	0x04bd0009,
-	0x99f094bd,
-	0x17008005,
-	0x0009f602,
-	0x00f804bd,
-/* 0x0820: ctx_chan */
-	0x0007347e,
-	0xb87e0c0a,
-	0x050f0000,
-	0x00071c7e,
-/* 0x0832: ctx_mmio_exec */
-	0x039800f8,
-	0x81008041,
-	0x0003f602,
-	0x34bd04bd,
-/* 0x0840: ctx_mmio_loop */
-	0xf4ff34c4,
-	0x00450e1b,
-	0x0653f002,
-	0xf80535fa,
-/* 0x0851: ctx_mmio_pull */
-	0x804e9803,
-	0x7e814f98,
-	0xb600008f,
-	0x12b60830,
-	0xdf1bf401,
-/* 0x0864: ctx_mmio_done */
-	0x80160398,
-	0xf6028100,
-	0x04bd0003,
-	0x414000b5,
-	0x13f00100,
-	0x0601fa06,
-	0x00f803f8,
-/* 0x0880: ctx_xfer */
-	0x0080040e,
-	0x0ef60302,
-/* 0x088b: ctx_xfer_idle */
-	0x8e04bd00,
-	0xcf030000,
-	0xe4f100ee,
-	0x1bf42000,
-	0x0611f4f5,
-/* 0x089f: ctx_xfer_pre */
-	0x0f0c02f4,
-	0x06fd7e10,
-	0x1b11f400,
-/* 0x08a8: ctx_xfer_pre_load */
-	0xac7e020f,
-	0xbb7e0006,
-	0xcd7e0006,
-	0xf4bd0006,
-	0x0006ac7e,
-	0x0007347e,
-/* 0x08c0: ctx_xfer_exec */
-	0xbd160198,
-	0x05008024,
-	0x0002f601,
-	0x1fb204bd,
-	0x41a5008e,
-	0x00008f7e,
-	0xf001fcf0,
-	0x24b6022c,
-	0x05f2fd01,
-	0x048effb2,
-	0x8f7e41a5,
-	0x167e0000,
-	0x24bd0002,
-	0x0247fc80,
-	0xbd0002f6,
-	0x012cf004,
-	0x800320b6,
-	0xf6024afc,
+	0xb6810198,
+	0x02981814,
+	0x0825b680,
+	0xb50512fd,
+	0x94bd1601,
+	0x800999f0,
+	0xf6023700,
+	0x04bd0009,
+	0x02810080,
+	0xbd0001f6,
+	0x80010204,
+	0xf6028800,
 	0x04bd0002,
-	0xf001acf0,
-	0x000b06a5,
-	0x98000c98,
-	0x000e010d,
-	0x00013d7e,
-	0xec7e080a,
-	0x0a7e0000,
-	0x01f40002,
-	0x7e0c0a12,
+	0xf0010041,
+	0x01fa0613,
+	0xbd03f805,
+	0x0999f094,
+	0x02170080,
+	0xbd0009f6,
+	0xf094bd04,
+	0x00800599,
+	0x09f60217,
+	0xf804bd00,
+/* 0x0821: ctx_chan */
+	0x07357e00,
+	0x7e0c0a00,
 	0x0f0000b8,
-	0x071c7e05,
-	0x2d02f400,
-/* 0x093c: ctx_xfer_post */
-	0xac7e020f,
-	0xf4bd0006,
-	0x0006fd7e,
-	0x0002277e,
-	0x0006bb7e,
-	0xac7ef4bd,
+	0x071d7e05,
+/* 0x0833: ctx_mmio_exec */
+	0x9800f800,
+	0x00804103,
+	0x03f60281,
+	0xbd04bd00,
+/* 0x0841: ctx_mmio_loop */
+	0xff34c434,
+	0x450e1bf4,
+	0x53f00200,
+	0x0535fa06,
+/* 0x0852: ctx_mmio_pull */
+	0x4e9803f8,
+	0x814f9880,
+	0x00008f7e,
+	0xb60830b6,
+	0x1bf40112,
+/* 0x0865: ctx_mmio_done */
+	0x160398df,
+	0x02810080,
+	0xbd0003f6,
+	0x4000b504,
+	0xf0010041,
+	0x01fa0613,
+	0xf803f806,
+/* 0x0881: ctx_xfer */
+	0x80040e00,
+	0xf6030200,
+	0x04bd000e,
+/* 0x088c: ctx_xfer_idle */
+	0x0300008e,
+	0xf100eecf,
+	0xf42000e4,
+	0x11f4f51b,
+	0x0c02f406,
+/* 0x08a0: ctx_xfer_pre */
+	0xfe7e100f,
 	0x11f40006,
-	0x40019810,
-	0xf40511fd,
-	0x327e070b,
-/* 0x0966: ctx_xfer_no_post_mmio */
-/* 0x0966: ctx_xfer_done */
-	0x00f80008,
+/* 0x08a9: ctx_xfer_pre_load */
+	0x7e020f1b,
+	0x7e0006ad,
+	0x7e0006bc,
+	0xbd0006ce,
+	0x06ad7ef4,
+	0x07357e00,
+/* 0x08c1: ctx_xfer_exec */
+	0x16019800,
+	0x008024bd,
+	0x02f60105,
+	0xb204bd00,
+	0xa5008e1f,
+	0x008f7e41,
+	0x01fcf000,
+	0xb6022cf0,
+	0xf2fd0124,
+	0x8effb205,
+	0x7e41a504,
+	0x7e00008f,
+	0xbd000216,
+	0x47fc8024,
+	0x0002f602,
+	0x2cf004bd,
+	0x0320b601,
+	0x024afc80,
+	0xbd0002f6,
+	0x01acf004,
+	0x0b06a5f0,
+	0x000c9800,
+	0x0e010d98,
+	0x013d7e00,
+	0x7e080a00,
+	0x7e0000ec,
+	0xf400020a,
+	0x0c0a1201,
+	0x0000b87e,
+	0x1d7e050f,
+	0x02f40007,
+/* 0x093d: ctx_xfer_post */
+	0x7e020f2d,
+	0xbd0006ad,
+	0x06fe7ef4,
+	0x02277e00,
+	0x06bc7e00,
+	0x7ef4bd00,
+	0xf40006ad,
+	0x01981011,
+	0x0511fd40,
+	0x7e070bf4,
+/* 0x0967: ctx_xfer_no_post_mmio */
+/* 0x0967: ctx_xfer_done */
+	0xf8000833,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index c578deb5867a..dd8f85b8b3a7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -26,9 +26,9 @@
 #include "fuc/os.h"
 
 #include <core/client.h>
-#include <core/option.h>
 #include <core/firmware.h>
-#include <subdev/secboot.h>
+#include <core/option.h>
+#include <subdev/acr.h>
 #include <subdev/fb.h>
 #include <subdev/mc.h>
 #include <subdev/pmu.h>
@@ -1636,7 +1636,7 @@ gf100_gr_intr(struct nvkm_gr *base)
 
 static void
 gf100_gr_init_fw(struct nvkm_falcon *falcon,
-		 struct gf100_gr_fuc *code, struct gf100_gr_fuc *data)
+		 struct nvkm_blob *code, struct nvkm_blob *data)
 {
 	nvkm_falcon_load_dmem(falcon, data->data, 0x0, data->size, 0);
 	nvkm_falcon_load_imem(falcon, code->data, 0x0, code->size, 0, 0, false);
@@ -1690,26 +1690,30 @@ gf100_gr_init_ctxctl_ext(struct gf100_gr *gr)
 {
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	struct nvkm_secboot *sb = device->secboot;
-	u32 secboot_mask = 0;
+	u32 lsf_mask = 0;
 	int ret;
 
 	/* load fuc microcode */
 	nvkm_mc_unk260(device, 0);
 
 	/* securely-managed falcons must be reset using secure boot */
-	if (nvkm_secboot_is_managed(sb, NVKM_SECBOOT_FALCON_FECS))
-		secboot_mask |= BIT(NVKM_SECBOOT_FALCON_FECS);
-	else
-		gf100_gr_init_fw(gr->fecs.falcon, &gr->fuc409c, &gr->fuc409d);
 
-	if (nvkm_secboot_is_managed(sb, NVKM_SECBOOT_FALCON_GPCCS))
-		secboot_mask |= BIT(NVKM_SECBOOT_FALCON_GPCCS);
-	else
-		gf100_gr_init_fw(gr->gpccs.falcon, &gr->fuc41ac, &gr->fuc41ad);
+	if (!nvkm_acr_managed_falcon(device, NVKM_ACR_LSF_FECS)) {
+		gf100_gr_init_fw(&gr->fecs.falcon, &gr->fecs.inst,
+						   &gr->fecs.data);
+	} else {
+		lsf_mask |= BIT(NVKM_ACR_LSF_FECS);
+	}
 
-	if (secboot_mask != 0) {
-		int ret = nvkm_secboot_reset(sb, secboot_mask);
+	if (!nvkm_acr_managed_falcon(device, NVKM_ACR_LSF_GPCCS)) {
+		gf100_gr_init_fw(&gr->gpccs.falcon, &gr->gpccs.inst,
+						    &gr->gpccs.data);
+	} else {
+		lsf_mask |= BIT(NVKM_ACR_LSF_GPCCS);
+	}
+
+	if (lsf_mask) {
+		ret = nvkm_acr_bootstrap_falcons(device, lsf_mask);
 		if (ret)
 			return ret;
 	}
@@ -1721,8 +1725,8 @@ gf100_gr_init_ctxctl_ext(struct gf100_gr *gr)
 	nvkm_wr32(device, 0x41a10c, 0x00000000);
 	nvkm_wr32(device, 0x40910c, 0x00000000);
 
-	nvkm_falcon_start(gr->gpccs.falcon);
-	nvkm_falcon_start(gr->fecs.falcon);
+	nvkm_falcon_start(&gr->gpccs.falcon);
+	nvkm_falcon_start(&gr->fecs.falcon);
 
 	if (nvkm_msec(device, 2000,
 		if (nvkm_rd32(device, 0x409800) & 0x00000001)
@@ -1784,18 +1788,18 @@ gf100_gr_init_ctxctl_int(struct gf100_gr *gr)
 
 	/* load HUB microcode */
 	nvkm_mc_unk260(device, 0);
-	nvkm_falcon_load_dmem(gr->fecs.falcon,
+	nvkm_falcon_load_dmem(&gr->fecs.falcon,
 			      gr->func->fecs.ucode->data.data, 0x0,
 			      gr->func->fecs.ucode->data.size, 0);
-	nvkm_falcon_load_imem(gr->fecs.falcon,
+	nvkm_falcon_load_imem(&gr->fecs.falcon,
 			      gr->func->fecs.ucode->code.data, 0x0,
 			      gr->func->fecs.ucode->code.size, 0, 0, false);
 
 	/* load GPC microcode */
-	nvkm_falcon_load_dmem(gr->gpccs.falcon,
+	nvkm_falcon_load_dmem(&gr->gpccs.falcon,
 			      gr->func->gpccs.ucode->data.data, 0x0,
 			      gr->func->gpccs.ucode->data.size, 0);
-	nvkm_falcon_load_imem(gr->gpccs.falcon,
+	nvkm_falcon_load_imem(&gr->gpccs.falcon,
 			      gr->func->gpccs.ucode->code.data, 0x0,
 			      gr->func->gpccs.ucode->code.size, 0, 0, false);
 	nvkm_mc_unk260(device, 1);
@@ -1941,17 +1945,6 @@ gf100_gr_oneinit(struct nvkm_gr *base)
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	int i, j;
-	int ret;
-
-	ret = nvkm_falcon_v1_new(subdev, "FECS", 0x409000, &gr->fecs.falcon);
-	if (ret)
-		return ret;
-
-	mutex_init(&gr->fecs.mutex);
-
-	ret = nvkm_falcon_v1_new(subdev, "GPCCS", 0x41a000, &gr->gpccs.falcon);
-	if (ret)
-		return ret;
 
 	nvkm_pmu_pgob(device->pmu, false);
 
@@ -1992,11 +1985,11 @@ gf100_gr_init_(struct nvkm_gr *base)
 
 	nvkm_pmu_pgob(gr->base.engine.subdev.device->pmu, false);
 
-	ret = nvkm_falcon_get(gr->fecs.falcon, subdev);
+	ret = nvkm_falcon_get(&gr->fecs.falcon, subdev);
 	if (ret)
 		return ret;
 
-	ret = nvkm_falcon_get(gr->gpccs.falcon, subdev);
+	ret = nvkm_falcon_get(&gr->gpccs.falcon, subdev);
 	if (ret)
 		return ret;
 
@@ -2004,49 +1997,34 @@ gf100_gr_init_(struct nvkm_gr *base)
 }
 
 static int
-gf100_gr_fini_(struct nvkm_gr *base, bool suspend)
+gf100_gr_fini(struct nvkm_gr *base, bool suspend)
 {
 	struct gf100_gr *gr = gf100_gr(base);
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
-	nvkm_falcon_put(gr->gpccs.falcon, subdev);
-	nvkm_falcon_put(gr->fecs.falcon, subdev);
+	nvkm_falcon_put(&gr->gpccs.falcon, subdev);
+	nvkm_falcon_put(&gr->fecs.falcon, subdev);
 	return 0;
 }
 
-void
-gf100_gr_dtor_fw(struct gf100_gr_fuc *fuc)
-{
-	kfree(fuc->data);
-	fuc->data = NULL;
-}
-
-static void
-gf100_gr_dtor_init(struct gf100_gr_pack *pack)
-{
-	vfree(pack);
-}
-
 void *
 gf100_gr_dtor(struct nvkm_gr *base)
 {
 	struct gf100_gr *gr = gf100_gr(base);
 
-	if (gr->func->dtor)
-		gr->func->dtor(gr);
 	kfree(gr->data);
 
-	nvkm_falcon_del(&gr->gpccs.falcon);
-	nvkm_falcon_del(&gr->fecs.falcon);
+	nvkm_falcon_dtor(&gr->gpccs.falcon);
+	nvkm_falcon_dtor(&gr->fecs.falcon);
 
-	gf100_gr_dtor_fw(&gr->fuc409c);
-	gf100_gr_dtor_fw(&gr->fuc409d);
-	gf100_gr_dtor_fw(&gr->fuc41ac);
-	gf100_gr_dtor_fw(&gr->fuc41ad);
+	nvkm_blob_dtor(&gr->fecs.inst);
+	nvkm_blob_dtor(&gr->fecs.data);
+	nvkm_blob_dtor(&gr->gpccs.inst);
+	nvkm_blob_dtor(&gr->gpccs.data);
 
-	gf100_gr_dtor_init(gr->fuc_bundle);
-	gf100_gr_dtor_init(gr->fuc_method);
-	gf100_gr_dtor_init(gr->fuc_sw_ctx);
-	gf100_gr_dtor_init(gr->fuc_sw_nonctx);
+	vfree(gr->bundle);
+	vfree(gr->method);
+	vfree(gr->sw_ctx);
+	vfree(gr->sw_nonctx);
 
 	return gr;
 }
@@ -2056,7 +2034,7 @@ gf100_gr_ = {
 	.dtor = gf100_gr_dtor,
 	.oneinit = gf100_gr_oneinit,
 	.init = gf100_gr_init_,
-	.fini = gf100_gr_fini_,
+	.fini = gf100_gr_fini,
 	.intr = gf100_gr_intr,
 	.units = gf100_gr_units,
 	.chan_new = gf100_gr_chan_new,
@@ -2067,87 +2045,24 @@ gf100_gr_ = {
 	.ctxsw.inst = gf100_gr_ctxsw_inst,
 };
 
-int
-gf100_gr_ctor_fw_legacy(struct gf100_gr *gr, const char *fwname,
-			struct gf100_gr_fuc *fuc, int ret)
-{
-	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
-	struct nvkm_device *device = subdev->device;
-	const struct firmware *fw;
-	char f[32];
-
-	/* see if this firmware has a legacy path */
-	if (!strcmp(fwname, "fecs_inst"))
-		fwname = "fuc409c";
-	else if (!strcmp(fwname, "fecs_data"))
-		fwname = "fuc409d";
-	else if (!strcmp(fwname, "gpccs_inst"))
-		fwname = "fuc41ac";
-	else if (!strcmp(fwname, "gpccs_data"))
-		fwname = "fuc41ad";
-	else {
-		/* nope, let's just return the error we got */
-		nvkm_error(subdev, "failed to load %s\n", fwname);
-		return ret;
-	}
-
-	/* yes, try to load from the legacy path */
-	nvkm_debug(subdev, "%s: falling back to legacy path\n", fwname);
-
-	snprintf(f, sizeof(f), "nouveau/nv%02x_%s", device->chipset, fwname);
-	ret = request_firmware(&fw, f, device->dev);
-	if (ret) {
-		snprintf(f, sizeof(f), "nouveau/%s", fwname);
-		ret = request_firmware(&fw, f, device->dev);
-		if (ret) {
-			nvkm_error(subdev, "failed to load %s\n", fwname);
-			return ret;
-		}
-	}
-
-	fuc->size = fw->size;
-	fuc->data = kmemdup(fw->data, fuc->size, GFP_KERNEL);
-	release_firmware(fw);
-	return (fuc->data != NULL) ? 0 : -ENOMEM;
-}
-
-int
-gf100_gr_ctor_fw(struct gf100_gr *gr, const char *fwname,
-		 struct gf100_gr_fuc *fuc)
-{
-	const struct firmware *fw;
-	int ret;
-
-	ret = nvkm_firmware_get(&gr->base.engine.subdev, fwname, &fw);
-	if (ret) {
-		ret = gf100_gr_ctor_fw_legacy(gr, fwname, fuc, ret);
-		if (ret)
-			return -ENODEV;
-		return 0;
-	}
-
-	fuc->size = fw->size;
-	fuc->data = kmemdup(fw->data, fuc->size, GFP_KERNEL);
-	nvkm_firmware_put(fw);
-	return (fuc->data != NULL) ? 0 : -ENOMEM;
-}
-
-int
-gf100_gr_ctor(const struct gf100_gr_func *func, struct nvkm_device *device,
-	      int index, struct gf100_gr *gr)
-{
-	gr->func = func;
-	gr->firmware = nvkm_boolopt(device->cfgopt, "NvGrUseFW",
-				    func->fecs.ucode == NULL);
-
-	return nvkm_gr_ctor(&gf100_gr_, device, index,
-			    gr->firmware || func->fecs.ucode != NULL,
-			    &gr->base);
-}
+static const struct nvkm_falcon_func
+gf100_gr_flcn = {
+	.fbif = 0x600,
+	.load_imem = nvkm_falcon_v1_load_imem,
+	.load_dmem = nvkm_falcon_v1_load_dmem,
+	.read_dmem = nvkm_falcon_v1_read_dmem,
+	.bind_context = nvkm_falcon_v1_bind_context,
+	.wait_for_halt = nvkm_falcon_v1_wait_for_halt,
+	.clear_interrupt = nvkm_falcon_v1_clear_interrupt,
+	.set_start_addr = nvkm_falcon_v1_set_start_addr,
+	.start = nvkm_falcon_v1_start,
+	.enable = nvkm_falcon_v1_enable,
+	.disable = nvkm_falcon_v1_disable,
+};
 
 int
-gf100_gr_new_(const struct gf100_gr_func *func, struct nvkm_device *device,
-	      int index, struct nvkm_gr **pgr)
+gf100_gr_new_(const struct gf100_gr_fwif *fwif,
+	      struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
 	struct gf100_gr *gr;
 	int ret;
@@ -2156,22 +2071,49 @@ gf100_gr_new_(const struct gf100_gr_func *func, struct nvkm_device *device,
 		return -ENOMEM;
 	*pgr = &gr->base;
 
-	ret = gf100_gr_ctor(func, device, index, gr);
+	ret = nvkm_gr_ctor(&gf100_gr_, device, index, true, &gr->base);
 	if (ret)
 		return ret;
 
-	if (gr->firmware) {
-		if (gf100_gr_ctor_fw(gr, "fecs_inst", &gr->fuc409c) ||
-		    gf100_gr_ctor_fw(gr, "fecs_data", &gr->fuc409d) ||
-		    gf100_gr_ctor_fw(gr, "gpccs_inst", &gr->fuc41ac) ||
-		    gf100_gr_ctor_fw(gr, "gpccs_data", &gr->fuc41ad))
-			return -ENODEV;
-	}
+	fwif = nvkm_firmware_load(&gr->base.engine.subdev, fwif, "Gr", gr);
+	if (IS_ERR(fwif))
+		return -ENODEV;
+
+	gr->func = fwif->func;
+
+	ret = nvkm_falcon_ctor(&gf100_gr_flcn, &gr->base.engine.subdev,
+			       "fecs", 0x409000, &gr->fecs.falcon);
+	if (ret)
+		return ret;
+
+	mutex_init(&gr->fecs.mutex);
+
+	ret = nvkm_falcon_ctor(&gf100_gr_flcn, &gr->base.engine.subdev,
+			       "gpccs", 0x41a000, &gr->gpccs.falcon);
+	if (ret)
+		return ret;
 
 	return 0;
 }
 
 void
+gf100_gr_init_num_tpc_per_gpc(struct gf100_gr *gr, bool pd, bool ds)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	int gpc, i, j;
+	u32 data;
+
+	for (gpc = 0, i = 0; i < 4; i++) {
+		for (data = 0, j = 0; j < 8 && gpc < gr->gpc_nr; j++, gpc++)
+			data |= gr->tpc_nr[gpc] << (j * 4);
+		if (pd)
+			nvkm_wr32(device, 0x406028 + (i * 4), data);
+		if (ds)
+			nvkm_wr32(device, 0x405870 + (i * 4), data);
+	}
+}
+
+void
 gf100_gr_init_400054(struct gf100_gr *gr)
 {
 	nvkm_wr32(gr->base.engine.subdev.device, 0x400054, 0x34ce3464);
@@ -2295,8 +2237,8 @@ gf100_gr_init(struct gf100_gr *gr)
 
 	gr->func->init_gpc_mmu(gr);
 
-	if (gr->fuc_sw_nonctx)
-		gf100_gr_mmio(gr, gr->fuc_sw_nonctx);
+	if (gr->sw_nonctx)
+		gf100_gr_mmio(gr, gr->sw_nonctx);
 	else
 		gf100_gr_mmio(gr, gr->func->mmio);
 
@@ -2320,6 +2262,8 @@ gf100_gr_init(struct gf100_gr *gr)
 		gr->func->init_bios_2(gr);
 	if (gr->func->init_swdx_pes_mask)
 		gr->func->init_swdx_pes_mask(gr);
+	if (gr->func->init_fs)
+		gr->func->init_fs(gr);
 
 	nvkm_wr32(device, 0x400500, 0x00010001);
 
@@ -2338,8 +2282,8 @@ gf100_gr_init(struct gf100_gr *gr)
 	if (gr->func->init_40601c)
 		gr->func->init_40601c(gr);
 
-	nvkm_wr32(device, 0x404490, 0xc0000000);
 	nvkm_wr32(device, 0x406018, 0xc0000000);
+	nvkm_wr32(device, 0x404490, 0xc0000000);
 
 	if (gr->func->init_sked_hww_esr)
 		gr->func->init_sked_hww_esr(gr);
@@ -2454,7 +2398,66 @@ gf100_gr = {
 };
 
 int
+gf100_gr_nofw(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif)
+{
+	gr->firmware = false;
+	return 0;
+}
+
+static int
+gf100_gr_load_fw(struct gf100_gr *gr, const char *name,
+		 struct nvkm_blob *blob)
+{
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	const struct firmware *fw;
+	char f[32];
+	int ret;
+
+	snprintf(f, sizeof(f), "nouveau/nv%02x_%s", device->chipset, name);
+	ret = request_firmware(&fw, f, device->dev);
+	if (ret) {
+		snprintf(f, sizeof(f), "nouveau/%s", name);
+		ret = request_firmware(&fw, f, device->dev);
+		if (ret) {
+			nvkm_error(subdev, "failed to load %s\n", name);
+			return ret;
+		}
+	}
+
+	blob->size = fw->size;
+	blob->data = kmemdup(fw->data, blob->size, GFP_KERNEL);
+	release_firmware(fw);
+	return (blob->data != NULL) ? 0 : -ENOMEM;
+}
+
+int
+gf100_gr_load(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+
+	if (!nvkm_boolopt(device->cfgopt, "NvGrUseFW", false))
+		return -EINVAL;
+
+	if (gf100_gr_load_fw(gr, "fuc409c", &gr->fecs.inst) ||
+	    gf100_gr_load_fw(gr, "fuc409d", &gr->fecs.data) ||
+	    gf100_gr_load_fw(gr, "fuc41ac", &gr->gpccs.inst) ||
+	    gf100_gr_load_fw(gr, "fuc41ad", &gr->gpccs.data))
+		return -ENOENT;
+
+	gr->firmware = true;
+	return 0;
+}
+
+static const struct gf100_gr_fwif
+gf100_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gf100_gr },
+	{ -1, gf100_gr_nofw, &gf100_gr },
+	{}
+};
+
+int
 gf100_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gf100_gr, device, index, pgr);
+	return gf100_gr_new_(gf100_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index fafdd0bbea9b..88bcb57c2e07 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -31,6 +31,8 @@
 #include <subdev/mmu.h>
 #include <engine/falcon.h>
 
+struct nvkm_acr_lsfw;
+
 #define GPC_MAX 32
 #define TPC_MAX_PER_GPC 8
 #define TPC_MAX (GPC_MAX * TPC_MAX_PER_GPC)
@@ -55,11 +57,6 @@ struct gf100_gr_mmio {
 	int buffer;
 };
 
-struct gf100_gr_fuc {
-	u32 *data;
-	u32  size;
-};
-
 struct gf100_gr_zbc_color {
 	u32 format;
 	u32 ds[4];
@@ -83,29 +80,30 @@ struct gf100_gr {
 	struct nvkm_gr base;
 
 	struct {
-		struct nvkm_falcon *falcon;
+		struct nvkm_falcon falcon;
+		struct nvkm_blob inst;
+		struct nvkm_blob data;
+
 		struct mutex mutex;
 		u32 disable;
 	} fecs;
 
 	struct {
-		struct nvkm_falcon *falcon;
+		struct nvkm_falcon falcon;
+		struct nvkm_blob inst;
+		struct nvkm_blob data;
 	} gpccs;
 
-	struct gf100_gr_fuc fuc409c;
-	struct gf100_gr_fuc fuc409d;
-	struct gf100_gr_fuc fuc41ac;
-	struct gf100_gr_fuc fuc41ad;
 	bool firmware;
 
 	/*
 	 * Used if the register packs are loaded from NVIDIA fw instead of
 	 * using hardcoded arrays. To be allocated with vzalloc().
 	 */
-	struct gf100_gr_pack *fuc_sw_nonctx;
-	struct gf100_gr_pack *fuc_sw_ctx;
-	struct gf100_gr_pack *fuc_bundle;
-	struct gf100_gr_pack *fuc_method;
+	struct gf100_gr_pack *sw_nonctx;
+	struct gf100_gr_pack *sw_ctx;
+	struct gf100_gr_pack *bundle;
+	struct gf100_gr_pack *method;
 
 	struct gf100_gr_zbc_color zbc_color[NVKM_LTC_MAX_ZBC_CNT];
 	struct gf100_gr_zbc_depth zbc_depth[NVKM_LTC_MAX_ZBC_CNT];
@@ -140,12 +138,6 @@ struct gf100_gr {
 	u32 size_pm;
 };
 
-int gf100_gr_ctor(const struct gf100_gr_func *, struct nvkm_device *,
-		  int, struct gf100_gr *);
-int gf100_gr_new_(const struct gf100_gr_func *, struct nvkm_device *,
-		  int, struct nvkm_gr **);
-void *gf100_gr_dtor(struct nvkm_gr *);
-
 int gf100_gr_fecs_bind_pointer(struct gf100_gr *, u32 inst);
 
 struct gf100_gr_func_zbc {
@@ -157,7 +149,6 @@ struct gf100_gr_func_zbc {
 };
 
 struct gf100_gr_func {
-	void (*dtor)(struct gf100_gr *);
 	void (*oneinit_tiles)(struct gf100_gr *);
 	void (*oneinit_sm_id)(struct gf100_gr *);
 	int (*init)(struct gf100_gr *);
@@ -171,6 +162,7 @@ struct gf100_gr_func {
 	void (*init_rop_active_fbps)(struct gf100_gr *);
 	void (*init_bios_2)(struct gf100_gr *);
 	void (*init_swdx_pes_mask)(struct gf100_gr *);
+	void (*init_fs)(struct gf100_gr *);
 	void (*init_fecs_exceptions)(struct gf100_gr *);
 	void (*init_ds_hww_esr_2)(struct gf100_gr *);
 	void (*init_40601c)(struct gf100_gr *);
@@ -217,6 +209,7 @@ void gf100_gr_init_419eb4(struct gf100_gr *);
 void gf100_gr_init_tex_hww_esr(struct gf100_gr *, int, int);
 void gf100_gr_init_shader_exceptions(struct gf100_gr *, int, int);
 void gf100_gr_init_400054(struct gf100_gr *);
+void gf100_gr_init_num_tpc_per_gpc(struct gf100_gr *, bool, bool);
 extern const struct gf100_gr_func_zbc gf100_gr_zbc;
 
 void gf117_gr_init_zcull(struct gf100_gr *);
@@ -245,10 +238,18 @@ void gp100_gr_init_fecs_exceptions(struct gf100_gr *);
 void gp100_gr_init_shader_exceptions(struct gf100_gr *, int, int);
 void gp100_gr_zbc_clear_color(struct gf100_gr *, int);
 void gp100_gr_zbc_clear_depth(struct gf100_gr *, int);
+extern const struct gf100_gr_func_zbc gp100_gr_zbc;
 
 void gp102_gr_init_swdx_pes_mask(struct gf100_gr *);
 extern const struct gf100_gr_func_zbc gp102_gr_zbc;
 
+extern const struct gf100_gr_func gp107_gr;
+
+void gv100_gr_init_419bd8(struct gf100_gr *);
+void gv100_gr_init_504430(struct gf100_gr *, int, int);
+void gv100_gr_init_shader_exceptions(struct gf100_gr *, int, int);
+void gv100_gr_trap_mp(struct gf100_gr *, int, int);
+
 #define gf100_gr_chan(p) container_of((p), struct gf100_gr_chan, object)
 #include <core/object.h>
 
@@ -269,9 +270,6 @@ struct gf100_gr_chan {
 
 void gf100_gr_ctxctl_debug(struct gf100_gr *);
 
-void gf100_gr_dtor_fw(struct gf100_gr_fuc *);
-int  gf100_gr_ctor_fw(struct gf100_gr *, const char *,
-		      struct gf100_gr_fuc *);
 u64  gf100_gr_units(struct nvkm_gr *);
 void gf100_gr_zbc_init(struct gf100_gr *);
 
@@ -294,8 +292,8 @@ struct gf100_gr_pack {
 		  for (init = pack->init; init && init->count; init++)
 
 struct gf100_gr_ucode {
-	struct gf100_gr_fuc code;
-	struct gf100_gr_fuc data;
+	struct nvkm_blob code;
+	struct nvkm_blob data;
 };
 
 extern struct gf100_gr_ucode gf100_gr_fecs_ucode;
@@ -310,17 +308,6 @@ void gf100_gr_icmd(struct gf100_gr *, const struct gf100_gr_pack *);
 void gf100_gr_mthd(struct gf100_gr *, const struct gf100_gr_pack *);
 int  gf100_gr_init_ctxctl(struct gf100_gr *);
 
-/* external bundles loading functions */
author	Linus Torvalds <torvalds@linux-foundation.org>	2020-01-30 08:04:01 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2020-01-30 08:04:01 -0800
commit	9f68e3655aae6d49d6ba05dd263f99f33c2567af (patch)
tree	42c2c4579c4acbbb456695326af4f4ad8f402813
parent	4cadc60d6bcfee9c626d4b55e9dc1475d21ad3bb (diff)
parent	d47c7f06268082bc0082a15297a07c0da59b0fc4 (diff)